From 825cd268a3a02e80a9c36dada664d25074243d26 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 26 Dec 2018 09:30:48 +0100 Subject: [PATCH 001/362] [youtube] detect DRM protected videos(#1774) --- youtube_dl/extractor/youtube.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 954853e00..4b06cb597 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1077,6 +1077,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://invidio.us/watch?v=BaW_jenozKc', 'only_matching': True, }, + { + # DRM protected + 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', + 'only_matching': True, + } ] def __init__(self, *args, **kwargs): @@ -1673,6 +1678,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '"token" parameter not in video info for unknown reason', video_id=video_id) + if video_info.get('license_info'): + raise ExtractorError('This video is DRM protected.', expected=True) + video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} From 140a13f5de1ff8e6bf7ba0d27b38063a2b20fa33 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 26 Dec 2018 10:55:28 +0100 Subject: [PATCH 002/362] [youtube] extract more format metadata --- youtube_dl/extractor/youtube.py | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 4b06cb597..ac3b4fc17 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1794,6 +1794,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'height': int_or_none(width_height[1]), } q = qualities(['small', 'medium', 'hd720']) + streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) + if streaming_formats: + for fmt in streaming_formats: + itag = str_or_none(fmt.get('itag')) + if not itag: + continue + quality = fmt.get('quality') + quality_label = fmt.get('qualityLabel') or quality + formats_spec[itag] = { + 'asr': int_or_none(fmt.get('audioSampleRate')), + 'filesize': int_or_none(fmt.get('contentLength')), + 'format_note': quality_label, + 'fps': int_or_none(fmt.get('fps')), + 'height': int_or_none(fmt.get('height')), + 'quality': q(quality), + # bitrate for itag 43 is always 2147483647 + 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, + 'width': int_or_none(fmt.get('width')), + } formats = [] for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) @@ -1876,7 +1895,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): filesize = int_or_none(url_data.get( 'clen', [None])[0]) or _extract_filesize(url) - quality = url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0] + quality = url_data.get('quality', [None])[0] more_fields = { 'filesize': filesize, @@ -1884,7 +1903,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'width': width, 'height': height, 'fps': int_or_none(url_data.get('fps', [None])[0]), - 'format_note': quality, + 'format_note': url_data.get('quality_label', [None])[0] or quality, 'quality': q(quality), } for key, value in more_fields.items(): From c2dd2dc086653f46defe0bc6bee9b5e339e67dea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 19:57:01 +0700 Subject: [PATCH 003/362] [youtube] Unescape HTML for series (closes #18641) --- youtube_dl/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index ac3b4fc17..539ff6ff2 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2043,7 +2043,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r']+id="watch7-headline"[^>]*>\s*]*>.*?>(?P[^<]+)\s*S(?P\d+)\s*•\s*E(?P\d+)', video_webpage) if m_episode: - series = m_episode.group('series') + series = unescapeHTML(m_episode.group('series')) season_number = int(m_episode.group('season')) episode_number = int(m_episode.group('episode')) else: From e4d51e751e361faaedaa50baf37501106459ab73 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 20:59:53 +0700 Subject: [PATCH 004/362] [beeg] Fix extraction (closes #18610, closes #18626) --- youtube_dl/extractor/beeg.py | 75 ++++++------------------------------ 1 file changed, 11 insertions(+), 64 deletions(-) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index bf22a41b7..1086d7632 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,15 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_chr, - compat_ord, - compat_urllib_parse_unquote, -) +from ..compat import compat_str from ..utils import ( int_or_none, - parse_iso8601, - urljoin, + unified_timestamp, ) @@ -36,29 +31,9 @@ class BeegIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - cpl_url = self._search_regex( - r']+src=(["\'])(?P(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1', - webpage, 'cpl', default=None, group='url') - - cpl_url = urljoin(url, cpl_url) - - beeg_version, beeg_salt = [None] * 2 - - if cpl_url: - cpl = self._download_webpage( - self._proto_relative_url(cpl_url), video_id, - 'Downloading cpl JS', fatal=False) - if cpl: - beeg_version = int_or_none(self._search_regex( - r'beeg_version\s*=\s*([^\b]+)', cpl, - 'beeg version', default=None)) or self._search_regex( - r'/(\d+)\.js', cpl_url, 'beeg version', default=None) - beeg_salt = self._search_regex( - r'beeg_salt\s*=\s*(["\'])(?P.+?)\1', cpl, 'beeg salt', - default=None, group='beeg_salt') - - beeg_version = beeg_version or '2185' - beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H' + beeg_version = self._search_regex( + r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', + default='1546225636701') for api_path in ('', 'api.'): video = self._download_json( @@ -68,37 +43,6 @@ class BeegIE(InfoExtractor): if video: break - def split(o, e): - def cut(s, x): - n.append(s[:x]) - return s[x:] - n = [] - r = len(o) % e - if r > 0: - o = cut(o, r) - while len(o) > e: - o = cut(o, e) - n.append(o) - return n - - def decrypt_key(key): - # Reverse engineered from http://static.beeg.com/cpl/1738.js - a = beeg_salt - e = compat_urllib_parse_unquote(key) - o = ''.join([ - compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) - for n in range(len(e))]) - return ''.join(split(o, 3)[::-1]) - - def decrypt_url(encrypted_url): - encrypted_url = self._proto_relative_url( - encrypted_url.replace('{DATA_MARKERS}', ''), 'https:') - key = self._search_regex( - r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None) - if not key: - return encrypted_url - return encrypted_url.replace(key, decrypt_key(key)) - formats = [] for format_id, video_url in video.items(): if not video_url: @@ -108,18 +52,20 @@ class BeegIE(InfoExtractor): if not height: continue formats.append({ - 'url': decrypt_url(video_url), + 'url': self._proto_relative_url( + video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'), 'format_id': format_id, 'height': int(height), }) self._sort_formats(formats) title = video['title'] - video_id = video.get('id') or video_id + video_id = compat_str(video.get('id') or video_id) display_id = video.get('code') description = video.get('desc') + series = video.get('ps_name') - timestamp = parse_iso8601(video.get('date'), ' ') + timestamp = unified_timestamp(video.get('date')) duration = int_or_none(video.get('duration')) tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None @@ -129,6 +75,7 @@ class BeegIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'series': series, 'timestamp': timestamp, 'duration': duration, 'tags': tags, From 4e1ddc8da9b318873d71d0283838af6aec1bc98d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 21:05:07 +0700 Subject: [PATCH 005/362] [npo:live] Add support for npostart.nl (closes #18644) --- youtube_dl/extractor/npo.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index c2cb85a73..5a427c396 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -363,7 +363,7 @@ class NPOIE(NPOBaseIE): class NPOLiveIE(NPOBaseIE): IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P[^/?#&]+))?' + _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' _TESTS = [{ 'url': 'http://www.npo.nl/live/npo-1', @@ -380,6 +380,9 @@ class NPOLiveIE(NPOBaseIE): }, { 'url': 'http://www.npo.nl/live', 'only_matching': True, + }, { + 'url': 'https://www.npostart.nl/live/npo-1', + 'only_matching': True, }] def _real_extract(self, url): From 373941c5f0c163bf9f2fbbe7f65ee549a228720f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 23:20:40 +0700 Subject: [PATCH 006/362] [bbc] Add support for another embed pattern (closes #18643) --- youtube_dl/extractor/bbc.py | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index abcfa301d..eac9a5a46 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -795,6 +795,15 @@ class BBCIE(BBCCoUkIE): 'uploader': 'Radio 3', 'uploader_id': 'bbc_radio_three', }, + }, { + 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227', + 'info_dict': { + 'id': 'p06w9tws', + 'ext': 'mp4', + 'title': 'md5:2fabf12a726603193a2879a055f72514', + 'description': 'Learn English words and phrases from this story', + }, + 'add_ie': [BBCCoUkIE.ie_key()], }] @classmethod @@ -945,6 +954,15 @@ class BBCIE(BBCCoUkIE): if entries: return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227 + group_id = self._search_regex( + r']+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX, + webpage, 'group id', default=None) + if playlist_id: + return self.url_result( + 'https://www.bbc.co.uk/programmes/%s' % group_id, + ie=BBCCoUkIE.ie_key()) + # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX, From 32ac3d49ae83fe933515096a74068a8033131f4d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 23:57:46 +0700 Subject: [PATCH 007/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/ChangeLog b/ChangeLog index 510013e89..31458dbd9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,23 @@ +version + +Extractors ++ [bbc] Add support for another embed pattern (#18643) ++ [npo:live] Add support for npostart.nl (#18644) +* [beeg] Fix extraction (#18610, #18626) +* [youtube] Unescape HTML for series (#18641) ++ [youtube] Extract more format metadata +* [youtube] Detect DRM protected videos (#1774) +* [youtube] Relax HTML5 player regular expressions (#18465, #18466) +* [youtube] Extend HTML5 player regular expression (#17516) ++ [liveleak] Add support for another embed type and restore original + format extraction ++ [crackle] Extract ISM and HTTP formats ++ [twitter] Pass Referer with card request (#18579) +* [mediasite] Extend URL regular expression (#18558) ++ [lecturio] Add support for lecturio.de (#18562) ++ [discovery] Add support for Scripps Networks watch domains (#17947) + + version 2018.12.17 Extractors From 9d9daed4647c0a0798adee5a580e9fd95478cf6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 23:59:52 +0700 Subject: [PATCH 008/362] release 2018.12.31 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 10 +++++++--- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 5 files changed, 13 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index b84559932..b2fe6ee6a 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.17** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.31*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.31** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.12.17 +[debug] youtube-dl version 2018.12.31 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index cba87190d..24617264c 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -153,15 +153,19 @@ After you have ensured this site is distributing its content legally, you can fo 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. -8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. -9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): + + $ flake8 youtube_dl/extractor/yourextractor.py + +9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! diff --git a/ChangeLog b/ChangeLog index 31458dbd9..72bfe2110 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.31 Extractors + [bbc] Add support for another embed pattern (#18643) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 31d20f255..e92064432 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -438,6 +438,7 @@ - **Lecture2Go** - **Lecturio** - **LecturioCourse** + - **LecturioDeCourse** - **LEGO** - **Lemonde** - **Lenta** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0461aac0c..87de5848d 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.17' +__version__ = '2018.12.31' From 6b688b8942a0bd18b2a3835e69a903f1eeffee2a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Jan 2019 18:12:44 +0700 Subject: [PATCH 009/362] [bitchute] Fix extraction (closes #18567) --- youtube_dl/extractor/bitchute.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 43b4732aa..aa034355a 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -5,7 +5,10 @@ import itertools import re from .common import InfoExtractor -from ..utils import urlencode_postdata +from ..utils import ( + orderedSet, + urlencode_postdata, +) class BitChuteIE(InfoExtractor): @@ -43,10 +46,15 @@ class BitChuteIE(InfoExtractor): 'description', webpage, 'title', default=None) or self._og_search_description(webpage) + format_urls = [] + for mobj in re.finditer( + r'addWebSeed\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage): + format_urls.append(mobj.group('url')) + format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage)) + formats = [ - {'url': mobj.group('url')} - for mobj in re.finditer( - r'addWebSeed\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage)] + {'url': format_url} + for format_url in orderedSet(format_urls)] self._sort_formats(formats) description = self._html_search_regex( From 38d15ba7f981cc82db91edcbf05ea3844082d045 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Jan 2019 20:31:48 +0700 Subject: [PATCH 010/362] [manyvids] Fix extraction (closes #18604, closes #18614) --- youtube_dl/extractor/manyvids.py | 62 +++++++++++++++++++++++++++----- 1 file changed, 53 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/manyvids.py b/youtube_dl/extractor/manyvids.py index b94b3c2ab..e8d7163e4 100644 --- a/youtube_dl/extractor/manyvids.py +++ b/youtube_dl/extractor/manyvids.py @@ -2,12 +2,18 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + determine_ext, + int_or_none, + str_to_int, + urlencode_postdata, +) class ManyVidsIE(InfoExtractor): _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P\d+)' - _TEST = { + _TESTS = [{ + # preview video 'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/', 'md5': '03f11bb21c52dd12a05be21a5c7dcc97', 'info_dict': { @@ -17,7 +23,18 @@ class ManyVidsIE(InfoExtractor): 'view_count': int, 'like_count': int, }, - } + }, { + # full video + 'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/', + 'md5': 'f3e8f7086409e9b470e2643edb96bdcc', + 'info_dict': { + 'id': '935718', + 'ext': 'mp4', + 'title': 'MY FACE REVEAL', + 'view_count': int, + 'like_count': int, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -28,12 +45,41 @@ class ManyVidsIE(InfoExtractor): r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video URL', group='url') - title = '%s (Preview)' % self._html_search_regex( - r']+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') + title = self._html_search_regex( + (r']+class=["\']item-title[^>]+>([^<]+)', + r']+class=["\']h2 m-0["\'][^>]*>([^<]+)'), + webpage, 'title', default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', fatal=True) + + if any(p in webpage for p in ('preview_videos', '_preview.mp4')): + title += ' (Preview)' + + mv_token = self._search_regex( + r'data-mvtoken=(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'mv token', default=None, group='value') + + if mv_token: + # Sets some cookies + self._download_webpage( + 'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php', + video_id, fatal=False, data=urlencode_postdata({ + 'mvtoken': mv_token, + 'vid': video_id, + }), headers={ + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest' + }) + + if determine_ext(video_url) == 'm3u8': + formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + else: + formats = [{'url': video_url}] like_count = int_or_none(self._search_regex( r'data-likes=["\'](\d+)', webpage, 'like count', default=None)) - view_count = int_or_none(self._html_search_regex( + view_count = str_to_int(self._html_search_regex( r'(?s)]+class="views-wrapper"[^>]*>(.+?) Date: Sun, 30 Dec 2018 14:30:36 +0100 Subject: [PATCH 011/362] [rmcdecouverte] Update _VALID_URL (closes #18595) --- youtube_dl/extractor/rmcdecouverte.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/rmcdecouverte.py b/youtube_dl/extractor/rmcdecouverte.py index e921ca3e6..c44b90274 100644 --- a/youtube_dl/extractor/rmcdecouverte.py +++ b/youtube_dl/extractor/rmcdecouverte.py @@ -10,18 +10,18 @@ from ..compat import ( class RMCDecouverteIE(InfoExtractor): - _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P\d+)' + _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/.+/program_(?P\d+)' _TEST = { - 'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=13502&title=AQUAMEN:LES%20ROIS%20DES%20AQUARIUMS%20:UN%20DELICIEUX%20PROJET', + 'url': 'https://rmcdecouverte.bfmtv.com/wheeler-dealers-occasions-a-saisir/program_2566/', 'info_dict': { - 'id': '5419055995001', + 'id': '5983675500001', 'ext': 'mp4', - 'title': 'UN DELICIEUX PROJET', - 'description': 'md5:63610df7c8b1fc1698acd4d0d90ba8b5', + 'title': 'CORVETTE', + 'description': 'md5:c1e8295521e45ffebf635d6a7658f506', 'uploader_id': '1969646226001', - 'upload_date': '20170502', - 'timestamp': 1493745308, + 'upload_date': '20181226', + 'timestamp': 1545861635, }, 'params': { 'skip_download': True, From d9f1123c08e21c7170b906c7de2562b7293f7a3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Jan 2019 20:49:13 +0700 Subject: [PATCH 012/362] [rmcdecouverte] Improve, bypass geo restriction and add support for live (closes #18697) --- youtube_dl/extractor/rmcdecouverte.py | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/rmcdecouverte.py b/youtube_dl/extractor/rmcdecouverte.py index c44b90274..c3623edcc 100644 --- a/youtube_dl/extractor/rmcdecouverte.py +++ b/youtube_dl/extractor/rmcdecouverte.py @@ -1,18 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE from ..compat import ( compat_parse_qs, compat_urlparse, ) +from ..utils import smuggle_url class RMCDecouverteIE(InfoExtractor): - _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/.+/program_(?P\d+)' + _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:(?:[^/]+/)*program_(?P\d+)|(?Pmediaplayer-direct))' - _TEST = { + _TESTS = [{ 'url': 'https://rmcdecouverte.bfmtv.com/wheeler-dealers-occasions-a-saisir/program_2566/', 'info_dict': { 'id': '5983675500001', @@ -27,12 +30,17 @@ class RMCDecouverteIE(InfoExtractor): 'skip_download': True, }, 'skip': 'only available for a week', - } + }, { + # live, geo restricted, bypassable + 'url': 'https://rmcdecouverte.bfmtv.com/mediaplayer-direct/', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s' def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') or mobj.group('live_id') + webpage = self._download_webpage(url, display_id) brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) if brightcove_legacy_url: brightcove_id = compat_parse_qs(compat_urlparse.urlparse( @@ -41,5 +49,7 @@ class RMCDecouverteIE(InfoExtractor): brightcove_id = self._search_regex( r'data-video-id=["\'](\d+)', webpage, 'brightcove id') return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', - brightcove_id) + smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['FR']}), + 'BrightcoveNew', brightcove_id) From 9b5c8751eeb10fd41c560696d73fec3401055ddc Mon Sep 17 00:00:00 2001 From: iwconfig Date: Tue, 1 Jan 2019 15:39:18 +0100 Subject: [PATCH 013/362] [extractors] Add missing age limits --- youtube_dl/extractor/cammodels.py | 2 ++ youtube_dl/extractor/camtube.py | 2 ++ youtube_dl/extractor/camwithher.py | 2 ++ youtube_dl/extractor/yourporn.py | 2 ++ 4 files changed, 8 insertions(+) diff --git a/youtube_dl/extractor/cammodels.py b/youtube_dl/extractor/cammodels.py index 79350817f..1eb81b75e 100644 --- a/youtube_dl/extractor/cammodels.py +++ b/youtube_dl/extractor/cammodels.py @@ -14,6 +14,7 @@ class CamModelsIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.cammodels.com/cam/AutumnKnight/', 'only_matching': True, + 'age_limit': 18 }] def _real_extract(self, url): @@ -93,4 +94,5 @@ class CamModelsIE(InfoExtractor): 'title': self._live_title(user_id), 'is_live': True, 'formats': formats, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/camtube.py b/youtube_dl/extractor/camtube.py index c7d40f849..b3be3bdcf 100644 --- a/youtube_dl/extractor/camtube.py +++ b/youtube_dl/extractor/camtube.py @@ -20,6 +20,7 @@ class CamTubeIE(InfoExtractor): 'duration': 1274, 'timestamp': 1528018608, 'upload_date': '20180603', + 'age_limit': 18 }, 'params': { 'skip_download': True, @@ -66,4 +67,5 @@ class CamTubeIE(InfoExtractor): 'like_count': like_count, 'creator': creator, 'formats': formats, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/camwithher.py b/youtube_dl/extractor/camwithher.py index afbc5ea26..bbc5205fd 100644 --- a/youtube_dl/extractor/camwithher.py +++ b/youtube_dl/extractor/camwithher.py @@ -25,6 +25,7 @@ class CamWithHerIE(InfoExtractor): 'comment_count': int, 'uploader': 'MileenaK', 'upload_date': '20160322', + 'age_limit': 18, }, 'params': { 'skip_download': True, @@ -84,4 +85,5 @@ class CamWithHerIE(InfoExtractor): 'comment_count': comment_count, 'uploader': uploader, 'upload_date': upload_date, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index a9951f3b8..432d1fff4 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -14,6 +14,7 @@ class YourPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'md5:c9f43630bd968267672651ba905a7d35', 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 18 }, } @@ -38,4 +39,5 @@ class YourPornIE(InfoExtractor): 'url': video_url, 'title': title, 'thumbnail': thumbnail, + 'age_limit': 18 } From 0e713dbb116493181218c38dc03716feda2fa7d9 Mon Sep 17 00:00:00 2001 From: biwubo <45994985+biwubo@users.noreply.github.com> Date: Tue, 1 Jan 2019 15:48:06 +0000 Subject: [PATCH 014/362] [acast:channel] Add support for play.acast.com (closes #18587) --- youtube_dl/extractor/acast.py | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index b32f74a37..c4362be88 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -79,17 +79,27 @@ class ACastIE(InfoExtractor): class ACastChannelIE(InfoExtractor): IE_NAME = 'acast:channel' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/#?]+)' - _TEST = { - 'url': 'https://www.acast.com/condenasttraveler', + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/#?]+) + ''' + _TESTS = [{ + 'url': 'https://www.acast.com/todayinfocus', 'info_dict': { - 'id': '50544219-29bb-499e-a083-6087f4cb7797', - 'title': 'Condé Nast Traveler Podcast', - 'description': 'md5:98646dee22a5b386626ae31866638fbd', + 'id': '4efc5294-5385-4847-98bd-519799ce5786', + 'title': 'Today in Focus', + 'description': 'md5:9ba5564de5ce897faeb12963f4537a64', }, - 'playlist_mincount': 20, - } - _API_BASE_URL = 'https://www.acast.com/api/' + 'playlist_mincount': 35, + }, { + 'url': 'http://play.acast.com/s/ft-banking-weekly', + 'only_matching': True, + }] + _API_BASE_URL = 'https://play.acast.com/api/' _PAGE_SIZE = 10 @classmethod @@ -102,7 +112,7 @@ class ACastChannelIE(InfoExtractor): channel_slug, note='Download page %d of channel data' % page) for cast in casts: yield self.url_result( - 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']), + 'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']), 'ACast', cast['id']) def _real_extract(self, url): From 696f4e41149a8f91e963d33e2f6ea9bc835f2260 Mon Sep 17 00:00:00 2001 From: Sergey M Date: Tue, 1 Jan 2019 23:13:39 +0700 Subject: [PATCH 015/362] [README.md] Add more guide lines for regular expressions --- README.md | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index b3c39bf66..bdc5faeec 100644 --- a/README.md +++ b/README.md @@ -1133,11 +1133,33 @@ title = meta.get('title') or self._og_search_title(webpage) This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. -### Make regular expressions flexible +### Regular expressions -When using regular expressions try to write them fuzzy and flexible. +#### Don't capture groups you don't use + +Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing. + +##### Example + +Don't capture id attribute name here since you can't use it for anything anyway. + +Correct: + +```python +r'(?:id|ID)=(?P\d+)' +``` + +Incorrect: +```python +r'(id|ID)=(?P\d+)' +``` + + +#### Make regular expressions relaxed and flexible + +When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on. -#### Example +##### Example Say you need to extract `title` from the following HTML code: From 1d803085d730bf2aaf54e5cea2362133b3fdb831 Mon Sep 17 00:00:00 2001 From: v-delta <45652398+v-delta@users.noreply.github.com> Date: Tue, 1 Jan 2019 17:26:59 +0100 Subject: [PATCH 016/362] [yourporn] Fix extraction --- youtube_dl/extractor/yourporn.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 432d1fff4..c8dc29bd8 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -27,7 +27,7 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]).replace('/cdn/', '/cdn2/') + video_id)[video_id]).replace('/cdn/', '/cdn3/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', From 8437f5089f2fac85a249c4368c2ea1415955d8b0 Mon Sep 17 00:00:00 2001 From: Sergey M Date: Tue, 1 Jan 2019 23:50:02 +0700 Subject: [PATCH 017/362] [README.md] Add long lines policy to coding conventions --- README.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/README.md b/README.md index bdc5faeec..901595444 100644 --- a/README.md +++ b/README.md @@ -1192,6 +1192,25 @@ title = self._search_regex( webpage, 'title', group='title') ``` +### Long lines policy + +There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse. + +For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit: + +Correct: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + +Incorrect: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=' +'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + ### Use safe conversion functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. From d226c560a6250d03ff5f27d5b078f894d448a0b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Elan=20Ruusam=C3=A4e?= Date: Tue, 1 Jan 2019 18:56:05 +0200 Subject: [PATCH 018/362] Refactor code to use url_result --- youtube_dl/extractor/audiomack.py | 2 +- youtube_dl/extractor/cnn.py | 12 ++---------- youtube_dl/extractor/freespeech.py | 7 ++----- youtube_dl/extractor/generic.py | 5 +---- youtube_dl/extractor/livestream.py | 5 +---- youtube_dl/extractor/savefrom.py | 7 ++----- youtube_dl/extractor/ted.py | 6 ++---- youtube_dl/extractor/testurl.py | 6 +----- youtube_dl/extractor/wimp.py | 6 +----- 9 files changed, 13 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index 62049b921..cc7771354 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -62,7 +62,7 @@ class AudiomackIE(InfoExtractor): # Audiomack wraps a lot of soundcloud tracks in their branded wrapper # if so, pass the work off to the soundcloud extractor if SoundcloudIE.suitable(api_response['url']): - return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'} + return self.url_result(api_response['url'], SoundcloudIE.ie_key()) return { 'id': compat_str(api_response.get('id', album_url_tag)), diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 5fc311f53..774b71055 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -119,11 +119,7 @@ class CNNBlogsIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, url_basename(url)) cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url') - return { - '_type': 'url', - 'url': cnn_url, - 'ie_key': CNNIE.ie_key(), - } + return self.url_result(cnn_url, CNNIE.ie_key()) class CNNArticleIE(InfoExtractor): @@ -145,8 +141,4 @@ class CNNArticleIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, url_basename(url)) cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') - return { - '_type': 'url', - 'url': 'http://cnn.com/video/?/video/' + cnn_url, - 'ie_key': CNNIE.ie_key(), - } + return self.url_result('http://cnn.com/video/?/video/' + cnn_url, CNNIE.ie_key()) diff --git a/youtube_dl/extractor/freespeech.py b/youtube_dl/extractor/freespeech.py index 486a49c05..ea9c3e317 100644 --- a/youtube_dl/extractor/freespeech.py +++ b/youtube_dl/extractor/freespeech.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .youtube import YoutubeIE class FreespeechIE(InfoExtractor): @@ -27,8 +28,4 @@ class FreespeechIE(InfoExtractor): r'data-video-url="([^"]+)"', webpage, 'youtube url') - return { - '_type': 'url', - 'url': youtube_url, - 'ie_key': 'Youtube', - } + return self.url_result(youtube_url, YoutubeIE.ie_key()) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 65b482333..067de28cd 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2197,10 +2197,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index c4776bbf3..e55b1a202 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -363,7 +363,4 @@ class LivestreamShortenerIE(InfoExtractor): id = mobj.group('id') webpage = self._download_webpage(url, id) - return { - '_type': 'url', - 'url': self._og_search_url(webpage), - } + return self.url_result(self._og_search_url(webpage)) diff --git a/youtube_dl/extractor/savefrom.py b/youtube_dl/extractor/savefrom.py index 30f9cf824..21e44b69a 100644 --- a/youtube_dl/extractor/savefrom.py +++ b/youtube_dl/extractor/savefrom.py @@ -30,8 +30,5 @@ class SaveFromIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = os.path.splitext(url.split('/')[-1])[0] - return { - '_type': 'url', - 'id': video_id, - 'url': mobj.group('url'), - } + + return self.url_result(mobj.group('url'), video_id=video_id) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index f9b6aa48f..d3e4205f5 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -203,10 +203,8 @@ class TEDIE(InfoExtractor): ext_url = None if service.lower() == 'youtube': ext_url = external.get('code') - return { - '_type': 'url', - 'url': ext_url or external['uri'], - } + + return self.url_result(ext_url or external['uri']) resources_ = player_talk.get('resources') or talk_info.get('resources') diff --git a/youtube_dl/extractor/testurl.py b/youtube_dl/extractor/testurl.py index 46918adb0..84a14a0bd 100644 --- a/youtube_dl/extractor/testurl.py +++ b/youtube_dl/extractor/testurl.py @@ -61,8 +61,4 @@ class TestURLIE(InfoExtractor): self.to_screen('Test URL: %s' % tc['url']) - return { - '_type': 'url', - 'url': tc['url'], - 'id': video_id, - } + return self.url_result(tc['url'], video_id=video_id) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 3dab9145b..ea234e3c5 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -40,11 +40,7 @@ class WimpIE(InfoExtractor): r'data-id=["\']([0-9A-Za-z_-]{11})'), webpage, 'video URL', default=None) if youtube_id: - return { - '_type': 'url', - 'url': youtube_id, - 'ie_key': YoutubeIE.ie_key(), - } + return self.url_result(youtube_id, YoutubeIE.ie_key()) info_dict = self._extract_jwplayer_data( webpage, video_id, require_title=False) From 751e051557372ab3fa41d839e7e6a149aa2d04b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Jan 2019 17:26:15 +0700 Subject: [PATCH 019/362] [packtpub] Add support for subscription.packtpub.com (closes #18718) --- youtube_dl/extractor/packtpub.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py index 56a2a1083..1324137df 100644 --- a/youtube_dl/extractor/packtpub.py +++ b/youtube_dl/extractor/packtpub.py @@ -24,9 +24,9 @@ class PacktPubBaseIE(InfoExtractor): class PacktPubIE(PacktPubBaseIE): - _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro', 'md5': '1e74bd6cfd45d7d07666f4684ef58f70', 'info_dict': { @@ -37,7 +37,10 @@ class PacktPubIE(PacktPubBaseIE): 'timestamp': 1490918400, 'upload_date': '20170331', }, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro', + 'only_matching': True, + }] _NETRC_MACHINE = 'packtpub' _TOKEN = None @@ -110,15 +113,18 @@ class PacktPubIE(PacktPubBaseIE): class PacktPubCourseIE(PacktPubBaseIE): - _VALID_URL = r'(?Phttps?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+))' - _TEST = { + _VALID_URL = r'(?Phttps?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+))' + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215', 'info_dict': { 'id': '9781787122215', 'title': 'Learn Nodejs by building 12 projects [Video]', }, 'playlist_count': 90, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215', + 'only_matching': True, + }] @classmethod def suitable(cls, url): From 2122d7151deca9c7047426320cd73152cb907afa Mon Sep 17 00:00:00 2001 From: nyuszika7h Date: Wed, 2 Jan 2019 17:46:07 +0100 Subject: [PATCH 020/362] [discovery] Use geo verification headers --- youtube_dl/extractor/discovery.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 44fbc41bb..b70c307a7 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -94,11 +94,12 @@ class DiscoveryIE(DiscoveryGoBaseIE): })['access_token'] try: + headers = self.geo_verification_headers() + headers['Authorization'] = 'Bearer ' + access_token + stream = self._download_json( 'https://api.discovery.com/v1/streaming/video/' + video_id, - display_id, headers={ - 'Authorization': 'Bearer ' + access_token, - }) + display_id, headers=headers) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): e_description = self._parse_json( From aeb72b3a413c8a9d11e3c002b8ab2612b9075a56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Jan 2019 23:51:23 +0700 Subject: [PATCH 021/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/ChangeLog b/ChangeLog index 72bfe2110..1a28d6be0 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,18 @@ +version + +Extractors +* [discovery] Use geo verification headers (#17838) ++ [packtpub] Add support for subscription.packtpub.com (#18718) +* [yourporn] Fix extraction (#18583) ++ [acast:channel] Add support for play.acast.com (#18587) ++ [extractors] Add missing age limits (#18621) ++ [rmcdecouverte] Add support for live stream +* [rmcdecouverte] Bypass geo restriction +* [rmcdecouverte] Update URL regular expression (#18595, 18697) +* [manyvids] Fix extraction (#18604, #18614) +* [bitchute] Fix extraction (#18567) + + version 2018.12.31 Extractors From d7c3af7a72a1e6bd7f93321cce4daf2a13ebdf12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Jan 2019 23:52:54 +0700 Subject: [PATCH 022/362] release 2019.01.02 --- .github/ISSUE_TEMPLATE.md | 6 ++--- CONTRIBUTING.md | 47 ++++++++++++++++++++++++++++++++++++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 4 files changed, 49 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index b2fe6ee6a..3986bbc8e 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.31*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.31** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.02*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.02** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.12.31 +[debug] youtube-dl version 2019.01.02 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 24617264c..a71b045d0 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -261,11 +261,33 @@ title = meta.get('title') or self._og_search_title(webpage) This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. -### Make regular expressions flexible +### Regular expressions -When using regular expressions try to write them fuzzy and flexible. +#### Don't capture groups you don't use + +Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing. + +##### Example + +Don't capture id attribute name here since you can't use it for anything anyway. + +Correct: + +```python +r'(?:id|ID)=(?P\d+)' +``` + +Incorrect: +```python +r'(id|ID)=(?P\d+)' +``` + + +#### Make regular expressions relaxed and flexible + +When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on. -#### Example +##### Example Say you need to extract `title` from the following HTML code: @@ -298,6 +320,25 @@ title = self._search_regex( webpage, 'title', group='title') ``` +### Long lines policy + +There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse. + +For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit: + +Correct: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + +Incorrect: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=' +'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + ### Use safe conversion functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. diff --git a/ChangeLog b/ChangeLog index 1a28d6be0..41d190a72 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.01.02 Extractors * [discovery] Use geo verification headers (#17838) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 87de5848d..07a444706 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.31' +__version__ = '2019.01.02' From c87f65e43dea0f9edf1b5ed8979e274902fb60a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 4 Jan 2019 22:21:53 +0700 Subject: [PATCH 023/362] [carambatv:page] Fix extraction (closes #18739) --- youtube_dl/extractor/carambatv.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/extractor/carambatv.py b/youtube_dl/extractor/carambatv.py index 9ba909a91..b57b86af7 100644 --- a/youtube_dl/extractor/carambatv.py +++ b/youtube_dl/extractor/carambatv.py @@ -82,6 +82,12 @@ class CarambaTVPageIE(InfoExtractor): webpage = self._download_webpage(url, video_id) videomore_url = VideomoreIE._extract_url(webpage) + if not videomore_url: + videomore_id = self._search_regex( + r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id', + default=None) + if videomore_id: + videomore_url = 'videomore:%s' % videomore_id if videomore_url: title = self._og_search_title(webpage) return { From de0359c0af3667605464212e66ba4048b6ba093b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 5 Jan 2019 03:40:41 +0700 Subject: [PATCH 024/362] [tvnow] Fix and rework extractors, prepare for a switch to the new API (closes #17245, closes #18499) --- youtube_dl/extractor/extractors.py | 4 +- youtube_dl/extractor/tvnow.py | 378 +++++++++++++++++++++-------- 2 files changed, 283 insertions(+), 99 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d72f52e36..3b1dfc451 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1193,7 +1193,9 @@ from .tvnet import TVNetIE from .tvnoe import TVNoeIE from .tvnow import ( TVNowIE, - TVNowListIE, + TVNowNewIE, + TVNowSeasonIE, + TVNowAnnualIE, TVNowShowIE, ) from .tvp import ( diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py index 60937616f..3c6a60c39 100644 --- a/youtube_dl/extractor/tvnow.py +++ b/youtube_dl/extractor/tvnow.py @@ -10,8 +10,9 @@ from ..utils import ( int_or_none, parse_iso8601, parse_duration, - try_get, + str_or_none, update_url_query, + urljoin, ) @@ -24,8 +25,7 @@ class TVNowBaseIE(InfoExtractor): def _call_api(self, path, video_id, query): return self._download_json( - 'https://api.tvnow.de/v3/' + path, - video_id, query=query) + 'https://api.tvnow.de/v3/' + path, video_id, query=query) def _extract_video(self, info, display_id): video_id = compat_str(info['id']) @@ -108,6 +108,11 @@ class TVNowIE(TVNowBaseIE): (?!(?:list|jahr)(?:/|$))(?P[^/?\#&]+) ''' + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url) + else super(TVNowIE, cls).suitable(url)) + _TESTS = [{ 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player', 'info_dict': { @@ -116,7 +121,6 @@ class TVNowIE(TVNowBaseIE): 'ext': 'mp4', 'title': 'Der neue Porsche 911 GT 3', 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', - 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1495994400, 'upload_date': '20170528', 'duration': 5283, @@ -161,136 +165,314 @@ class TVNowIE(TVNowBaseIE): info = self._call_api( 'movies/' + display_id, display_id, query={ 'fields': ','.join(self._VIDEO_FIELDS), - 'station': mobj.group(1), }) return self._extract_video(info, display_id) -class TVNowListBaseIE(TVNowBaseIE): - _SHOW_VALID_URL = r'''(?x) - (?P - https?:// - (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/ - (?P[^/]+) - ) +class TVNowNewIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?Phttps?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien))/ + (?P[^/]+)-\d+/ + [^/]+/ + episode-\d+-(?P[^/?$&]+)-(?P\d+) ''' - def _extract_list_info(self, display_id, show_id): - fields = list(self._SHOW_FIELDS) - fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) - fields.extend( - 'formatTabs.formatTabPages.container.movies.%s' % field - for field in self._VIDEO_FIELDS) - return self._call_api( - 'formats/seo', display_id, query={ - 'fields': ','.join(fields), - 'name': show_id + '.php' - }) - - -class TVNowListIE(TVNowListBaseIE): - _VALID_URL = r'%s/(?:list|jahr)/(?P[^?\#&]+)' % TVNowListBaseIE._SHOW_VALID_URL - - _SHOW_FIELDS = ('title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', ) - _TESTS = [{ - 'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell', - 'info_dict': { - 'id': '28296', - 'title': '30 Minuten Deutschland - Aktuell', - }, - 'playlist_mincount': 1, - }, { - 'url': 'https://www.tvnow.de/vox/ab-ins-beet/list/staffel-14', - 'only_matching': True, - }, { - 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/2018/3', + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', 'only_matching': True, }] - @classmethod - def suitable(cls, url): - return (False if TVNowIE.suitable(url) - else super(TVNowListIE, cls).suitable(url)) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + base_url = re.sub(r'(?:shows|serien)', '_', mobj.group('base_url')) + show, episode = mobj.group('show', 'episode') + return self.url_result( + # Rewrite new URLs to the old format and use extraction via old API + # at api.tvnow.de as a loophole for bypassing premium content checks + '%s/%s/%s' % (base_url, show, episode), + ie=TVNowIE.ie_key(), video_id=mobj.group('id')) + + +class TVNowNewBaseIE(InfoExtractor): + def _call_api(self, path, video_id, query={}): + result = self._download_json( + 'https://apigw.tvnow.de/module/' + path, video_id, query=query) + error = result.get('error') + if error: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error), expected=True) + return result + + +""" +TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it +when api.tvnow.de is shut down. This version can't bypass premium checks though. +class TVNowIE(TVNowNewBaseIE): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien)/[^/]+/ + (?:[^/]+/)+ + (?P[^/?$&]+)-(?P\d+) + ''' + + _TESTS = [{ + # episode with annual navigation + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', + 'info_dict': { + 'id': '331082', + 'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3', + 'ext': 'mp4', + 'title': 'Der neue Porsche 911 GT 3', + 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1495994400, + 'upload_date': '20170528', + 'duration': 5283, + 'series': 'GRIP - Das Motormagazin', + 'season_number': 14, + 'episode_number': 405, + 'episode': 'Der neue Porsche 911 GT 3', + }, + }, { + # rtl2, episode with season navigation + 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471/staffel-3/episode-14-bernd-steht-seit-der-trennung-von-seiner-frau-allein-da-526124', + 'only_matching': True, + }, { + # rtlnitro + 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13/episode-5-auf-eigene-faust-pilot-366822', + 'only_matching': True, + }, { + # superrtl + 'url': 'https://www.tvnow.de/shows/die-lustigsten-schlamassel-der-welt-1221/staffel-2/episode-14-u-a-ketchup-effekt-364120', + 'only_matching': True, + }, { + # ntv + 'url': 'https://www.tvnow.de/shows/startup-news-10674/staffel-2/episode-39-goetter-in-weiss-387630', + 'only_matching': True, + }, { + # vox + 'url': 'https://www.tvnow.de/shows/auto-mobil-174/2017-11/episode-46-neues-vom-automobilmarkt-2017-11-19-17-00-00-380072', + 'only_matching': True, + }, { + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', + 'only_matching': True, + }] + + def _extract_video(self, info, url, display_id): + config = info['config'] + source = config['source'] + + video_id = compat_str(info.get('id') or source['videoId']) + title = source['title'].strip() + + paths = [] + for manifest_url in (info.get('manifest') or {}).values(): + if not manifest_url: + continue + manifest_url = update_url_query(manifest_url, {'filter': ''}) + path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path') + if path in paths: + continue + paths.append(path) + + def url_repl(proto, suffix): + return re.sub( + r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub( + r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)', + '.ism/' + suffix, manifest_url)) + + formats = self._extract_mpd_formats( + url_repl('dash', '.mpd'), video_id, + mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + url_repl('hss', 'Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + url_repl('hls', '.m3u8'), video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + if formats: + break + else: + if try_get(info, lambda x: x['rights']['isDrm']): + raise ExtractorError( + 'Video %s is DRM protected' % video_id, expected=True) + if try_get(config, lambda x: x['boards']['geoBlocking']['block']): + raise self.raise_geo_restricted() + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + self._sort_formats(formats) + + description = source.get('description') + thumbnail = url_or_none(source.get('poster')) + timestamp = unified_timestamp(source.get('previewStart')) + duration = parse_duration(source.get('length')) + + series = source.get('format') + season_number = int_or_none(self._search_regex( + r'staffel-(\d+)', url, 'season number', default=None)) + episode_number = int_or_none(self._search_regex( + r'episode-(\d+)', url, 'episode number', default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'series': series, + 'season_number': season_number, + 'episode_number': episode_number, + 'episode': title, + 'formats': formats, + } def _real_extract(self, url): - base_url, show_id, season_id = re.match(self._VALID_URL, url).groups() + display_id, video_id = re.match(self._VALID_URL, url).groups() + info = self._call_api('player/' + video_id, video_id) + return self._extract_video(info, video_id, display_id) +""" - list_info = self._extract_list_info(season_id, show_id) - season = next( - season for season in list_info['formatTabs']['items'] - if season.get('seoheadline') == season_id) +class TVNowListBaseIE(TVNowNewBaseIE): + _SHOW_VALID_URL = r'''(?x) + (?P + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/ + [^/?#&]+-(?P\d+) + ) + ''' - title = list_info.get('title') - headline = season.get('headline') - if title and headline: - title = '%s - %s' % (title, headline) - else: - title = headline or title + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) + else super(TVNowListBaseIE, cls).suitable(url)) + + def _extract_items(self, url, show_id, list_id, query): + items = self._call_api( + 'teaserrow/format/episode/' + show_id, list_id, + query=query)['items'] entries = [] - for container in season['formatTabPages']['items']: - items = try_get( - container, lambda x: x['container']['movies']['items'], - list) or [] - for info in items: - seo_url = info.get('seoUrl') - if not seo_url: - continue - video_id = info.get('id') - entries.append(self.url_result( - '%s/%s/player' % (base_url, seo_url), TVNowIE.ie_key(), - compat_str(video_id) if video_id else None)) + for item in items: + if not isinstance(item, dict): + continue + item_url = urljoin(url, item.get('url')) + if not item_url: + continue + video_id = str_or_none(item.get('id') or item.get('videoId')) + item_title = item.get('subheadline') or item.get('text') + entries.append(self.url_result( + item_url, ie=TVNowNewIE.ie_key(), video_id=video_id, + video_title=item_title)) - return self.playlist_result( - entries, compat_str(season.get('id') or season_id), title) + return self.playlist_result(entries, '%s/%s' % (show_id, list_id)) + + +class TVNowSeasonIE(TVNowListBaseIE): + _VALID_URL = r'%s/staffel-(?P\d+)' % TVNowListBaseIE._SHOW_VALID_URL + _TESTS = [{ + 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13', + 'info_dict': { + 'id': '1815/13', + }, + 'playlist_mincount': 22, + }] + + def _real_extract(self, url): + _, show_id, season_id = re.match(self._VALID_URL, url).groups() + return self._extract_items( + url, show_id, season_id, {'season': season_id}) + + +class TVNowAnnualIE(TVNowListBaseIE): + _VALID_URL = r'%s/(?P\d{4})-(?P\d{2})' % TVNowListBaseIE._SHOW_VALID_URL + _TESTS = [{ + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05', + 'info_dict': { + 'id': '1669/2017-05', + }, + 'playlist_mincount': 2, + }] + + def _real_extract(self, url): + _, show_id, year, month = re.match(self._VALID_URL, url).groups() + return self._extract_items( + url, show_id, '%s-%s' % (year, month), { + 'year': int(year), + 'month': int(month), + }) class TVNowShowIE(TVNowListBaseIE): _VALID_URL = TVNowListBaseIE._SHOW_VALID_URL - - _SHOW_FIELDS = ('id', 'title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - _VIDEO_FIELDS = () - _TESTS = [{ - 'url': 'https://www.tvnow.at/vox/ab-ins-beet', + # annual navigationType + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669', 'info_dict': { - 'id': 'ab-ins-beet', - 'title': 'Ab ins Beet!', + 'id': '1669', }, - 'playlist_mincount': 7, + 'playlist_mincount': 73, }, { - 'url': 'https://www.tvnow.at/vox/ab-ins-beet/list', - 'only_matching': True, - }, { - 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/', - 'only_matching': True, + # season navigationType + 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471', + 'info_dict': { + 'id': '11471', + }, + 'playlist_mincount': 3, }] @classmethod def suitable(cls, url): - return (False if TVNowIE.suitable(url) or TVNowListIE.suitable(url) + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) else super(TVNowShowIE, cls).suitable(url)) def _real_extract(self, url): base_url, show_id = re.match(self._VALID_URL, url).groups() - list_info = self._extract_list_info(show_id, show_id) + result = self._call_api( + 'teaserrow/format/navigation/' + show_id, show_id) + + items = result['items'] entries = [] - for season_info in list_info['formatTabs']['items']: - season_url = season_info.get('seoheadline') - if not season_url: - continue - season_id = season_info.get('id') - entries.append(self.url_result( - '%s/list/%s' % (base_url, season_url), TVNowListIE.ie_key(), - compat_str(season_id) if season_id else None, - season_info.get('headline'))) + navigation = result.get('navigationType') + if navigation == 'annual': + for item in items: + if not isinstance(item, dict): + continue + year = int_or_none(item.get('year')) + if year is None: + continue + months = item.get('months') + if not isinstance(months, list): + continue + for month_dict in months: + if not isinstance(month_dict, dict) or not month_dict: + continue + month_number = int_or_none(list(month_dict.keys())[0]) + if month_number is None: + continue + entries.append(self.url_result( + '%s/%04d-%02d' % (base_url, year, month_number), + ie=TVNowAnnualIE.ie_key())) + elif navigation == 'season': + for item in items: + if not isinstance(item, dict): + continue + season_number = int_or_none(item.get('season')) + if season_number is None: + continue + entries.append(self.url_result( + '%s/staffel-%d' % (base_url, season_number), + ie=TVNowSeasonIE.ie_key())) + else: + raise ExtractorError('Unknown navigationType') - return self.playlist_result(entries, show_id, list_info.get('title')) + return self.playlist_result(entries, show_id) From b7acc83550598b9facf1b31d3d9a1c2823b29cbe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Jan 2019 00:55:39 +0700 Subject: [PATCH 025/362] [utils] Add language codes replaced in 1989 revision of ISO 639 to ISO639Utils (closes #18765) --- youtube_dl/utils.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 62e769fd5..64b524d2f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2968,6 +2968,7 @@ class ISO639Utils(object): 'gv': 'glv', 'ha': 'hau', 'he': 'heb', + 'iw': 'heb', # Replaced by he in 1989 revision 'hi': 'hin', 'ho': 'hmo', 'hr': 'hrv', @@ -2977,6 +2978,7 @@ class ISO639Utils(object): 'hz': 'her', 'ia': 'ina', 'id': 'ind', + 'in': 'ind', # Replaced by id in 1989 revision 'ie': 'ile', 'ig': 'ibo', 'ii': 'iii', @@ -3091,6 +3093,7 @@ class ISO639Utils(object): 'wo': 'wol', 'xh': 'xho', 'yi': 'yid', + 'ji': 'yid', # Replaced by he yi 1989 revision 'yo': 'yor', 'za': 'zha', 'zh': 'zho', From 04fb6928da5e34fb3c7eaf50592a141400e00487 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Jan 2019 00:57:24 +0700 Subject: [PATCH 026/362] [postprocessor/ffmpeg] Embed subtitles with non-standard language codes (refs #18765) --- youtube_dl/postprocessor/ffmpeg.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 757b496a1..efcd39d57 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -384,9 +384,8 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): opts += ['-c:s', 'mov_text'] for (i, lang) in enumerate(sub_langs): opts.extend(['-map', '%d:0' % (i + 1)]) - lang_code = ISO639Utils.short2long(lang) - if lang_code is not None: - opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) + lang_code = ISO639Utils.short2long(lang) or lang + opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) temp_filename = prepend_extension(filename, 'temp') self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename) From e9a50fba8603128dcb81fa1b59206a0cb106d540 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Jan 2019 01:02:34 +0700 Subject: [PATCH 027/362] [utils] Fix typo --- youtube_dl/utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 64b524d2f..d2d3c1a9f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3093,7 +3093,7 @@ class ISO639Utils(object): 'wo': 'wol', 'xh': 'xho', 'yi': 'yid', - 'ji': 'yid', # Replaced by he yi 1989 revision + 'ji': 'yid', # Replaced by yi in 1989 revision 'yo': 'yor', 'za': 'zha', 'zh': 'zho', From bcc334a3c66f2465cd63be284e389cc4c7a78203 Mon Sep 17 00:00:00 2001 From: 4rensiker <4rensics@gmx.de> Date: Tue, 8 Jan 2019 02:44:42 +0100 Subject: [PATCH 028/362] [dtube] Fix extraction (closes #18741) --- youtube_dl/extractor/dtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dtube.py b/youtube_dl/extractor/dtube.py index 5887887e1..20190c9cc 100644 --- a/youtube_dl/extractor/dtube.py +++ b/youtube_dl/extractor/dtube.py @@ -48,7 +48,7 @@ class DTubeIE(InfoExtractor): def canonical_url(h): if not h: return None - return 'https://ipfs.io/ipfs/' + h + return 'https://video.dtube.top/ipfs/' + h formats = [] for q in ('240', '480', '720', '1080', ''): From 0266854f63baaa9669b30ee49c5e7e9f353970dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 08:46:34 +0700 Subject: [PATCH 029/362] [dtube] Update test --- youtube_dl/extractor/dtube.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/dtube.py b/youtube_dl/extractor/dtube.py index 20190c9cc..114d2dbe3 100644 --- a/youtube_dl/extractor/dtube.py +++ b/youtube_dl/extractor/dtube.py @@ -15,16 +15,16 @@ from ..utils import ( class DTubeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P[0-9a-z.-]+)/(?P[0-9a-z]{8})' _TEST = { - 'url': 'https://d.tube/#!/v/benswann/zqd630em', - 'md5': 'a03eaa186618ffa7a3145945543a251e', + 'url': 'https://d.tube/#!/v/broncnutz/x380jtr1', + 'md5': '9f29088fa08d699a7565ee983f56a06e', 'info_dict': { - 'id': 'zqd630em', + 'id': 'x380jtr1', 'ext': 'mp4', - 'title': 'Reality Check: FDA\'s Disinformation Campaign on Kratom', - 'description': 'md5:700d164e066b87f9eac057949e4227c2', - 'uploader_id': 'benswann', - 'upload_date': '20180222', - 'timestamp': 1519328958, + 'title': 'Lefty 3-Rings is Back Baby!! NCAA Picks', + 'description': 'md5:60be222088183be3a42f196f34235776', + 'uploader_id': 'broncnutz', + 'upload_date': '20190107', + 'timestamp': 1546854054, }, 'params': { 'format': '480p', From 8cb5c2181ac039e92a20247f266f48cee2411748 Mon Sep 17 00:00:00 2001 From: Awal Garg Date: Mon, 7 Jan 2019 17:41:12 +0530 Subject: [PATCH 030/362] [hungama] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/hungama.py | 32 ++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) create mode 100644 youtube_dl/extractor/hungama.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 3b1dfc451..5ff34216f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -469,6 +469,7 @@ from .hrti import ( ) from .huajiao import HuajiaoIE from .huffpost import HuffPostIE +from .hungama import HungamaIE from .hypem import HypemIE from .iconosquare import IconosquareIE from .ign import ( diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py new file mode 100644 index 000000000..e51440299 --- /dev/null +++ b/youtube_dl/extractor/hungama.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class HungamaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)hungama\.com/song/[\w\d-]+/(?P[0-9]+)' + _TEST = { + 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', + 'md5': '396fa7e8e7e67aa25da0edc4cac9b785', + 'info_dict': { + 'id': '2931166', + 'ext': 'mp4', + 'title': 'Kitni Haseen Zindagi', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + player_data = self._download_json('https://www.hungama.com/audio-player-data/track/%s?_country=IN' % video_id, video_id)[0] + title = player_data.get('song_name') or self._og_search_title(webpage) + track_data = self._download_json(player_data['file'], video_id) + media_url = track_data['response']['media_url'] + + return { + 'id': video_id, + 'title': title, + 'formats': self._extract_m3u8_formats(media_url, video_id, ext='mp4'), + } From 06b4b90c70636d8044b7a2f588503cadf8b202d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 09:09:49 +0700 Subject: [PATCH 031/362] [hungama] Fix code and extract more metadata (closes #18771) --- youtube_dl/extractor/hungama.py | 41 +++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py index e51440299..d9ad1281a 100644 --- a/youtube_dl/extractor/hungama.py +++ b/youtube_dl/extractor/hungama.py @@ -2,31 +2,54 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import int_or_none class HungamaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)hungama\.com/song/[\w\d-]+/(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P[0-9]+)' _TEST = { 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', - 'md5': '396fa7e8e7e67aa25da0edc4cac9b785', + 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', 'info_dict': { 'id': '2931166', 'ext': 'mp4', - 'title': 'Kitni Haseen Zindagi', + 'title': 'Lucky Ali - Kitni Haseen Zindagi', + 'track': 'Kitni Haseen Zindagi', + 'artist': 'Lucky Ali', + 'album': 'Aks', + 'release_year': 2000, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - player_data = self._download_json('https://www.hungama.com/audio-player-data/track/%s?_country=IN' % video_id, video_id)[0] - title = player_data.get('song_name') or self._og_search_title(webpage) - track_data = self._download_json(player_data['file'], video_id) - media_url = track_data['response']['media_url'] + data = self._download_json( + 'https://www.hungama.com/audio-player-data/track/%s' % video_id, + video_id, query={'_country': 'IN'})[0] + + track = data['song_name'] + artist = data.get('singer_name') + + m3u8_url = self._download_json( + data.get('file') or data['preview_link'], + video_id)['response']['media_url'] + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + title = '%s - %s' % (artist, track) if artist else track + thumbnail = data.get('img_src') or data.get('album_image') return { 'id': video_id, 'title': title, - 'formats': self._extract_m3u8_formats(media_url, video_id, ext='mp4'), + 'thumbnail': thumbnail, + 'track': track, + 'artist': artist, + 'album': data.get('album_name'), + 'release_year': int_or_none(data.get('date')), + 'formats': formats, } From 391256dc0ee5e6ac8d3022455de207b8b02a5b10 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 10:02:00 +0700 Subject: [PATCH 032/362] [extractor/common] Add support for movies in _json_ld --- youtube_dl/extractor/common.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e5f8136fc..f507400cc 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1250,6 +1250,13 @@ class InfoExtractor(object): part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries') if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'): info['series'] = unescapeHTML(part_of_series.get('name')) + elif item_type == 'Movie': + info.update({ + 'title': unescapeHTML(e.get('name')), + 'description': unescapeHTML(e.get('description')), + 'duration': parse_duration(e.get('duration')), + 'timestamp': unified_timestamp(e.get('dateCreated')), + }) elif item_type in ('Article', 'NewsArticle'): info.update({ 'timestamp': parse_iso8601(e.get('datePublished')), From 440863ade10c70bec272c1ffe17b63c877e46ca7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 10:02:49 +0700 Subject: [PATCH 033/362] [extractor/common] Use episode name as title in _json_ld --- youtube_dl/extractor/common.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f507400cc..9e7febcad 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1239,11 +1239,14 @@ class InfoExtractor(object): if expected_type is not None and expected_type != item_type: return info if item_type in ('TVEpisode', 'Episode'): + episode_name = unescapeHTML(e.get('name')) info.update({ - 'episode': unescapeHTML(e.get('name')), + 'episode': episode_name, 'episode_number': int_or_none(e.get('episodeNumber')), 'description': unescapeHTML(e.get('description')), }) + if not info.get('title') and episode_name: + info['title'] = episode_name part_of_season = e.get('partOfSeason') if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'): info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) From 2543938bbe393ceef8dca6a69b441d54df099107 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 10:03:44 +0700 Subject: [PATCH 034/362] [hungama] Add support for videos (closes #17402) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/hungama.py | 78 +++++++++++++++++++++++++++--- 2 files changed, 74 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 5ff34216f..ddeb70284 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -469,7 +469,10 @@ from .hrti import ( ) from .huajiao import HuajiaoIE from .huffpost import HuffPostIE -from .hungama import HungamaIE +from .hungama import ( + HungamaIE, + HungamaSongIE, +) from .hypem import HypemIE from .iconosquare import IconosquareIE from .ign import ( diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py index d9ad1281a..3fdaac5b6 100644 --- a/youtube_dl/extractor/hungama.py +++ b/youtube_dl/extractor/hungama.py @@ -2,11 +2,73 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + urlencode_postdata, +) class HungamaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P[0-9]+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?hungama\.com/ + (?: + (?:video|movie)/[^/]+/| + tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/ + ) + (?P\d+) + ''' + _TESTS = [{ + 'url': 'http://www.hungama.com/video/krishna-chants/39349649/', + 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', + 'info_dict': { + 'id': '2931166', + 'ext': 'mp4', + 'title': 'Lucky Ali - Kitni Haseen Zindagi', + 'track': 'Kitni Haseen Zindagi', + 'artist': 'Lucky Ali', + 'album': 'Aks', + 'release_year': 2000, + } + }, { + 'url': 'https://www.hungama.com/movie/kahaani-2/44129919/', + 'only_matching': True, + }, { + 'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + info = self._search_json_ld(webpage, video_id) + + m3u8_url = self._download_json( + 'https://www.hungama.com/index.php', video_id, + data=urlencode_postdata({'content_id': video_id}), headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'X-Requested-With': 'XMLHttpRequest', + }, query={ + 'c': 'common', + 'm': 'get_video_mdn_url', + })['stream_url'] + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + info.update({ + 'id': video_id, + 'formats': formats, + }) + return info + + +class HungamaSongIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P\d+)' _TEST = { 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', @@ -22,21 +84,21 @@ class HungamaIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + audio_id = self._match_id(url) data = self._download_json( - 'https://www.hungama.com/audio-player-data/track/%s' % video_id, - video_id, query={'_country': 'IN'})[0] + 'https://www.hungama.com/audio-player-data/track/%s' % audio_id, + audio_id, query={'_country': 'IN'})[0] track = data['song_name'] artist = data.get('singer_name') m3u8_url = self._download_json( data.get('file') or data['preview_link'], - video_id)['response']['media_url'] + audio_id)['response']['media_url'] formats = self._extract_m3u8_formats( - m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_url, audio_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls') self._sort_formats(formats) @@ -44,7 +106,7 @@ class HungamaIE(InfoExtractor): thumbnail = data.get('img_src') or data.get('album_image') return { - 'id': video_id, + 'id': audio_id, 'title': title, 'thumbnail': thumbnail, 'track': track, From 6089ff40e7cc7710e399db1be87fea103a190ee6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 9 Jan 2019 00:37:01 +0700 Subject: [PATCH 035/362] [youporn] Fix title and description extraction (closes #18748) --- youtube_dl/extractor/youporn.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index ea0bce784..d4eccb4b2 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -68,11 +68,9 @@ class YouPornIE(InfoExtractor): request.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(request, display_id) - title = self._search_regex( - [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P(?:(?!\1).)+)\1', - r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'], - webpage, 'title', group='title', - default=None) or self._og_search_title( + title = self._html_search_regex( + r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', + webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or self._html_search_meta( 'title', webpage, fatal=True) @@ -134,7 +132,11 @@ class YouPornIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - description = self._og_search_description(webpage, default=None) + description = self._html_search_regex( + r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>', + webpage, 'description', + default=None) or self._og_search_description( + webpage, default=None) thumbnail = self._search_regex( r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', webpage, 'thumbnail', fatal=False, group='thumbnail') From 3c1089dba41f137dcc6c373daacdc19a24aef81c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Jan 2019 14:23:26 +0100 Subject: [PATCH 036/362] [gaia] Add new extractor(#14605) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/gaia.py | 98 ++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) create mode 100644 youtube_dl/extractor/gaia.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ddeb70284..c7d04d366 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -411,6 +411,7 @@ from .funk import ( from .funnyordie import FunnyOrDieIE from .fusion import FusionIE from .fxnetworks import FXNetworksIE +from .gaia import GaiaIE from .gameinformer import GameInformerIE from .gameone import ( GameOneIE, diff --git a/youtube_dl/extractor/gaia.py b/youtube_dl/extractor/gaia.py new file mode 100644 index 000000000..f2eef3f4c --- /dev/null +++ b/youtube_dl/extractor/gaia.py @@ -0,0 +1,98 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + str_or_none, + strip_or_none, + try_get, +) + + +class GaiaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)' + _TESTS = [{ + 'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature', + 'info_dict': { + 'id': '89356', + 'ext': 'mp4', + 'title': 'Connecting with Universal Consciousness', + 'description': 'md5:844e209ad31b7d31345f5ed689e3df6f', + 'upload_date': '20151116', + 'timestamp': 1447707266, + 'duration': 936, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview', + 'info_dict': { + 'id': '89351', + 'ext': 'mp4', + 'title': 'Connecting with Universal Consciousness', + 'description': 'md5:844e209ad31b7d31345f5ed689e3df6f', + 'upload_date': '20151116', + 'timestamp': 1447707266, + 'duration': 53, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id, vtype = re.search(self._VALID_URL, url).groups() + node_id = self._download_json( + 'https://brooklyn.gaia.com/pathinfo', display_id, query={ + 'path': 'video/' + display_id, + })['id'] + node = self._download_json( + 'https://brooklyn.gaia.com/node/%d' % node_id, node_id) + vdata = node[vtype] + media_id = compat_str(vdata['nid']) + title = node['title'] + + media = self._download_json( + 'https://brooklyn.gaia.com/media/' + media_id, media_id) + formats = self._extract_m3u8_formats( + media['mediaUrls']['bcHLS'], media_id, 'mp4') + self._sort_formats(formats) + + subtitles = {} + text_tracks = media.get('textTracks', {}) + for key in ('captions', 'subtitles'): + for lang, sub_url in text_tracks.get(key, {}).items(): + subtitles.setdefault(lang, []).append({ + 'url': sub_url, + }) + + fivestar = node.get('fivestar', {}) + fields = node.get('fields', {}) + + def get_field_value(key, value_key='value'): + return try_get(fields, lambda x: x[key][0][value_key]) + + return { + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'description': strip_or_none(get_field_value('body') or get_field_value('teaser')), + 'timestamp': int_or_none(node.get('created')), + 'subtitles': subtitles, + 'duration': int_or_none(vdata.get('duration')), + 'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])), + 'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])), + 'comment_count': int_or_none(node.get('comment_count')), + 'series': try_get(node, lambda x: x['series']['title'], compat_str), + 'season_number': int_or_none(get_field_value('season')), + 'season_id': str_or_none(get_field_value('series_nid', 'nid')), + 'episode_number': int_or_none(get_field_value('episode')), + } From 65615be36874fe98d5a972546e8024cda3879c86 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Jan 2019 19:17:58 +0100 Subject: [PATCH 037/362] [globo] set GLBID cookie manually(closes #17346) --- youtube_dl/extractor/globo.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index c2140c362..fb8f7679b 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -72,7 +72,7 @@ class GloboIE(InfoExtractor): return try: - self._download_json( + glb_id = (self._download_json( 'https://login.globo.com/api/authentication', None, data=json.dumps({ 'payload': { 'email': email, @@ -81,7 +81,9 @@ class GloboIE(InfoExtractor): }, }).encode(), headers={ 'Content-Type': 'application/json; charset=utf-8', - }) + }) or {}).get('glbId') + if glb_id: + self._set_cookie('.globo.com', 'GLBID', glb_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: resp = self._parse_json(e.cause.read(), None) From 4ad159c7b0ce476171aad1eaa8a36f7b9b1cce65 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Jan 2019 20:39:48 +0100 Subject: [PATCH 038/362] [playplustv] Add new extractor(closes #18789) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/playplustv.py | 109 +++++++++++++++++++++++++++++ 2 files changed, 110 insertions(+) create mode 100644 youtube_dl/extractor/playplustv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c7d04d366..7d7e4247a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -861,6 +861,7 @@ from .piksel import PikselIE from .pinkbike import PinkbikeIE from .pladform import PladformIE from .playfm import PlayFMIE +from .playplustv import PlayPlusTVIE from .plays import PlaysTVIE from .playtvak import PlaytvakIE from .playvid import PlayvidIE diff --git a/youtube_dl/extractor/playplustv.py b/youtube_dl/extractor/playplustv.py new file mode 100644 index 000000000..419c2974b --- /dev/null +++ b/youtube_dl/extractor/playplustv.py @@ -0,0 +1,109 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + PUTRequest, +) + + +class PlayPlusTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?playplus\.tv/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' + _TEST = { + 'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e', + 'md5': 'd078cb89d7ab6b9df37ce23c647aef72', + 'info_dict': { + 'id': 'db8d274a5163424e967f35a30ddafb8e', + 'ext': 'mp4', + 'title': 'Capítulo 179 - Final', + 'description': 'md5:01085d62d8033a1e34121d3c3cabc838', + 'timestamp': 1529992740, + 'upload_date': '20180626', + }, + 'skip': 'Requires account credential', + } + _NETRC_MACHINE = 'playplustv' + _GEO_COUNTRIES = ['BR'] + _token = None + _profile_id = None + + def _call_api(self, resource, video_id=None, query=None): + return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={ + 'Authorization': 'Bearer ' + self._token, + }, query=query) + + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + self.raise_login_required() + + req = PUTRequest( + 'https://api.playplus.tv/api/web/login', json.dumps({ + 'email': email, + 'password': password, + }).encode(), { + 'Content-Type': 'application/json; charset=utf-8', + }) + + try: + self._token = self._download_json(req, None)['token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError(self._parse_json( + e.cause.read(), None)['errorMessage'], expected=True) + raise + + self._profile = self._call_api('Profiles')['list'][0]['_id'] + + def _real_extract(self, url): + project_id, media_id = re.match(self._VALID_URL, url).groups() + media = self._call_api( + 'Media', media_id, { + 'profileId': self._profile, + 'projectId': project_id, + 'mediaId': media_id, + })['obj'] + title = media['title'] + + formats = [] + for f in media.get('files', []): + f_url = f.get('url') + if not f_url: + continue + file_info = f.get('fileInfo') or {} + formats.append({ + 'url': f_url, + 'width': int_or_none(file_info.get('width')), + 'height': int_or_none(file_info.get('height')), + }) + self._sort_formats(formats) + + thumbnails = [] + for thumb in media.get('thumbs', []): + thumb_url = thumb.get('url') + if not thumb_url: + continue + thumbnails.append({ + 'url': thumb_url, + 'width': int_or_none(thumb.get('width')), + 'height': int_or_none(thumb.get('height')), + }) + + return { + 'id': media_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': clean_html(media.get('description')) or media.get('shortDescription'), + 'timestamp': int_or_none(media.get('publishDate'), 1000), + 'view_count': int_or_none(media.get('numberOfViews')), + 'comment_count': int_or_none(media.get('numberOfComments')), + 'tags': media.get('tags'), + } From 96c186e1fd8af4943eeaa8c858f9cb0f15e8b265 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 09:05:00 +0100 Subject: [PATCH 039/362] [fox] add support National Geographic(closes #17985)(closes #15333)(closes #14698) --- youtube_dl/extractor/extractors.py | 6 +- youtube_dl/extractor/fox.py | 93 +++++++------- youtube_dl/extractor/nationalgeographic.py | 135 --------------------- 3 files changed, 48 insertions(+), 186 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7d7e4247a..a01d99b85 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -687,11 +687,7 @@ from .myvi import ( MyviEmbedIE, ) from .myvidster import MyVidsterIE -from .nationalgeographic import ( - NationalGeographicVideoIE, - NationalGeographicIE, - NationalGeographicEpisodeGuideIE, -) +from .nationalgeographic import NationalGeographicVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import ( diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 11d6c9c32..b1c91f095 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals +# import json +# import uuid + from .adobepass import AdobePassIE -from .uplynk import UplynkPreplayIE -from ..compat import compat_str from ..utils import ( - HEADRequest, int_or_none, parse_age_limit, parse_duration, @@ -16,7 +16,7 @@ from ..utils import ( class FOXIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)' + _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)' _TESTS = [{ # clip 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/', @@ -43,41 +43,47 @@ class FOXIE(AdobePassIE): # episode, geo-restricted, tv provided required 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, + }, { + 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', + 'only_matching': True, }] + # _access_token = None + + # def _call_api(self, path, video_id, data=None): + # headers = { + # 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + # } + # if self._access_token: + # headers['Authorization'] = 'Bearer ' + self._access_token + # return self._download_json( + # 'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers) + + # def _real_initialize(self): + # self._access_token = self._call_api( + # 'login', None, json.dumps({ + # 'deviceId': compat_str(uuid.uuid4()), + # }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) video = self._download_json( - 'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id, + 'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id, video_id, headers={ 'apikey': 'abdcbed02c124d393b39e818a4312055', 'Content-Type': 'application/json', 'Referer': url, }) + # video = self._call_api('vodplayer/' + video_id, video_id) title = video['name'] release_url = video['videoRelease']['url'] - - description = video.get('description') - duration = int_or_none(video.get('durationInSeconds')) or int_or_none( - video.get('duration')) or parse_duration(video.get('duration')) - timestamp = unified_timestamp(video.get('datePublished')) - rating = video.get('contentRating') - age_limit = parse_age_limit(rating) + # release_url = video['url'] data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} - creator = data.get('brand') or data.get('network') or video.get('network') - - series = video.get('seriesName') or data.get( - 'seriesName') or data.get('show') - season_number = int_or_none(video.get('seasonNumber')) - episode = video.get('name') - episode_number = int_or_none(video.get('episodeNumber')) - release_year = int_or_none(video.get('releaseYear')) - + rating = video.get('contentRating') if data.get('authRequired'): resource = self._get_mvpd_resource( 'fbc-fox', title, video.get('guid'), rating) @@ -86,6 +92,18 @@ class FOXIE(AdobePassIE): 'auth': self._extract_mvpd_auth( url, video_id, 'fbc-fox', resource) }) + m3u8_url = self._download_json(release_url, video_id)['playURL'] + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) + + duration = int_or_none(video.get('durationInSeconds')) or int_or_none( + video.get('duration')) or parse_duration(video.get('duration')) + timestamp = unified_timestamp(video.get('datePublished')) + creator = data.get('brand') or data.get('network') or video.get('network') + series = video.get('seriesName') or data.get( + 'seriesName') or data.get('show') subtitles = {} for doc_rel in video.get('documentReleases', []): @@ -98,36 +116,19 @@ class FOXIE(AdobePassIE): }] break - info = { + return { 'id': video_id, 'title': title, - 'description': description, + 'formats': formats, + 'description': video.get('description'), 'duration': duration, 'timestamp': timestamp, - 'age_limit': age_limit, + 'age_limit': parse_age_limit(rating), 'creator': creator, 'series': series, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - 'release_year': release_year, + 'season_number': int_or_none(video.get('seasonNumber')), + 'episode': video.get('name'), + 'episode_number': int_or_none(video.get('episodeNumber')), + 'release_year': int_or_none(video.get('releaseYear')), 'subtitles': subtitles, } - - urlh = self._request_webpage(HEADRequest(release_url), video_id) - video_url = compat_str(urlh.geturl()) - - if UplynkPreplayIE.suitable(video_url): - info.update({ - '_type': 'url_transparent', - 'url': video_url, - 'ie_key': UplynkPreplayIE.ie_key(), - }) - else: - m3u8_url = self._download_json(release_url, video_id)['playURL'] - formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls') - self._sort_formats(formats) - info['formats'] = formats - return info diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index 4d2ee6408..165964ca0 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,15 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .adobepass import AdobePassIE -from .theplatform import ThePlatformIE from ..utils import ( smuggle_url, url_basename, - update_url_query, - get_element_by_class, ) @@ -64,132 +58,3 @@ class NationalGeographicVideoIE(InfoExtractor): {'force_smil_url': True}), 'id': guid, } - - -class NationalGeographicIE(ThePlatformIE, AdobePassIE): - IE_NAME = 'natgeo' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)' - - _TESTS = [ - { - 'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/', - 'md5': '518c9aa655686cf81493af5cc21e2a04', - 'info_dict': { - 'id': 'vKInpacll2pC', - 'ext': 'mp4', - 'title': 'Uncovering a Universal Knowledge', - 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a', - 'timestamp': 1458680907, - 'upload_date': '20160322', - 'uploader': 'NEWA-FNG-NGTV', - }, - 'add_ie': ['ThePlatform'], - }, - { - 'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/', - 'md5': 'c4912f656b4cbe58f3e000c489360989', - 'info_dict': { - 'id': 'Pok5lWCkiEFA', - 'ext': 'mp4', - 'title': 'The Stunning Red Bird of Paradise', - 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c', - 'timestamp': 1459362152, - 'upload_date': '20160330', - 'uploader': 'NEWA-FNG-NGTV', - }, - 'add_ie': ['ThePlatform'], - }, - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/', - 'only_matching': True, - } - ] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - release_url = self._search_regex( - r'video_auth_playlist_url\s*=\s*"([^"]+)"', - webpage, 'release url') - theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path') - video_id = theplatform_path.split('/')[-1] - query = { - 'mbr': 'true', - } - is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False) - if is_auth == 'auth': - auth_resource_id = self._search_regex( - r"video_auth_resourceId\s*=\s*'([^']+)'", - webpage, 'auth resource id') - query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id) - - formats = [] - subtitles = {} - for key, value in (('switch', 'http'), ('manifest', 'm3u')): - tp_query = query.copy() - tp_query.update({ - key: value, - }) - tp_formats, tp_subtitles = self._extract_theplatform_smil( - update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - info = self._extract_theplatform_metadata(theplatform_path, display_id) - info.update({ - 'id': video_id, - 'formats': formats, - 'subtitles': subtitles, - 'display_id': display_id, - }) - return info - - -class NationalGeographicEpisodeGuideIE(InfoExtractor): - IE_NAME = 'natgeo:episodeguide' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide' - _TESTS = [ - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/', - 'info_dict': { - 'id': 'the-story-of-god-with-morgan-freeman-season-1', - 'title': 'The Story of God with Morgan Freeman - Season 1', - }, - 'playlist_mincount': 6, - }, - { - 'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2', - 'info_dict': { - 'id': 'underworld-inc-season-2', - 'title': 'Underworld, Inc. - Season 2', - }, - 'playlist_mincount': 7, - }, - ] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - show = get_element_by_class('show', webpage) - selected_season = self._search_regex( - r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>', - webpage, 'selected season') - entries = [ - self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic') - for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)] - return self.playlist_result( - entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')), - '%s - %s' % (show, selected_season)) From 7c072f00d66f3b3f44d301059443480a5c83d3c0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 10:50:18 +0100 Subject: [PATCH 040/362] [jwplatform] use JW Platform Delivery API V2 and add support for more urls --- youtube_dl/extractor/jwplatform.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 63d0dc998..d19a6a774 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,8 +7,8 @@ from .common import InfoExtractor class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' - _TEST = { + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' + _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', 'info_dict': { @@ -19,7 +19,10 @@ class JWPlatformIE(InfoExtractor): 'upload_date': '20081127', 'timestamp': 1227796140, } - } + }, { + 'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js', + 'only_matching': True, + }] @staticmethod def _extract_url(webpage): @@ -34,5 +37,5 @@ class JWPlatformIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) + json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id) return self._parse_jwplayer_data(json_data, video_id) From 432aba1c5e68cf8efccb868107785a15617d5109 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 10:54:46 +0100 Subject: [PATCH 041/362] [outsidetv] Add new extractor(closes #18774) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/outsidetv.py | 28 ++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) create mode 100644 youtube_dl/extractor/outsidetv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a01d99b85..de38c6641 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -829,6 +829,7 @@ from .orf import ( ORFOE1IE, ORFIPTVIE, ) +from .outsidetv import OutsideTVIE from .packtpub import ( PacktPubIE, PacktPubCourseIE, diff --git a/youtube_dl/extractor/outsidetv.py b/youtube_dl/extractor/outsidetv.py new file mode 100644 index 000000000..c5333b08c --- /dev/null +++ b/youtube_dl/extractor/outsidetv.py @@ -0,0 +1,28 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class OutsideTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?outsidetv\.com/(?:[^/]+/)*?play/[a-zA-Z0-9]{8}/\d+/\d+/(?P<id>[a-zA-Z0-9]{8})' + _TESTS = [{ + 'url': 'http://www.outsidetv.com/category/snow/play/ZjQYboH6/1/10/Hdg0jukV/4', + 'md5': '192d968fedc10b2f70ec31865ffba0da', + 'info_dict': { + 'id': 'Hdg0jukV', + 'ext': 'mp4', + 'title': 'Home - Jackson Ep 1 | Arbor Snowboards', + 'description': 'md5:41a12e94f3db3ca253b04bb1e8d8f4cd', + 'upload_date': '20181225', + 'timestamp': 1545742800, + } + }, { + 'url': 'http://www.outsidetv.com/home/play/ZjQYboH6/1/10/Hdg0jukV/4', + 'only_matching': True, + }] + + def _real_extract(self, url): + jw_media_id = self._match_id(url) + return self.url_result( + 'jwplatform:' + jw_media_id, 'JWPlatform', jw_media_id) From c3e543893bfba7faa7c13e53fbe6b60f936b81f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Jan 2019 22:46:53 +0700 Subject: [PATCH 042/362] [youtube] Extract live HLS URL from player response (closes #18799) --- youtube_dl/extractor/youtube.py | 55 +++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 539ff6ff2..29773877e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1931,31 +1931,38 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'http_chunk_size': 10485760, } formats.append(dct) - elif video_info.get('hlsvp'): - manifest_url = video_info['hlsvp'][0] - formats = [] - m3u8_formats = self._extract_m3u8_formats( - manifest_url, video_id, 'mp4', fatal=False) - for a_format in m3u8_formats: - itag = self._search_regex( - r'/itag/(\d+)/', a_format['url'], 'itag', default=None) - if itag: - a_format['format_id'] = itag - if itag in self._formats: - dct = self._formats[itag].copy() - dct.update(a_format) - a_format = dct - a_format['player_url'] = player_url - # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming - a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' - formats.append(a_format) else: - error_message = clean_html(video_info.get('reason', [None])[0]) - if not error_message: - error_message = extract_unavailable_message() - if error_message: - raise ExtractorError(error_message, expected=True) - raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') + manifest_url = ( + url_or_none(try_get( + player_response, + lambda x: x['streamingData']['hlsManifestUrl'], + compat_str)) or + url_or_none(try_get( + video_info, lambda x: x['hlsvp'][0], compat_str))) + if manifest_url: + formats = [] + m3u8_formats = self._extract_m3u8_formats( + manifest_url, video_id, 'mp4', fatal=False) + for a_format in m3u8_formats: + itag = self._search_regex( + r'/itag/(\d+)/', a_format['url'], 'itag', default=None) + if itag: + a_format['format_id'] = itag + if itag in self._formats: + dct = self._formats[itag].copy() + dct.update(a_format) + a_format = dct + a_format['player_url'] = player_url + # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming + a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' + formats.append(a_format) + else: + error_message = clean_html(video_info.get('reason', [None])[0]) + if not error_message: + error_message = extract_unavailable_message() + if error_message: + raise ExtractorError(error_message, expected=True) + raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info') # uploader video_uploader = try_get( From a4491dd55c5feaf02ac8969caafd637265cbeede Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Jan 2019 23:23:19 +0700 Subject: [PATCH 043/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/ChangeLog b/ChangeLog index 41d190a72..c7d090c6c 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,29 @@ +version <unreleased> + +Core +* [extractor/common] Use episode name as title in _json_ld ++ [extractor/common] Add support for movies in _json_ld +* [postprocessor/ffmpeg] Embed subtitles with non-standard language codes + (#18765) ++ [utils] Add language codes replaced in 1989 revision of ISO 639 + to ISO639Utils (#18765) + +Extractors +* [youtube] Extract live HLS URL from player response (#18799) ++ [outsidetv] Add support for outsidetv.com (#18774) +* [jwplatform] Use JW Platform Delivery API V2 and add support for more URLs ++ [fox] Add support National Geographic (#17985, #15333, #14698) ++ [playplustv] Add support for playplus.tv (#18789) +* [globo] Set GLBID cookie manually (#17346) ++ [gaia] Add support for gaia.com (#14605) +* [youporn] Fix title and description extraction (#18748) ++ [hungama] Add support for hungama.com (#17402, #18771) +* [dtube] Fix extraction (#18741) +* [tvnow] Fix and rework extractors and prepare for a switch to the new API + (#17245, #18499) +* [carambatv:page] Fix extraction (#18739) + + version 2019.01.02 Extractors From b64f6e690ff84052751c593a8826a40a63cb1d84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Jan 2019 23:26:54 +0700 Subject: [PATCH 044/362] release 2019.01.10 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 11 ++++++++--- youtube_dl/version.py | 2 +- 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 3986bbc8e..d6abdbcb7 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.02*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.02** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.10** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.02 +[debug] youtube-dl version 2019.01.10 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index c7d090c6c..3d60754c5 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.10 Core * [extractor/common] Use episode name as title in _json_ld diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e92064432..c01409419 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -320,6 +320,7 @@ - **Fusion** - **Fux** - **FXNetworks** + - **Gaia** - **GameInformer** - **GameOne** - **gameone:playlist** @@ -370,6 +371,8 @@ - **HRTiPlaylist** - **Huajiao**: 花椒直播 - **HuffPost**: Huffington Post + - **Hungama** + - **HungamaSong** - **Hypem** - **Iconosquare** - **ign.com** @@ -540,8 +543,6 @@ - **MyviEmbed** - **MyVisionTV** - **n-tv.de** - - **natgeo** - - **natgeo:episodeguide** - **natgeo:video** - **Naver** - **NBA** @@ -642,6 +643,7 @@ - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek - **OsnatelTV** + - **OutsideTV** - **PacktPub** - **PacktPubCourse** - **PandaTV**: 熊猫TV @@ -666,6 +668,7 @@ - **Pinkbike** - **Pladform** - **play.fm** + - **PlayPlusTV** - **PlaysTV** - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz - **Playvid** @@ -934,7 +937,9 @@ - **TVNet** - **TVNoe** - **TVNow** - - **TVNowList** + - **TVNowAnnual** + - **TVNowNew** + - **TVNowSeason** - **TVNowShow** - **tvp**: Telewizja Polska - **tvp:embed**: Telewizja Polska diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 07a444706..5ba61f489 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.02' +__version__ = '2019.01.10' From c469e8808c723d6ba090c0b33c292622a3cb555e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 18:48:52 +0100 Subject: [PATCH 045/362] [playplustv] add support for playplus.com(#18789) --- youtube_dl/extractor/playplustv.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/playplustv.py b/youtube_dl/extractor/playplustv.py index 419c2974b..1e30ab23a 100644 --- a/youtube_dl/extractor/playplustv.py +++ b/youtube_dl/extractor/playplustv.py @@ -15,7 +15,7 @@ from ..utils import ( class PlayPlusTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?playplus\.tv/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' + _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' _TEST = { 'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e', 'md5': 'd078cb89d7ab6b9df37ce23c647aef72', From a64646e417615173c9436887116402c9c4c9f6ee Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 11 Jan 2019 15:09:44 +0100 Subject: [PATCH 046/362] [postprocessor/ffmpeg] sanitize ffmpeg version for Ubuntu and Arch Linux systems(closes #18813) --- youtube_dl/postprocessor/ffmpeg.py | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index efcd39d57..173bdbe68 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -79,6 +79,19 @@ class FFmpegPostProcessor(PostProcessor): programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] prefer_ffmpeg = True + def get_ffmpeg_version(path): + ver = get_exe_version(path, args=['-version']) + if ver: + regexs = [ + r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu + r'n([0-9.]+)$', # Arch Linux + ] + for regex in regexs: + mobj = re.match(regex, ver) + if mobj: + ver = mobj.group(1) + return ver + self.basename = None self.probe_basename = None @@ -110,11 +123,10 @@ class FFmpegPostProcessor(PostProcessor): self._paths = dict( (p, os.path.join(location, p)) for p in programs) self._versions = dict( - (p, get_exe_version(self._paths[p], args=['-version'])) - for p in programs) + (p, get_ffmpeg_version(self._paths[p])) for p in programs) if self._versions is None: self._versions = dict( - (p, get_exe_version(p, args=['-version'])) for p in programs) + (p, get_ffmpeg_version(p)) for p in programs) self._paths = dict((p, p) for p in programs) if prefer_ffmpeg is False: From 5caa531a1a7e070e3bef8cc60c3d00c3f7ab1e6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 11 Jan 2019 23:47:23 +0700 Subject: [PATCH 047/362] [postprocessor/ffmpeg] PEP 8 --- youtube_dl/postprocessor/ffmpeg.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 173bdbe68..a9fafa363 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -83,8 +83,8 @@ class FFmpegPostProcessor(PostProcessor): ver = get_exe_version(path, args=['-version']) if ver: regexs = [ - r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu - r'n([0-9.]+)$', # Arch Linux + r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu + r'n([0-9.]+)$', # Arch Linux ] for regex in regexs: mobj = re.match(regex, ver) From cbdc688c41876714f1d7e2f82ba9d11f6695448a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 12 Jan 2019 00:30:06 +0700 Subject: [PATCH 048/362] [postprocessor/ffmpeg] Relax ubuntu ffmpeg version regex --- youtube_dl/postprocessor/ffmpeg.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index a9fafa363..39a905380 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -83,8 +83,9 @@ class FFmpegPostProcessor(PostProcessor): ver = get_exe_version(path, args=['-version']) if ver: regexs = [ - r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu + r'(?:\d+:)?([0-9.]+)-[0-9]+ubuntu[0-9.]+$', # Ubuntu, see [1] r'n([0-9.]+)$', # Arch Linux + # 1. http://www.ducea.com/2006/06/17/ubuntu-package-version-naming-explanation/ ] for regex in regexs: mobj = re.match(regex, ver) From 60a899bb7ed583b4c40289925c8127e746c683ea Mon Sep 17 00:00:00 2001 From: Atlas Sullivan <AtlasJan@gmx.com> Date: Fri, 11 Jan 2019 19:15:48 +0000 Subject: [PATCH 049/362] [README.md] Fix typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 901595444..70bcfaccf 100644 --- a/README.md +++ b/README.md @@ -496,7 +496,7 @@ The `-o` option allows users to indicate a template for the output file names. **tl;dr:** [navigate me to examples](#output-template-examples). -The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are: +The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are: - `id` (string): Video identifier - `title` (string): Video title From ed8db0a25c93f5611dfae81ee8f15cbc177bd0ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 12 Jan 2019 04:56:17 +0700 Subject: [PATCH 050/362] [wistia] Extend _VALID_URL (closes #18823) --- youtube_dl/extractor/wistia.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 01a51275e..fa142b974 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,7 +12,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -38,6 +38,9 @@ class WistiaIE(InfoExtractor): }, { 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt', 'only_matching': True, + }, { + 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json', + 'only_matching': True, }] @staticmethod From d65f6e734b5c00acbb396f4569907f7957e1cbef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 13 Jan 2019 03:57:31 +0700 Subject: [PATCH 051/362] [bitchute] Check formats (#18833) --- youtube_dl/extractor/bitchute.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index aa034355a..4f39424f5 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -55,6 +55,7 @@ class BitChuteIE(InfoExtractor): formats = [ {'url': format_url} for format_url in orderedSet(format_urls)] + self._check_formats(formats, video_id) self._sort_formats(formats) description = self._html_search_regex( From f1ab3b7de7667c0382bf6eb6364ccab4260c0654 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 13 Jan 2019 10:01:26 +0100 Subject: [PATCH 052/362] [downloader/hls] fix uplynk ad skipping(closes #18824) --- youtube_dl/downloader/hls.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index fd304527e..4def8e2d5 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -75,10 +75,14 @@ class HlsFD(FragmentFD): fd.add_progress_hook(ph) return fd.real_download(filename, info_dict) - def is_ad_fragment(s): + def is_ad_fragment_start(s): return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad')) + def is_ad_fragment_end(s): + return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or + s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment')) + media_frags = 0 ad_frags = 0 ad_frag_next = False @@ -87,12 +91,13 @@ class HlsFD(FragmentFD): if not line: continue if line.startswith('#'): - if is_ad_fragment(line): - ad_frags += 1 + if is_ad_fragment_start(line): ad_frag_next = True + elif is_ad_fragment_end(line): + ad_frag_next = False continue if ad_frag_next: - ad_frag_next = False + ad_frags += 1 continue media_frags += 1 @@ -123,7 +128,6 @@ class HlsFD(FragmentFD): if line: if not line.startswith('#'): if ad_frag_next: - ad_frag_next = False continue frag_index += 1 if frag_index <= ctx['fragment_index']: @@ -196,8 +200,10 @@ class HlsFD(FragmentFD): 'start': sub_range_start, 'end': sub_range_start + int(splitted_byte_range[0]), } - elif is_ad_fragment(line): + elif is_ad_fragment_start(line): ad_frag_next = True + elif is_ad_fragment_end(line): + ad_frag_next = False self._finish_frag_download(ctx) From 3b983ee471305946709dcb83fa3799fc26a7db03 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 13 Jan 2019 15:46:54 +0100 Subject: [PATCH 053/362] [curiositystream] add support for non app urls --- youtube_dl/extractor/curiositystream.py | 56 +++++++++++++------------ 1 file changed, 29 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/curiositystream.py b/youtube_dl/extractor/curiositystream.py index 35b1e7a34..e4a7fca6c 100644 --- a/youtube_dl/extractor/curiositystream.py +++ b/youtube_dl/extractor/curiositystream.py @@ -46,8 +46,24 @@ class CuriosityStreamBaseIE(InfoExtractor): self._handle_errors(result) self._auth_token = result['message']['auth_token'] - def _extract_media_info(self, media): - video_id = compat_str(media['id']) + +class CuriosityStreamIE(CuriosityStreamBaseIE): + IE_NAME = 'curiositystream' + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)' + _TEST = { + 'url': 'https://app.curiositystream.com/video/2', + 'md5': '262bb2f257ff301115f1973540de8983', + 'info_dict': { + 'id': '2', + 'ext': 'mp4', + 'title': 'How Did You Develop The Internet?', + 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + media = self._call_api('media/' + video_id, video_id) title = media['title'] formats = [] @@ -114,38 +130,21 @@ class CuriosityStreamBaseIE(InfoExtractor): } -class CuriosityStreamIE(CuriosityStreamBaseIE): - IE_NAME = 'curiositystream' - _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)' - _TEST = { - 'url': 'https://app.curiositystream.com/video/2', - 'md5': '262bb2f257ff301115f1973540de8983', - 'info_dict': { - 'id': '2', - 'ext': 'mp4', - 'title': 'How Did You Develop The Internet?', - 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - media = self._call_api('media/' + video_id, video_id) - return self._extract_media_info(media) - - class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): IE_NAME = 'curiositystream:collection' - _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)' + _TESTS = [{ 'url': 'https://app.curiositystream.com/collection/2', 'info_dict': { 'id': '2', 'title': 'Curious Minds: The Internet', 'description': 'How is the internet shaping our lives in the 21st Century?', }, - 'playlist_mincount': 12, - } + 'playlist_mincount': 17, + }, { + 'url': 'https://curiositystream.com/series/2', + 'only_matching': True, + }] def _real_extract(self, url): collection_id = self._match_id(url) @@ -153,7 +152,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): 'collections/' + collection_id, collection_id) entries = [] for media in collection.get('media', []): - entries.append(self._extract_media_info(media)) + media_id = compat_str(media.get('id')) + entries.append(self.url_result( + 'https://curiositystream.com/video/' + media_id, + CuriosityStreamIE.ie_key(), media_id)) return self.playlist_result( entries, collection_id, collection.get('title'), collection.get('description')) From 10026329c2534635876921da229f382098b8f8e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 14 Jan 2019 23:23:51 +0700 Subject: [PATCH 054/362] [skylinewebcams] Fix extraction (closes #18853) --- youtube_dl/extractor/skylinewebcams.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/skylinewebcams.py b/youtube_dl/extractor/skylinewebcams.py index 5b4aaac6f..b7f8ac736 100644 --- a/youtube_dl/extractor/skylinewebcams.py +++ b/youtube_dl/extractor/skylinewebcams.py @@ -26,7 +26,7 @@ class SkylineWebcamsIE(InfoExtractor): webpage = self._download_webpage(url, video_id) stream_url = self._search_regex( - r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, + r'(?:url|source)\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, 'stream url', group='url') title = self._og_search_title(webpage) From 929ba3997b026fd9fafe15d447732d8ccdf367bb Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 15 Jan 2019 10:23:59 +0100 Subject: [PATCH 055/362] [funimation] fix extraction(closes #14089) --- youtube_dl/extractor/funimation.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py index 07d01caec..8bbedca26 100644 --- a/youtube_dl/extractor/funimation.py +++ b/youtube_dl/extractor/funimation.py @@ -1,6 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals +import random +import string + from .common import InfoExtractor from ..compat import compat_HTTPError from ..utils import ( @@ -87,7 +90,7 @@ class FunimationIE(InfoExtractor): video_id = title_data.get('id') or self._search_regex([ r"KANE_customdimensions.videoID\s*=\s*'(\d+)';", - r'<iframe[^>]+src="/player/(\d+)"', + r'<iframe[^>]+src="/player/(\d+)', ], webpage, 'video_id', default=None) if not video_id: player_url = self._html_search_meta([ @@ -108,8 +111,10 @@ class FunimationIE(InfoExtractor): if self._TOKEN: headers['Authorization'] = 'Token %s' % self._TOKEN sources = self._download_json( - 'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id, - video_id, headers=headers)['items'] + 'https://www.funimation.com/api/showexperience/%s/' % video_id, + video_id, headers=headers, query={ + 'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]), + })['items'] except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: error = self._parse_json(e.cause.read(), video_id)['errors'][0] From 561b456e2d10e60b74a1bee6154bb7fdb0bfaf60 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 01:12:58 +0700 Subject: [PATCH 056/362] [youtube] Extract DASH formats from player response (closes #18804) --- youtube_dl/extractor/youtube.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 29773877e..cca149107 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1545,6 +1545,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if dash_mpd and dash_mpd[0] not in dash_mpds: dash_mpds.append(dash_mpd[0]) + def add_dash_mpd_pr(pl_response): + dash_mpd = url_or_none(try_get( + pl_response, lambda x: x['streamingData']['dashManifestUrl'], + compat_str)) + if dash_mpd and dash_mpd not in dash_mpds: + dash_mpds.append(dash_mpd) + is_live = None view_count = None @@ -1602,6 +1609,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if isinstance(pl_response, dict): player_response = pl_response if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): + add_dash_mpd_pr(player_response) # We also try looking in get_video_info since it may contain different dashmpd # URL that points to a DASH manifest with possibly different itag set (some itags # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH @@ -1633,6 +1641,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): pl_response = get_video_info.get('player_response', [None])[0] if isinstance(pl_response, dict): player_response = pl_response + add_dash_mpd_pr(player_response) add_dash_mpd(get_video_info) if view_count is None: view_count = extract_view_count(get_video_info) From 2f483bc1c389709623117079439708783122b5ec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 01:28:50 +0700 Subject: [PATCH 057/362] [youtube] Skip unsupported adaptive stream type (#18804) --- youtube_dl/extractor/youtube.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index cca149107..5e93b5329 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1827,6 +1827,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): url_data = compat_parse_qs(url_data_str) if 'itag' not in url_data or 'url' not in url_data: continue + stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) + # Unsupported FORMAT_STREAM_TYPE_OTF + if stream_type == 3: + continue format_id = url_data['itag'][0] url = url_data['url'][0] From a16c7c033a161f310b69d444edc9dbf67cfc49ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:17:49 +0700 Subject: [PATCH 058/362] [test/helper] Add support for maxcount and count collection len test checkers --- test/helper.py | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/test/helper.py b/test/helper.py index aa9a1c9b2..e62aab11e 100644 --- a/test/helper.py +++ b/test/helper.py @@ -153,15 +153,27 @@ def expect_value(self, got, expected, field): isinstance(got, compat_str), 'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got))) got = 'md5:' + md5(got) - elif isinstance(expected, compat_str) and expected.startswith('mincount:'): + elif isinstance(expected, compat_str) and re.match(r'^(?:min|max)?count:\d+', expected): self.assertTrue( isinstance(got, (list, dict)), 'Expected field %s to be a list or a dict, but it is of type %s' % ( field, type(got).__name__)) - expected_num = int(expected.partition(':')[2]) - assertGreaterEqual( + op, _, expected_num = expected.partition(':') + expected_num = int(expected_num) + if op == 'mincount': + assert_func = assertGreaterEqual + msg_tmpl = 'Expected %d items in field %s, but only got %d' + elif op == 'maxcount': + assert_func = assertLessEqual + msg_tmpl = 'Expected maximum %d items in field %s, but got %d' + elif op == 'count': + assert_func = assertEqual + msg_tmpl = 'Expected exactly %d items in field %s, but got %d' + else: + assert False + assert_func( self, len(got), expected_num, - 'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got))) + msg_tmpl % (expected_num, field, len(got))) return self.assertEqual( expected, got, @@ -237,6 +249,20 @@ def assertGreaterEqual(self, got, expected, msg=None): self.assertTrue(got >= expected, msg) +def assertLessEqual(self, got, expected, msg=None): + if not (got <= expected): + if msg is None: + msg = '%r not less than or equal to %r' % (got, expected) + self.assertTrue(got <= expected, msg) + + +def assertEqual(self, got, expected, msg=None): + if not (got == expected): + if msg is None: + msg = '%r not equal to %r' % (got, expected) + self.assertTrue(got == expected, msg) + + def expect_warnings(ydl, warnings_re): real_warning = ydl.report_warning From 4fe54c128a11d394874505af75aaa5a2276aa3ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:18:27 +0700 Subject: [PATCH 059/362] [youtube] Update tests and add a tests for #18804 --- youtube_dl/extractor/youtube.py | 57 +++++++++++++++++---------------- 1 file changed, 29 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 5e93b5329..730935657 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -498,7 +498,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', 'upload_date': '20121002', - 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], @@ -527,7 +526,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Icona Pop', 'uploader_id': 'IconaPop', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', - 'license': 'Standard YouTube License', 'creator': 'Icona Pop', 'track': 'I Love It (feat. Charli XCX)', 'artist': 'Icona Pop', @@ -540,14 +538,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': '07FYdnEawAQ', 'ext': 'mp4', 'upload_date': '20130703', - 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)', 'alt_title': 'Tunnel Vision', - 'description': 'md5:64249768eec3bc4276236606ea996373', + 'description': 'md5:07dab3356cde4199048e4c7cd93471e1', 'duration': 419, 'uploader': 'justintimberlakeVEVO', 'uploader_id': 'justintimberlakeVEVO', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', - 'license': 'Standard YouTube License', 'creator': 'Justin Timberlake', 'track': 'Tunnel Vision', 'artist': 'Justin Timberlake', @@ -566,7 +563,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'SET India', 'uploader_id': 'setindia', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', - 'license': 'Standard YouTube License', 'age_limit': 18, } }, @@ -581,7 +577,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'phihag', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', 'upload_date': '20121002', - 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], @@ -605,7 +600,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', 'description': '', 'uploader': '8KVIDEO', - 'license': 'Standard YouTube License', 'title': 'UHDTV TEST 8K VIDEO.mp4' }, 'params': { @@ -620,13 +614,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'info_dict': { 'id': 'IB3lcPjvWLA', 'ext': 'm4a', - 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', - 'description': 'md5:1900ed86ee514927b9e00fbead6969a5', + 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', + 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', 'duration': 244, 'uploader': 'AfrojackVEVO', 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', - 'license': 'Standard YouTube License', }, 'params': { 'youtube_include_dash_manifest': True, @@ -640,13 +633,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', - 'alt_title': 'Shake It Off', - 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', + 'description': 'md5:bec2185232c05479482cb5a9b82719bf', 'duration': 242, 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', - 'license': 'Standard YouTube License', 'creator': 'Taylor Swift', }, 'params': { @@ -662,10 +653,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'duration': 219, 'upload_date': '20100909', - 'uploader': 'TJ Kirk', + 'uploader': 'Amazing Atheist', 'uploader_id': 'TheAmazingAtheist', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', - 'license': 'Standard YouTube License', 'title': 'Burning Everyone\'s Koran', 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', } @@ -683,7 +673,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'WitcherGame', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', 'upload_date': '20140605', - 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -692,7 +681,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', 'info_dict': { 'id': '6kLq3WMV1nU', - 'ext': 'webm', + 'ext': 'mp4', 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', 'duration': 246, @@ -700,7 +689,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'LloydVEVO', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', 'upload_date': '20110629', - 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -718,7 +706,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'creator': 'deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', - 'license': 'Standard YouTube License', 'title': 'Deadmau5 - Some Chords (HD)', 'alt_title': 'Some Chords', }, @@ -736,7 +723,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150827', 'uploader_id': 'olympic', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', - 'license': 'Standard YouTube License', 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', 'uploader': 'Olympic', 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', @@ -758,7 +744,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', 'uploader': '孫ᄋᄅ', - 'license': 'Standard YouTube License', 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', }, }, @@ -792,7 +777,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'dorappi2000', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', 'uploader': 'dorappi2000', - 'license': 'Standard YouTube License', 'formats': 'mincount:31', }, 'skip': 'not actual anymore', @@ -808,7 +792,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Airtek', 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', - 'license': 'Standard YouTube License', 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', }, 'params': { @@ -881,6 +864,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'This video is not available.', }, { # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536) @@ -917,7 +901,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'IronSoulElf', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', 'uploader': 'IronSoulElf', - 'license': 'Standard YouTube License', 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', 'track': 'Dark Walk - Position Music', 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', @@ -1021,13 +1004,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'iqKdEhx-dD4', 'ext': 'mp4', 'title': 'Isolation - Mind Field (Ep 1)', - 'description': 'md5:25b78d2f64ae81719f5c96319889b736', + 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f', 'duration': 2085, 'upload_date': '20170118', 'uploader': 'Vsauce', 'uploader_id': 'Vsauce', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', - 'license': 'Standard YouTube License', 'series': 'Mind Field', 'season_number': 1, 'episode_number': 1, @@ -1053,7 +1035,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'New Century Foundation', 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', - 'license': 'Standard YouTube License', }, 'params': { 'skip_download': True, @@ -1081,6 +1062,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # DRM protected 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', 'only_matching': True, + }, + { + # Video with unsupported adaptive stream type formats + 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', + 'info_dict': { + 'id': 'Z4Vy8R84T1U', + 'ext': 'mp4', + 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 433, + 'upload_date': '20130923', + 'uploader': 'Amelia Putri Harwita', + 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', + 'formats': 'maxcount:10', + }, + 'params': { + 'skip_download': True, + 'youtube_include_dash_manifest': False, + }, } ] From b0d73a745656443baf3e2134d9ca03bd3a4a934c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:20:10 +0700 Subject: [PATCH 060/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index 3d60754c5..d25169074 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version <unreleased> + +Core ++ [test/helper] Add support for maxcount and count collection len checkers +* [downloader/hls] Fix uplynk ad skipping (#18824) +* [postprocessor/ffmpeg] Improve ffmpeg version parsing (#18813) + +Extractors +* [youtube] Skip unsupported adaptive stream type (#18804) ++ [youtube] Extract DASH formats from player response (#18804) +* [funimation] Fix extraction (#14089) +* [skylinewebcams] Fix extraction (#18853) ++ [curiositystream] Add support for non app URLs ++ [bitchute] Check formats (#18833) +* [wistia] Extend URL regular expression (#18823) ++ [playplustv] Add support for playplus.com (#18789) + + version 2019.01.10 Core From bfc8eeea57251796d44f1e10b61d06760690bc25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:24:08 +0700 Subject: [PATCH 061/362] release 2019.01.16 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index d6abdbcb7..650f78511 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.10** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.16*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.16** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.10 +[debug] youtube-dl version 2019.01.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index d25169074..13019bf2b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.16 Core + [test/helper] Add support for maxcount and count collection len checkers diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 5ba61f489..c13f3a38a 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.10' +__version__ = '2019.01.16' From fa4ac365f69cbd51e4c9801984ebea49a12825b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 17 Jan 2019 10:24:44 +0700 Subject: [PATCH 062/362] [youtube] Extend JS player signature function name regexes (closes #18890, closes #18891, closes #18893) --- youtube_dl/extractor/youtube.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 730935657..c8bf98b58 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1198,8 +1198,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): funcname = self._search_regex( (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', - r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(', + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') From f53cecd796dbb698abbde6ac2f7f973dba78f8a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 17 Jan 2019 10:25:50 +0700 Subject: [PATCH 063/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/ChangeLog b/ChangeLog index 13019bf2b..171034a75 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,10 @@ +version <unreleased> + +Extractors +* [youtube] Extend JS player signature function name regular expressions + (#18890, #18891, #18893) + + version 2019.01.16 Core From 29639b363ddab7903ceae096912a0227c8017533 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 17 Jan 2019 10:27:17 +0700 Subject: [PATCH 064/362] release 2019.01.17 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 650f78511..841bca914 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.16*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.16** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.17** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.16 +[debug] youtube-dl version 2019.01.17 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 171034a75..902301765 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.17 Extractors * [youtube] Extend JS player signature function name regular expressions diff --git a/youtube_dl/version.py b/youtube_dl/version.py index c13f3a38a..ea3f62928 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.16' +__version__ = '2019.01.17' From 79fec976b0c250446ea9a9eb7323fb2045ee37fe Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Jan 2019 09:44:08 +0100 Subject: [PATCH 065/362] [vimeo] fix extraction for password protected player URLs(closes #18889) --- youtube_dl/extractor/vimeo.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 5e15f060b..fd37f919b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import json import re import itertools @@ -392,6 +393,22 @@ class VimeoIE(VimeoBaseInfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://player.vimeo.com/video/68375962', + 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', + 'info_dict': { + 'id': '68375962', + 'ext': 'mp4', + 'title': 'youtube-dl password protected test video', + 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', + 'uploader_id': 'user18948128', + 'uploader': 'Jaime Marquínez Ferrándiz', + 'duration': 10, + }, + 'params': { + 'videopassword': 'youtube-dl', + }, + }, { 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', 'only_matching': True, @@ -452,7 +469,9 @@ class VimeoIE(VimeoBaseInfoExtractor): password = self._downloader.params.get('videopassword') if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') - data = urlencode_postdata({'password': password}) + data = urlencode_postdata({ + 'password': base64.b64encode(password.encode()), + }) pass_url = url + '/check-password' password_request = sanitized_Request(pass_url, data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') From e2dd132f054df5b6c09b7c274752a77d8ba44f8d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Jan 2019 23:56:37 +0100 Subject: [PATCH 066/362] [cartoonnetwork] fix extraction(closes #15664)(closes #17224) --- youtube_dl/extractor/cartoonnetwork.py | 56 +++++++++++++++++--------- 1 file changed, 38 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/cartoonnetwork.py b/youtube_dl/extractor/cartoonnetwork.py index 6aeebd7b3..48b33617f 100644 --- a/youtube_dl/extractor/cartoonnetwork.py +++ b/youtube_dl/extractor/cartoonnetwork.py @@ -1,20 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .turner import TurnerBaseIE +from ..utils import int_or_none class CartoonNetworkIE(TurnerBaseIE): _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html' _TEST = { - 'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html', + 'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html', 'info_dict': { - 'id': '8a250ab04ed07e6c014ef3f1e2f9016c', + 'id': '6e3375097f63874ebccec7ef677c1c3845fa850e', 'ext': 'mp4', - 'title': 'Starfire the Cat Lady', - 'description': 'Robin decides to become a cat so that Starfire will finally love him.', + 'title': 'How to Draw Upgrade', + 'description': 'md5:2061d83776db7e8be4879684eefe8c0f', }, 'params': { # m3u8 download @@ -25,18 +24,39 @@ class CartoonNetworkIE(TurnerBaseIE): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups() - query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id - return self._extract_cvp_info( - 'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, { - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big', - 'tokenizer_src': 'https://token.vgtf.net/token/token_mobile', - }, - }, { + + def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False): + metadata_re = '' + if content_re: + metadata_re = r'|video_metadata\.content_' + content_re + return self._search_regex( + r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re), + webpage, name, fatal=fatal) + + media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True) + title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True) + + info = self._extract_ngtv_info( + media_id, {'networkId': 'cartoonnetwork'}, { 'url': url, 'site_name': 'CartoonNetwork', - 'auth_required': self._search_regex( - r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);', - webpage, 'auth required', default='false') == 'true', + 'auth_required': find_field('authType', 'auth type') != 'unauth', }) + + series = find_field( + 'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage) + info.update({ + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'description': self._html_search_meta('description', webpage), + 'series': series, + 'episode': title, + }) + + for field in ('season', 'episode'): + field_name = field + 'Number' + info[field + '_number'] = int_or_none(find_field( + field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage)) + + return info From 2bfc1d9d68dec097fd8093dc0284dd0cd64beb2e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 19 Jan 2019 21:25:15 +0100 Subject: [PATCH 067/362] [extractor/common] imporove HLS video only format detection(closes #18923) --- youtube_dl/extractor/common.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 9e7febcad..af621b74b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1596,6 +1596,7 @@ class InfoExtractor(object): # References: # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21 # 2. https://github.com/rg3/youtube-dl/issues/12211 + # 3. https://github.com/rg3/youtube-dl/issues/18923 # We should try extracting formats only from master playlists [1, 4.3.4], # i.e. playlists that describe available qualities. On the other hand @@ -1667,11 +1668,16 @@ class InfoExtractor(object): rendition = stream_group[0] return rendition.get('NAME') or stream_group_id + # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF inorder to have the + # chance to detect video only formats when EXT-X-STREAM-INF tags + # precede EXT-X-MEDIA tags in HLS manifest such as [3]. + for line in m3u8_doc.splitlines(): + if line.startswith('#EXT-X-MEDIA:'): + extract_media(line) + for line in m3u8_doc.splitlines(): if line.startswith('#EXT-X-STREAM-INF:'): last_stream_inf = parse_m3u8_attributes(line) - elif line.startswith('#EXT-X-MEDIA:'): - extract_media(line) elif line.startswith('#') or not line.strip(): continue else: From f28363ad1fb45b4450ae6f09ff9aff8f93227e40 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 19 Jan 2019 21:25:53 +0100 Subject: [PATCH 068/362] [ted] correct acodec for http formats(#18923) --- youtube_dl/extractor/ted.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index d3e4205f5..645942dfd 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -265,6 +265,8 @@ class TEDIE(InfoExtractor): 'format_id': m3u8_format['format_id'].replace('hls', 'http'), 'protocol': 'http', }) + if f.get('acodec') == 'none': + del f['acodec'] formats.append(f) audio_download = talk_info.get('audioDownload') From 379306ef55b64c966392c072b17a450831fec252 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 19 Jan 2019 21:35:02 +0100 Subject: [PATCH 069/362] [extractor/common] fix typo --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index af621b74b..6e36e6778 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1668,7 +1668,7 @@ class InfoExtractor(object): rendition = stream_group[0] return rendition.get('NAME') or stream_group_id - # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF inorder to have the + # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF in order to have the # chance to detect video only formats when EXT-X-STREAM-INF tags # precede EXT-X-MEDIA tags in HLS manifest such as [3]. for line in m3u8_doc.splitlines(): From 2cc779f497ae20d6e0e28fc546a25723cfea631a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 13:48:09 +0700 Subject: [PATCH 070/362] [YoutubeDL] Add negation support for string comparisons in format selection expressions (closes #18600, closes #18805) --- README.md | 3 ++- test/test_YoutubeDL.py | 46 +++++++++++++++++++++++++++++++++++++++++ youtube_dl/YoutubeDL.py | 9 +++++--- 3 files changed, 54 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 70bcfaccf..886696015 100644 --- a/README.md +++ b/README.md @@ -667,13 +667,14 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, ` - `asr`: Audio sampling rate in Hertz - `fps`: Frame rate -Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields: +Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields: - `ext`: File extension - `acodec`: Name of the audio codec in use - `vcodec`: Name of the video codec in use - `container`: Name of the container format - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - `format_id`: A short description of the format +Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster. diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index f0f5a8470..df8994b84 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -239,6 +239,52 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') + def test_format_selection_string_ops(self): + formats = [ + {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + # equals (=) + ydl = YDL({'format': '[format_id=abc-cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not equal (!=) + ydl = YDL({'format': '[format_id!=abc-cba]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # starts with (^=) + ydl = YDL({'format': '[format_id^=abc]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not start with (!^=) + ydl = YDL({'format': '[format_id!^=abc-cba]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # ends with ($=) + ydl = YDL({'format': '[format_id$=cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not end with (!$=) + ydl = YDL({'format': '[format_id!$=abc-cba]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # contains (*=) + ydl = YDL({'format': '[format_id*=-]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not contain (!*=) + ydl = YDL({'format': '[format_id!*=-]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + def test_youtube_format_selection(self): order = [ '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 4493fd0e1..a827414dc 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1063,21 +1063,24 @@ class YoutubeDL(object): if not m: STR_OPERATORS = { '=': operator.eq, - '!=': operator.ne, '^=': lambda attr, value: attr.startswith(value), '$=': lambda attr, value: attr.endswith(value), '*=': lambda attr, value: value in attr, } str_operator_rex = re.compile(r'''(?x) \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id) - \s*(?P<op>%s)(?P<none_inclusive>\s*\?)? + \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)? \s*(?P<value>[a-zA-Z0-9._-]+) \s*$ ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) m = str_operator_rex.search(filter_spec) if m: comparison_value = m.group('value') - op = STR_OPERATORS[m.group('op')] + str_op = STR_OPERATORS[m.group('op')] + if m.group('negation'): + op = lambda attr, value: not str_op + else: + op = str_op if not m: raise ValueError('Invalid filter specification %r' % filter_spec) From 4e58d9fabbfef80b2ecc0d20959bdf9dd3705e73 Mon Sep 17 00:00:00 2001 From: Sergey M <dstftw@gmail.com> Date: Sun, 20 Jan 2019 14:23:35 +0700 Subject: [PATCH 071/362] [README.md] Fix formatting --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 886696015..4ba982907 100644 --- a/README.md +++ b/README.md @@ -674,6 +674,7 @@ Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends - `container`: Name of the container format - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - `format_id`: A short description of the format + Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster. From fc746c3fdd7d40935a11e72b5cb69a8aee840e94 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 20 Jan 2019 09:04:51 +0100 Subject: [PATCH 072/362] [test/test_InfoExtractor] add test for #18923 --- test/test_InfoExtractor.py | 59 ++++++++++++++++++++++++++++++- test/testdata/m3u8/ted_18923.m3u8 | 28 +++++++++++++++ 2 files changed, 86 insertions(+), 1 deletion(-) create mode 100644 test/testdata/m3u8/ted_18923.m3u8 diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 06be72616..75fa0bbb7 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -497,7 +497,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ 'width': 1280, 'height': 720, }] - ) + ), + ( + # https://github.com/rg3/youtube-dl/issues/18923 + # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa + 'ted_18923', + 'http://hls.ted.com/talks/31241.m3u8', + [{ + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '600k-Audio', + 'vcodec': 'none', + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '68', + 'vcodec': 'none', + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '163', + 'acodec': 'none', + 'width': 320, + 'height': 180, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '481', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '769', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '984', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '1255', + 'acodec': 'none', + 'width': 640, + 'height': 360, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '1693', + 'acodec': 'none', + 'width': 853, + 'height': 480, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '2462', + 'acodec': 'none', + 'width': 1280, + 'height': 720, + }] + ), ] for m3u8_file, m3u8_url, expected_formats in _TEST_CASES: diff --git a/test/testdata/m3u8/ted_18923.m3u8 b/test/testdata/m3u8/ted_18923.m3u8 new file mode 100644 index 000000000..52a27118b --- /dev/null +++ b/test/testdata/m3u8/ted_18923.m3u8 @@ -0,0 +1,28 @@ +#EXTM3U +#EXT-X-VERSION:4 +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1255659,PROGRAM-ID=1,CODECS="avc1.42c01e,mp4a.40.2",RESOLUTION=640x360 +/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=163154,PROGRAM-ID=1,CODECS="avc1.42c00c,mp4a.40.2",RESOLUTION=320x180 +/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=481701,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=769968,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=984037,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1693925,PROGRAM-ID=1,CODECS="avc1.4d401f,mp4a.40.2",RESOLUTION=853x480 +/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=2462469,PROGRAM-ID=1,CODECS="avc1.640028,mp4a.40.2",RESOLUTION=1280x720 +/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=68101,PROGRAM-ID=1,CODECS="mp4a.40.2",DEFAULT=YES +/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b + +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=74298,PROGRAM-ID=1,CODECS="avc1.42c00c",RESOLUTION=320x180,URI="/videos/BorisHesser_2018S/video/64k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=216200,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/180k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=304717,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/320k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=350933,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/450k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=495850,PROGRAM-ID=1,CODECS="avc1.42c01e",RESOLUTION=640x360,URI="/videos/BorisHesser_2018S/video/600k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=810750,PROGRAM-ID=1,CODECS="avc1.4d401f",RESOLUTION=853x480,URI="/videos/BorisHesser_2018S/video/950k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=1273700,PROGRAM-ID=1,CODECS="avc1.640028",RESOLUTION=1280x720,URI="/videos/BorisHesser_2018S/video/1500k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" + +#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="600k",LANGUAGE="en",NAME="Audio",AUTOSELECT=YES,DEFAULT=YES,URI="/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b",BANDWIDTH=614400 From 15870747f02effba9376fd1a1500c32d36d1b811 Mon Sep 17 00:00:00 2001 From: aviperes <avipr24@gmail.com> Date: Sun, 20 Jan 2019 10:15:01 +0200 Subject: [PATCH 073/362] [odnoklassniki] Detect paid videos --- youtube_dl/extractor/odnoklassniki.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 190d8af4d..114b93c07 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -115,6 +115,10 @@ class OdnoklassnikiIE(InfoExtractor): }, { 'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#', 'only_matching': True, + }, { + # Paid video + 'url': 'https://ok.ru/video/954886983203', + 'only_matching': True, }] def _real_extract(self, url): @@ -244,6 +248,11 @@ class OdnoklassnikiIE(InfoExtractor): 'ext': 'flv', }) + if not formats: + payment_info = metadata.get('paymentInfo') + if payment_info: + raise ExtractorError('This video is paid, subscribe to download it', expected=True) + self._sort_formats(formats) info['formats'] = formats From 31fbedc06a349bc555ab934588544f75734e3a55 Mon Sep 17 00:00:00 2001 From: jhwgh1968 <jhwgh1968@users.noreply.github.com> Date: Sun, 20 Jan 2019 09:10:46 +0000 Subject: [PATCH 074/362] [instagram] Add base extractor for playlists and tag extractor --- youtube_dl/extractor/extractors.py | 6 +- youtube_dl/extractor/instagram.py | 136 +++++++++++++++++++++-------- 2 files changed, 105 insertions(+), 37 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index de38c6641..24361def4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -494,7 +494,11 @@ from .ina import InaIE from .inc import IncIE from .indavideo import IndavideoEmbedIE from .infoq import InfoQIE -from .instagram import InstagramIE, InstagramUserIE +from .instagram import ( + InstagramIE, + InstagramUserIE, + InstagramTagIE, +) from .internazionale import InternazionaleIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 7e0e838f0..ffd87b55f 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -227,44 +227,37 @@ class InstagramIE(InfoExtractor): } -class InstagramUserIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])' - IE_DESC = 'Instagram user profile' - IE_NAME = 'instagram:user' - _TEST = { - 'url': 'https://instagram.com/porsche', - 'info_dict': { - 'id': 'porsche', - 'title': 'porsche', - }, - 'playlist_count': 5, - 'params': { - 'extract_flat': True, - 'skip_download': True, - 'playlistend': 5, - } - } +class InstagramPlaylistIE(InfoExtractor): + # A superclass for handling any kind of query based on GraphQL which + # results in a playlist. - _gis_tmpl = None + _gis_tmpl = None # used to cache GIS request type - def _entries(self, data): + def _parse_graphql(self, webpage, item_id): + # Reads a webpage and returns its GraphQL data. + return self._parse_json( + self._search_regex( + r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'), + item_id) + + def _extract_graphql(self, data, url): + # Parses GraphQL queries containing videos and generates a playlist. def get_count(suffix): return int_or_none(try_get( node, lambda x: x['edge_media_' + suffix]['count'])) - uploader_id = data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + uploader_id = self._match_id(url) csrf_token = data['config']['csrf_token'] rhx_gis = data.get('rhx_gis') or '3c7ca9dcefcf966d11dacf1f151335e8' - self._set_cookie('instagram.com', 'ig_pr', '1') - cursor = '' for page_num in itertools.count(1): - variables = json.dumps({ - 'id': uploader_id, + variables = { 'first': 12, 'after': cursor, - }) + } + variables.update(self._query_vars_for(data)) + variables = json.dumps(variables) if self._gis_tmpl: gis_tmpls = [self._gis_tmpl] @@ -276,21 +269,26 @@ class InstagramUserIE(InfoExtractor): '%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']), ] + # try all of the ways to generate a GIS query, and not only use the + # first one that works, but cache it for future requests for gis_tmpl in gis_tmpls: try: - media = self._download_json( + json_data = self._download_json( 'https://www.instagram.com/graphql/query/', uploader_id, 'Downloading JSON page %d' % page_num, headers={ 'X-Requested-With': 'XMLHttpRequest', 'X-Instagram-GIS': hashlib.md5( ('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(), }, query={ - 'query_hash': '42323d64886122307be10013ad2dcc44', + 'query_hash': self._QUERY_HASH, 'variables': variables, - })['data']['user']['edge_owner_to_timeline_media'] + }) + media = self._parse_timeline_from(json_data) self._gis_tmpl = gis_tmpl break except ExtractorError as e: + # if it's an error caused by a bad query, and there are + # more GIS templates to try, ignore it and keep trying if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if gis_tmpl != gis_tmpls[-1]: continue @@ -348,14 +346,80 @@ class InstagramUserIE(InfoExtractor): break def _real_extract(self, url): - username = self._match_id(url) + user_or_tag = self._match_id(url) + webpage = self._download_webpage(url, user_or_tag) + data = self._parse_graphql(webpage, user_or_tag) - webpage = self._download_webpage(url, username) - - data = self._parse_json( - self._search_regex( - r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'), - username) + self._set_cookie('instagram.com', 'ig_pr', '1') return self.playlist_result( - self._entries(data), username, username) + self._extract_graphql(data, url), user_or_tag, user_or_tag) + + +class InstagramUserIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])' + IE_DESC = 'Instagram user profile' + IE_NAME = 'instagram:user' + _TEST = { + 'url': 'https://instagram.com/porsche', + 'info_dict': { + 'id': 'porsche', + 'title': 'porsche', + }, + 'playlist_count': 5, + 'params': { + 'extract_flat': True, + 'skip_download': True, + 'playlistend': 5, + } + } + + _QUERY_HASH = '42323d64886122307be10013ad2dcc44', + + @staticmethod + def _parse_timeline_from(data): + # extracts the media timeline data from a GraphQL result + return data['data']['user']['edge_owner_to_timeline_media'] + + @staticmethod + def _query_vars_for(data): + # returns a dictionary of variables to add to the timeline query based + # on the GraphQL of the original page + return { + 'id': data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + } + + +class InstagramTagIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/explore/tags/(?P<id>[^/]+)' + IE_DESC = 'Instagram hashtag search' + IE_NAME = 'instagram:tag' + _TEST = { + 'url': 'https://instagram.com/explore/tags/lolcats', + 'info_dict': { + 'id': 'lolcats', + 'title': 'lolcats', + }, + 'playlist_count': 50, + 'params': { + 'extract_flat': True, + 'skip_download': True, + 'playlistend': 50, + } + } + + _QUERY_HASH = 'f92f56d47dc7a55b606908374b43a314', + + @staticmethod + def _parse_timeline_from(data): + # extracts the media timeline data from a GraphQL result + return data['data']['hashtag']['edge_hashtag_to_media'] + + @staticmethod + def _query_vars_for(data): + # returns a dictionary of variables to add to the timeline query based + # on the GraphQL of the original page + return { + 'tag_name': + data['entry_data']['TagPage'][0]['graphql']['hashtag']['name'] + } From 6ca3fa898cd066422daea3d5be53efdae22187d8 Mon Sep 17 00:00:00 2001 From: yonaikerlol <lawlietrs7@gmail.com> Date: Sun, 20 Jan 2019 05:24:21 -0400 Subject: [PATCH 075/362] [streamango] Add support for fruithosts.net --- youtube_dl/extractor/streamango.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py index fcaa5ac0b..efb259f96 100644 --- a/youtube_dl/extractor/streamango.py +++ b/youtube_dl/extractor/streamango.py @@ -14,7 +14,7 @@ from ..utils import ( class StreamangoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4', 'md5': 'e992787515a182f55e38fc97588d802a', @@ -38,6 +38,9 @@ class StreamangoIE(InfoExtractor): }, { 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4', 'only_matching': True, + }, { + 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4', + 'only_matching': True, }] def _real_extract(self, url): From 289ef490f77cb35c43d98b9d2ea4cf529c24895e Mon Sep 17 00:00:00 2001 From: Anthony Fok <foka@debian.org> Date: Sun, 30 Dec 2018 02:44:40 -0700 Subject: [PATCH 076/362] [hketv] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/hketv.py | 185 +++++++++++++++++++++++++++++ 2 files changed, 186 insertions(+) create mode 100644 youtube_dl/extractor/hketv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 24361def4..574a47e6d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -452,6 +452,7 @@ from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .hgtv import HGTVComShowIE +from .hketv import HKETVIE from .hidive import HiDiveIE from .historicfilms import HistoricFilmsIE from .hitbox import HitboxIE, HitboxLiveIE diff --git a/youtube_dl/extractor/hketv.py b/youtube_dl/extractor/hketv.py new file mode 100644 index 000000000..b5790cdee --- /dev/null +++ b/youtube_dl/extractor/hketv.py @@ -0,0 +1,185 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + merge_dicts, + str_or_none, + str_to_int, + try_get, + unified_strdate, + urlencode_postdata, + urljoin, +) + + +class HKETVIE(InfoExtractor): + IE_NAME = 'hketv' + IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau' + _GEO_BYPASS = False + _GEO_COUNTRIES = ['HK'] + _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'https://www.hkedcity.net/etv/resource/2932360618', + 'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7', + 'info_dict': { + 'id': '2932360618', + 'ext': 'mp4', + 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', + 'description': '本節目輯錄了「閱讀滿Fun嘉年華」和「二○一八響應世界閱讀日――悅愛閱讀・愈讀愈愛」的活動花絮，並由學者、作家、演藝界人士等，分享培養子女閱讀興趣和習慣的方法，以及呼籲大家一同分享閱讀的樂趣。', + 'upload_date': '20181024', + 'duration': 900, + 'subtitles': { + 'en': [{ + 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=en', + 'ext': 'srt', + }], + 'zh-Hant': [{ + 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=qmt', + 'ext': 'srt', + }], + } + }, + }, { + 'url': 'https://www.hkedcity.net/etv/resource/972641418', + 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', + 'info_dict': { + 'id': '972641418', + 'ext': 'mp4', + 'title': '衣冠楚楚 (天使系列之一)', + 'description': '天國仙境，有兩位可愛的天使小姐妹。她們對幾千年來天使衣著一成不變頗有不滿。她們下望人世間：只見人們穿著七彩繽紛、款式各異的服裝，漂亮極了。天使姐妹決定下凡考察衣著，以設計天使新裝。 下到人間，姐妹試穿各式各樣的衣著，引發連串奇特有趣的情節：她們穿著校服在街上閒逛時，被女警誤認為逃學而送回學校，到校後又被體育老師誤認為是新同學，匆匆忙忙換上運動服後在操場上大顯神通。她們穿著護士服在醫院散步時，又被誤認為當班護士，而投入追尋失蹤病童、治病救人的工作中去。姐妹倆還到過玩具店，與布娃娃們談論衣著。她們也去過服裝設計學校，被當成小模特兒而試穿各式服裝。最令姐妹倆興奮的是一場盛大的民族服裝表演會。身穿盛裝的十二個民族的少女在台上翩翩起舞，各種服飾七彩繽紛、美不勝收。姐妹們情不自禁地穿上民族服裝，小天使變成了少數民族姑娘……最後天使姐妹回到天上，對於天使究竟穿甚麼樣的衣服好，她們還是拿不定主意。 節目通過天使姐妹的奇特經歷，反復示範各式衣服鞋襪的正確讀音及談論衣著時的常用句式，並以盛大的民族服裝表演活動，帶出有關服裝的文化知識。內容豐富而饒有趣味。', + 'upload_date': '20070109', + 'duration': 907, + 'subtitles': {}, + }, + }] + + _CC_LANGS = { + '中文（繁體中文）': 'zh-Hant', + '中文（简体中文）': 'zh-Hans', + 'English': 'en', + 'Bahasa Indonesia': 'id', + '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi', + '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne', + 'Tagalog': 'tl', + '\u0e44\u0e17\u0e22': 'th', + '\u0627\u0631\u062f\u0648': 'ur', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + title = self._html_search_meta('ed_title', webpage, fatal=True) + + file_id = self._html_search_regex(r'post_var\["file_id"\]\s*=\s*(.+?);', webpage, 'file ID') + curr_url = self._html_search_regex(r'post_var\["curr_url"\]\s*=\s*"(.+?)";', webpage, 'curr URL') + data = { + 'action': 'get_info', + 'curr_url': curr_url, + 'file_id': file_id, + 'video_url': file_id, + } + _APPS_BASE_URL = 'https://apps.hkedcity.net' + handler_url = _APPS_BASE_URL + '/media/play/handler.php' + + response = self._download_json( + handler_url, video_id, + data=urlencode_postdata(data), + headers=merge_dicts({'Content-Type': 'application/x-www-form-urlencoded'}, + self.geo_verification_headers())) + + result = response['result'] + + formats = [] + subtitles = {} + + if response.get('success') and response.get('access'): + width = int_or_none(result.get('width')) + height = int_or_none(result.get('height')) + + playlist0 = try_get(result, lambda x: x['playlist'][0], dict) + fmts = playlist0.get('sources') + for fmt in fmts: + file_path = fmt.get('file') + if file_path: + file_url = urljoin(_APPS_BASE_URL, file_path) + # If we ever wanted to provide the final resolved URL that + # does not require cookies, albeit with a shorter lifespan: + # urlh = self._downloader.urlopen(file_url) + # resolved_url = urlh.geturl() + + label = fmt.get('label') + w = None + h = None + if label == 'HD': + h = 720 + elif label == 'SD': + h = 360 + if h: + if width and height: + w = h * width // height + else: + w = h * 4 // 3 + + formats.append({ + 'format_id': label, + 'ext': fmt.get('type'), + 'url': file_url, + 'width': w, + 'height': h, + }) + + tracks = playlist0.get('tracks', []) + for track in tracks: + if not isinstance(track, dict): + continue + track_kind = str_or_none(track.get('kind')) + if not track_kind or not isinstance(track_kind, compat_str): + continue + if track_kind.lower() not in ('captions', 'subtitles'): + continue + track_url = urljoin(_APPS_BASE_URL, track.get('file')) + if not track_url: + continue + track_label = track.get('label') + subtitles.setdefault(self._CC_LANGS.get(track_label, track_label), []).append({ + 'url': self._proto_relative_url(track_url), + 'ext': 'srt', + }) + + else: + error = clean_html(response.get('access_err_msg')) + if 'Video streaming is not available in your country' in error: + self.raise_geo_restricted(msg=error, countries=self._GEO_COUNTRIES) + else: + raise ExtractorError(error) + + # Likes + emotion = self._download_json( + 'https://emocounter.hkedcity.net/handler.php', + video_id, + data=urlencode_postdata({ + 'action': 'get_emotion', + 'data[bucket_id]': 'etv', + 'data[identifier]': video_id, + }), + headers={'Content-Type': 'application/x-www-form-urlencoded'}, + fatal=False) + like_count = int_or_none(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'])) + + return { + 'id': video_id, + 'title': title, + 'description': self._html_search_meta('description', webpage, fatal=False), + 'upload_date': unified_strdate(self._html_search_meta('ed_date', webpage, fatal=False), day_first=False), + 'duration': int_or_none(result.get('length')), + 'formats': formats, + 'subtitles': subtitles, + 'thumbnail': urljoin(_APPS_BASE_URL, result.get('image')), + 'view_count': str_to_int(result.get('view_count')), + 'like_count': like_count, + } From 73c19aaa9f74e9383a7aaf0dfb3c608727d5b6b2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 17:42:25 +0700 Subject: [PATCH 077/362] [hketv] Improve and simplify (closes #18696) --- youtube_dl/extractor/hketv.py | 180 ++++++++++++++++++---------------- 1 file changed, 93 insertions(+), 87 deletions(-) diff --git a/youtube_dl/extractor/hketv.py b/youtube_dl/extractor/hketv.py index b5790cdee..b57927fc1 100644 --- a/youtube_dl/extractor/hketv.py +++ b/youtube_dl/extractor/hketv.py @@ -8,8 +8,8 @@ from ..utils import ( ExtractorError, int_or_none, merge_dicts, + parse_count, str_or_none, - str_to_int, try_get, unified_strdate, urlencode_postdata, @@ -30,20 +30,12 @@ class HKETVIE(InfoExtractor): 'id': '2932360618', 'ext': 'mp4', 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', - 'description': '本節目輯錄了「閱讀滿Fun嘉年華」和「二○一八響應世界閱讀日――悅愛閱讀・愈讀愈愛」的活動花絮，並由學者、作家、演藝界人士等，分享培養子女閱讀興趣和習慣的方法，以及呼籲大家一同分享閱讀的樂趣。', + 'description': 'md5:d5286d05219ef50e0613311cbe96e560', 'upload_date': '20181024', 'duration': 900, - 'subtitles': { - 'en': [{ - 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=en', - 'ext': 'srt', - }], - 'zh-Hant': [{ - 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=qmt', - 'ext': 'srt', - }], - } + 'subtitles': 'count:2', }, + 'skip': 'Geo restricted to HK', }, { 'url': 'https://www.hkedcity.net/etv/resource/972641418', 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', @@ -51,11 +43,15 @@ class HKETVIE(InfoExtractor): 'id': '972641418', 'ext': 'mp4', 'title': '衣冠楚楚 (天使系列之一)', - 'description': '天國仙境，有兩位可愛的天使小姐妹。她們對幾千年來天使衣著一成不變頗有不滿。她們下望人世間：只見人們穿著七彩繽紛、款式各異的服裝，漂亮極了。天使姐妹決定下凡考察衣著，以設計天使新裝。 下到人間，姐妹試穿各式各樣的衣著，引發連串奇特有趣的情節：她們穿著校服在街上閒逛時，被女警誤認為逃學而送回學校，到校後又被體育老師誤認為是新同學，匆匆忙忙換上運動服後在操場上大顯神通。她們穿著護士服在醫院散步時，又被誤認為當班護士，而投入追尋失蹤病童、治病救人的工作中去。姐妹倆還到過玩具店，與布娃娃們談論衣著。她們也去過服裝設計學校，被當成小模特兒而試穿各式服裝。最令姐妹倆興奮的是一場盛大的民族服裝表演會。身穿盛裝的十二個民族的少女在台上翩翩起舞，各種服飾七彩繽紛、美不勝收。姐妹們情不自禁地穿上民族服裝，小天使變成了少數民族姑娘……最後天使姐妹回到天上，對於天使究竟穿甚麼樣的衣服好，她們還是拿不定主意。 節目通過天使姐妹的奇特經歷，反復示範各式衣服鞋襪的正確讀音及談論衣著時的常用句式，並以盛大的民族服裝表演活動，帶出有關服裝的文化知識。內容豐富而饒有趣味。', + 'description': 'md5:10bb3d659421e74f58e5db5691627b0f', 'upload_date': '20070109', 'duration': 907, 'subtitles': {}, }, + 'params': { + 'geo_verification_proxy': '<HK proxy here>', + }, + 'skip': 'Geo restricted to HK', }] _CC_LANGS = { @@ -69,117 +65,127 @@ class HKETVIE(InfoExtractor): '\u0e44\u0e17\u0e22': 'th', '\u0627\u0631\u062f\u0648': 'ur', } + _FORMAT_HEIGHTS = { + 'SD': 360, + 'HD': 720, + } + _APPS_BASE_URL = 'https://apps.hkedcity.net' def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_meta('ed_title', webpage, fatal=True) - file_id = self._html_search_regex(r'post_var\["file_id"\]\s*=\s*(.+?);', webpage, 'file ID') - curr_url = self._html_search_regex(r'post_var\["curr_url"\]\s*=\s*"(.+?)";', webpage, 'curr URL') + title = ( + self._html_search_meta( + ('ed_title', 'search.ed_title'), webpage, default=None) or + self._search_regex( + r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1', + webpage, 'title', default=None, group='url') or + self._html_search_regex( + r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or + self._og_search_title(webpage) + ) + + file_id = self._search_regex( + r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);', + webpage, 'file ID') + curr_url = self._search_regex( + r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";', + webpage, 'curr URL') data = { 'action': 'get_info', 'curr_url': curr_url, 'file_id': file_id, 'video_url': file_id, } - _APPS_BASE_URL = 'https://apps.hkedcity.net' - handler_url = _APPS_BASE_URL + '/media/play/handler.php' response = self._download_json( - handler_url, video_id, + self._APPS_BASE_URL + '/media/play/handler.php', video_id, data=urlencode_postdata(data), - headers=merge_dicts({'Content-Type': 'application/x-www-form-urlencoded'}, - self.geo_verification_headers())) + headers=merge_dicts({ + 'Content-Type': 'application/x-www-form-urlencoded'}, + self.geo_verification_headers())) result = response['result'] + if not response.get('success') or not response.get('access'): + error = clean_html(response.get('access_err_msg')) + if 'Video streaming is not available in your country' in error: + self.raise_geo_restricted( + msg=error, countries=self._GEO_COUNTRIES) + else: + raise ExtractorError(error, expected=True) + formats = [] + + width = int_or_none(result.get('width')) + height = int_or_none(result.get('height')) + + playlist0 = result['playlist'][0] + for fmt in playlist0['sources']: + file_url = urljoin(self._APPS_BASE_URL, fmt.get('file')) + if not file_url: + continue + # If we ever wanted to provide the final resolved URL that + # does not require cookies, albeit with a shorter lifespan: + # urlh = self._downloader.urlopen(file_url) + # resolved_url = urlh.geturl() + label = fmt.get('label') + h = self._FORMAT_HEIGHTS.get(label) + w = h * width // height if h and width and height else None + formats.append({ + 'format_id': label, + 'ext': fmt.get('type'), + 'url': file_url, + 'width': w, + 'height': h, + }) + self._sort_formats(formats) + subtitles = {} - - if response.get('success') and response.get('access'): - width = int_or_none(result.get('width')) - height = int_or_none(result.get('height')) - - playlist0 = try_get(result, lambda x: x['playlist'][0], dict) - fmts = playlist0.get('sources') - for fmt in fmts: - file_path = fmt.get('file') - if file_path: - file_url = urljoin(_APPS_BASE_URL, file_path) - # If we ever wanted to provide the final resolved URL that - # does not require cookies, albeit with a shorter lifespan: - # urlh = self._downloader.urlopen(file_url) - # resolved_url = urlh.geturl() - - label = fmt.get('label') - w = None - h = None - if label == 'HD': - h = 720 - elif label == 'SD': - h = 360 - if h: - if width and height: - w = h * width // height - else: - w = h * 4 // 3 - - formats.append({ - 'format_id': label, - 'ext': fmt.get('type'), - 'url': file_url, - 'width': w, - 'height': h, - }) - - tracks = playlist0.get('tracks', []) - for track in tracks: - if not isinstance(track, dict): - continue - track_kind = str_or_none(track.get('kind')) - if not track_kind or not isinstance(track_kind, compat_str): - continue - if track_kind.lower() not in ('captions', 'subtitles'): - continue - track_url = urljoin(_APPS_BASE_URL, track.get('file')) - if not track_url: - continue - track_label = track.get('label') - subtitles.setdefault(self._CC_LANGS.get(track_label, track_label), []).append({ + tracks = try_get(playlist0, lambda x: x['tracks'], list) or [] + for track in tracks: + if not isinstance(track, dict): + continue + track_kind = str_or_none(track.get('kind')) + if not track_kind or not isinstance(track_kind, compat_str): + continue + if track_kind.lower() not in ('captions', 'subtitles'): + continue + track_url = urljoin(self._APPS_BASE_URL, track.get('file')) + if not track_url: + continue + track_label = track.get('label') + subtitles.setdefault(self._CC_LANGS.get( + track_label, track_label), []).append({ 'url': self._proto_relative_url(track_url), 'ext': 'srt', }) - else: - error = clean_html(response.get('access_err_msg')) - if 'Video streaming is not available in your country' in error: - self.raise_geo_restricted(msg=error, countries=self._GEO_COUNTRIES) - else: - raise ExtractorError(error) - # Likes emotion = self._download_json( - 'https://emocounter.hkedcity.net/handler.php', - video_id, + 'https://emocounter.hkedcity.net/handler.php', video_id, data=urlencode_postdata({ 'action': 'get_emotion', 'data[bucket_id]': 'etv', 'data[identifier]': video_id, }), headers={'Content-Type': 'application/x-www-form-urlencoded'}, - fatal=False) - like_count = int_or_none(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'])) + fatal=False) or {} + like_count = int_or_none(try_get( + emotion, lambda x: x['data']['emotion_data'][0]['count'])) return { 'id': video_id, 'title': title, - 'description': self._html_search_meta('description', webpage, fatal=False), - 'upload_date': unified_strdate(self._html_search_meta('ed_date', webpage, fatal=False), day_first=False), + 'description': self._html_search_meta( + 'description', webpage, fatal=False), + 'upload_date': unified_strdate(self._html_search_meta( + 'ed_date', webpage, fatal=False), day_first=False), 'duration': int_or_none(result.get('length')), 'formats': formats, 'subtitles': subtitles, - 'thumbnail': urljoin(_APPS_BASE_URL, result.get('image')), - 'view_count': str_to_int(result.get('view_count')), + 'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')), + 'view_count': parse_count(result.get('view_count')), 'like_count': like_count, } From a1a460759815414c6194bc921ac77a5533b6e02e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 18:21:31 +0700 Subject: [PATCH 078/362] [vimeo] Fix video password verification for videos protected by Referer HTTP header --- youtube_dl/extractor/vimeo.py | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index fd37f919b..6215b3258 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -435,6 +435,8 @@ class VimeoIE(VimeoBaseInfoExtractor): 'url': 'https://vimeo.com/160743502/abd0e13fb4', 'only_matching': True, } + # https://gettingthingsdone.com/workflowmap/ + # vimeo embed with check-password page protected by Referer header ] @staticmethod @@ -465,20 +467,22 @@ class VimeoIE(VimeoBaseInfoExtractor): urls = VimeoIE._extract_urls(url, webpage) return urls[0] if urls else None - def _verify_player_video_password(self, url, video_id): + def _verify_player_video_password(self, url, video_id, headers): password = self._downloader.params.get('videopassword') if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') data = urlencode_postdata({ 'password': base64.b64encode(password.encode()), }) - pass_url = url + '/check-password' - password_request = sanitized_Request(pass_url, data) - password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - password_request.add_header('Referer', url) - return self._download_json( - password_request, video_id, - 'Verifying the password', 'Wrong password') + headers = merge_dicts(headers, { + 'Content-Type': 'application/x-www-form-urlencoded', + }) + checked = self._download_json( + url + '/check-password', video_id, + 'Verifying the password', data=data, headers=headers) + if checked is False: + raise ExtractorError('Wrong video password', expected=True) + return checked def _real_initialize(self): self._login() @@ -591,7 +595,7 @@ class VimeoIE(VimeoBaseInfoExtractor): cause=e) else: if config.get('view') == 4: - config = self._verify_player_video_password(redirect_url, video_id) + config = self._verify_player_video_password(redirect_url, video_id, headers) vod = config.get('video', {}).get('vod', {}) From 29cfcb43da8ac60e6c2eddad095a41c800d4d95a Mon Sep 17 00:00:00 2001 From: Alexandre Huot <alexandre.huot@usherbrooke.ca> Date: Sun, 20 Jan 2019 06:33:09 -0500 Subject: [PATCH 079/362] [radiocanada] Relax DRM check --- youtube_dl/extractor/radiocanada.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index b952e59b4..302f67d96 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -49,6 +49,16 @@ class RadioCanadaIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + }, + { + # with protectionType but not actually DRM protected + 'url': 'radiocanada:toutv:140872', + 'info_dict': { + 'id': '140872', + 'title': 'Épisode 1', + 'series': 'District 31', + }, + 'only_matching': True, } ] @@ -67,8 +77,10 @@ class RadioCanadaIE(InfoExtractor): el = find_xpath_attr(metadata, './/Meta', 'name', name) return el.text if el is not None else None + # protectionType does not necessarily mean the video is DRM protected (see + # https://github.com/rg3/youtube-dl/pull/18609). if get_meta('protectionType'): - raise ExtractorError('This video is DRM protected.', expected=True) + self.report_warning('This video is probably DRM protected.') device_types = ['ipad'] if not smuggled_data: From 6945b9e78f38284eb4e440b7badea2fc60b66c2f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 20 Jan 2019 13:31:41 +0100 Subject: [PATCH 080/362] [extractor/common] improve jwplayer relative url handling(closes #18892) --- youtube_dl/extractor/common.py | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 6e36e6778..95456b291 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2630,7 +2630,7 @@ class InfoExtractor(object): 'id': this_video_id, 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')), 'description': video_data.get('description'), - 'thumbnail': self._proto_relative_url(video_data.get('image')), + 'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))), 'timestamp': int_or_none(video_data.get('pubdate')), 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), 'subtitles': subtitles, @@ -2657,12 +2657,9 @@ class InfoExtractor(object): for source in jwplayer_sources_data: if not isinstance(source, dict): continue - source_url = self._proto_relative_url(source.get('file')) - if not source_url: - continue - if base_url: - source_url = compat_urlparse.urljoin(base_url, source_url) - if source_url in urls: + source_url = urljoin( + base_url, self._proto_relative_url(source.get('file'))) + if not source_url or source_url in urls: continue urls.append(source_url) source_type = source.get('type') or '' From fad4ceb53404227f471af2f3544c4c14a5df4acb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 20:21:24 +0700 Subject: [PATCH 081/362] [utils] Fix urljoin for paths with non-http(s) schemes --- test/test_utils.py | 2 ++ youtube_dl/utils.py | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/test/test_utils.py b/test/test_utils.py index 9e28e008f..409482c3b 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -507,6 +507,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(urljoin('http://foo.de/', ''), None) self.assertEqual(urljoin('http://foo.de/', ['foobar']), None) self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt') + self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de') + self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de') def test_url_or_none(self): self.assertEqual(url_or_none(None), None) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index d2d3c1a9f..d0cb65814 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1868,7 +1868,7 @@ def urljoin(base, path): path = path.decode('utf-8') if not isinstance(path, compat_str) or not path: return None - if re.match(r'^(?:https?:)?//', path): + if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path): return path if isinstance(base, bytes): base = base.decode('utf-8') From 07f9febc4b86a9cd819329f3a7daafdbe9455f40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 22:07:01 +0700 Subject: [PATCH 082/362] [tnaflix] Pass Referer in metadata request (closes #18925) --- youtube_dl/extractor/tnaflix.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 6798ef4c3..b3573c6e0 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -96,7 +96,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor): cfg_xml = self._download_xml( cfg_url, display_id, 'Downloading metadata', - transform_source=fix_xml_ampersands) + transform_source=fix_xml_ampersands, headers={'Referer': url}) formats = [] From 19d6991312405f5af108af28b3721966720fc72d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 22 Jan 2019 03:03:53 +0700 Subject: [PATCH 083/362] [videomore] Improve extraction and fix season extractor (closes #18908) --- youtube_dl/extractor/videomore.py | 96 ++++++++++++++++++++++++++++--- 1 file changed, 88 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/videomore.py b/youtube_dl/extractor/videomore.py index 9b56630de..e3eda3327 100644 --- a/youtube_dl/extractor/videomore.py +++ b/youtube_dl/extractor/videomore.py @@ -4,8 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, + orderedSet, + parse_duration, + str_or_none, + unified_strdate, + url_or_none, xpath_element, xpath_text, ) @@ -13,7 +19,19 @@ from ..utils import ( class VideomoreIE(InfoExtractor): IE_NAME = 'videomore' - _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)' + _VALID_URL = r'''(?x) + videomore:(?P<sid>\d+)$| + https?://(?:player\.)?videomore\.ru/ + (?: + (?: + embed| + [^/]+/[^/]+ + )/| + [^/]*\?.*?\btrack_id= + ) + (?P<id>\d+) + (?:[/?#&]|\.(?:xml|json)|$) + ''' _TESTS = [{ 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617', 'md5': '44455a346edc0d509ac5b5a5b531dc35', @@ -79,6 +97,9 @@ class VideomoreIE(InfoExtractor): }, { 'url': 'videomore:367617', 'only_matching': True, + }, { + 'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=', + 'only_matching': True, }] @staticmethod @@ -136,7 +157,7 @@ class VideomoreIE(InfoExtractor): class VideomoreVideoIE(InfoExtractor): IE_NAME = 'videomore:video' - _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ # single video with og:video:iframe 'url': 'http://videomore.ru/elki_3', @@ -176,6 +197,9 @@ class VideomoreVideoIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so', + 'only_matching': True, }] @classmethod @@ -196,13 +220,16 @@ class VideomoreVideoIE(InfoExtractor): r'track-id=["\'](\d+)', r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id') video_url = 'videomore:%s' % video_id + else: + video_id = None - return self.url_result(video_url, VideomoreIE.ie_key()) + return self.url_result( + video_url, ie=VideomoreIE.ie_key(), video_id=video_id) class VideomoreSeasonIE(InfoExtractor): IE_NAME = 'videomore:season' - _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ 'url': 'http://videomore.ru/molodezhka/sezon_promo', 'info_dict': { @@ -210,8 +237,16 @@ class VideomoreSeasonIE(InfoExtractor): 'title': 'Молодежка Промо', }, 'playlist_mincount': 12, + }, { + 'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url)) + else super(VideomoreSeasonIE, cls).suitable(url)) + def _real_extract(self, url): display_id = self._match_id(url) @@ -219,9 +254,54 @@ class VideomoreSeasonIE(InfoExtractor): title = self._og_search_title(webpage) - entries = [ - self.url_result(item) for item in re.findall( - r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' - % display_id, webpage)] + data = self._parse_json( + self._html_search_regex( + r'\bclass=["\']seasons-tracks["\'][^>]+\bdata-custom-data=(["\'])(?P<value>{.+?})\1', + webpage, 'data', default='{}', group='value'), + display_id, fatal=False) + + entries = [] + + if data: + episodes = data.get('episodes') + if isinstance(episodes, list): + for ep in episodes: + if not isinstance(ep, dict): + continue + ep_id = int_or_none(ep.get('id')) + ep_url = url_or_none(ep.get('url')) + if ep_id: + e = { + 'url': 'videomore:%s' % ep_id, + 'id': compat_str(ep_id), + } + elif ep_url: + e = {'url': ep_url} + else: + continue + e.update({ + '_type': 'url', + 'ie_key': VideomoreIE.ie_key(), + 'title': str_or_none(ep.get('title')), + 'thumbnail': url_or_none(ep.get('image')), + 'duration': parse_duration(ep.get('duration')), + 'episode_number': int_or_none(ep.get('number')), + 'upload_date': unified_strdate(ep.get('date')), + }) + entries.append(e) + + if not entries: + entries = [ + self.url_result( + 'videomore:%s' % video_id, ie=VideomoreIE.ie_key(), + video_id=video_id) + for video_id in orderedSet(re.findall( + r':(?:id|key)=["\'](\d+)["\']', webpage))] + + if not entries: + entries = [ + self.url_result(item) for item in re.findall( + r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' + % display_id, webpage)] return self.playlist_result(entries, display_id, title) From 4b85f0f9db9329ef1774a66c3e2fd4da558a5201 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Jan 2019 14:38:29 +0100 Subject: [PATCH 084/362] [vrv] add support for authentication(closes #14307) --- youtube_dl/extractor/vrv.py | 95 ++++++++++++++++++++++--------------- 1 file changed, 56 insertions(+), 39 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 483a3be3a..014513051 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -11,10 +11,12 @@ import time from .common import InfoExtractor from ..compat import ( + compat_HTTPError, compat_urllib_parse_urlencode, compat_urllib_parse, ) from ..utils import ( + ExtractorError, float_or_none, int_or_none, ) @@ -24,29 +26,41 @@ class VRVBaseIE(InfoExtractor): _API_DOMAIN = None _API_PARAMS = {} _CMS_SIGNING = {} + _TOKEN = None + _TOKEN_SECRET = '' def _call_api(self, path, video_id, note, data=None): + # https://tools.ietf.org/html/rfc5849#section-3 base_url = self._API_DOMAIN + '/core/' + path - encoded_query = compat_urllib_parse_urlencode({ + query = { 'oauth_consumer_key': self._API_PARAMS['oAuthKey'], 'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), 'oauth_signature_method': 'HMAC-SHA1', 'oauth_timestamp': int(time.time()), - 'oauth_version': '1.0', - }) + } + if self._TOKEN: + query['oauth_token'] = self._TOKEN + encoded_query = compat_urllib_parse_urlencode(query) headers = self.geo_verification_headers() if data: data = json.dumps(data).encode() headers['Content-Type'] = 'application/json' - method = 'POST' if data else 'GET' - base_string = '&'.join([method, compat_urllib_parse.quote(base_url, ''), compat_urllib_parse.quote(encoded_query, '')]) + base_string = '&'.join([ + 'POST' if data else 'GET', + compat_urllib_parse.quote(base_url, ''), + compat_urllib_parse.quote(encoded_query, '')]) oauth_signature = base64.b64encode(hmac.new( - (self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'), + (self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'), base_string.encode(), hashlib.sha1).digest()).decode() encoded_query += '&oauth_signature=' + compat_urllib_parse.quote(oauth_signature, '') - return self._download_json( - '?'.join([base_url, encoded_query]), video_id, - note='Downloading %s JSON metadata' % note, headers=headers, data=data) + try: + return self._download_json( + '?'.join([base_url, encoded_query]), video_id, + note='Downloading %s JSON metadata' % note, headers=headers, data=data) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True) + raise def _call_cms(self, path, video_id, note): if not self._CMS_SIGNING: @@ -55,19 +69,22 @@ class VRVBaseIE(InfoExtractor): self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING, note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers()) - def _set_api_params(self, webpage, video_id): - if not self._API_PARAMS: - self._API_PARAMS = self._parse_json(self._search_regex( - r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>', - webpage, 'api config'), video_id)['cxApiParams'] - self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co') - def _get_cms_resource(self, resource_key, video_id): return self._call_api( 'cms_resource', video_id, 'resource path', data={ 'resource_key': resource_key, })['__links__']['cms_resource']['href'] + def _real_initialize(self): + webpage = self._download_webpage( + 'https://vrv.co/', None, headers=self.geo_verification_headers()) + self._API_PARAMS = self._parse_json(self._search_regex( + [ + r'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)', + r'window\.__APP_CONFIG__\s*=\s*({.+})' + ], webpage, 'app config'), None)['cxApiParams'] + self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co') + class VRVIE(VRVBaseIE): IE_NAME = 'vrv' @@ -86,6 +103,22 @@ class VRVIE(VRVBaseIE): 'skip_download': True, }, }] + _NETRC_MACHINE = 'vrv' + + def _real_initialize(self): + super(VRVIE, self)._real_initialize() + + email, password = self._get_login_info() + if email is None: + return + + token_credentials = self._call_api( + 'authenticate/by:credentials', None, 'Token Credentials', data={ + 'email': email, + 'password': password, + }) + self._TOKEN = token_credentials['oauth_token'] + self._TOKEN_SECRET = token_credentials['oauth_token_secret'] def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang): if not url or stream_format not in ('hls', 'dash'): @@ -116,28 +149,16 @@ class VRVIE(VRVBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, - headers=self.geo_verification_headers()) - media_resource = self._parse_json(self._search_regex( - [ - r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:</script>|;)', - r'window\.__INITIAL_STATE__\s*=\s*({.+})' - ], webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {} - video_data = media_resource.get('json') - if not video_data: - self._set_api_params(webpage, video_id) - episode_path = self._get_cms_resource( - 'cms:/episodes/' + video_id, video_id) - video_data = self._call_cms(episode_path, video_id, 'video') + episode_path = self._get_cms_resource( + 'cms:/episodes/' + video_id, video_id) + video_data = self._call_cms(episode_path, video_id, 'video') title = video_data['title'] - streams_json = media_resource.get('streams', {}).get('json', {}) - if not streams_json: - self._set_api_params(webpage, video_id) - streams_path = video_data['__links__']['streams']['href'] - streams_json = self._call_cms(streams_path, video_id, 'streams') + streams_path = video_data['__links__'].get('streams', {}).get('href') + if not streams_path: + self.raise_login_required() + streams_json = self._call_cms(streams_path, video_id, 'streams') audio_locale = streams_json.get('audio_locale') formats = [] @@ -202,11 +223,7 @@ class VRVSeriesIE(VRVBaseIE): def _real_extract(self, url): series_id = self._match_id(url) - webpage = self._download_webpage( - url, series_id, - headers=self.geo_verification_headers()) - self._set_api_params(webpage, series_id) seasons_path = self._get_cms_resource( 'cms:/seasons?series_id=' + series_id, series_id) seasons_data = self._call_cms(seasons_path, series_id, 'seasons') From 503b604a316837b9dd6ef32045e4e9bbfb6a1363 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Jan 2019 18:21:37 +0100 Subject: [PATCH 085/362] [vrv] fix oauth signing for python 2(#14307) --- youtube_dl/extractor/vrv.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 014513051..6c060ae76 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -32,14 +32,14 @@ class VRVBaseIE(InfoExtractor): def _call_api(self, path, video_id, note, data=None): # https://tools.ietf.org/html/rfc5849#section-3 base_url = self._API_DOMAIN + '/core/' + path - query = { - 'oauth_consumer_key': self._API_PARAMS['oAuthKey'], - 'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), - 'oauth_signature_method': 'HMAC-SHA1', - 'oauth_timestamp': int(time.time()), - } + query = [ + ('oauth_consumer_key', self._API_PARAMS['oAuthKey']), + ('oauth_nonce', ''.join([random.choice(string.ascii_letters) for _ in range(32)])), + ('oauth_signature_method', 'HMAC-SHA1'), + ('oauth_timestamp', int(time.time())), + ] if self._TOKEN: - query['oauth_token'] = self._TOKEN + query.append(('oauth_token', self._TOKEN)) encoded_query = compat_urllib_parse_urlencode(query) headers = self.geo_verification_headers() if data: From 278d061a0c5eae20963c0a6df4b9b13fd1537186 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 03:51:29 +0700 Subject: [PATCH 086/362] [pornhub] Bypass scrape detection (closes #5930) --- youtube_dl/extractor/pornhub.py | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index e377de196..f5f3e6593 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -10,7 +10,9 @@ from .common import InfoExtractor from ..compat import ( compat_HTTPError, compat_str, + compat_urllib_request, ) +from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, @@ -126,6 +128,26 @@ class PornHubIE(InfoExtractor): 'only_matching': True, }] + def _download_webpage_handle(self, *args, **kwargs): + def dl(*args, **kwargs): + return super(PornHubIE, self)._download_webpage_handle(*args, **kwargs) + + webpage, urlh = dl(*args, **kwargs) + + if any(re.search(p, webpage) for p in ( + r'<body\b[^>]+\bonload=["\']go\(\)', + r'document\.cookie\s*=\s*["\']RNKEY=', + r'document\.location\.reload\(true\)')): + url_or_request = args[0] + url = (url_or_request.get_full_url() + if isinstance(url_or_request, compat_urllib_request.Request) + else url_or_request) + phantom = PhantomJSwrapper(self, required_version='2.0') + phantom.get(url, html=webpage) + webpage, urlh = dl(*args, **kwargs) + + return webpage, urlh + @staticmethod def _extract_urls(webpage): return re.findall( From 6510a3aa971c00525969040ad654249c0c73f125 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 03:55:41 +0700 Subject: [PATCH 087/362] [crunchyroll] Extend _VALID_URL (closes #18955) --- youtube_dl/extractor/crunchyroll.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 4a68d092b..5e2cbe41d 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -144,7 +144,7 @@ class CrunchyrollBaseIE(InfoExtractor): class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): IE_NAME = 'crunchyroll' - _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { @@ -269,6 +269,9 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): }, { 'url': 'http://www.crunchyroll.com/media-723735', 'only_matching': True, + }, { + 'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921', + 'only_matching': True, }] _FORMAT_IDS = { From 71a1f61700789fb0d61fc6ad9681b6f0899d2f51 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 04:12:06 +0700 Subject: [PATCH 088/362] [pornhub] Apply scrape detection bypass for all extractors --- youtube_dl/extractor/pornhub.py | 46 +++++++++++++++++---------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index f5f3e6593..be93d5d48 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -24,7 +24,29 @@ from ..utils import ( ) -class PornHubIE(InfoExtractor): +class PornHubBaseIE(InfoExtractor): + def _download_webpage_handle(self, *args, **kwargs): + def dl(*args, **kwargs): + return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) + + webpage, urlh = dl(*args, **kwargs) + + if any(re.search(p, webpage) for p in ( + r'<body\b[^>]+\bonload=["\']go\(\)', + r'document\.cookie\s*=\s*["\']RNKEY=', + r'document\.location\.reload\(true\)')): + url_or_request = args[0] + url = (url_or_request.get_full_url() + if isinstance(url_or_request, compat_urllib_request.Request) + else url_or_request) + phantom = PhantomJSwrapper(self, required_version='2.0') + phantom.get(url, html=webpage) + webpage, urlh = dl(*args, **kwargs) + + return webpage, urlh + + +class PornHubIE(PornHubBaseIE): IE_DESC = 'PornHub and Thumbzilla' _VALID_URL = r'''(?x) https?:// @@ -128,26 +150,6 @@ class PornHubIE(InfoExtractor): 'only_matching': True, }] - def _download_webpage_handle(self, *args, **kwargs): - def dl(*args, **kwargs): - return super(PornHubIE, self)._download_webpage_handle(*args, **kwargs) - - webpage, urlh = dl(*args, **kwargs) - - if any(re.search(p, webpage) for p in ( - r'<body\b[^>]+\bonload=["\']go\(\)', - r'document\.cookie\s*=\s*["\']RNKEY=', - r'document\.location\.reload\(true\)')): - url_or_request = args[0] - url = (url_or_request.get_full_url() - if isinstance(url_or_request, compat_urllib_request.Request) - else url_or_request) - phantom = PhantomJSwrapper(self, required_version='2.0') - phantom.get(url, html=webpage) - webpage, urlh = dl(*args, **kwargs) - - return webpage, urlh - @staticmethod def _extract_urls(webpage): return re.findall( @@ -329,7 +331,7 @@ class PornHubIE(InfoExtractor): } -class PornHubPlaylistBaseIE(InfoExtractor): +class PornHubPlaylistBaseIE(PornHubBaseIE): def _extract_entries(self, webpage, host): # Only process container div with main playlist content skipping # drop-down menu that uses similar pattern for videos (see From 0670bdd8f2bca39fdeadc63e1cd53b5d5b3e638c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 04:43:55 +0700 Subject: [PATCH 089/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/ChangeLog b/ChangeLog index 902301765..687796a0e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,32 @@ +version <unreleased> + +Core +* [utils] Fix urljoin for paths with non-http(s) schemes +* [extractor/common] Improve jwplayer relative URL handling (#18892) ++ [YoutubeDL] Add negation support for string comparisons in format selection + expressions (#18600, #18805) +* [extractor/common] Improve HLS video-only format detection (#18923) + +Extractors +* [crunchyroll] Extend URL regular expression (#18955) +* [pornhub] Bypass scrape detection (#4822, #5930, #7074, #10175, #12722, + #17197, #18338 #18842, #18899) ++ [vrv] Add support for authentication (#14307) +* [videomore:season] Fix extraction +* [videomore] Improve extraction (#18908) ++ [tnaflix] Pass Referer in metadata request (#18925) +* [radiocanada] Relax DRM check (#18608, #18609) +* [vimeo] Fix video password verification for videos protected by + Referer HTTP header ++ [hketv] Add support for hkedcity.net (#18696) ++ [streamango] Add support for fruithosts.net (#18710) ++ [instagram] Add support for tags (#18757) ++ [odnoklassniki] Detect paid videos (#18876) +* [ted] Correct acodec for HTTP formats (#18923) +* [cartoonnetwork] Fix extraction (#15664, #17224) +* [vimeo] Fix extraction for password protected player URLs (#18889) + + version 2019.01.17 Extractors From 435e382423f860aca82a58d7c3db58cbfa242b40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 04:46:55 +0700 Subject: [PATCH 090/362] release 2019.01.23 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 841bca914..db3ebaeed 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.17** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.23*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.23** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.17 +[debug] youtube-dl version 2019.01.23 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 687796a0e..55ad44315 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.23 Core * [utils] Fix urljoin for paths with non-http(s) schemes diff --git a/docs/supportedsites.md b/docs/supportedsites.md index c01409419..d759d0273 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -361,6 +361,7 @@ - **hitbox** - **hitbox:live** - **HitRecord** + - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau - **HornBunny** - **HotNewHipHop** - **hotstar** @@ -386,6 +387,7 @@ - **IndavideoEmbed** - **InfoQ** - **Instagram** + - **instagram:tag**: Instagram hashtag search - **instagram:user**: Instagram user profile - **Internazionale** - **InternetVideoArchive** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index ea3f62928..d77949eed 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.17' +__version__ = '2019.01.23' From e118a8794ffe5a3a414afd489726f34d753b0b23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 01:34:41 +0700 Subject: [PATCH 091/362] [YoutubeDL] Fix typo in string negation implementation and add more tests (closes #18961) --- test/test_YoutubeDL.py | 30 +++++++++++++++++++++++++++--- youtube_dl/YoutubeDL.py | 2 +- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index df8994b84..1d7452744 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -242,6 +242,7 @@ class TestFormatSelection(unittest.TestCase): def test_format_selection_string_ops(self): formats = [ {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, + {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL}, ] info_dict = _make_result(formats) @@ -253,6 +254,11 @@ class TestFormatSelection(unittest.TestCase): # does not equal (!=) ydl = YDL({'format': '[format_id!=abc-cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) # starts with (^=) @@ -262,7 +268,12 @@ class TestFormatSelection(unittest.TestCase): self.assertEqual(downloaded['format_id'], 'abc-cba') # does not start with (!^=) - ydl = YDL({'format': '[format_id!^=abc-cba]'}) + ydl = YDL({'format': '[format_id!^=abc]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) # ends with ($=) @@ -272,16 +283,29 @@ class TestFormatSelection(unittest.TestCase): self.assertEqual(downloaded['format_id'], 'abc-cba') # does not end with (!$=) - ydl = YDL({'format': '[format_id!$=abc-cba]'}) + ydl = YDL({'format': '[format_id!$=cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) # contains (*=) - ydl = YDL({'format': '[format_id*=-]'}) + ydl = YDL({'format': '[format_id*=bc-cb]'}) ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'abc-cba') # does not contain (!*=) + ydl = YDL({'format': '[format_id!*=bc-cb]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + ydl = YDL({'format': '[format_id!*=-]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index a827414dc..80ed8d7e5 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1078,7 +1078,7 @@ class YoutubeDL(object): comparison_value = m.group('value') str_op = STR_OPERATORS[m.group('op')] if m.group('negation'): - op = lambda attr, value: not str_op + op = lambda attr, value: not str_op(attr, value) else: op = str_op From 7d311586eda9eae9430da3f6d18932d79127daa7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 01:44:09 +0700 Subject: [PATCH 092/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/ChangeLog b/ChangeLog index 55ad44315..a28c6e951 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version <unreleased> + +Core +* [YoutubeDL] Fix negation for string operators in format selection (#18961) + + version 2019.01.23 Core From a1e171233d86a064865353cc820969c10cb1f251 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 01:46:23 +0700 Subject: [PATCH 093/362] release 2019.01.24 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index db3ebaeed..63aefe013 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.23*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.23** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.24*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.24** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.23 +[debug] youtube-dl version 2019.01.24 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index a28c6e951..1fda747bb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.24 Core * [YoutubeDL] Fix negation for string operators in format selection (#18961) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index d77949eed..18c1f8d4c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.23' +__version__ = '2019.01.24' From 9713d1d1e0a7eff5c1b9873a2f4f054111a568ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 02:30:12 +0700 Subject: [PATCH 094/362] [openload] Add support for oload.club (closes #18969) --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index cf51e4770..b713e78b8 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club) ) )/ (?:f|embed)/ @@ -334,6 +334,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.fun/f/gb6G1H4sHXY', 'only_matching': True, + }, { + 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 118afcf52ff23726e5f0c436083710f5c63230fa Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 23 Jan 2019 22:16:21 +0100 Subject: [PATCH 095/362] [go] fix adobe pass requests for Disney Now(closes #18901) --- youtube_dl/extractor/go.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index ec9dd6e3a..206d89e82 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -25,15 +25,15 @@ class GoIE(AdobePassIE): }, 'watchdisneychannel': { 'brand': '004', - 'requestor_id': 'Disney', + 'resource_id': 'Disney', }, 'watchdisneyjunior': { 'brand': '008', - 'requestor_id': 'DisneyJunior', + 'resource_id': 'DisneyJunior', }, 'watchdisneyxd': { 'brand': '009', - 'requestor_id': 'DisneyXD', + 'resource_id': 'DisneyXD', } } _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\ @@ -130,8 +130,8 @@ class GoIE(AdobePassIE): 'device': '001', } if video_data.get('accesslevel') == '1': - requestor_id = site_info['requestor_id'] - resource = self._get_mvpd_resource( + requestor_id = site_info.get('requestor_id', 'DisneyChannels') + resource = site_info.get('resource_id') or self._get_mvpd_resource( requestor_id, title, video_id, None) auth = self._extract_mvpd_auth( url, video_id, requestor_id, resource) From eb35b163adf61f8ff0ee6c504e98bc94db16e705 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 24 Jan 2019 20:23:04 +0100 Subject: [PATCH 096/362] [postprocessor/ffmpeg] fallback to ffmpeg/avconv for audio codec detection(closes #681) --- youtube_dl/postprocessor/ffmpeg.py | 53 +++++++++++++++++++----------- 1 file changed, 34 insertions(+), 19 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 39a905380..b952b0970 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -9,9 +9,6 @@ import re from .common import AudioConversionError, PostProcessor -from ..compat import ( - compat_subprocess_get_DEVNULL, -) from ..utils import ( encodeArgument, encodeFilename, @@ -165,27 +162,45 @@ class FFmpegPostProcessor(PostProcessor): return self._paths[self.probe_basename] def get_audio_codec(self, path): - if not self.probe_available: - raise PostProcessingError('ffprobe or avprobe not found. Please install one.') + if not self.probe_available and not self.available: + raise PostProcessingError('ffprobe/avprobe and ffmpeg/avconv not found. Please install one.') try: - cmd = [ - encodeFilename(self.probe_executable, True), - encodeArgument('-show_streams'), - encodeFilename(self._ffmpeg_filename_argument(path), True)] + if self.probe_available: + cmd = [ + encodeFilename(self.probe_executable, True), + encodeArgument('-show_streams')] + else: + cmd = [ + encodeFilename(self.executable, True), + encodeArgument('-i')] + cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True)) if self._downloader.params.get('verbose', False): - self._downloader.to_screen('[debug] %s command line: %s' % (self.basename, shell_quote(cmd))) - handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE, stdin=subprocess.PIPE) - output = handle.communicate()[0] - if handle.wait() != 0: + self._downloader.to_screen( + '[debug] %s command line: %s' % (self.basename, shell_quote(cmd))) + handle = subprocess.Popen( + cmd, stderr=subprocess.PIPE, + stdout=subprocess.PIPE, stdin=subprocess.PIPE) + stdout_data, stderr_data = handle.communicate() + expected_ret = 0 if self.probe_available else 1 + if handle.wait() != expected_ret: return None except (IOError, OSError): return None - audio_codec = None - for line in output.decode('ascii', 'ignore').split('\n'): - if line.startswith('codec_name='): - audio_codec = line.split('=')[1].strip() - elif line.strip() == 'codec_type=audio' and audio_codec is not None: - return audio_codec + output = (stdout_data if self.probe_available else stderr_data).decode('ascii', 'ignore') + if self.probe_available: + audio_codec = None + for line in output.split('\n'): + if line.startswith('codec_name='): + audio_codec = line.split('=')[1].strip() + elif line.strip() == 'codec_type=audio' and audio_codec is not None: + return audio_codec + else: + # Stream #FILE_INDEX:STREAM_INDEX[STREAM_ID](LANGUAGE): CODEC_TYPE: CODEC_NAME + mobj = re.search( + r'Stream\s*#\d+:\d+(?:\[0x[0-9a-f]+\])?(?:\([a-z]{3}\))?:\s*Audio:\s*([0-9a-z]+)', + output) + if mobj: + return mobj.group(1) return None def run_ffmpeg_multiple_files(self, input_paths, out_path, opts): From 0eba178fce80923515f4a9ac411e46648a19d78c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 25 Jan 2019 04:04:58 +0700 Subject: [PATCH 097/362] [nhk] Extend _VALID_URL (closes #18968) --- youtube_dl/extractor/nhk.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 5c8cd76dc..d4acbcc3e 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -5,8 +5,8 @@ from ..utils import ExtractorError class NhkVodIE(InfoExtractor): - _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)' - _TEST = { + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)' + _TESTS = [{ # Videos available only for a limited period of time. Visit # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples. 'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815', @@ -19,7 +19,10 @@ class NhkVodIE(InfoExtractor): 'episode': 'The Kimono as Global Fashion', }, 'skip': 'Videos available only for a limited period of time', - } + }, { + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/', + 'only_matching': True, + }] _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k' def _real_extract(self, url): From 1602a240a7742f9e0a02b3f0effd215d00d859f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 25 Jan 2019 04:16:49 +0700 Subject: [PATCH 098/362] [drtv] Fix extraction (closes #18989) --- youtube_dl/extractor/drtv.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index f757745ba..8d63ca433 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -77,10 +77,9 @@ class DRTVIE(InfoExtractor): r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), webpage, 'video id') - programcard = self._download_json( - 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, - video_id, 'Downloading video JSON') - data = programcard['Data'][0] + data = self._download_json( + 'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, + video_id, 'Downloading video JSON', query={'expanded': 'true'}) title = remove_end(self._og_search_title( webpage, default=None), ' | TV | DR') or data['Title'] @@ -97,7 +96,7 @@ class DRTVIE(InfoExtractor): formats = [] subtitles = {} - for asset in data['Assets']: + for asset in [data['PrimaryAsset']]: kind = asset.get('Kind') if kind == 'Image': thumbnail = asset.get('Uri') From ae18d58297c16a300a89693360efd19be4a97e92 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 25 Jan 2019 11:01:27 +0100 Subject: [PATCH 099/362] [usatoday] fix extraction for videos with custom brightcove partner id(closes #18990) --- youtube_dl/extractor/usatoday.py | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/usatoday.py b/youtube_dl/extractor/usatoday.py index e5678dc78..b2103448d 100644 --- a/youtube_dl/extractor/usatoday.py +++ b/youtube_dl/extractor/usatoday.py @@ -3,21 +3,23 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, get_element_by_attribute, parse_duration, + try_get, update_url_query, - ExtractorError, ) from ..compat import compat_str class USATodayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?usatoday\.com/(?:[^/]+/)*(?P<id>[^?/#]+)' - _TEST = { + _TESTS = [{ + # Brightcove Partner ID = 29906170001 'url': 'http://www.usatoday.com/media/cinematic/video/81729424/us-france-warn-syrian-regime-ahead-of-new-peace-talks/', - 'md5': '4d40974481fa3475f8bccfd20c5361f8', + 'md5': '033587d2529dc3411a1ab3644c3b8827', 'info_dict': { - 'id': '81729424', + 'id': '4799374959001', 'ext': 'mp4', 'title': 'US, France warn Syrian regime ahead of new peace talks', 'timestamp': 1457891045, @@ -25,8 +27,20 @@ class USATodayIE(InfoExtractor): 'uploader_id': '29906170001', 'upload_date': '20160313', } - } - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/29906170001/38a9eecc-bdd8-42a3-ba14-95397e48b3f8_default/index.html?videoId=%s' + }, { + # ui-video-data[asset_metadata][items][brightcoveaccount] = 28911775001 + 'url': 'https://www.usatoday.com/story/tech/science/2018/08/21/yellowstone-supervolcano-eruption-stop-worrying-its-blow/973633002/', + 'info_dict': { + 'id': '5824495846001', + 'ext': 'mp4', + 'title': 'Yellowstone more likely to crack rather than explode', + 'timestamp': 1534790612, + 'description': 'md5:3715e7927639a4f16b474e9391687c62', + 'uploader_id': '28911775001', + 'upload_date': '20180820', + } + }] + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' def _real_extract(self, url): display_id = self._match_id(url) @@ -35,10 +49,11 @@ class USATodayIE(InfoExtractor): if not ui_video_data: raise ExtractorError('no video on the webpage', expected=True) video_data = self._parse_json(ui_video_data, display_id) + item = try_get(video_data, lambda x: x['asset_metadata']['items'], dict) or {} return { '_type': 'url_transparent', - 'url': self.BRIGHTCOVE_URL_TEMPLATE % video_data['brightcove_id'], + 'url': self.BRIGHTCOVE_URL_TEMPLATE % (item.get('brightcoveaccount', '29906170001'), item.get('brightcoveid') or video_data['brightcove_id']), 'id': compat_str(video_data['id']), 'title': video_data['title'], 'thumbnail': video_data.get('thumbnail'), From 252abb1e8b881aa9d3942c436711ac33235b37cd Mon Sep 17 00:00:00 2001 From: Sergey M <dstftw@gmail.com> Date: Sat, 26 Jan 2019 15:29:19 +0700 Subject: [PATCH 100/362] [README.md] Mention more convenience extraction functions --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 4ba982907..c1572f771 100644 --- a/README.md +++ b/README.md @@ -1213,7 +1213,7 @@ Incorrect: 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' ``` -### Use safe conversion functions +### Use convenience conversion and parsing functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. @@ -1221,6 +1221,8 @@ Use `url_or_none` for safe URL processing. Use `try_get` for safe metadata extraction from parsed JSON. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. + Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples From 845333acf6280761d19f91b3e018c418d922a0de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 04:14:54 +0700 Subject: [PATCH 101/362] [wakanim] Add extractor (closes #14374) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/wakanim.py | 55 ++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/wakanim.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 574a47e6d..2ffcffa9e 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1373,6 +1373,7 @@ from .vuclip import VuClipIE from .vvvvid import VVVVIDIE from .vyborymos import VyboryMosIE from .vzaar import VzaarIE +from .wakanim import WakanimIE from .walla import WallaIE from .washingtonpost import ( WashingtonPostIE, diff --git a/youtube_dl/extractor/wakanim.py b/youtube_dl/extractor/wakanim.py new file mode 100644 index 000000000..1d588bdd6 --- /dev/null +++ b/youtube_dl/extractor/wakanim.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + merge_dicts, + urljoin, +) + + +class WakanimIE(InfoExtractor): + _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)' + _TEST = { + 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu', + 'info_dict': { + 'id': '2997', + 'ext': 'mp4', + 'title': 'Episode 02', + 'description': 'md5:2927701ea2f7e901de8bfa8d39b2852d', + 'series': 'The Asterisk War (OmU.)', + 'season_number': 1, + 'episode': 'Episode 02', + 'episode_number': 2, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + m3u8_url = urljoin(url, self._search_regex( + r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url', + group='url')) + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + info = self._search_json_ld(webpage, video_id, default={}) + + title = self._search_regex( + (r'<h1[^>]+\bclass=["\']episode_h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1', + r'<span[^>]+\bclass=["\']episode_title["\'][^>]*>(?P<title>[^<]+)'), + webpage, 'title', default=None, group='title') + + return merge_dicts(info, { + 'id': video_id, + 'title': title, + 'formats': formats, + }) From 458fd30f56785d514862dcb8a604a329d8e29ec6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 04:36:58 +0700 Subject: [PATCH 102/362] [extractor/common] Extract season in _json_ld --- youtube_dl/extractor/common.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 95456b291..c4ea2882f 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1249,7 +1249,10 @@ class InfoExtractor(object): info['title'] = episode_name part_of_season = e.get('partOfSeason') if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'): - info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) + info.update({ + 'season': unescapeHTML(part_of_season.get('name')), + 'season_number': int_or_none(part_of_season.get('seasonNumber')), + }) part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries') if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'): info['series'] = unescapeHTML(part_of_series.get('name')) From 30cd1a5f3920d7485225a5d57b6ce41be4cde672 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Jan 2019 22:52:54 +0100 Subject: [PATCH 103/362] [wakanim] detect DRM protected videos --- youtube_dl/extractor/wakanim.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/wakanim.py b/youtube_dl/extractor/wakanim.py index 1d588bdd6..f9a2395d9 100644 --- a/youtube_dl/extractor/wakanim.py +++ b/youtube_dl/extractor/wakanim.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, merge_dicts, urljoin, ) @@ -10,7 +11,7 @@ from ..utils import ( class WakanimIE(InfoExtractor): _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu', 'info_dict': { 'id': '2997', @@ -26,7 +27,11 @@ class WakanimIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, - } + }, { + # DRM Protected + 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/7843/sword-art-online-alicization-omu-arc-2-folge-15-omu', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -36,6 +41,12 @@ class WakanimIE(InfoExtractor): m3u8_url = urljoin(url, self._search_regex( r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url', group='url')) + # https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls + encryption = self._search_regex( + r'encryption%3D(c(?:enc|bc(?:s-aapl)?))', + m3u8_url, 'encryption', default=None) + if encryption and encryption in ('cenc', 'cbcs-aapl'): + raise ExtractorError('This video is DRM protected.', expected=True) formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', From 1fcc91663bc84a599cc613ff1fa0e4bc15f42a9e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 27 Jan 2019 10:53:38 +0100 Subject: [PATCH 104/362] [vice] fix extraction for locked videos(closes #16248) --- youtube_dl/extractor/vice.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 538258617..8fdfd743d 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -94,7 +94,6 @@ class ViceIE(AdobePassIE): 'url': 'https://www.viceland.com/en_us/video/thursday-march-1-2018/5a8f2d7ff1cdb332dd446ec1', 'only_matching': True, }] - _PREPLAY_HOST = 'vms.vice' @staticmethod def _extract_urls(webpage): @@ -158,9 +157,8 @@ class ViceIE(AdobePassIE): }) try: - host = 'www.viceland' if is_locked else self._PREPLAY_HOST preplay = self._download_json( - 'https://%s.com/%s/video/preplay/%s' % (host, locale, video_id), + 'https://vms.vice.com/%s/video/preplay/%s' % (locale, video_id), video_id, query=query) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401): From bf8ebc9cfe1ae2b62baf2116f84748db03c4df7c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 21:25:43 +0700 Subject: [PATCH 105/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/ChangeLog b/ChangeLog index 1fda747bb..9d5c25273 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,22 @@ +version <unreleased> + +Core ++ [extractor/common] Extract season in _json_ld +* [postprocessor/ffmpeg] Fallback to ffmpeg/avconv for audio codec detection + (#681) + +Extractors +* [vice] Fix extraction for locked videos (#16248) ++ [wakanim] Detect DRM protected videos ++ [wakanim] Add support for wakanim.tv (#14374) +* [usatoday] Fix extraction for videos with custom brightcove partner id + (#18990) +* [drtv] Fix extraction (#18989) +* [nhk] Extend URL regular expression (#18968) +* [go] Fix Adobe Pass requests for Disney Now (#18901) ++ [openload] Add support for oload.club (#18969) + + version 2019.01.24 Core From e71be6ee9f239308765443d49d91358fa306e48a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 21:28:09 +0700 Subject: [PATCH 106/362] release 2019.01.27 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 4 +++- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 5 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 63aefe013..f529e3f4b 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.24*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.24** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.27*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.27** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.24 +[debug] youtube-dl version 2019.01.27 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index a71b045d0..6c1739860 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -339,7 +339,7 @@ Incorrect: 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' ``` -### Use safe conversion functions +### Use convenience conversion and parsing functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. @@ -347,6 +347,8 @@ Use `url_or_none` for safe URL processing. Use `try_get` for safe metadata extraction from parsed JSON. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. + Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples diff --git a/ChangeLog b/ChangeLog index 9d5c25273..d94fe36ec 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.27 Core + [extractor/common] Extract season in _json_ld diff --git a/docs/supportedsites.md b/docs/supportedsites.md index d759d0273..6377bf815 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -1069,6 +1069,7 @@ - **VVVVID** - **VyboryMos** - **Vzaar** + - **Wakanim** - **Walla** - **WalyTV** - **washingtonpost** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 18c1f8d4c..ec89cfc64 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.24' +__version__ = '2019.01.27' From 2b3afe6b0fee226bb1e61027d815df088cb40757 Mon Sep 17 00:00:00 2001 From: Andrew Udvare <audvare@gmail.com> Date: Sun, 27 Jan 2019 22:24:37 -0500 Subject: [PATCH 107/362] [postprocessor/ffmpeg] Disable "Last message repeated" messages which cause non-zero exit status --- youtube_dl/postprocessor/ffmpeg.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index b952b0970..8ef03f43b 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -218,6 +218,7 @@ class FFmpegPostProcessor(PostProcessor): encodeFilename(self._ffmpeg_filename_argument(path), True) ]) cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + + ['-loglevel', 'repeat+info'] + files_cmd + [encodeArgument(o) for o in opts] + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) From 7f903dd8bfbc9c2de129d5b0be23ef62d8ca3df3 Mon Sep 17 00:00:00 2001 From: Tatsh <Tatsh@users.noreply.github.com> Date: Mon, 28 Jan 2019 10:57:14 -0500 Subject: [PATCH 108/362] [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding subtitles (closes #19042) Related issue: https://trac.ffmpeg.org/ticket/6016 --- youtube_dl/postprocessor/ffmpeg.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index b952b0970..fff2021ff 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -407,6 +407,9 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): # Don't copy the existing subtitles, we may be running the # postprocessor a second time '-map', '-0:s', + # Don't copy Apple TV chapters track, bin_data (see #19042, #19024, + # https://trac.ffmpeg.org/ticket/6016) + '-map', '-0:d', ] if information['ext'] == 'mp4': opts += ['-c:s', 'mov_text'] From 61ff92e11ea876532697451b1ed727f42274b109 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 29 Jan 2019 01:59:56 +0700 Subject: [PATCH 109/362] [postprocessor/ffmpeg] Wrap loglevel args in encodeArgument --- youtube_dl/postprocessor/ffmpeg.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 33dbcad9f..88b9ae9be 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -218,7 +218,7 @@ class FFmpegPostProcessor(PostProcessor): encodeFilename(self._ffmpeg_filename_argument(path), True) ]) cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + - ['-loglevel', 'repeat+info'] + + [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + files_cmd + [encodeArgument(o) for o in opts] + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) From a81daba2311cb4d6c5bc7e62b47438a78aa5c10f Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Mon, 28 Jan 2019 20:20:46 +0100 Subject: [PATCH 110/362] [zattoo] Add support for tv.salt.ch --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/zattoo.py | 11 +++++++++++ 2 files changed, 12 insertions(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2ffcffa9e..9d776ff45 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1497,6 +1497,7 @@ from .zattoo import ( QuantumTVIE, QuicklineIE, QuicklineLiveIE, + SaltTVIE, SAKTVIE, VTXTVIE, WalyTVIE, diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index 896276301..ee514666b 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -420,3 +420,14 @@ class EinsUndEinsTVIE(ZattooIE): 'url': 'https://www.1und1.tv/watch/abc/123-abc', 'only_matching': True, }] + + +class SaltTVIE(ZattooIE): + _NETRC_MACHINE = 'salttv' + _HOST = 'tv.salt.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://tv.salt.ch/watch/abc/123-abc', + 'only_matching': True, + }] From 41c2c254d3c30afde395e8abbe0ced2c53485a78 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Jan 2019 22:39:08 +0100 Subject: [PATCH 111/362] [fox] fix extraction for free videos(#19060) --- youtube_dl/extractor/fox.py | 46 ++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index b1c91f095..2d6c97ec9 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -1,10 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -# import json -# import uuid +import json +import uuid from .adobepass import AdobePassIE +from ..compat import compat_str from ..utils import ( int_or_none, parse_age_limit, @@ -47,38 +48,31 @@ class FOXIE(AdobePassIE): 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', 'only_matching': True, }] - # _access_token = None + _access_token = None - # def _call_api(self, path, video_id, data=None): - # headers = { - # 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', - # } - # if self._access_token: - # headers['Authorization'] = 'Bearer ' + self._access_token - # return self._download_json( - # 'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers) + def _call_api(self, path, video_id, data=None): + headers = { + 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + } + if self._access_token: + headers['Authorization'] = 'Bearer ' + self._access_token + return self._download_json( + 'https://api2.fox.com/v2.0/' + path, + video_id, data=data, headers=headers) - # def _real_initialize(self): - # self._access_token = self._call_api( - # 'login', None, json.dumps({ - # 'deviceId': compat_str(uuid.uuid4()), - # }).encode())['accessToken'] + def _real_initialize(self): + self._access_token = self._call_api( + 'login', None, json.dumps({ + 'deviceId': compat_str(uuid.uuid4()), + }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) - video = self._download_json( - 'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id, - video_id, headers={ - 'apikey': 'abdcbed02c124d393b39e818a4312055', - 'Content-Type': 'application/json', - 'Referer': url, - }) - # video = self._call_api('vodplayer/' + video_id, video_id) + video = self._call_api('vodplayer/' + video_id, video_id) title = video['name'] - release_url = video['videoRelease']['url'] - # release_url = video['url'] + release_url = video['url'] data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} From 6df196f32e68ec22bd854c4d779b9d94e04e63b2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 29 Jan 2019 00:31:49 +0100 Subject: [PATCH 112/362] [fox] add support for locked videos using cookies(closes #19060) --- youtube_dl/extractor/extractors.py | 5 ++- youtube_dl/extractor/fox.py | 50 +++++++++++----------- youtube_dl/extractor/nationalgeographic.py | 22 ++++++++++ 3 files changed, 51 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9d776ff45..b40be42e6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -692,7 +692,10 @@ from .myvi import ( MyviEmbedIE, ) from .myvidster import MyVidsterIE -from .nationalgeographic import NationalGeographicVideoIE +from .nationalgeographic import ( + NationalGeographicVideoIE, + NationalGeographicTVIE, +) from .naver import NaverIE from .nba import NBAIE from .nbc import ( diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 2d6c97ec9..568656542 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -5,19 +5,23 @@ import json import uuid from .adobepass import AdobePassIE -from ..compat import compat_str +from ..compat import ( + compat_HTTPError, + compat_str, + compat_urllib_parse_unquote, +) from ..utils import ( + ExtractorError, int_or_none, parse_age_limit, parse_duration, try_get, unified_timestamp, - update_url_query, ) class FOXIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)' + _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)' _TESTS = [{ # clip 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/', @@ -32,6 +36,7 @@ class FOXIE(AdobePassIE): 'upload_date': '20170901', 'creator': 'FOX', 'series': 'Gotham', + 'age_limit': 14, }, 'params': { 'skip_download': True, @@ -44,15 +49,14 @@ class FOXIE(AdobePassIE): # episode, geo-restricted, tv provided required 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, - }, { - 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', - 'only_matching': True, }] + _HOME_PAGE_URL = 'https://www.fox.com/' + _API_KEY = 'abdcbed02c124d393b39e818a4312055' _access_token = None def _call_api(self, path, video_id, data=None): headers = { - 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + 'X-Api-Key': self._API_KEY, } if self._access_token: headers['Authorization'] = 'Bearer ' + self._access_token @@ -61,10 +65,16 @@ class FOXIE(AdobePassIE): video_id, data=data, headers=headers) def _real_initialize(self): - self._access_token = self._call_api( - 'login', None, json.dumps({ - 'deviceId': compat_str(uuid.uuid4()), - }).encode())['accessToken'] + if not self._access_token: + mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth') + if mvpd_auth: + self._access_token = (self._parse_json(compat_urllib_parse_unquote( + mvpd_auth.value), None, fatal=False) or {}).get('accessToken') + if not self._access_token: + self._access_token = self._call_api( + 'login', None, json.dumps({ + 'deviceId': compat_str(uuid.uuid4()), + }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) @@ -73,25 +83,15 @@ class FOXIE(AdobePassIE): title = video['name'] release_url = video['url'] - - data = try_get( - video, lambda x: x['trackingData']['properties'], dict) or {} - - rating = video.get('contentRating') - if data.get('authRequired'): - resource = self._get_mvpd_resource( - 'fbc-fox', title, video.get('guid'), rating) - release_url = update_url_query( - release_url, { - 'auth': self._extract_mvpd_auth( - url, video_id, 'fbc-fox', resource) - }) m3u8_url = self._download_json(release_url, video_id)['playURL'] formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') self._sort_formats(formats) + data = try_get( + video, lambda x: x['trackingData']['properties'], dict) or {} + duration = int_or_none(video.get('durationInSeconds')) or int_or_none( video.get('duration')) or parse_duration(video.get('duration')) timestamp = unified_timestamp(video.get('datePublished')) @@ -117,7 +117,7 @@ class FOXIE(AdobePassIE): 'description': video.get('description'), 'duration': duration, 'timestamp': timestamp, - 'age_limit': parse_age_limit(rating), + 'age_limit': parse_age_limit(video.get('contentRating')), 'creator': creator, 'series': series, 'season_number': int_or_none(video.get('seasonNumber')), diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index 165964ca0..ee12e2b47 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .fox import FOXIE from ..utils import ( smuggle_url, url_basename, @@ -58,3 +59,24 @@ class NationalGeographicVideoIE(InfoExtractor): {'force_smil_url': True}), 'id': guid, } + + +class NationalGeographicTVIE(FOXIE): + _VALID_URL = r'https?://(?:www\.)?nationalgeographic\.com/tv/watch/(?P<id>[\da-fA-F]+)' + _TESTS = [{ + 'url': 'https://www.nationalgeographic.com/tv/watch/6a875e6e734b479beda26438c9f21138/', + 'info_dict': { + 'id': '6a875e6e734b479beda26438c9f21138', + 'ext': 'mp4', + 'title': 'Why Nat Geo? Valley of the Boom', + 'description': 'The lives of prominent figures in the tech world, including their friendships, rivalries, victories and failures.', + 'timestamp': 1542662458, + 'upload_date': '20181119', + 'age_limit': 14, + }, + 'params': { + 'skip_download': True, + }, + }] + _HOME_PAGE_URL = 'https://www.nationalgeographic.com/tv/' + _API_KEY = '238bb0a0c2aba67922c48709ce0c06fd' From a2d821d7112fb1423f99ddf309a843c80cc3be2d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 29 Jan 2019 23:33:09 +0700 Subject: [PATCH 113/362] [drtv] Improve extraction (closes #19039) + Add support for EncryptedUri videos + Extract more metadata * Fix subtitles extraction --- youtube_dl/extractor/drtv.py | 133 +++++++++++++++++++++++++++-------- 1 file changed, 102 insertions(+), 31 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index 8d63ca433..c5f211128 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,15 +1,25 @@ # coding: utf-8 from __future__ import unicode_literals +import binascii +import hashlib +import re + + from .common import InfoExtractor +from ..aes import aes_cbc_decrypt +from ..compat import compat_urllib_parse_unquote from ..utils import ( + bytes_to_intlist, ExtractorError, int_or_none, + intlist_to_bytes, float_or_none, mimetype2ext, - parse_iso8601, - remove_end, + str_or_none, + unified_timestamp, update_url_query, + url_or_none, ) @@ -20,23 +30,31 @@ class DRTVIE(InfoExtractor): IE_NAME = 'drtv' _TESTS = [{ 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10', - 'md5': '7ae17b4e18eb5d29212f424a7511c184', + 'md5': '25e659cccc9a2ed956110a299fdf5983', 'info_dict': { 'id': 'klassen-darlig-taber-10', 'ext': 'mp4', 'title': 'Klassen - Dårlig taber (10)', 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa', - 'timestamp': 1471991907, - 'upload_date': '20160823', + 'timestamp': 1539085800, + 'upload_date': '20181009', 'duration': 606.84, + 'series': 'Klassen', + 'season': 'Klassen I', + 'season_number': 1, + 'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b', + 'episode': 'Episode 10', + 'episode_number': 10, + 'release_year': 2016, }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { # embed 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang', 'info_dict': { - 'id': 'christiania-pusher-street-ryddes-drdkrjpo', + 'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6', 'ext': 'mp4', - 'title': 'LIVE Christianias rydning af Pusher Street er i gang', + 'title': 'christiania pusher street ryddes drdkrjpo', 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5', 'timestamp': 1472800279, 'upload_date': '20160902', @@ -45,17 +63,18 @@ class DRTVIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { # with SignLanguage formats 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder', 'info_dict': { 'id': 'historien-om-danmark-stenalder', 'ext': 'mp4', - 'title': 'Historien om Danmark: Stenalder (1)', + 'title': 'Historien om Danmark: Stenalder', 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a', - 'timestamp': 1490401996, - 'upload_date': '20170325', - 'duration': 3502.04, + 'timestamp': 1546628400, + 'upload_date': '20190104', + 'duration': 3502.56, 'formats': 'mincount:20', }, 'params': { @@ -74,19 +93,26 @@ class DRTVIE(InfoExtractor): video_id = self._search_regex( (r'data-(?:material-identifier|episode-slug)="([^"]+)"', - r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), - webpage, 'video id') + r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), + webpage, 'video id', default=None) + + if not video_id: + video_id = compat_urllib_parse_unquote(self._search_regex( + r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', + webpage, 'urn')) data = self._download_json( 'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, video_id, 'Downloading video JSON', query={'expanded': 'true'}) - title = remove_end(self._og_search_title( - webpage, default=None), ' | TV | DR') or data['Title'] + title = str_or_none(data.get('Title')) or re.sub( + r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '', + self._og_search_title(webpage)) description = self._og_search_description( webpage, default=None) or data.get('Description') - timestamp = parse_iso8601(data.get('CreatedTime')) + timestamp = unified_timestamp( + data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime')) thumbnail = None duration = None @@ -96,16 +122,51 @@ class DRTVIE(InfoExtractor): formats = [] subtitles = {} - for asset in [data['PrimaryAsset']]: + assets = [] + primary_asset = data.get('PrimaryAsset') + if isinstance(primary_asset, dict): + assets.append(primary_asset) + secondary_assets = data.get('SecondaryAssets') + if isinstance(secondary_assets, list): + for secondary_asset in secondary_assets: + if isinstance(secondary_asset, dict): + assets.append(secondary_asset) + + def hex_to_bytes(hex): + return binascii.a2b_hex(hex.encode('ascii')) + + def decrypt_uri(e): + n = int(e[2:10], 16) + a = e[10 + n:] + data = bytes_to_intlist(hex_to_bytes(e[10:10 + n])) + key = bytes_to_intlist(hashlib.sha256( + ('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest()) + iv = bytes_to_intlist(hex_to_bytes(a)) + decrypted = aes_cbc_decrypt(data, key, iv) + return intlist_to_bytes( + decrypted[:-decrypted[-1]]).decode('utf-8').split('?')[0] + + for asset in assets: kind = asset.get('Kind') if kind == 'Image': - thumbnail = asset.get('Uri') + thumbnail = url_or_none(asset.get('Uri')) elif kind in ('VideoResource', 'AudioResource'): duration = float_or_none(asset.get('DurationInMilliseconds'), 1000) restricted_to_denmark = asset.get('RestrictedToDenmark') asset_target = asset.get('Target') for link in asset.get('Links', []): uri = link.get('Uri') + if not uri: + encrypted_uri = link.get('EncryptedUri') + if not encrypted_uri: + continue + try: + uri = decrypt_uri(encrypted_uri) + except Exception: + self.report_warning( + 'Unable to decrypt EncryptedUri', video_id) + continue + uri = url_or_none(uri) if not uri: continue target = link.get('Target') @@ -139,19 +200,22 @@ class DRTVIE(InfoExtractor): 'vcodec': 'none' if kind == 'AudioResource' else None, 'preference': preference, }) - subtitles_list = asset.get('SubtitlesList') - if isinstance(subtitles_list, list): - LANGS = { - 'Danish': 'da', - } - for subs in subtitles_list: - if not subs.get('Uri'): - continue - lang = subs.get('Language') or 'da' - subtitles.setdefault(LANGS.get(lang, lang), []).append({ - 'url': subs['Uri'], - 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt' - }) + subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist') + if isinstance(subtitles_list, list): + LANGS = { + 'Danish': 'da', + } + for subs in subtitles_list: + if not isinstance(subs, dict): + continue + sub_uri = url_or_none(subs.get('Uri')) + if not sub_uri: + continue + lang = subs.get('Language') or 'da' + subtitles.setdefault(LANGS.get(lang, lang), []).append({ + 'url': sub_uri, + 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt' + }) if not formats and restricted_to_denmark: self.raise_geo_restricted( @@ -169,6 +233,13 @@ class DRTVIE(InfoExtractor): 'duration': duration, 'formats': formats, 'subtitles': subtitles, + 'series': str_or_none(data.get('SeriesTitle')), + 'season': str_or_none(data.get('SeasonTitle')), + 'season_number': int_or_none(data.get('SeasonNumber')), + 'season_id': str_or_none(data.get('SeasonUrn')), + 'episode': str_or_none(data.get('EpisodeTitle')), + 'episode_number': int_or_none(data.get('EpisodeNumber')), + 'release_year': int_or_none(data.get('ProductionYear')), } From 41cff90c41006b30213c7f676bd3920a1612b717 Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Mon, 28 Jan 2019 19:42:49 -0400 Subject: [PATCH 114/362] [yourporn] Fix extraction and extract duration (closes #18815, closes #18852) change cdn to cdn4 for the video_url --- youtube_dl/extractor/yourporn.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index c8dc29bd8..01e5f0c0e 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import urljoin +from ..utils import ( + parse_duration, + urljoin +) class YourPornIE(InfoExtractor): @@ -27,17 +30,21 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]).replace('/cdn/', '/cdn3/') + video_id)[video_id]).replace('/cdn/', '/cdn4/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', default=None) or self._og_search_description(webpage)).strip() + thumbnail = self._og_search_thumbnail(webpage) + duration = parse_duration(self._search_regex(r'duration:[^0-9]*([0-9:]+)', + webpage, 'duration', default=None)) return { 'id': video_id, 'url': video_url, 'title': title, + 'duration': duration, 'thumbnail': thumbnail, 'age_limit': 18 } From 9868f1ab1853484d7a6c38cd6fa0d94a11914cae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 29 Jan 2019 23:56:42 +0700 Subject: [PATCH 115/362] [yourporn] Improve (closes #19061) --- youtube_dl/extractor/yourporn.py | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 01e5f0c0e..2c63f9752 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( parse_duration, - urljoin + urljoin, ) @@ -17,7 +17,11 @@ class YourPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'md5:c9f43630bd968267672651ba905a7d35', 'thumbnail': r're:^https?://.*\.jpg$', - 'age_limit': 18 + 'duration': 165, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, }, } @@ -35,16 +39,16 @@ class YourPornIE(InfoExtractor): title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', default=None) or self._og_search_description(webpage)).strip() - thumbnail = self._og_search_thumbnail(webpage) + duration = parse_duration(self._search_regex( + r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration', + default=None)) - duration = parse_duration(self._search_regex(r'duration:[^0-9]*([0-9:]+)', - webpage, 'duration', default=None)) return { 'id': video_id, 'url': video_url, 'title': title, - 'duration': duration, 'thumbnail': thumbnail, - 'age_limit': 18 + 'duration': duration, + 'age_limit': 18, } From 5496754ae4c9097f37cfd9b307261cbbca438260 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 00:03:19 +0700 Subject: [PATCH 116/362] [fox] Remove unused imports --- youtube_dl/extractor/fox.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 568656542..0ffceeb7c 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -6,12 +6,10 @@ import uuid from .adobepass import AdobePassIE from ..compat import ( - compat_HTTPError, compat_str, compat_urllib_parse_unquote, ) from ..utils import ( - ExtractorError, int_or_none, parse_age_limit, parse_duration, From ca01e5f9039dd6c0d5abff5c7139f82c5d1dfba7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 00:05:32 +0700 Subject: [PATCH 117/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index d94fe36ec..8f5343b23 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version <unreleased> + +Core +* [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding + subtitles (#19024, #19042) +* [postprocessor/ffmpeg] Disable "Last message repeated" messages (#19025) + +Extractors +* [yourporn] Fix extraction and extract duration (#18815, #18852, #19061) +* [drtv] Improve extraction (#19039) + + Add support for EncryptedUri videos + + Extract more metadata + * Fix subtitles extraction ++ [fox] Add support for locked videos using cookies (#19060) +* [fox] Fix extraction for free videos (#19060) ++ [zattoo] Add support for tv.salt.ch (#19059) + + version 2019.01.27 Core From 1063b4c7073ce056f694b1690dd5d5a1a06fb347 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 00:08:39 +0700 Subject: [PATCH 118/362] release 2019.01.30 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index f529e3f4b..3944a4a38 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.27*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.27** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.27 +[debug] youtube-dl version 2019.01.30 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 8f5343b23..745fffeaa 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.30 Core * [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 6377bf815..2918520c3 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -546,6 +546,7 @@ - **MyVisionTV** - **n-tv.de** - **natgeo:video** + - **NationalGeographicTV** - **Naver** - **NBA** - **NBC** @@ -776,6 +777,7 @@ - **safari:api** - **safari:course**: safaribooksonline.com online courses - **SAKTV** + - **SaltTV** - **Sapo**: SAPO Vídeos - **savefrom.net** - **SBS**: sbs.com.au diff --git a/youtube_dl/version.py b/youtube_dl/version.py index ec89cfc64..97818d0c7 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.27' +__version__ = '2019.01.30' From ce52c7c111602f41d7f9c498f2915fd255ba2eab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 06:15:23 +0700 Subject: [PATCH 119/362] [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (closes #19067) --- youtube_dl/postprocessor/ffmpeg.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 88b9ae9be..5bcb00ac0 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -217,11 +217,13 @@ class FFmpegPostProcessor(PostProcessor): encodeArgument('-i'), encodeFilename(self._ffmpeg_filename_argument(path), True) ]) - cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + - [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + - files_cmd + - [encodeArgument(o) for o in opts] + - [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) + cmd = [encodeFilename(self.executable, True), encodeArgument('-y')] + # avconv does not have repeat option + if self.basename == 'ffmpeg': + cmd += [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + cmd += (files_cmd + + [encodeArgument(o) for o in opts] + + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) if self._downloader.params.get('verbose', False): self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd)) From c2a0fe2ea7422c437a27c8fac57c7e865517354b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 06:17:25 +0700 Subject: [PATCH 120/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/ChangeLog b/ChangeLog index 745fffeaa..e6de6ca03 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version <unreleased> + +Core +* [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (#19067) + + version 2019.01.30 Core From 7b0f9df23d9842ddb2a545a0ceaf594daa0e12ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 06:19:36 +0700 Subject: [PATCH 121/362] release 2019.01.30.1 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 3944a4a38..423a08e4d 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30.1*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30.1** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.30 +[debug] youtube-dl version 2019.01.30.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index e6de6ca03..4872cd9fc 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.30.1 Core * [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (#19067) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 97818d0c7..be3bbdd73 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.30' +__version__ = '2019.01.30.1' From 645c4885cf38ecb244412dffda2760f4c0e72033 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 30 Jan 2019 14:43:44 +0100 Subject: [PATCH 122/362] [crackle] authorize media detail request(closes #16931) --- youtube_dl/extractor/crackle.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index f73ef6b63..49bf3a4f9 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -1,7 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals, division +import hashlib +import hmac import re +import time from .common import InfoExtractor from ..compat import compat_HTTPError @@ -74,13 +77,16 @@ class CrackleIE(InfoExtractor): for country in countries: try: + # Authorization generation algorithm is reverse engineered from: + # https://www.sonycrackle.com/static/js/main.ea93451f.chunk.js + media_detail_url = 'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s?disableProtocols=true' % (video_id, country) + timestamp = time.strftime('%Y%m%d%H%M', time.gmtime()) + h = hmac.new(b'IGSLUQCBDFHEOIFM', '|'.join([media_detail_url, timestamp]).encode(), hashlib.sha1).hexdigest().upper() media = self._download_json( - 'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s' - % (video_id, country), video_id, - 'Downloading media JSON as %s' % country, - 'Unable to download media JSON', query={ - 'disableProtocols': 'true', - 'format': 'json' + media_detail_url, video_id, 'Downloading media JSON as %s' % country, + 'Unable to download media JSON', headers={ + 'Accept': 'application/json', + 'Authorization': '|'.join([h, timestamp, '117', '1']), }) except ExtractorError as e: # 401 means geo restriction, trying next country From 15e832ff2a1bee42b299d3498439cf789c16fffa Mon Sep 17 00:00:00 2001 From: Batuhan's Unmaintained Account <batuhanosmantaskaya@gmail.com> Date: Wed, 30 Jan 2019 19:39:02 +0300 Subject: [PATCH 123/362] [openload] Add support for oload.info --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index b713e78b8..747aa298a 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info) ) )/ (?:f|embed)/ @@ -337,6 +337,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', 'only_matching': True, + }, { + 'url': 'https://oload.info/f/5NEAbI2BDSk', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 9613e14a92429046b162145dfd40dee5795ca409 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 31 Jan 2019 00:15:45 +0700 Subject: [PATCH 124/362] [openload] Add support for openload.pw and oload.pw (closes #18930) --- youtube_dl/extractor/openload.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 747aa298a..a2ae25272 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -248,8 +248,8 @@ class OpenloadIE(InfoExtractor): (?P<host> (?:www\.)? (?: - openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info) + openload\.(?:co|io|link|pw)| + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw) ) )/ (?:f|embed)/ @@ -340,6 +340,12 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.info/f/5NEAbI2BDSk', 'only_matching': True, + }, { + 'url': 'https://openload.pw/f/WyKgK8s94N0', + 'only_matching': True, + }, { + 'url': 'https://oload.pw/f/WyKgK8s94N0', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 49fe4175ae165527a0b06b8d97cdc85d83041fef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 1 Feb 2019 01:48:10 +0700 Subject: [PATCH 125/362] [drtv] Improve preference (closes #19079) --- youtube_dl/extractor/drtv.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index c5f211128..0c7e350f0 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -171,10 +171,13 @@ class DRTVIE(InfoExtractor): continue target = link.get('Target') format_id = target or '' - preference = None - if asset_target in ('SpokenSubtitles', 'SignLanguage'): + if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'): preference = -1 format_id += '-%s' % asset_target + elif asset_target == 'Default': + preference = 1 + else: + preference = None if target == 'HDS': f4m_formats = self._extract_f4m_formats( uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43', From 3ef2da2d21061bd44df0b0a0d27e82a365209662 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 04:00:29 +0700 Subject: [PATCH 126/362] [soundcloud] Fix paged playlists extraction, add support for albums and update client id --- youtube_dl/extractor/soundcloud.py | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 81c81c8d5..030840fd8 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -34,7 +34,7 @@ class SoundcloudIE(InfoExtractor): (?:(?:(?:www\.|m\.)?soundcloud\.com/ (?!stations/track) (?P<uploader>[\w\d-]+)/ - (?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) + (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) @@ -157,7 +157,7 @@ class SoundcloudIE(InfoExtractor): }, ] - _CLIENT_ID = 'LvWovRaJZlWCHql0bISuum8Bd2KX79mb' + _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK' @staticmethod def _extract_urls(webpage): @@ -368,7 +368,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): - _API_BASE = 'https://api.soundcloud.com' _API_V2_BASE = 'https://api-v2.soundcloud.com' def _extract_playlist(self, base_url, playlist_id, playlist_title): @@ -389,8 +388,12 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): next_href, playlist_id, 'Downloading track page %s' % (i + 1)) collection = response['collection'] - if not collection: - break + + if not isinstance(collection, list): + collection = [] + + # Empty collection may be returned, in this case we proceed + # straight to next_href def resolve_permalink_url(candidates): for cand in candidates: @@ -429,7 +432,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): (?:(?:www|m)\.)?soundcloud\.com/ (?P<user>[^/]+) (?:/ - (?P<rsrc>tracks|sets|reposts|likes|spotlight) + (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight) )? /?(?:[?#].*)?$ ''' @@ -476,13 +479,17 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'title': 'Grynpyret (Spotlight)', }, 'playlist_mincount': 1, + }, { + 'url': 'https://soundcloud.com/soft-cell-official/albums', + 'only_matching': True, }] _BASE_URL_MAP = { - 'all': '%s/profile/soundcloud:users:%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_BASE, + 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, + 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, + 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'reposts': '%s/profile/soundcloud:users:%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, + 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, } @@ -490,6 +497,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): _TITLE_MAP = { 'all': 'All', 'tracks': 'Tracks', + 'albums': 'Albums', 'sets': 'Playlists', 'reposts': 'Reposts', 'likes': 'Likes', From b6423e6ca215e1583e013cf7b2c1faf8d3dcace7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 04:11:32 +0700 Subject: [PATCH 127/362] [soundcloud:user] Update tests --- youtube_dl/extractor/soundcloud.py | 48 ++++++++++++++++-------------- 1 file changed, 26 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 030840fd8..13463ae4f 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -438,40 +438,47 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): ''' IE_NAME = 'soundcloud:user' _TESTS = [{ - 'url': 'https://soundcloud.com/the-akashic-chronicler', + 'url': 'https://soundcloud.com/soft-cell-official', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (All)', + 'id': '207965082', + 'title': 'Soft Cell (All)', }, - 'playlist_mincount': 74, + 'playlist_mincount': 28, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/tracks', + 'url': 'https://soundcloud.com/soft-cell-official/tracks', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Tracks)', + 'id': '207965082', + 'title': 'Soft Cell (Tracks)', }, - 'playlist_mincount': 37, + 'playlist_mincount': 27, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/sets', + 'url': 'https://soundcloud.com/soft-cell-official/albums', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Playlists)', + 'id': '207965082', + 'title': 'Soft Cell (Albums)', + }, + 'playlist_mincount': 1, + }, { + 'url': 'https://soundcloud.com/jcv246/sets', + 'info_dict': { + 'id': '12982173', + 'title': 'Jordi / cv (Playlists)', }, 'playlist_mincount': 2, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/reposts', + 'url': 'https://soundcloud.com/jcv246/reposts', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Reposts)', + 'id': '12982173', + 'title': 'Jordi / cv (Reposts)', }, - 'playlist_mincount': 7, + 'playlist_mincount': 6, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/likes', + 'url': 'https://soundcloud.com/clalberg/likes', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Likes)', + 'id': '11817582', + 'title': 'clalberg (Likes)', }, - 'playlist_mincount': 321, + 'playlist_mincount': 5, }, { 'url': 'https://soundcloud.com/grynpyret/spotlight', 'info_dict': { @@ -479,9 +486,6 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'title': 'Grynpyret (Spotlight)', }, 'playlist_mincount': 1, - }, { - 'url': 'https://soundcloud.com/soft-cell-official/albums', - 'only_matching': True, }] _BASE_URL_MAP = { From e9fef7ee4e666b60bc7a757391f16e2be76f6cbb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 05:44:31 +0700 Subject: [PATCH 128/362] [YoutubeDL] Fallback to ie_key of matching extractor while making download archive id when no explicit ie_key is provided (#19022) --- youtube_dl/YoutubeDL.py | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 80ed8d7e5..c168415ce 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -2060,15 +2060,21 @@ class YoutubeDL(object): self.report_warning('Unable to remove downloaded original file') def _make_archive_id(self, info_dict): + video_id = info_dict.get('id') + if not video_id: + return # Future-proof against any change in case # and backwards compatibility with prior versions - extractor = info_dict.get('extractor_key') + extractor = info_dict.get('extractor_key') or info_dict.get('ie_key') # key in a playlist if extractor is None: - if 'id' in info_dict: - extractor = info_dict.get('ie_key') # key in a playlist - if extractor is None: - return None # Incomplete video information - return extractor.lower() + ' ' + info_dict['id'] + # Try to find matching extractor for the URL and take its ie_key + for ie in self._ies: + if ie.suitable(info_dict['url']): + extractor = ie.ie_key() + break + else: + return + return extractor.lower() + ' ' + video_id def in_download_archive(self, info_dict): fn = self.params.get('download_archive') @@ -2076,7 +2082,7 @@ class YoutubeDL(object): return False vid_id = self._make_archive_id(info_dict) - if vid_id is None: + if not vid_id: return False # Incomplete video information try: From b9bc1cff721b6f63e733c6ababeec45b92f1484b Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Fri, 1 Feb 2019 19:04:00 -0400 Subject: [PATCH 129/362] [drtuber] Extract duration --- youtube_dl/extractor/drtuber.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index 5c41c8022..2baea585b 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -4,7 +4,9 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, NO_DEFAULT, + parse_duration, str_to_int, ) @@ -65,6 +67,9 @@ class DrTuberIE(InfoExtractor): }) self._sort_formats(formats) + duration = int_or_none(video_data.get('duration')) or parse_duration( + video_data.get('duration_format')) + title = self._html_search_regex( (r'<h1[^>]+class=["\']title[^>]+>([^<]+)', r'<title>([^<]+)\s*@\s+DrTuber', @@ -103,4 +108,5 @@ class DrTuberIE(InfoExtractor): 'comment_count': comment_count, 'categories': categories, 'age_limit': self._rta_search(webpage), + 'duration': duration, } From 6cc6e0c34d0f67747be7bac91690820f47b26acb Mon Sep 17 00:00:00 2001 From: Cory Hall <corydantehall@gmail.com> Date: Thu, 31 Jan 2019 20:51:37 -0500 Subject: [PATCH 130/362] [soundcloud:pagedplaylist] Add ie and title to entries (#19022) rel: https://github.com/rg3/youtube-dl/issues/19022 --- youtube_dl/extractor/soundcloud.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 13463ae4f..1c8d3c53b 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -395,18 +395,20 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): # Empty collection may be returned, in this case we proceed # straight to next_href - def resolve_permalink_url(candidates): - for cand in candidates: + def append_url_result(entries, item): + for cand in (item, item.get('track'), item.get('playlist')): if isinstance(cand, dict): permalink_url = cand.get('permalink_url') - entry_id = self._extract_id(cand) if permalink_url and permalink_url.startswith('http'): - return permalink_url, entry_id + return entries.append( + self.url_result( + permalink_url, + ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + video_id=self._extract_id(cand), + video_title=cand.get('title'))) for e in collection: - permalink_url, entry_id = resolve_permalink_url((e, e.get('track'), e.get('playlist'))) - if permalink_url: - entries.append(self.url_result(permalink_url, video_id=entry_id)) + append_url_result(entries, e) next_href = response.get('next_href') if not next_href: From 7c5307f4c4e91ef6551d70cd844b93fbdc5c3cf0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 23:40:06 +0700 Subject: [PATCH 131/362] [soundcloud:pagedplaylist] Improve (closes #19086) --- youtube_dl/extractor/soundcloud.py | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 1c8d3c53b..5536e7851 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -18,6 +18,7 @@ from ..utils import ( int_or_none, unified_strdate, update_url_query, + url_or_none, ) @@ -395,20 +396,23 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): # Empty collection may be returned, in this case we proceed # straight to next_href - def append_url_result(entries, item): - for cand in (item, item.get('track'), item.get('playlist')): - if isinstance(cand, dict): - permalink_url = cand.get('permalink_url') - if permalink_url and permalink_url.startswith('http'): - return entries.append( - self.url_result( - permalink_url, - ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, - video_id=self._extract_id(cand), - video_title=cand.get('title'))) + def resolve_entry(candidates): + for cand in candidates: + if not isinstance(cand, dict): + continue + permalink_url = url_or_none(cand.get('permalink_url')) + if not permalink_url: + continue + return self.url_result( + permalink_url, + ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + video_id=self._extract_id(cand), + video_title=cand.get('title')) for e in collection: - append_url_result(entries, e) + entry = resolve_entry((e, e.get('track'), e.get('playlist'))) + if entry: + entries.append(entry) next_href = response.get('next_href') if not next_href: From 0efcb5a2fe0c3024d3e5affe74b3d0d416413ffa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 3 Feb 2019 00:33:45 +0700 Subject: [PATCH 132/362] [vporn] Remove extractor (closes #16276) Handled by generic extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/vporn.py | 123 ----------------------------- 2 files changed, 124 deletions(-) delete mode 100644 youtube_dl/extractor/vporn.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b40be42e6..693c16e49 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1362,7 +1362,6 @@ from .voxmedia import ( VoxMediaVolumeIE, VoxMediaIE, ) -from .vporn import VpornIE from .vrt import VRTIE from .vrak import VrakIE from .vrv import ( diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py deleted file mode 100644 index 858ac9e71..000000000 --- a/youtube_dl/extractor/vporn.py +++ /dev/null @@ -1,123 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - parse_duration, - str_to_int, - urljoin, -) - - -class VpornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)' - _TESTS = [ - { - 'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/', - 'md5': 'facf37c1b86546fa0208058546842c55', - 'info_dict': { - 'id': '497944', - 'display_id': 'violet-on-her-th-birthday', - 'ext': 'mp4', - 'title': 'Violet on her 19th birthday', - 'description': 'Violet dances in front of the camera which is sure to get you horny.', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'kileyGrope', - 'categories': ['Masturbation', 'Teen'], - 'duration': 393, - 'age_limit': 18, - 'view_count': int, - }, - 'skip': 'video removed', - }, - { - 'url': 'http://www.vporn.com/female/hana-shower/523564/', - 'md5': 'ced35a4656198a1664cf2cda1575a25f', - 'info_dict': { - 'id': '523564', - 'display_id': 'hana-shower', - 'ext': 'mp4', - 'title': 'Hana Shower', - 'description': 'Hana showers at the bathroom.', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Hmmmmm', - 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'], - 'duration': 588, - 'age_limit': 18, - 'view_count': int, - } - }, - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') - - webpage = self._download_webpage(url, display_id) - - errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!' - if errmsg in webpage: - raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) - - title = self._html_search_regex( - r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() - description = self._html_search_regex( - r'class="(?:descr|description_txt)">(.*?)</div>', - webpage, 'description', fatal=False) - thumbnail = urljoin('http://www.vporn.com', self._html_search_regex( - r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', - default=None)) - - uploader = self._html_search_regex( - r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>', - webpage, 'uploader', fatal=False) - - categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage) - - duration = parse_duration(self._search_regex( - r'Runtime:\s*</span>\s*(\d+ min \d+ sec)', - webpage, 'duration', fatal=False)) - - view_count = str_to_int(self._search_regex( - r'class="views">([\d,\.]+) [Vv]iews<', - webpage, 'view count', fatal=False)) - comment_count = str_to_int(self._html_search_regex( - r"'Comments \(([\d,\.]+)\)'", - webpage, 'comment count', default=None)) - - formats = [] - - for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage): - video_url = video[1] - fmt = { - 'url': video_url, - 'format_id': video[0], - } - m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url) - if m: - fmt.update({ - 'width': int(m.group('width')), - 'height': int(m.group('height')), - 'vbr': int(m.group('vbr')), - }) - formats.append(fmt) - - self._sort_formats(formats) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'categories': categories, - 'duration': duration, - 'view_count': view_count, - 'comment_count': comment_count, - 'age_limit': 18, - 'formats': formats, - } From eecf788b90fa4d49567c714f5a613fdd2b6e2507 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 3 Feb 2019 09:10:09 +0100 Subject: [PATCH 133/362] [teachable] add support for courses.workitdaily.com (closes #18871) --- youtube_dl/extractor/teachable.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 47ac95ee8..c1a9deafe 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -27,6 +27,7 @@ class TeachableBaseIE(InfoExtractor): 'market.saleshacker.com': 'saleshacker', 'learnability.org': 'learnability', 'edurila.com': 'edurila', + 'courses.workitdaily.com': 'workitdaily', } _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys())) From 07fbfef1c7e36b25dd7098be73ab76b87378a015 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 3 Feb 2019 12:10:41 +0100 Subject: [PATCH 134/362] [radiocanada] switch to the new media requests(closes #19115) --- youtube_dl/extractor/radiocanada.py | 133 ++++++++-------------------- 1 file changed, 39 insertions(+), 94 deletions(-) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 302f67d96..58e294892 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -5,14 +5,10 @@ import re from .common import InfoExtractor from ..utils import ( - xpath_text, - find_xpath_attr, determine_ext, + ExtractorError, int_or_none, unified_strdate, - xpath_element, - ExtractorError, - determine_protocol, unsmuggle_url, ) @@ -61,107 +57,53 @@ class RadioCanadaIE(InfoExtractor): 'only_matching': True, } ] + _GEO_COUNTRIES = ['CA'] + + def _call_api(self, path, video_id, app_code, query): + query.update({ + 'appCode': app_code, + 'idMedia': video_id, + 'output': 'json', + }) + return self._download_json( + 'https://services.radio-canada.ca/media/' + path, video_id, headers={ + 'Authorization': 'Client-Key 773aea60-0e80-41bb-9c7f-e6d7c3ad17fb' + }, query=query) def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) app_code, video_id = re.match(self._VALID_URL, url).groups() - metadata = self._download_xml( - 'http://api.radio-canada.ca/metaMedia/v1/index.ashx', - video_id, note='Downloading metadata XML', query={ - 'appCode': app_code, - 'idMedia': video_id, - }) + metas = self._call_api('meta/v1/index.ashx', video_id, app_code, {})['Metas'] def get_meta(name): - el = find_xpath_attr(metadata, './/Meta', 'name', name) - return el.text if el is not None else None + for meta in metas: + if meta.get('name') == name: + text = meta.get('text') + if text: + return text # protectionType does not necessarily mean the video is DRM protected (see # https://github.com/rg3/youtube-dl/pull/18609). if get_meta('protectionType'): self.report_warning('This video is probably DRM protected.') - device_types = ['ipad'] - if not smuggled_data: - device_types.append('flash') - device_types.append('android') - - formats = [] - error = None - # TODO: extract f4m formats - # f4m formats can be extracted using flashhd device_type but they produce unplayable file - for device_type in device_types: - validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx' - query = { - 'appCode': app_code, - 'idMedia': video_id, - 'connectionType': 'broadband', - 'multibitrate': 'true', - 'deviceType': device_type, - } - if smuggled_data: - validation_url = 'https://services.radio-canada.ca/media/validation/v2/' - query.update(smuggled_data) - else: - query.update({ - # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction - 'paysJ391wsHjbOJwvCs26toz': 'CA', - 'bypasslock': 'NZt5K62gRqfc', - }) - v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False) - v_url = xpath_text(v_data, 'url') - if not v_url: - continue - if v_url == 'null': - error = xpath_text(v_data, 'message') - continue - ext = determine_ext(v_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - v_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - v_url, video_id, f4m_id='hds', fatal=False)) - else: - ext = determine_ext(v_url) - bitrates = xpath_element(v_data, 'bitrates') - for url_e in bitrates.findall('url'): - tbr = int_or_none(url_e.get('bitrate')) - if not tbr: - continue - f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url) - protocol = determine_protocol({'url': f_url}) - f = { - 'format_id': '%s-%d' % (protocol, tbr), - 'url': f_url, - 'ext': 'flv' if protocol == 'rtmp' else ext, - 'protocol': protocol, - 'width': int_or_none(url_e.get('width')), - 'height': int_or_none(url_e.get('height')), - 'tbr': tbr, - } - mobj = re.match(r'(?P<url>rtmp://[^/]+/[^/]+)/(?P<playpath>[^?]+)(?P<auth>\?.+)', f_url) - if mobj: - f.update({ - 'url': mobj.group('url') + mobj.group('auth'), - 'play_path': mobj.group('playpath'), - }) - formats.append(f) - if protocol == 'rtsp': - base_url = self._search_regex( - r'rtsp://([^?]+)', f_url, 'base url', default=None) - if base_url: - base_url = 'http://' + base_url - formats.extend(self._extract_m3u8_formats( - base_url + '/playlist.m3u8', video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - base_url + '/manifest.f4m', video_id, - f4m_id='hds', fatal=False)) - if not formats and error: + query = { + 'connectionType': 'hd', + 'deviceType': 'ipad', + 'multibitrate': 'true', + } + if smuggled_data: + query.update(smuggled_data) + v_data = self._call_api('validation/v2/', video_id, app_code, query) + v_url = v_data.get('url') + if not v_url: + error = v_data['message'] + if error == "Le contenu sélectionné n'est pas disponible dans votre pays": + raise self.raise_geo_restricted(error, self._GEO_COUNTRIES) raise ExtractorError( '%s said: %s' % (self.IE_NAME, error), expected=True) + formats = self._extract_m3u8_formats(v_url, video_id, 'mp4') self._sort_formats(formats) subtitles = {} @@ -189,8 +131,8 @@ class RadioCanadaIE(InfoExtractor): class RadioCanadaAudioVideoIE(InfoExtractor): 'radiocanada:audiovideo' - _VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P<id>[0-9]+)' - _TEST = { + _VALID_URL = r'https?://ici\.radio-canada\.ca/([^/]+/)*media-(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam', 'info_dict': { 'id': '7527184', @@ -203,7 +145,10 @@ class RadioCanadaAudioVideoIE(InfoExtractor): # m3u8 download 'skip_download': True, }, - } + }, { + 'url': 'https://ici.radio-canada.ca/info/videos/media-7527184/barack-obama-au-vietnam', + 'only_matching': True, + }] def _real_extract(self, url): return self.url_result('radiocanada:medianet:%s' % self._match_id(url)) From 70c3ee13671798d7e3b80ea9be863ef73bd08653 Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Mon, 4 Feb 2019 13:06:04 -0400 Subject: [PATCH 135/362] [pornhd] Extract like count --- youtube_dl/extractor/pornhd.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index b52879c7a..a079cd32a 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -23,6 +23,7 @@ class PornHdIE(InfoExtractor): 'description': 'md5:3748420395e03e31ac96857a8f125b2b', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, + 'like_count': int, 'age_limit': 18, } }, { @@ -37,6 +38,7 @@ class PornHdIE(InfoExtractor): 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, + 'like_count': int, 'age_limit': 18, }, 'skip': 'Not available anymore', @@ -85,6 +87,11 @@ class PornHdIE(InfoExtractor): r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage, 'thumbnail', fatal=False, group='url') + like_count = int_or_none(self._search_regex( + (r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes', + r'class=["\']save-count["\'][^>]*>\s*(\d+)'), + webpage, 'like count', fatal=False)) + return { 'id': video_id, 'display_id': display_id, @@ -92,6 +99,7 @@ class PornHdIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'view_count': view_count, + 'like_count': like_count, 'formats': formats, 'age_limit': 18, } From 48fb963b2f9495922a4acf751608167cbc273693 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Feb 2019 00:07:37 +0700 Subject: [PATCH 136/362] [pornhd] Fix formats extraction --- youtube_dl/extractor/pornhd.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index a079cd32a..27d65d4b9 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -4,9 +4,11 @@ import re from .common import InfoExtractor from ..utils import ( + determine_ext, ExtractorError, int_or_none, js_to_json, + urljoin, ) @@ -14,7 +16,7 @@ class PornHdIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?' _TESTS = [{ 'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video', - 'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5', + 'md5': '87f1540746c1d32ec7a2305c12b96b25', 'info_dict': { 'id': '9864', 'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video', @@ -67,12 +69,14 @@ class PornHdIE(InfoExtractor): formats = [] for format_id, video_url in sources.items(): + video_url = urljoin(url, video_url) if not video_url: continue height = int_or_none(self._search_regex( r'^(\d+)[pP]', format_id, 'height', default=None)) formats.append({ 'url': video_url, + 'ext': determine_ext(video_url, 'mp4'), 'format_id': format_id, 'height': height, }) From d2d970d07ec82f648b62bff8b15ac0b57d0d0496 Mon Sep 17 00:00:00 2001 From: JChris246 <chris.401@live.com> Date: Mon, 4 Feb 2019 13:33:54 -0400 Subject: [PATCH 137/362] [pornhub] Fix tags and categories extraction (closes #13720) --- youtube_dl/extractor/pornhub.py | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index be93d5d48..428324ef0 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, - js_to_json, orderedSet, remove_quotes, str_to_int, @@ -303,14 +302,17 @@ class PornHubIE(PornHubBaseIE): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - page_params = self._parse_json(self._search_regex( - r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', - webpage, 'page parameters', group='data', default='{}'), - video_id, transform_source=js_to_json, fatal=False) - tags = categories = None - if page_params: - tags = page_params.get('tags', '').split(',') - categories = page_params.get('categories', '').split(',') + def _get_items(class_name): + div = self._search_regex( + r'<div class="' + class_name + '">([\S\s]+?)</div>', + webpage, class_name, default=None) + if div: + return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)] + else: + return None + + categories = _get_items('categoriesWrapper') + tags = _get_items('tagsWrapper') return { 'id': video_id, From 5dda1edef93d94c9a49672f905df0c49c75c5739 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Feb 2019 23:06:55 +0700 Subject: [PATCH 138/362] [pornhub] Improve and simplify (closes #19135) --- youtube_dl/extractor/pornhub.py | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 428324ef0..641083da7 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -302,17 +302,12 @@ class PornHubIE(PornHubBaseIE): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - def _get_items(class_name): + def extract_list(meta_key): div = self._search_regex( - r'<div class="' + class_name + '">([\S\s]+?)</div>', - webpage, class_name, default=None) + r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>' + % meta_key, webpage, meta_key, default=None) if div: - return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)] - else: - return None - - categories = _get_items('categoriesWrapper') - tags = _get_items('tagsWrapper') + return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div) return { 'id': video_id, @@ -327,8 +322,8 @@ class PornHubIE(PornHubBaseIE): 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, - 'tags': tags, - 'categories': categories, + 'tags': extract_list('tags'), + 'categories': extract_list('categories'), 'subtitles': subtitles, } From 8fecc7353df35f6cac305c04a4e203fb2bbb4827 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Feb 2019 13:59:12 +0100 Subject: [PATCH 139/362] [toutv] fix authentication(closes #16398)(closes #18700) --- youtube_dl/extractor/radiocanada.py | 47 +++++++++++++++++--------- youtube_dl/extractor/toutv.py | 51 +++++++++-------------------- 2 files changed, 47 insertions(+), 51 deletions(-) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 58e294892..dd95f99f2 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -4,12 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, int_or_none, unified_strdate, - unsmuggle_url, ) @@ -58,23 +58,35 @@ class RadioCanadaIE(InfoExtractor): } ] _GEO_COUNTRIES = ['CA'] + _access_token = None + _claims = None - def _call_api(self, path, video_id, app_code, query): + def _call_api(self, path, video_id=None, app_code=None, query=None): + if not query: + query = {} query.update({ - 'appCode': app_code, - 'idMedia': video_id, + 'client_key': '773aea60-0e80-41bb-9c7f-e6d7c3ad17fb', 'output': 'json', }) - return self._download_json( - 'https://services.radio-canada.ca/media/' + path, video_id, headers={ - 'Authorization': 'Client-Key 773aea60-0e80-41bb-9c7f-e6d7c3ad17fb' - }, query=query) + if video_id: + query.update({ + 'appCode': app_code, + 'idMedia': video_id, + }) + if self._access_token: + query['access_token'] = self._access_token + try: + return self._download_json( + 'https://services.radio-canada.ca/media/' + path, video_id, query=query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422): + data = self._parse_json(e.cause.read().decode(), None) + error = data.get('error_description') or data['errorMessage']['text'] + raise ExtractorError(error, expected=True) + raise - def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - app_code, video_id = re.match(self._VALID_URL, url).groups() - - metas = self._call_api('meta/v1/index.ashx', video_id, app_code, {})['Metas'] + def _extract_info(self, app_code, video_id): + metas = self._call_api('meta/v1/index.ashx', video_id, app_code)['Metas'] def get_meta(name): for meta in metas: @@ -93,14 +105,16 @@ class RadioCanadaIE(InfoExtractor): 'deviceType': 'ipad', 'multibitrate': 'true', } - if smuggled_data: - query.update(smuggled_data) + if self._claims: + query['claims'] = self._claims v_data = self._call_api('validation/v2/', video_id, app_code, query) v_url = v_data.get('url') if not v_url: error = v_data['message'] if error == "Le contenu sélectionné n'est pas disponible dans votre pays": raise self.raise_geo_restricted(error, self._GEO_COUNTRIES) + if error == 'Le contenu sélectionné est disponible seulement en premium': + self.raise_login_required(error) raise ExtractorError( '%s said: %s' % (self.IE_NAME, error), expected=True) formats = self._extract_m3u8_formats(v_url, video_id, 'mp4') @@ -128,6 +142,9 @@ class RadioCanadaIE(InfoExtractor): 'formats': formats, } + def _real_extract(self, url): + return self._extract_info(*re.match(self._VALID_URL, url).groups()) + class RadioCanadaAudioVideoIE(InfoExtractor): 'radiocanada:audiovideo' diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index 2e7876cc5..f1ab91cf2 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -3,22 +3,19 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .radiocanada import RadioCanadaIE from ..utils import ( - int_or_none, - js_to_json, - urlencode_postdata, extract_attributes, - smuggle_url, + int_or_none, + merge_dicts, + urlencode_postdata, ) -class TouTvIE(InfoExtractor): +class TouTvIE(RadioCanadaIE): _NETRC_MACHINE = 'toutv' IE_NAME = 'tou.tv' _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)' - _access_token = None - _claims = None _TESTS = [{ 'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17', @@ -46,18 +43,14 @@ class TouTvIE(InfoExtractor): email, password = self._get_login_info() if email is None: return - state = 'http://ici.tou.tv/' - webpage = self._download_webpage(state, None, 'Downloading homepage') - toutvlogin = self._parse_json(self._search_regex( - r'(?s)toutvlogin\s*=\s*({.+?});', webpage, 'toutvlogin'), None, js_to_json) - authorize_url = toutvlogin['host'] + '/auth/oauth/v2/authorize' login_webpage = self._download_webpage( - authorize_url, None, 'Downloading login page', query={ - 'client_id': toutvlogin['clientId'], - 'redirect_uri': 'https://ici.tou.tv/login/loginCallback', + 'https://services.radio-canada.ca/auth/oauth/v2/authorize', + None, 'Downloading login page', query={ + 'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36', + 'redirect_uri': 'https://ici.tou.tv/logincallback', 'response_type': 'token', - 'scope': 'media-drmt openid profile email id.write media-validation.read.privileged', - 'state': state, + 'scope': 'id.write media-validation.read', + 'state': '/', }) def extract_form_url_and_data(wp, default_form_url, form_spec_re=''): @@ -86,12 +79,7 @@ class TouTvIE(InfoExtractor): self._access_token = self._search_regex( r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', urlh.geturl(), 'access token') - self._claims = self._download_json( - 'https://services.radio-canada.ca/media/validation/v2/getClaims', - None, 'Extracting Claims', query={ - 'token': self._access_token, - 'access_token': self._access_token, - })['claims'] + self._claims = self._call_api('validation/v2/getClaims')['claims'] def _real_extract(self, url): path = self._match_id(url) @@ -102,19 +90,10 @@ class TouTvIE(InfoExtractor): self.report_warning('This video is probably DRM protected.', path) video_id = metadata['IdMedia'] details = metadata['Details'] - title = details['OriginalTitle'] - video_url = 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id) - if self._access_token and self._claims: - video_url = smuggle_url(video_url, { - 'access_token': self._access_token, - 'claims': self._claims, - }) - return { - '_type': 'url_transparent', - 'url': video_url, + return merge_dicts({ 'id': video_id, - 'title': title, + 'title': details.get('OriginalTitle'), 'thumbnail': details.get('ImageUrl'), 'duration': int_or_none(details.get('LengthInSeconds')), - } + }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id)) From 241c5d7d384dcb01a62702274cfbead01f537145 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Feb 2019 19:38:10 +0100 Subject: [PATCH 140/362] [trutv] fix extraction(closes #17336) --- youtube_dl/extractor/trutv.py | 84 +++++++++++++++++++++++------------ 1 file changed, 56 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/trutv.py b/youtube_dl/extractor/trutv.py index 3a5782525..ce892c8c5 100644 --- a/youtube_dl/extractor/trutv.py +++ b/youtube_dl/extractor/trutv.py @@ -4,44 +4,72 @@ from __future__ import unicode_literals import re from .turner import TurnerBaseIE +from ..utils import ( + int_or_none, + parse_iso8601, +) class TruTVIE(TurnerBaseIE): - _VALID_URL = r'https?://(?:www\.)?trutv\.com(?:(?P<path>/shows/[^/]+/videos/[^/?#]+?)\.html|/full-episodes/[^/]+/(?P<id>\d+))' + _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P<series_slug>[0-9A-Za-z-]+)/(?:videos/(?P<clip_slug>[0-9A-Za-z-]+)|(?P<id>\d+))' _TEST = { - 'url': 'http://www.trutv.com/shows/10-things/videos/you-wont-believe-these-sports-bets.html', - 'md5': '2cdc844f317579fed1a7251b087ff417', + 'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html', 'info_dict': { - 'id': '/shows/10-things/videos/you-wont-believe-these-sports-bets', + 'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1', 'ext': 'mp4', - 'title': 'You Won\'t Believe These Sports Bets', - 'description': 'Jamie Lee sits down with a bookie to discuss the bizarre world of illegal sports betting.', - 'upload_date': '20130305', - } + 'title': 'Sunlight-Activated Flower', + 'description': "A customer is stunned when he sees Michael's sunlight-activated flower.", + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, } def _real_extract(self, url): - path, video_id = re.match(self._VALID_URL, url).groups() - auth_required = False - if path: - data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path + series_slug, clip_slug, video_id = re.match(self._VALID_URL, url).groups() + + if video_id: + path = 'episode' + display_id = video_id else: - webpage = self._download_webpage(url, video_id) - video_id = self._search_regex( - r"TTV\.TVE\.episodeId\s*=\s*'([^']+)';", - webpage, 'video id', default=video_id) - auth_required = self._search_regex( - r'TTV\.TVE\.authRequired\s*=\s*(true|false);', - webpage, 'auth required', default='false') == 'true' - data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id - return self._extract_cvp_info( - data_src, path, { - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big', - 'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do', - }, - }, { + path = 'series/clip' + display_id = clip_slug + + data = self._download_json( + 'https://api.trutv.com/v2/web/%s/%s/%s' % (path, series_slug, display_id), + display_id) + video_data = data['episode'] if video_id else data['info'] + media_id = video_data['mediaId'] + title = video_data['title'].strip() + + info = self._extract_ngtv_info( + media_id, {}, { 'url': url, 'site_name': 'truTV', - 'auth_required': auth_required, + 'auth_required': video_data.get('isAuthRequired'), }) + + thumbnails = [] + for image in video_data.get('images', []): + image_url = image.get('srcUrl') + if not image_url: + continue + thumbnails.append({ + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + info.update({ + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'description': video_data.get('description'), + 'thumbnails': thumbnails, + 'timestamp': parse_iso8601(video_data.get('publicationDate')), + 'series': video_data.get('showTitle'), + 'season_number': int_or_none(video_data.get('seasonNum')), + 'episode_number': int_or_none(video_data.get('episodeNum')), + }) + return info From f06a1cabe8b3831b5f2ff3bc27f5e7336c597e92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 7 Feb 2019 23:57:58 +0700 Subject: [PATCH 141/362] [spankbang] Extend _VALID_URL --- youtube_dl/extractor/spankbang.py | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index 67500b69c..e48cfff71 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -12,7 +12,7 @@ from ..utils import ( class SpankBangIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video' + _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)' _TESTS = [{ 'url': 'http://spankbang.com/3vvn/video/fantasy+solo', 'md5': '1cc433e1d6aa14bc376535b8679302f7', @@ -41,13 +41,22 @@ class SpankBangIE(InfoExtractor): # 4k 'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k', 'only_matching': True, + }, { + 'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/', + 'only_matching': True, + }, { + 'url': 'https://m.spankbang.com/3vvn/play', + 'only_matching': True, + }, { + 'url': 'https://spankbang.com/2y3td/embed/', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id, headers={ - 'Cookie': 'country=US' - }) + webpage = self._download_webpage( + url.replace('/%s/embed' % video_id, '/%s/video' % video_id), + video_id, headers={'Cookie': 'country=US'}) if re.search(r'<[^>]+\bid=["\']video_removed', webpage): raise ExtractorError( From 49bd993fd9adbcf6b5c11a7ec11c2b4a552e49c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 00:09:50 +0700 Subject: [PATCH 142/362] [spankbang:playlist] Add extractor (closes #19145) --- youtube_dl/extractor/extractors.py | 5 ++++- youtube_dl/extractor/spankbang.py | 33 +++++++++++++++++++++++++++++- 2 files changed, 36 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 693c16e49..d7685cd87 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1058,7 +1058,10 @@ from .southpark import ( SouthParkEsIE, SouthParkNlIE ) -from .spankbang import SpankBangIE +from .spankbang import ( + SpankBangIE, + SpankBangPlaylistIE, +) from .spankwire import SpankwireIE from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index e48cfff71..fbe6ef31a 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + orderedSet, parse_duration, parse_resolution, str_to_int, @@ -12,7 +13,7 @@ from ..utils import ( class SpankBangIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)' + _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b' _TESTS = [{ 'url': 'http://spankbang.com/3vvn/video/fantasy+solo', 'md5': '1cc433e1d6aa14bc376535b8679302f7', @@ -103,3 +104,33 @@ class SpankBangIE(InfoExtractor): 'formats': formats, 'age_limit': age_limit, } + + +class SpankBangPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+' + _TEST = { + 'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties', + 'info_dict': { + 'id': 'ug0k', + 'title': 'Big Ass Titties', + }, + 'playlist_mincount': 50, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage( + url, playlist_id, headers={'Cookie': 'country=US; mobile=on'}) + + entries = [self.url_result( + 'https://spankbang.com/%s/video' % video_id, + ie=SpankBangIE.ie_key(), video_id=video_id) + for video_id in orderedSet(re.findall( + r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))] + + title = self._html_search_regex( + r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title', + fatal=False) + + return self.playlist_result(entries, playlist_id, title) From 22f5f5c6fcd2d7f0c9f1ff3019fe0b957b771f44 Mon Sep 17 00:00:00 2001 From: Ales Jirasek <schunkac@gmail.com> Date: Wed, 10 Oct 2018 23:47:21 +0200 Subject: [PATCH 143/362] [malltv] Add extractor (closes #18058) --- test/test_InfoExtractor.py | 2 ++ youtube_dl/extractor/common.py | 2 +- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/malltv.py | 58 ++++++++++++++++++++++++++++++ youtube_dl/utils.py | 2 +- 5 files changed, 63 insertions(+), 2 deletions(-) create mode 100644 youtube_dl/extractor/malltv.py diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 75fa0bbb7..f0aa8466b 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -61,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase): <meta content='Foo' property=og:foobar> <meta name="og:test1" content='foo > < bar'/> <meta name="og:test2" content="foo >//< bar"/> + <meta property=og-test3 content='Ill-formatted opengraph'/> ''' self.assertEqual(ie._og_search_title(html), 'Foo') self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') @@ -69,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase): self.assertEqual(ie._og_search_property('foobar', html), 'Foo') self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') + self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph') self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar') self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True) self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index c4ea2882f..c3b0586a0 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1058,7 +1058,7 @@ class InfoExtractor(object): @staticmethod def _og_regexes(prop): content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))' - property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)' + property_re = (r'(?:name|property)=(?:\'og[:-]%(prop)s\'|"og[:-]%(prop)s"|\s*og[:-]%(prop)s\b)' % {'prop': re.escape(prop)}) template = r'<meta[^>]+?%s[^>]+?%s' return [ diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d7685cd87..f212b5116 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -619,6 +619,7 @@ from .mailru import ( MailRuMusicSearchIE, ) from .makertv import MakerTVIE +from .malltv import MallTVIE from .mangomolo import ( MangomoloVideoIE, MangomoloLiveIE, diff --git a/youtube_dl/extractor/malltv.py b/youtube_dl/extractor/malltv.py new file mode 100644 index 000000000..7e0876ecc --- /dev/null +++ b/youtube_dl/extractor/malltv.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from .common import InfoExtractor +from ..utils import parse_duration, merge_dicts + + +class MallTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:.+/)?(?P<id>.+)(?:\?.*$|$)' + _TESTS = [ + { + 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'md5': '9ced0de056534410837077e23bfba796', + 'info_dict': { + 'id': 't0zzt0', + 'ext': 'mp4', + 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', + 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', + 'upload_date': '20181007', + 'timestamp': 1538870400 + } + }, + { + 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'md5': '9ced0de056534410837077e23bfba796', + 'only_matching': 1, + 'info_dict': { + 'id': 't0zzt0', + 'ext': 'mp4', + 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', + 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', + 'upload_date': '20181007', + 'timestamp': 1538870400 + } + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + src_id_regex = r'(?P<src><source src=([\"\'])?.+?/(?P<id>\w{6,}?)/index)(?P<after>\1?[^>]*?>)' + video_id = self._search_regex(src_id_regex, webpage, 'ID', + group='id') + info = self._search_json_ld(webpage, video_id, default={}) + html = re.sub(src_id_regex, r'\g<src>.m3u8\g<after>', webpage) + media = self._parse_html5_media_entries(url, html, video_id) + thumbnail = info.get('thumbnail', self._og_search_thumbnail(webpage)) + duration = parse_duration(info.get('duration')) + result = { + 'id': video_id, + 'title': info.get('title', self._og_search_title(webpage)), + 'description': self._og_search_description(webpage) + } + result.update({'thumbnail': thumbnail}) + result.update({'duration': duration}) + + return merge_dicts(media[0], info, result) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index d0cb65814..f5a0bb4b0 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -184,7 +184,7 @@ DATE_FORMATS_MONTH_FIRST.extend([ ]) PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)" -JSON_LD_RE = r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>' +JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>' def preferredencoding(): From 4de3cb883c61eeec56d8d271375a0624d481ad37 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 00:43:10 +0700 Subject: [PATCH 144/362] [malltv] Fix issues and simplify (closes #17856) --- youtube_dl/extractor/malltv.py | 85 ++++++++++++++++------------------ 1 file changed, 40 insertions(+), 45 deletions(-) diff --git a/youtube_dl/extractor/malltv.py b/youtube_dl/extractor/malltv.py index 7e0876ecc..e13c2e11a 100644 --- a/youtube_dl/extractor/malltv.py +++ b/youtube_dl/extractor/malltv.py @@ -2,57 +2,52 @@ from __future__ import unicode_literals import re + from .common import InfoExtractor -from ..utils import parse_duration, merge_dicts +from ..utils import merge_dicts class MallTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:.+/)?(?P<id>.+)(?:\?.*$|$)' - _TESTS = [ - { - 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'md5': '9ced0de056534410837077e23bfba796', - 'info_dict': { - 'id': 't0zzt0', - 'ext': 'mp4', - 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', - 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', - 'upload_date': '20181007', - 'timestamp': 1538870400 - } - }, - { - 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'md5': '9ced0de056534410837077e23bfba796', - 'only_matching': 1, - 'info_dict': { - 'id': 't0zzt0', - 'ext': 'mp4', - 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', - 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', - 'upload_date': '20181007', - 'timestamp': 1538870400 - } + _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'md5': '1c4a37f080e1f3023103a7b43458e518', + 'info_dict': { + 'id': 't0zzt0', + 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'ext': 'mp4', + 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', + 'description': 'md5:25fc0ec42a72ba602b602c683fa29deb', + 'duration': 216, + 'timestamp': 1538870400, + 'upload_date': '20181007', + 'view_count': int, } - ] + }, { + 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'only_matching': True, + }] def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - src_id_regex = r'(?P<src><source src=([\"\'])?.+?/(?P<id>\w{6,}?)/index)(?P<after>\1?[^>]*?>)' - video_id = self._search_regex(src_id_regex, webpage, 'ID', - group='id') - info = self._search_json_ld(webpage, video_id, default={}) - html = re.sub(src_id_regex, r'\g<src>.m3u8\g<after>', webpage) - media = self._parse_html5_media_entries(url, html, video_id) - thumbnail = info.get('thumbnail', self._og_search_thumbnail(webpage)) - duration = parse_duration(info.get('duration')) - result = { - 'id': video_id, - 'title': info.get('title', self._og_search_title(webpage)), - 'description': self._og_search_description(webpage) - } - result.update({'thumbnail': thumbnail}) - result.update({'duration': duration}) - return merge_dicts(media[0], info, result) + webpage = self._download_webpage( + url, display_id, headers=self.geo_verification_headers()) + + SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b' + video_id = self._search_regex( + SOURCE_RE, webpage, 'video id', group='id') + + media = self._parse_html5_media_entries( + url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id, + m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0] + + info = self._search_json_ld(webpage, video_id, default={}) + + return merge_dicts(media, info, { + 'id': video_id, + 'display_id': display_id, + 'title': self._og_search_title(webpage, default=None) or display_id, + 'description': self._og_search_description(webpage, default=None), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), + }) From 1211bb6dace4773f67bbf46b8944317679573a1f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 01:08:48 +0700 Subject: [PATCH 145/362] [YoutubeDL] Improve _make_archive_id (closes #19149) --- youtube_dl/YoutubeDL.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index c168415ce..bc9fc270c 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -82,6 +82,7 @@ from .utils import ( sanitize_url, sanitized_Request, std_headers, + str_or_none, subtitles_filename, UnavailableVideoError, url_basename, @@ -2067,9 +2068,12 @@ class YoutubeDL(object): # and backwards compatibility with prior versions extractor = info_dict.get('extractor_key') or info_dict.get('ie_key') # key in a playlist if extractor is None: + url = str_or_none(info_dict.get('url')) + if not url: + return # Try to find matching extractor for the URL and take its ie_key for ie in self._ies: - if ie.suitable(info_dict['url']): + if ie.suitable(url): extractor = ie.ie_key() break else: From f1f5b47255a44e791a84b769c523127e0f047578 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 01:10:12 +0700 Subject: [PATCH 146/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/ChangeLog b/ChangeLog index 4872cd9fc..b0fbde43d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,32 @@ +version <unreleased> + +Core +* [utils] Improve JSON-LD regular expression (#18058) +* [YoutubeDL] Fallback to ie_key of matching extractor while making + download archive id when no explicit ie_key is provided (#19022) + +Extractors ++ [malltv] Add support for mall.tv (#18058, #17856) ++ [spankbang:playlist] Add support for playlists (#19145) +* [spankbang] Extend URL regular expression +* [trutv] Fix extraction (#17336) +* [toutv] Fix authentication (#16398, #18700) +* [pornhub] Fix tags and categories extraction (#13720, #19135) +* [pornhd] Fix formats extraction ++ [pornhd] Extract like count (#19123, #19125) +* [radiocanada] Switch to the new media requests (#19115) ++ [teachable] Add support for courses.workitdaily.com (#18871) +- [vporn] Remove extractor (#16276) ++ [soundcloud:pagedplaylist] Add ie and title to entries (#19022, #19086) ++ [drtuber] Extract duration (#19078) +* [soundcloud] Fix paged playlists extraction, add support for albums and update client id +* [soundcloud] Update client id +* [drtv] Improve preference (#19079) ++ [openload] Add support for openload.pw and oload.pw (#18930) ++ [openload] Add support for oload.info (#19073) +* [crackle] Authorize media detail request (#16931) + + version 2019.01.30.1 Core From 04eacf54530e6a17129d3f1b90f759f9935f2b85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 01:12:51 +0700 Subject: [PATCH 147/362] release 2019.02.08 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 ++- youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 423a08e4d..7128d998f 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30.1*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30.1** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.08*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.08** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.30.1 +[debug] youtube-dl version 2019.02.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index b0fbde43d..398528f76 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.02.08 Core * [utils] Improve JSON-LD regular expression (#18058) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 2918520c3..32fe6b647 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -476,6 +476,7 @@ - **mailru:music**: Музыка@Mail.Ru - **mailru:music:search**: Музыка@Mail.Ru - **MakerTV** + - **MallTV** - **mangomolo:live** - **mangomolo:video** - **ManyVids** @@ -827,6 +828,7 @@ - **southpark.nl** - **southparkstudios.dk** - **SpankBang** + - **SpankBangPlaylist** - **Spankwire** - **Spiegel** - **Spiegel:Article**: Articles on spiegel.de @@ -1057,7 +1059,6 @@ - **Voot** - **VoxMedia** - **VoxMediaVolume** - - **Vporn** - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **Vrak** - **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be diff --git a/youtube_dl/version.py b/youtube_dl/version.py index be3bbdd73..4dc5a611e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.30.1' +__version__ = '2019.02.08' From 91effe22a091035bc5abace2fcf562a0db89090f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 8 Feb 2019 07:21:31 +0100 Subject: [PATCH 148/362] [linkedin:learning] extract chapter_number and chapter_id(closes #19162) --- youtube_dl/extractor/linkedin.py | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py index 259fc4c5e..5a86b0064 100644 --- a/youtube_dl/extractor/linkedin.py +++ b/youtube_dl/extractor/linkedin.py @@ -34,12 +34,15 @@ class LinkedInLearningBaseIE(InfoExtractor): 'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value, }, query=query)['elements'][0] - def _get_video_id(self, urn, course_slug, video_slug): + def _get_urn_id(self, video_data): + urn = video_data.get('urn') if urn: mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn) if mobj: return mobj.group(1) - return '%s/%s' % (course_slug, video_slug) + + def _get_video_id(self, video_data, course_slug, video_slug): + return self._get_urn_id(video_data) or '%s/%s' % (course_slug, video_slug) def _real_initialize(self): email, password = self._get_login_info() @@ -123,7 +126,7 @@ class LinkedInLearningIE(LinkedInLearningBaseIE): self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr')) return { - 'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug), + 'id': self._get_video_id(video_data, course_slug, video_slug), 'title': title, 'formats': formats, 'thumbnail': video_data.get('defaultThumbnail'), @@ -154,18 +157,21 @@ class LinkedInLearningCourseIE(LinkedInLearningBaseIE): course_data = self._call_api(course_slug, 'chapters,description,title') entries = [] - for chapter in course_data.get('chapters', []): + for chapter_number, chapter in enumerate(course_data.get('chapters', []), 1): chapter_title = chapter.get('title') + chapter_id = self._get_urn_id(chapter) for video in chapter.get('videos', []): video_slug = video.get('slug') if not video_slug: continue entries.append({ '_type': 'url_transparent', - 'id': self._get_video_id(video.get('urn'), course_slug, video_slug), + 'id': self._get_video_id(video, course_slug, video_slug), 'title': video.get('title'), 'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug), 'chapter': chapter_title, + 'chapter_number': chapter_number, + 'chapter_id': chapter_id, 'ie_key': LinkedInLearningIE.ie_key(), }) From e9dee7f1b26e1c23b011a5ad5433d4debc6b48ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 9 Feb 2019 23:49:37 +0700 Subject: [PATCH 149/362] [trunews] Add extractor (closes #19153) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/trunews.py | 75 ++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+) create mode 100644 youtube_dl/extractor/trunews.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f212b5116..3e1b63b4b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1171,6 +1171,7 @@ from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE +from .trunews import TruNewsIE from .trutv import TruTVIE from .tube8 import Tube8IE from .tubitv import TubiTvIE diff --git a/youtube_dl/extractor/trunews.py b/youtube_dl/extractor/trunews.py new file mode 100644 index 000000000..b0c7caabf --- /dev/null +++ b/youtube_dl/extractor/trunews.py @@ -0,0 +1,75 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + dict_get, + float_or_none, + int_or_none, + unified_timestamp, + update_url_query, + url_or_none, +) + + +class TruNewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', + 'md5': 'a19c024c3906ff954fac9b96ce66bb08', + 'info_dict': { + 'id': '5c5a21e65d3c196e1c0020cc', + 'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', + 'ext': 'mp4', + 'title': "Will Democrats Stage a Circus During President Trump's State of the Union Speech?", + 'description': 'md5:c583b72147cc92cf21f56a31aff7a670', + 'duration': 3685, + 'timestamp': 1549411440, + 'upload_date': '20190206', + }, + 'add_ie': ['Zype'], + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + video = self._download_json( + 'https://api.zype.com/videos', display_id, query={ + 'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H', + 'per_page': 1, + 'active': 'true', + 'friendly_title': display_id, + })['response'][0] + + zype_id = video['_id'] + + thumbnails = [] + thumbnails_list = video.get('thumbnails') + if isinstance(thumbnails_list, list): + for thumbnail in thumbnails_list: + if not isinstance(thumbnail, dict): + continue + thumbnail_url = url_or_none(thumbnail.get('url')) + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int_or_none(thumbnail.get('width')), + 'height': int_or_none(thumbnail.get('height')), + }) + + return { + '_type': 'url_transparent', + 'url': update_url_query( + 'https://player.zype.com/embed/%s.js' % zype_id, + {'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}), + 'ie_key': 'Zype', + 'id': zype_id, + 'display_id': display_id, + 'title': video.get('title'), + 'description': dict_get(video, ('description', 'ott_description', 'short_description')), + 'duration': int_or_none(video.get('duration')), + 'timestamp': unified_timestamp(video.get('published_at')), + 'average_rating': float_or_none(video.get('rating')), + 'view_count': int_or_none(video.get('request_count')), + 'thumbnails': thumbnails, + } From f516f44094d2244a805d8d0ac4d809fc6cd16782 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 10 Feb 2019 23:44:08 +0700 Subject: [PATCH 150/362] [soundcloud] Extract more metadata --- youtube_dl/extractor/soundcloud.py | 65 +++++++++++++++++++++++++----- 1 file changed, 56 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 5536e7851..15da3496e 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -16,7 +16,8 @@ from ..compat import ( from ..utils import ( ExtractorError, int_or_none, - unified_strdate, + try_get, + unified_timestamp, update_url_query, url_or_none, ) @@ -51,12 +52,17 @@ class SoundcloudIE(InfoExtractor): 'info_dict': { 'id': '62986583', 'ext': 'mp3', - 'upload_date': '20121011', + 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', 'uploader': 'E.T. ExTerrestrial Music', - 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', + 'timestamp': 1349920598, + 'upload_date': '20121011', 'duration': 143, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, } }, # not streamable song @@ -68,9 +74,14 @@ class SoundcloudIE(InfoExtractor): 'title': 'Goldrushed', 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', 'uploader': 'The Royal Concept', + 'timestamp': 1337635207, 'upload_date': '20120521', - 'duration': 227, + 'duration': 30, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, 'params': { # rtmp @@ -85,11 +96,16 @@ class SoundcloudIE(InfoExtractor): 'id': '123998367', 'ext': 'mp3', 'title': 'Youtube - Dl Test Video \'\' Ä↭', - 'uploader': 'jaimeMF', 'description': 'test chars: \"\'/\\ä↭', + 'uploader': 'jaimeMF', + 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # private link (alt format) @@ -100,11 +116,16 @@ class SoundcloudIE(InfoExtractor): 'id': '123998367', 'ext': 'mp3', 'title': 'Youtube - Dl Test Video \'\' Ä↭', - 'uploader': 'jaimeMF', 'description': 'test chars: \"\'/\\ä↭', + 'uploader': 'jaimeMF', + 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # downloadable song @@ -117,9 +138,14 @@ class SoundcloudIE(InfoExtractor): 'title': 'Bus Brakes', 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', + 'timestamp': 1389232924, 'upload_date': '20140109', 'duration': 17, 'license': 'cc-by-sa', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # private link, downloadable format @@ -132,9 +158,14 @@ class SoundcloudIE(InfoExtractor): 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', 'uploader': 'Ori Uplift Music', + 'timestamp': 1504206263, 'upload_date': '20170831', 'duration': 7449, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # no album art, use avatar pic for thumbnail @@ -147,10 +178,15 @@ class SoundcloudIE(InfoExtractor): 'title': 'Sideways (Prod. Mad Real)', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'uploader': 'garyvee', + 'timestamp': 1488152409, 'upload_date': '20170226', 'duration': 207, 'thumbnail': r're:https?://.*\.jpg', 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, 'params': { 'skip_download': True, @@ -176,22 +212,33 @@ class SoundcloudIE(InfoExtractor): def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None): track_id = compat_str(info['id']) + title = info['title'] name = full_title or track_id if quiet: self.report_extraction(name) thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') if isinstance(thumbnail, compat_str): thumbnail = thumbnail.replace('-large', '-t500x500') + username = try_get(info, lambda x: x['user']['username'], compat_str) + + def extract_count(key): + return int_or_none(info.get('%s_count' % key)) + result = { 'id': track_id, - 'uploader': info.get('user', {}).get('username'), - 'upload_date': unified_strdate(info.get('created_at')), - 'title': info['title'], + 'uploader': username, + 'timestamp': unified_timestamp(info.get('created_at')), + 'title': title, 'description': info.get('description'), 'thumbnail': thumbnail, 'duration': int_or_none(info.get('duration'), 1000), 'webpage_url': info.get('permalink_url'), 'license': info.get('license'), + 'view_count': extract_count('playback'), + 'like_count': extract_count('favoritings'), + 'comment_count': extract_count('comment'), + 'repost_count': extract_count('reposts'), + 'genre': info.get('genre'), } formats = [] query = {'client_id': self._CLIENT_ID} From 4c0e0dc9dc13d53a334f75f7d7b9073f79a2dfc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 11 Feb 2019 00:49:51 +0700 Subject: [PATCH 151/362] [rutube:embed] Fix extraction and add support private videos (closes #19163) --- youtube_dl/extractor/rutube.py | 115 +++++++++++++++++++++------------ 1 file changed, 72 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 10ac8ed1f..8f54d5675 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -21,7 +21,17 @@ from ..utils import ( class RutubeBaseIE(InfoExtractor): - def _extract_video(self, video, video_id=None, require_title=True): + def _download_api_info(self, video_id, query=None): + if not query: + query = {} + query['format'] = 'json' + return self._download_json( + 'http://rutube.ru/api/video/%s/' % video_id, + video_id, 'Downloading video JSON', + 'Unable to download video JSON', query=query) + + @staticmethod + def _extract_info(video, video_id=None, require_title=True): title = video['title'] if require_title else video.get('title') age_limit = video.get('is_adult') @@ -32,7 +42,7 @@ class RutubeBaseIE(InfoExtractor): category = try_get(video, lambda x: x['category']['name']) return { - 'id': video.get('id') or video_id, + 'id': video.get('id') or video_id if video_id else video['id'], 'title': title, 'description': video.get('description'), 'thumbnail': video.get('thumbnail_url'), @@ -47,6 +57,42 @@ class RutubeBaseIE(InfoExtractor): 'is_live': bool_or_none(video.get('is_livestream')), } + def _download_and_extract_info(self, video_id, query=None): + return self._extract_info( + self._download_api_info(video_id, query=query), video_id) + + def _download_api_options(self, video_id, query=None): + if not query: + query = {} + query['format'] = 'json' + return self._download_json( + 'http://rutube.ru/api/play/options/%s/' % video_id, + video_id, 'Downloading options JSON', + 'Unable to download options JSON', + headers=self.geo_verification_headers(), query=query) + + def _extract_formats(self, options, video_id): + formats = [] + for format_id, format_url in options['video_balancer'].items(): + ext = determine_ext(format_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id, fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + return formats + + def _download_and_extract_formats(self, video_id, query=None): + return self._extract_formats( + self._download_api_options(video_id, query=query), video_id) + class RutubeIE(RutubeBaseIE): IE_NAME = 'rutube' @@ -55,13 +101,13 @@ class RutubeIE(RutubeBaseIE): _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', - 'md5': '79938ade01294ef7e27574890d0d3769', + 'md5': '1d24f180fac7a02f3900712e5a5764d6', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', - 'duration': 80, + 'duration': 81, 'uploader': 'NTDRussian', 'uploader_id': '29790', 'timestamp': 1381943602, @@ -94,39 +140,12 @@ class RutubeIE(RutubeBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - - video = self._download_json( - 'http://rutube.ru/api/video/%s/?format=json' % video_id, - video_id, 'Downloading video JSON') - - info = self._extract_video(video, video_id) - - options = self._download_json( - 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, - video_id, 'Downloading options JSON', - headers=self.geo_verification_headers()) - - formats = [] - for format_id, format_url in options['video_balancer'].items(): - ext = determine_ext(format_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - format_url, video_id, f4m_id=format_id, fatal=False)) - else: - formats.append({ - 'url': format_url, - 'format_id': format_id, - }) - self._sort_formats(formats) - - info['formats'] = formats + info = self._download_and_extract_info(video_id) + info['formats'] = self._download_and_extract_formats(video_id) return info -class RutubeEmbedIE(InfoExtractor): +class RutubeEmbedIE(RutubeBaseIE): IE_NAME = 'rutube:embed' IE_DESC = 'Rutube embedded videos' _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)' @@ -135,7 +154,7 @@ class RutubeEmbedIE(InfoExtractor): 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'info_dict': { 'id': 'a10e53b86e8f349080f718582ce4c661', - 'ext': 'flv', + 'ext': 'mp4', 'timestamp': 1387830582, 'upload_date': '20131223', 'uploader_id': '297833', @@ -149,16 +168,26 @@ class RutubeEmbedIE(InfoExtractor): }, { 'url': 'http://rutube.ru/play/embed/8083783', 'only_matching': True, + }, { + # private video + 'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ', + 'only_matching': True, }] def _real_extract(self, url): embed_id = self._match_id(url) - webpage = self._download_webpage(url, embed_id) - - canonical_url = self._html_search_regex( - r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage, - 'Canonical URL') - return self.url_result(canonical_url, RutubeIE.ie_key()) + # Query may contain private videos token and should be passed to API + # requests (see #19163) + query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + options = self._download_api_options(embed_id, query) + video_id = options['effective_video'] + formats = self._extract_formats(options, video_id) + info = self._download_and_extract_info(video_id, query) + info.update({ + 'extractor_key': 'Rutube', + 'formats': formats, + }) + return info class RutubePlaylistBaseIE(RutubeBaseIE): @@ -181,7 +210,7 @@ class RutubePlaylistBaseIE(RutubeBaseIE): video_url = url_or_none(result.get('video_url')) if not video_url: continue - entry = self._extract_video(result, require_title=False) + entry = self._extract_info(result, require_title=False) entry.update({ '_type': 'url', 'url': video_url, From d777f3e81c5f9f6c7be39586703f1f076a2025a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 11 Feb 2019 04:39:23 +0700 Subject: [PATCH 152/362] [tvplayhome] Fix episode metadata extraction (closes #19190) --- youtube_dl/extractor/tvplay.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 8f1ff3b76..7c07b26bc 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -537,8 +537,9 @@ class TVPlayHomeIE(InfoExtractor): r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number', default=None)) episode = self._search_regex( - r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode', - default=None, group='value') + (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', + r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage, + 'episode', default=None, group='value') episode_number = int_or_none(self._search_regex( r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number', default=None)) From 7d8b89163c43dfec27dab5250183e52fce838389 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 11 Feb 2019 04:41:28 +0700 Subject: [PATCH 153/362] [tvplayhome] Fix video id extraction (closes #19190) --- youtube_dl/extractor/tvplay.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 7c07b26bc..d82d48f94 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -493,10 +493,9 @@ class TVPlayHomeIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_id = self._search_regex( - r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id', - default=None) + r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id') - if video_id: + if len(video_id) < 8: return self.url_result( 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id) From 985637cbbfc1a79091eb2f5ca4afec84f6616c75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 12 Feb 2019 00:13:50 +0700 Subject: [PATCH 154/362] [twitch] Add new source format detection approach (closes #19193) --- youtube_dl/extractor/twitch.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 401615683..8c87f6dd3 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -136,7 +136,12 @@ class TwitchBaseIE(InfoExtractor): source = next(f for f in formats if f['format_id'] == 'Source') source['preference'] = 10 except StopIteration: - pass # No Source stream present + for f in formats: + if '/chunked/' in f['url']: + f.update({ + 'source_preference': 10, + 'format_note': 'Source', + }) self._sort_formats(formats) From 6f5c1807f43b9dfd17fdc6932ae7ecb6c77fb1a0 Mon Sep 17 00:00:00 2001 From: bitraid <bitraid@protonmail.ch> Date: Tue, 12 Feb 2019 19:02:29 +0200 Subject: [PATCH 155/362] [imgur] Use video id as title fallback (closes #18590) --- youtube_dl/extractor/imgur.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 0eb54db3f..a5ba03efa 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -27,6 +27,10 @@ class ImgurIE(InfoExtractor): }, { 'url': 'https://i.imgur.com/crGpqCV.mp4', 'only_matching': True, + }, { + # no title + 'url': 'https://i.imgur.com/jxBXAMC.gifv', + 'only_matching': True, }] def _real_extract(self, url): @@ -87,7 +91,7 @@ class ImgurIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'title': self._og_search_title(webpage), + 'title': self._og_search_title(webpage, default=video_id), } From 7bee705d8f110f09d8e72b1c863ff197ccc1d4f1 Mon Sep 17 00:00:00 2001 From: yonaikerlol <lawlietrs7@gmail.com> Date: Thu, 14 Feb 2019 11:28:16 -0400 Subject: [PATCH 156/362] [openload] Add support for oload.live --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index a2ae25272..c1dcbb7eb 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link|pw)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live) ) )/ (?:f|embed)/ @@ -346,6 +346,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.pw/f/WyKgK8s94N0', 'only_matching': True, + }, { + 'url': 'https://oload.live/f/-Z58UZ-GR4M', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 794c1b6e02591b04da931fa59745bc47bfae7492 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 14 Feb 2019 23:40:46 +0700 Subject: [PATCH 157/362] [vshare] Pass Referer to download request (closes #19205, closes #19221) --- youtube_dl/extractor/vshare.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vshare.py b/youtube_dl/extractor/vshare.py index e4ec77889..c631ac1fa 100644 --- a/youtube_dl/extractor/vshare.py +++ b/youtube_dl/extractor/vshare.py @@ -48,7 +48,7 @@ class VShareIE(InfoExtractor): webpage = self._download_webpage( 'https://vshare.io/v/%s/width-650/height-430/1' % video_id, - video_id) + video_id, headers={'Referer': url}) title = self._html_search_regex( r'<title>([^<]+)', webpage, 'title') From 2b2da3ba10cc325d00b665aae87f0fa8508bccdf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 15 Feb 2019 23:56:29 +0700 Subject: [PATCH 158/362] [rai] Relax _VALID_URL (closes #19232) --- youtube_dl/extractor/rai.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 548a6553b..149153b8f 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -288,7 +288,7 @@ class RaiPlayPlaylistIE(InfoExtractor): class RaiIE(RaiBaseIE): - _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE + _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE _TESTS = [{ # var uniquename = "ContentItem-..." # data-id="ContentItem-..." @@ -375,6 +375,9 @@ class RaiIE(RaiBaseIE): # Direct MMS URL 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', 'only_matching': True, + }, { + 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html', + 'only_matching': True, }] def _extract_from_content_id(self, content_id, url): From ba2e3730d125eab952eded3bb7749d479a2262d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 16 Feb 2019 22:45:53 +0700 Subject: [PATCH 159/362] [noovo] Fix extraction (closes #19230) --- youtube_dl/extractor/noovo.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/noovo.py b/youtube_dl/extractor/noovo.py index 974de3c3e..b40770d07 100644 --- a/youtube_dl/extractor/noovo.py +++ b/youtube_dl/extractor/noovo.py @@ -57,7 +57,8 @@ class NoovoIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - bc_url = BrightcoveNewIE._extract_url(self, webpage) + brightcove_id = self._search_regex( + r'data-video-id=["\'](\d+)', webpage, 'brightcove id') data = self._parse_json( self._search_regex( @@ -89,7 +90,10 @@ class NoovoIE(InfoExtractor): return { '_type': 'url_transparent', 'ie_key': BrightcoveNewIE.ie_key(), - 'url': smuggle_url(bc_url, {'geo_countries': ['CA']}), + 'url': smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['CA']}), + 'id': brightcove_id, 'title': title, 'description': description, 'series': series, From ae65c93a26f2b3cf806477a3ee891aa461b5c6b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 00:58:13 +0700 Subject: [PATCH 160/362] [udemy] Update User-Agent and detect captcha (closes #14713, closes #15839, closes #18126) --- youtube_dl/extractor/udemy.py | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 105826e9b..89a7f6ade 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -123,10 +123,22 @@ class UdemyIE(InfoExtractor): def _download_webpage_handle(self, *args, **kwargs): headers = kwargs.get('headers', {}).copy() - headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' + headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36' kwargs['headers'] = headers - return super(UdemyIE, self)._download_webpage_handle( + ret = super(UdemyIE, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) + if not ret: + return ret + webpage, _ = ret + if any(p in webpage for p in ( + '>Please verify you are a human', + 'Access to this page has been denied because we believe you are using automation tools to browse the website', + '"_pxCaptcha"')): + raise ExtractorError( + 'Udemy asks you to solve a CAPTCHA. Login with browser, ' + 'solve CAPTCHA, then export cookies and pass cookie file to ' + 'youtube-dl with --cookies.', expected=True) + return ret def _download_json(self, url_or_request, *args, **kwargs): headers = { From d7d513891b7e63337218c5cb0bf743c8f7044381 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 01:05:01 +0700 Subject: [PATCH 161/362] [udemy] Extend _VALID_URLs (closes #14330, closes #15883) --- youtube_dl/extractor/udemy.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 89a7f6ade..ae8de9897 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -29,7 +29,7 @@ class UdemyIE(InfoExtractor): IE_NAME = 'udemy' _VALID_URL = r'''(?x) https?:// - www\.udemy\.com/ + (?:[^/]+\.)?udemy\.com/ (?: [^#]+\#/lecture/| lecture/view/?\?lectureId=| @@ -64,6 +64,9 @@ class UdemyIE(InfoExtractor): # only outputs rendition 'url': 'https://www.udemy.com/how-you-can-help-your-local-community-5-amazing-examples/learn/v4/t/lecture/3225750?start=0', 'only_matching': True, + }, { + 'url': 'https://wipro.udemy.com/java-tutorial/#/lecture/172757', + 'only_matching': True, }] def _extract_course_info(self, webpage, video_id): @@ -415,8 +418,14 @@ class UdemyIE(InfoExtractor): class UdemyCourseIE(UdemyIE): IE_NAME = 'udemy:course' - _VALID_URL = r'https?://(?:www\.)?udemy\.com/(?P[^/?#&]+)' - _TESTS = [] + _VALID_URL = r'https?://(?:[^/]+\.)?udemy\.com/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.udemy.com/java-tutorial/', + 'only_matching': True, + }, { + 'url': 'https://wipro.udemy.com/java-tutorial/', + 'only_matching': True, + }] @classmethod def suitable(cls, url): From c9a0ea6e51eff28b9a383a47215870fd5875fc3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 05:00:16 +0700 Subject: [PATCH 162/362] [bilibili] Update keys (closes #19233) --- youtube_dl/extractor/bilibili.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 4d6b051fe..3746671d3 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -93,8 +93,8 @@ class BiliBiliIE(InfoExtractor): }] }] - _APP_KEY = '84956560bc028eb7' - _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e' + _APP_KEY = 'iVGUTjsxvpLeuDCf' + _BILIBILI_KEY = 'aHRmhWMLkdeMuILqORnYZocwMBpMEOdt' def _report_error(self, result): if 'message' in result: From 659e93fcf5c0480ac461cda412335cecf6a5595f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 07:12:10 +0700 Subject: [PATCH 163/362] [linuxacademy] Add extractor (closes #12207) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/linuxacademy.py | 174 +++++++++++++++++++++++++++ 2 files changed, 175 insertions(+) create mode 100644 youtube_dl/extractor/linuxacademy.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 3e1b63b4b..c70452dcd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -593,6 +593,7 @@ from .linkedin import ( LinkedInLearningIE, LinkedInLearningCourseIE, ) +from .linuxacademy import LinuxAcademyIE from .litv import LiTVIE from .liveleak import ( LiveLeakIE, diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py new file mode 100644 index 000000000..a78c6556e --- /dev/null +++ b/youtube_dl/extractor/linuxacademy.py @@ -0,0 +1,174 @@ +from __future__ import unicode_literals + +import json +import random +import re + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_HTTPError, + compat_str, +) +from ..utils import ( + ExtractorError, + orderedSet, + unescapeHTML, + urlencode_postdata, + urljoin, +) + + +class LinuxAcademyIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?linuxacademy\.com/cp/ + (?: + courses/lesson/course/(?P\d+)/lesson/(?P\d+)| + modules/view/id/(?P\d+) + ) + ''' + _TESTS = [{ + 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2/module/154', + 'info_dict': { + 'id': '1498-2', + 'ext': 'mp4', + 'title': "Introduction to the Practitioner's Brief", + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Requires Linux Academy account credentials', + }, { + 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2', + 'only_matching': True, + }, { + 'url': 'https://linuxacademy.com/cp/modules/view/id/154', + 'info_dict': { + 'id': '154', + 'title': 'AWS Certified Cloud Practitioner', + 'description': 'md5:039db7e60e4aac9cf43630e0a75fa834', + }, + 'playlist_count': 41, + 'skip': 'Requires Linux Academy account credentials', + }] + + _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize' + _ORIGIN_URL = 'https://linuxacademy.com' + _CLIENT_ID = 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx' + _NETRC_MACHINE = 'linuxacademy' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + def random_string(): + return ''.join([ + random.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~') + for _ in range(32)]) + + webpage, urlh = self._download_webpage_handle( + self._AUTHORIZE_URL, None, 'Downloading authorize page', query={ + 'client_id': self._CLIENT_ID, + 'response_type': 'token id_token', + 'redirect_uri': self._ORIGIN_URL, + 'scope': 'openid email user_impersonation profile', + 'audience': self._ORIGIN_URL, + 'state': random_string(), + 'nonce': random_string(), + }) + + login_data = self._parse_json( + self._search_regex( + r'atob\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'login info', group='value'), None, + transform_source=lambda x: compat_b64decode(x).decode('utf-8') + )['extraParams'] + + login_data.update({ + 'client_id': self._CLIENT_ID, + 'redirect_uri': self._ORIGIN_URL, + 'tenant': 'lacausers', + 'connection': 'Username-Password-Authentication', + 'username': username, + 'password': password, + 'sso': 'true', + }) + + login_state_url = compat_str(urlh.geturl()) + + try: + login_page = self._download_webpage( + 'https://login.linuxacademy.com/usernamepassword/login', None, + 'Downloading login page', data=json.dumps(login_data).encode(), + headers={ + 'Content-Type': 'application/json', + 'Origin': 'https://login.linuxacademy.com', + 'Referer': login_state_url, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + error = self._parse_json(e.cause.read(), None) + message = error.get('description') or error['code'] + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, message), expected=True) + raise + + callback_page, urlh = self._download_webpage_handle( + 'https://login.linuxacademy.com/login/callback', None, + 'Downloading callback page', + data=urlencode_postdata(self._hidden_inputs(login_page)), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Origin': 'https://login.linuxacademy.com', + 'Referer': login_state_url, + }) + + access_token = self._search_regex( + r'access_token=([^=&]+)', compat_str(urlh.geturl()), + 'access token') + + self._download_webpage( + 'https://linuxacademy.com/cp/login/tokenValidateLogin/token/%s' + % access_token, None, 'Downloading token validation page') + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + chapter_id, lecture_id, course_id = mobj.group('chapter_id', 'lesson_id', 'course_id') + item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id) + + webpage = self._download_webpage(url, item_id) + + # course path + if course_id: + entries = [ + self.url_result( + urljoin(url, lesson_url), ie=LinuxAcademyIE.ie_key()) + for lesson_url in orderedSet(re.findall( + r']+\bhref=["\'](/cp/courses/lesson/course/\d+/lesson/\d+/module/\d+)', + webpage))] + title = unescapeHTML(self._html_search_regex( + (r'class=["\']course-title["\'][^>]*>(?P[^<]+)', + r'var\s+title\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), + webpage, 'title', default=None, group='value')) + description = unescapeHTML(self._html_search_regex( + r'var\s+description\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'description', default=None, group='value')) + return self.playlist_result(entries, course_id, title, description) + + # single video path + info = self._extract_jwplayer_data( + webpage, item_id, require_title=False, m3u8_id='hls',) + title = self._search_regex( + (r'>Lecture\s*:\s*(?P[^<]+)', + r'lessonName\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), webpage, + 'title', group='value') + info.update({ + 'id': item_id, + 'title': title, + }) + return info From 3c9647372e78134777d201e157a5ef42345c9da2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 13:38:21 +0700 Subject: [PATCH 164/362] [tvp] Fix description extraction, make thumbnail optional and fix tests --- youtube_dl/extractor/tvp.py | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 3954f0b93..f9bf600b0 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -19,12 +19,12 @@ class TVPIE(InfoExtractor): _TESTS = [{ 'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536', - 'md5': '8aa518c15e5cc32dfe8db400dc921fbb', + 'md5': 'a21eb0aa862f25414430f15fdfb9e76c', 'info_dict': { 'id': '194536', 'ext': 'mp4', - 'title': 'Czas honoru, I seria – odc. 13', - 'description': 'md5:381afa5bca72655fe94b05cfe82bf53d', + 'title': 'Czas honoru, odc. 13 – Władek', + 'description': 'md5:437f48b93558370b031740546b696e24', }, }, { 'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176', @@ -45,6 +45,7 @@ class TVPIE(InfoExtractor): 'title': 'Wiadomości, 28.09.2017, 19:30', 'description': 'Wydanie główne codziennego serwisu informacyjnego.' }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272', 'only_matching': True, @@ -75,8 +76,10 @@ class TVPIE(InfoExtractor): return { '_type': 'url_transparent', 'url': 'tvp:' + video_id, - 'description': self._og_search_description(webpage, default=None), - 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'description', webpage, default=None), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), 'ie_key': 'TVPEmbed', } @@ -87,6 +90,14 @@ class TVPEmbedIE(InfoExtractor): _VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P\d+)' _TESTS = [{ + 'url': 'tvp:194536', + 'md5': 'a21eb0aa862f25414430f15fdfb9e76c', + 'info_dict': { + 'id': '194536', + 'ext': 'mp4', + 'title': 'Czas honoru, odc. 13 – Władek', + }, + }, { 'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268', 'md5': '8c9cd59d16edabf39331f93bf8a766c7', 'info_dict': { From 34568dc2967d227630ed9d7150deaa62a689b937 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 13:39:00 +0700 Subject: [PATCH 165/362] [tvp] Detect unavailable videos --- youtube_dl/extractor/tvp.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index f9bf600b0..536b580fc 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -98,6 +98,7 @@ class TVPEmbedIE(InfoExtractor): 'title': 'Czas honoru, odc. 13 – Władek', }, }, { + # not available 'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268', 'md5': '8c9cd59d16edabf39331f93bf8a766c7', 'info_dict': { @@ -105,6 +106,7 @@ class TVPEmbedIE(InfoExtractor): 'ext': 'mp4', 'title': 'Panorama, 07.12.2015, 15:40', }, + 'skip': 'Transmisja została zakończona lub materiał niedostępny', }, { 'url': 'tvp:22670268', 'only_matching': True, @@ -116,10 +118,13 @@ class TVPEmbedIE(InfoExtractor): webpage = self._download_webpage( 'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id) - error_massage = get_element_by_attribute('class', 'msg error', webpage) - if error_massage: + error = self._html_search_regex( + r'(?s)]+\bclass=["\']notAvailable__text["\'][^>]*>(.+?)

', + webpage, 'error', default=None) or clean_html( + get_element_by_attribute('class', 'msg error', webpage)) + if error: raise ExtractorError('%s said: %s' % ( - self.IE_NAME, clean_html(error_massage)), expected=True) + self.IE_NAME, clean_html(error)), expected=True) title = self._search_regex( r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P.+?)\1', From d93083789bf9c318b18d52ac132e9495345b9ebc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 17 Feb 2019 14:09:30 +0700 Subject: [PATCH 166/362] [tvp:series] Fix extraction --- youtube_dl/extractor/tvp.py | 67 ++++++++++++++++--------------------- 1 file changed, 29 insertions(+), 38 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 536b580fc..05669a366 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,14 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor from ..utils import ( - determine_ext, clean_html, - get_element_by_attribute, + determine_ext, ExtractorError, + get_element_by_attribute, + orderedSet, ) @@ -198,46 +200,35 @@ class TVPEmbedIE(InfoExtractor): class TVPSeriesIE(InfoExtractor): IE_NAME = 'tvp:series' - _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$' + _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)/video' _TESTS = [{ - 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', + 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video', 'info_dict': { - 'title': 'Ogniem i mieczem', - 'id': '4278026', + 'id': '38678312', }, - 'playlist_count': 4, - }, { - 'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat', - 'info_dict': { - 'title': 'Boso przez świat', - 'id': '9329207', - }, - 'playlist_count': 86, + 'playlist_count': 115, }] + def _entries(self, url, display_id): + for page_num in itertools.count(1): + page = self._download_webpage( + url, display_id, 'Downloading page %d' % page_num, + query={'page': page_num}) + + video_ids = orderedSet(re.findall( + r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id, + page)) + + if not video_ids: + break + + for video_id in video_ids: + yield self.url_result( + 'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(), + video_id=video_id) + def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id, tries=5) - - title = self._html_search_regex( - r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series') - playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') - playlist = self._download_webpage( - 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' - 'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5, - note='Downloading playlist') - - videos_paths = re.findall( - '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist) - entries = [ - self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key()) - for v_path in videos_paths] - - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': display_id, - 'title': title, - 'entries': entries, - } + mobj = re.match(self._VALID_URL, url) + display_id, playlist_id = mobj.group('display_id', 'id') + return self.playlist_result(self._entries(url, display_id), playlist_id) From 388cfbd3d8915ebb99714ac8e7ce4151edf96d8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 17 Feb 2019 14:27:00 +0700 Subject: [PATCH 167/362] [tvp:website] Improve support --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/tvp.py | 26 ++++++++++++++++++++++---- 2 files changed, 23 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c70452dcd..923dfe7f4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1218,7 +1218,7 @@ from .tvnow import ( from .tvp import ( TVPEmbedIE, TVPIE, - TVPSeriesIE, + TVPWebsiteIE, ) from .tvplay import ( TVPlayIE, diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 05669a366..accff75b5 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -198,19 +198,36 @@ class TVPEmbedIE(InfoExtractor): } -class TVPSeriesIE(InfoExtractor): +class TVPWebsiteIE(InfoExtractor): IE_NAME = 'tvp:series' - _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)/video' + _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)' _TESTS = [{ + # series 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video', 'info_dict': { 'id': '38678312', }, 'playlist_count': 115, + }, { + # film + 'url': 'https://vod.tvp.pl/website/gloria,35139666', + 'info_dict': { + 'id': '36637049', + 'ext': 'mp4', + 'title': 'Gloria, Gloria', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['TVPEmbed'], + }, { + 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312', + 'only_matching': True, }] - def _entries(self, url, display_id): + def _entries(self, display_id, playlist_id): + url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id) for page_num in itertools.count(1): page = self._download_webpage( url, display_id, 'Downloading page %d' % page_num, @@ -231,4 +248,5 @@ class TVPSeriesIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id, playlist_id = mobj.group('display_id', 'id') - return self.playlist_result(self._entries(url, display_id), playlist_id) + return self.playlist_result( + self._entries(display_id, playlist_id), playlist_id) From c76fc5b22a70f9ac24fe7e34c37aa8ef82e85c49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Feb 2019 02:10:06 +0700 Subject: [PATCH 168/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/ChangeLog b/ChangeLog index 398528f76..adbdf166d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,28 @@ +version <unreleased> + +Extractors +* [tvp:website] Fix and improve extraction ++ [tvp] Detect unavailable videos +* [tvp] Fix description extraction and make thumbnail optional ++ [linuxacademy] Add support for linuxacademy.com (#12207) +* [bilibili] Update keys (#19233) +* [udemy] Extend URL regular expressions (#14330, #15883) +* [udemy] Update User-Agent and detect captcha (#14713, #15839, #18126) +* [noovo] Fix extraction (#19230) +* [rai] Relax URL regular expression (#19232) ++ [vshare] Pass Referer to download request (#19205, #19221) ++ [openload] Add support for oload.live (#19222) +* [imgur] Use video id as title fallback (#18590) ++ [twitch] Add new source format detection approach (#19193) +* [tvplayhome] Fix video id extraction (#19190) +* [tvplayhome] Fix episode metadata extraction (#19190) +* [rutube:embed] Fix extraction (#19163) ++ [rutube:embed] Add support private videos (#19163) ++ [soundcloud] Extract more metadata ++ [trunews] Add support for trunews.com (#19153) ++ [linkedin:learning] Extract chapter_number and chapter_id (#19162) + + version 2019.02.08 Core From 77a842c8926625fe791ed36613f183bb195394cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Feb 2019 02:11:11 +0700 Subject: [PATCH 169/362] release 2019.02.18 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 7128d998f..ff626883d 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.08*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.08** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.18** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.02.08 +[debug] youtube-dl version 2019.02.18 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index adbdf166d..f9dd7928f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.02.18 Extractors * [tvp:website] Fix and improve extraction diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 32fe6b647..d8a8d7ede 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -458,6 +458,7 @@ - **LineTV** - **linkedin:learning** - **linkedin:learning:course** + - **LinuxAcademy** - **LiTV** - **LiveLeak** - **LiveLeakEmbed** @@ -915,6 +916,7 @@ - **ToypicsUser**: Toypics user profile - **TrailerAddict** (Currently broken) - **Trilulilu** + - **TruNews** - **TruTV** - **Tube8** - **TubiTv** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 4dc5a611e..ea1d5a4a5 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.02.08' +__version__ = '2019.02.18' From caf48f557a8f4f904c88346bcfc462069b8745bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 21 Feb 2019 05:59:07 +0700 Subject: [PATCH 170/362] [metacafe] Fix family filter bypass (closes #19287) --- youtube_dl/extractor/metacafe.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 28f59f63c..9e92416d1 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -1,12 +1,13 @@ from __future__ import unicode_literals +import json import re from .common import InfoExtractor from ..compat import ( compat_parse_qs, + compat_urllib_parse, compat_urllib_parse_unquote, - compat_urllib_parse_urlencode, ) from ..utils import ( determine_ext, @@ -144,7 +145,7 @@ class MetacafeIE(InfoExtractor): headers = { # Disable family filter - 'Cookie': 'user=%s; ' % compat_urllib_parse_urlencode({'ffilter': False}) + 'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False})) } # AnyClip videos require the flashversion cookie so that we get the link From 37b239b3b66ea9e2a71bae41e9da6dba8ee5554c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 23 Feb 2019 00:43:29 +0700 Subject: [PATCH 171/362] [downloader/external] Fix infinite retries for curl (closes #19303) --- youtube_dl/downloader/external.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 958d00aac..0b88bfd94 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -121,7 +121,11 @@ class CurlFD(ExternalFD): cmd += self._valueless_option('--silent', 'noprogress') cmd += self._valueless_option('--verbose', 'verbose') cmd += self._option('--limit-rate', 'ratelimit') - cmd += self._option('--retry', 'retries') + retry = self._option('--retry', 'retries') + if len(retry) == 2: + if retry[1] in ('inf', 'infinite'): + retry[1] = '2147483647' + cmd += retry cmd += self._option('--max-filesize', 'max_filesize') cmd += self._option('--interface', 'source_address') cmd += self._option('--proxy', 'proxy') From 8c80603f1adea843d96c0598b902106c7a3efb7f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 23 Feb 2019 00:58:56 +0700 Subject: [PATCH 172/362] [downloader/external] Add support for rate limit and retries for wget --- youtube_dl/downloader/external.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 0b88bfd94..22e6093b3 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -164,6 +164,12 @@ class WgetFD(ExternalFD): cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies'] for key, val in info_dict['http_headers'].items(): cmd += ['--header', '%s: %s' % (key, val)] + cmd += self._option('--limit-rate', 'ratelimit') + retry = self._option('--tries', 'retries') + if len(retry) == 2: + if retry[1] in ('inf', 'infinite'): + retry[1] = '0' + cmd += retry cmd += self._option('--bind-address', 'source_address') cmd += self._option('--proxy', 'proxy') cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate') From f0228f56fb2441510aa966ba9298e388b209cde1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 24 Feb 2019 21:01:25 +0700 Subject: [PATCH 173/362] [bbccouk] Make subtitles non fatal (#19651) --- youtube_dl/extractor/bbc.py | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index eac9a5a46..13340ec64 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -1,8 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re import itertools +import re +import xml from .common import InfoExtractor from ..utils import ( @@ -17,6 +18,7 @@ from ..utils import ( parse_iso8601, try_get, unescapeHTML, + url_or_none, urlencode_postdata, urljoin, ) @@ -310,7 +312,13 @@ class BBCCoUkIE(InfoExtractor): def _get_subtitles(self, media, programme_id): subtitles = {} for connection in self._extract_connections(media): - captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') + cc_url = url_or_none(connection.get('href')) + if not cc_url: + continue + captions = self._download_xml( + cc_url, programme_id, 'Downloading captions', fatal=False) + if not isinstance(captions, xml.etree.ElementTree.Element): + continue lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') subtitles[lang] = [ { From 55b8588f0e4dd9597b6da5c46d05b9dd1e9f5960 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 24 Feb 2019 23:19:15 +0700 Subject: [PATCH 174/362] [servus] Fix extraction (closes #19297) --- youtube_dl/extractor/servus.py | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/servus.py b/youtube_dl/extractor/servus.py index 264e1dd8b..e579d42cf 100644 --- a/youtube_dl/extractor/servus.py +++ b/youtube_dl/extractor/servus.py @@ -1,31 +1,44 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor class ServusIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:at|de)/p/[^/]+/(?P<id>AA-\w+|\d+-\d+)' + _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)' _TESTS = [{ 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', - 'md5': '046dee641cda1c4cabe13baef3be2c1c', + 'md5': '3e1dd16775aa8d5cbef23628cfffc1f4', 'info_dict': { 'id': 'AA-1T6VBU5PW1W12', 'ext': 'mp4', - 'title': 'Die Grünen aus Volkssicht', - 'description': 'md5:052b5da1cb2cd7d562ef1f19be5a5cba', - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': 'Die Grünen aus Sicht des Volkes', + 'description': 'md5:1247204d85783afe3682644398ff2ec4', + 'thumbnail': r're:^https?://.*\.jpg', } }, { 'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/', 'only_matching': True, + }, { + 'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/', + 'only_matching': True, + }, { + 'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) + video_id = self._match_id(url).upper() webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage) + title = self._search_regex( + (r'videoLabel\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', + r'<h\d+[^>]+\bclass=["\']heading--(?:one|two)["\'][^>]*>(?P<title>[^<]+)'), + webpage, 'title', default=None, + group='title') or self._og_search_title(webpage) + title = re.sub(r'\s*-\s*Servus TV\s*$', '', title) description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) From db1c3a9d3f202cc6f3fd83a2a918869e7c0d147f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 27 Feb 2019 03:41:15 +0700 Subject: [PATCH 175/362] [periscope] Extract width and height (closes #20015) --- youtube_dl/extractor/periscope.py | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py index 8afe541ec..b337a56c0 100644 --- a/youtube_dl/extractor/periscope.py +++ b/youtube_dl/extractor/periscope.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, parse_iso8601, unescapeHTML, ) @@ -75,6 +76,14 @@ class PeriscopeIE(PeriscopeBaseIE): 'url': broadcast[image], } for image in ('image_url', 'image_url_small') if broadcast.get(image)] + width = int_or_none(broadcast.get('width')) + height = int_or_none(broadcast.get('height')) + + def add_width_and_height(f): + for key, val in (('width', width), ('height', height)): + if not f.get(key): + f[key] = val + video_urls = set() formats = [] for format_id in ('replay', 'rtmp', 'hls', 'https_hls', 'lhls', 'lhlsweb'): @@ -83,16 +92,21 @@ class PeriscopeIE(PeriscopeBaseIE): continue video_urls.add(video_url) if format_id != 'rtmp': - formats.extend(self._extract_m3u8_formats( + m3u8_formats = self._extract_m3u8_formats( video_url, token, 'mp4', entry_protocol='m3u8_native' if state in ('ended', 'timed_out') else 'm3u8', - m3u8_id=format_id, fatal=False)) + m3u8_id=format_id, fatal=False) + if len(m3u8_formats) == 1: + add_width_and_height(m3u8_formats[0]) + formats.extend(m3u8_formats) continue - formats.append({ + rtmp_format = { 'url': video_url, 'ext': 'flv' if format_id == 'rtmp' else 'mp4', - }) + } + add_width_and_height(rtmp_format) + formats.append(rtmp_format) self._sort_formats(formats) return { From 9d9a8676dc02101069cf5fa9862500d39352538c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 28 Feb 2019 23:26:52 +0700 Subject: [PATCH 176/362] [francetv:site] Extend video id regex (closes #20029, closes #20071) --- youtube_dl/extractor/francetv.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 2ffe83a78..3c4ef08a8 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -271,7 +271,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor): catalogue = None video_id = self._search_regex( - r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1', + r'(?:data-main-video\s*=|videoId\s*:)\s*(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', default=None, group='id') if not video_id: From ff60ec8f029d12c119855ec82d7ce9ecda388651 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 1 Mar 2019 00:47:18 +0700 Subject: [PATCH 177/362] [npo] Fix extraction (#20084) --- youtube_dl/extractor/npo.py | 120 +++++++++++++++++++++++++++++++++++- 1 file changed, 117 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 5a427c396..857845d35 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -12,11 +12,16 @@ from ..utils import ( ExtractorError, fix_xml_ampersands, int_or_none, + merge_dicts, orderedSet, parse_duration, qualities, + str_or_none, strip_jsonp, unified_strdate, + unified_timestamp, + url_or_none, + urlencode_postdata, ) @@ -176,9 +181,118 @@ class NPOIE(NPOBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - return self._get_info(video_id) + try: + return self._get_info(url, video_id) + except ExtractorError: + return self._get_old_info(video_id) - def _get_info(self, video_id): + def _get_info(self, url, video_id): + token = self._download_json( + 'https://www.npostart.nl/api/token', video_id, + 'Downloading token', headers={ + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest', + })['token'] + + player = self._download_json( + 'https://www.npostart.nl/player/%s' % video_id, video_id, + 'Downloading player JSON', data=urlencode_postdata({ + 'autoplay': 0, + 'share': 1, + 'pageUrl': url, + 'hasAdConsent': 0, + '_token': token, + })) + + player_token = player['token'] + + format_urls = set() + formats = [] + for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'): + streams = self._download_json( + 'https://start-player.npo.nl/video/%s/streams' % video_id, + video_id, 'Downloading %s profile JSON' % profile, fatal=False, + query={ + 'profile': profile, + 'quality': 'npo', + 'tokenId': player_token, + 'streamType': 'broadcast', + }) + if not streams: + continue + stream = streams.get('stream') + if not isinstance(stream, dict): + continue + stream_url = url_or_none(stream.get('src')) + if not stream_url or stream_url in format_urls: + continue + format_urls.add(stream_url) + if stream.get('protection') is not None: + continue + stream_type = stream.get('type') + stream_ext = determine_ext(stream_url) + if stream_type == 'application/dash+xml' or stream_ext == 'mpd': + formats.extend(self._extract_mpd_formats( + stream_url, video_id, mpd_id='dash', fatal=False)) + elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + elif '.ism/Manifest' in stream_url: + formats.extend(self._extract_ism_formats( + stream_url, video_id, ism_id='mss', fatal=False)) + else: + formats.append({ + 'url': stream_url, + }) + + self._sort_formats(formats) + + info = { + 'id': video_id, + 'title': video_id, + 'formats': formats, + } + + embed_url = url_or_none(player.get('embedUrl')) + if embed_url: + webpage = self._download_webpage( + embed_url, video_id, 'Downloading embed page', fatal=False) + if webpage: + video = self._parse_json( + self._search_regex( + r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video', + default='{}'), video_id) + if video: + title = video.get('episodeTitle') + subtitles = {} + subtitles_list = video.get('subtitles') + if isinstance(subtitles_list, list): + for cc in subtitles_list: + cc_url = url_or_none(cc.get('src')) + if not cc_url: + continue + lang = str_or_none(cc.get('language')) or 'nl' + subtitles.setdefault(lang, []).append({ + 'url': cc_url, + }) + return merge_dicts({ + 'title': title, + 'description': video.get('description'), + 'thumbnail': url_or_none( + video.get('still_image_url') or video.get('orig_image_url')), + 'duration': int_or_none(video.get('duration')), + 'timestamp': unified_timestamp(video.get('broadcastDate')), + 'creator': video.get('channel'), + 'series': video.get('title'), + 'episode': title, + 'episode_number': int_or_none(video.get('episodeNumber')), + 'subtitles': subtitles, + }, info) + + return info + + def _get_old_info(self, video_id): metadata = self._download_json( 'http://e.omroep.nl/metadata/%s' % video_id, video_id, @@ -280,7 +394,7 @@ class NPOIE(NPOBaseIE): # JSON else: video_url = stream_info.get('url') - if not video_url or video_url in urls: + if not video_url or 'vodnotavailable.' in video_url or video_url in urls: continue urls.add(video_url) if determine_ext(video_url) == 'm3u8': From 333f617b1207cb53efaa5e2f7af174cfa87deee1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 1 Mar 2019 01:02:36 +0700 Subject: [PATCH 178/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/ChangeLog b/ChangeLog index f9dd7928f..f717f99a8 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,18 @@ +version <unreleased> + +Core ++ [downloader/external] Add support for rate limit and retries for wget +* [downloader/external] Fix infinite retries for curl (#19303) + +Extractors +* [npo] Fix extraction (#20084) +* [francetv:site] Extend video id regex (#20029, #20071) ++ [periscope] Extract width and height (#20015) +* [servus] Fix extraction (#19297) +* [bbccouk] Make subtitles non fatal (#19651) +* [metacafe] Fix family filter bypass (#19287) + + version 2019.02.18 Extractors From 04c33bdfb3cd73e71bf0788f02998cab30cf1da2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 1 Mar 2019 01:03:51 +0700 Subject: [PATCH 179/362] release 2019.03.01 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index ff626883d..71a500f04 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.18** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.01*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.01** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.02.18 +[debug] youtube-dl version 2019.03.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index f717f99a8..018a30641 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.03.01 Core + [downloader/external] Add support for rate limit and retries for wget diff --git a/youtube_dl/version.py b/youtube_dl/version.py index ea1d5a4a5..42ba37f15 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.02.18' +__version__ = '2019.03.01' From 06242d44fe261999e2424d9ecb00f20ff30ccb9b Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 1 Mar 2019 08:14:34 +0100 Subject: [PATCH 180/362] [vimeo] add support for Vimeo Pro portfolio protected videos(closes #20070) --- youtube_dl/extractor/vimeo.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 6215b3258..6f32ea6f1 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -502,7 +502,11 @@ class VimeoIE(VimeoBaseInfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') orig_url = url - if mobj.group('pro') or mobj.group('player'): + if mobj.group('pro'): + # some videos require portfolio_id to be present in player url + # https://github.com/rg3/youtube-dl/issues/20070 + url = self._extract_url(url, self._download_webpage(url, video_id)) + elif mobj.group('player'): url = 'https://player.vimeo.com/video/' + video_id elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): url = 'https://vimeo.com/' + video_id From c5b02efe20cff1612104fd731c7f02cbbce4f5f3 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 1 Mar 2019 15:08:11 +0100 Subject: [PATCH 181/362] [sixplay] handle videos with empty assets(closes #20016) --- youtube_dl/extractor/sixplay.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index 0c4f865ef..35bc9fa50 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -61,7 +61,8 @@ class SixPlayIE(InfoExtractor): quality_key = qualities(['lq', 'sd', 'hq', 'hd']) formats = [] subtitles = {} - for asset in clip_data['assets']: + assets = clip_data.get('assets') or [] + for asset in assets: asset_url = asset.get('full_physical_path') protocol = asset.get('protocol') if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls: From 398e1e21d6cbf6eb1e8e7e84de4fad30b7d59613 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 1 Mar 2019 15:34:05 +0100 Subject: [PATCH 182/362] [espn] extend _VALID_URL regex(closes #20013) --- youtube_dl/extractor/espn.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 127c69b2e..8cc9bd165 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -29,7 +29,8 @@ class ESPNIE(OnceIE): (?: .*?\?.*?\bid=| /_/id/ - ) + )| + [^/]+/video/ ) )| (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/ @@ -94,6 +95,9 @@ class ESPNIE(OnceIE): }, { 'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets', 'only_matching': True, + }, { + 'url': 'http://www.espn.com/espnw/video/26066627/arkansas-gibson-completes-hr-cycle-four-innings', + 'only_matching': True, }] def _real_extract(self, url): From dca0e0040ae97b2fc0cd54d5e819a5a278937350 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 2 Mar 2019 08:01:42 +0100 Subject: [PATCH 183/362] Revert "use older login method(closes #11572)" This reverts commit cc6a960e134614f8af2a42dcd8bf146d63638a3c. --- youtube_dl/extractor/crunchyroll.py | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 5e2cbe41d..ce2e2d3ba 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -56,17 +56,6 @@ class CrunchyrollBaseIE(InfoExtractor): if username is None: return - self._download_webpage( - 'https://www.crunchyroll.com/?a=formhandler', - None, 'Logging in', 'Wrong login info', - data=urlencode_postdata({ - 'formname': 'RpcApiUser_Login', - 'next_url': 'https://www.crunchyroll.com/acct/membership', - 'name': username, - 'password': password, - })) - - ''' login_page = self._download_webpage( self._LOGIN_URL, None, 'Downloading login page') @@ -110,7 +99,6 @@ class CrunchyrollBaseIE(InfoExtractor): raise ExtractorError('Unable to login: %s' % error, expected=True) raise ExtractorError('Unable to log in') - ''' def _real_initialize(self): self._login() From a8f83f0c56e81b871a46c18fa9ebc6643370fa48 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 2 Mar 2019 08:25:47 +0100 Subject: [PATCH 184/362] [crunchyroll] fix is_logged check --- youtube_dl/extractor/crunchyroll.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index ce2e2d3ba..fd1e7afad 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -60,7 +60,7 @@ class CrunchyrollBaseIE(InfoExtractor): self._LOGIN_URL, None, 'Downloading login page') def is_logged(webpage): - return '<title>Redirecting' in webpage + return 'href="/logout"' in webpage # Already logged in if is_logged(login_page): From 7465e0aee2301c3e86fe38d6e0ef5ad01c16ec79 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 3 Mar 2019 06:25:45 +0700 Subject: [PATCH 185/362] [spankbang] Fix extraction (closes #20023) --- youtube_dl/extractor/spankbang.py | 45 +++++++++++++++++++++++++++---- 1 file changed, 40 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index fbe6ef31a..f11d728ca 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -9,6 +9,8 @@ from ..utils import ( parse_duration, parse_resolution, str_to_int, + url_or_none, + urlencode_postdata, ) @@ -64,16 +66,49 @@ class SpankBangIE(InfoExtractor): 'Video %s is not available' % video_id, expected=True) formats = [] - for mobj in re.finditer( - r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2', - webpage): - format_id, format_url = mobj.group('id', 'url') + + def extract_format(format_id, format_url): + f_url = url_or_none(format_url) + if not f_url: + return f = parse_resolution(format_id) f.update({ - 'url': format_url, + 'url': f_url, 'format_id': format_id, }) formats.append(f) + + STREAM_URL_PREFIX = 'stream_url_' + + for mobj in re.finditer( + r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2' + % STREAM_URL_PREFIX, webpage): + extract_format(mobj.group('id', 'url')) + + if not formats: + stream_key = self._search_regex( + r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', + webpage, 'stream key', group='value') + + sb_csrf_session = self._get_cookies( + 'https://spankbang.com')['sb_csrf_session'].value + + stream = self._download_json( + 'https://spankbang.com/api/videos/stream', video_id, + 'Downloading stream JSON', data=urlencode_postdata({ + 'id': stream_key, + 'data': 0, + 'sb_csrf_session': sb_csrf_session, + }), headers={ + 'Referer': url, + 'X-CSRFToken': sb_csrf_session, + }) + + for format_id, format_url in stream.items(): + if format_id.startswith(STREAM_URL_PREFIX): + extract_format( + format_id[len(STREAM_URL_PREFIX):], format_url) + self._sort_formats(formats) title = self._html_search_regex( From 7aeb788e564d397face83b580362189753edd9dd Mon Sep 17 00:00:00 2001 From: cclauss <cclauss@me.com> Date: Sun, 3 Mar 2019 02:16:48 +0100 Subject: [PATCH 186/362] [travis] Remove sudo: false Travis now recommends removing `sudo: false` from configuration: https://blog.travis-ci.com/2018-11-19-required-linux-infrastructure-migration. --- .travis.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.travis.yml b/.travis.yml index 79287ccf6..82e81d078 100644 --- a/.travis.yml +++ b/.travis.yml @@ -9,7 +9,6 @@ python: - "3.6" - "pypy" - "pypy3" -sudo: false env: - YTDL_TEST_SET=core - YTDL_TEST_SET=download From 8ae113ca9df0abd790e3391cd529bac42fce304f Mon Sep 17 00:00:00 2001 From: dimqua <dimqua@users.noreply.github.com> Date: Sun, 3 Mar 2019 04:19:36 +0300 Subject: [PATCH 187/362] [youtube] Add more invidious instances See [Invidious-Instances](https://github.com/omarroth/invidious/wiki/Invidious-Instances) for the reference. --- youtube_dl/extractor/youtube.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index c8bf98b58..457e2acea 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -352,6 +352,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?yourepeat\.com/| tube\.majestyc\.net/| (?:www\.)?invidio\.us/| + (?:www\.)?invidious\.snopyta\.org/| + (?:www\.)?invidious\.kabi\.tk/| + (?:www\.)?vid\.wxzm\.sx/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: From 0a5baf9c210df9f492ae48dd8fdae90561c971bd Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 3 Mar 2019 06:18:15 +0100 Subject: [PATCH 188/362] [libsyn] improve extraction(closes #20229) --- youtube_dl/extractor/libsyn.py | 64 +++++++++++++++++++--------------- 1 file changed, 35 insertions(+), 29 deletions(-) diff --git a/youtube_dl/extractor/libsyn.py b/youtube_dl/extractor/libsyn.py index f7311f483..2cf444258 100644 --- a/youtube_dl/extractor/libsyn.py +++ b/youtube_dl/extractor/libsyn.py @@ -1,12 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( + clean_html, + get_element_by_class, parse_duration, + strip_or_none, unified_strdate, ) @@ -21,7 +23,9 @@ class LibsynIE(InfoExtractor): 'id': '6385796', 'ext': 'mp3', 'title': "Champion Minded - Developing a Growth Mindset", - 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.', + # description fetched using another request: + # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796 + # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.', 'upload_date': '20180320', 'thumbnail': 're:^https?://.*', }, @@ -38,22 +42,36 @@ class LibsynIE(InfoExtractor): }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') - url = m.group('mainurl') + url, video_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, video_id) - podcast_title = self._search_regex( - r'<h3>([^<]+)</h3>', webpage, 'podcast title', default=None) - if podcast_title: - podcast_title = podcast_title.strip() - episode_title = self._search_regex( - r'(?:<div class="episode-title">|<h4>)([^<]+)</', webpage, 'episode title') - if episode_title: - episode_title = episode_title.strip() + data = self._parse_json(self._search_regex( + r'var\s+playlistItem\s*=\s*({.+?});', + webpage, 'JSON data block'), video_id) + + episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage) + if not episode_title: + self._search_regex( + [r'data-title="([^"]+)"', r'<title>(.+?)'], + webpage, 'episode title') + episode_title = episode_title.strip() + + podcast_title = strip_or_none(clean_html(self._search_regex( + r'

([^<]+)

', webpage, 'podcast title', + default=None) or get_element_by_class('podcast-title', webpage))) title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title + formats = [] + for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')): + f_url = data.get(k) + if not f_url: + continue + formats.append({ + 'url': f_url, + 'format_id': format_id, + }) + description = self._html_search_regex( r'(.+?)

', webpage, 'description', default=None) @@ -61,27 +79,15 @@ class LibsynIE(InfoExtractor): # Strip non-breaking and normal spaces description = description.replace('\u00A0', ' ').strip() release_date = unified_strdate(self._search_regex( - r'
Released: ([^<]+)<', webpage, 'release date', fatal=False)) - - data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block') - data = json.loads(data_json) - - formats = [{ - 'url': data['media_url'], - 'format_id': 'main', - }, { - 'url': data['media_url_libsyn'], - 'format_id': 'libsyn', - }] - thumbnail = data.get('thumbnail_url') - duration = parse_duration(data.get('duration')) + r'
Released: ([^<]+)<', + webpage, 'release date', default=None) or data.get('release_date')) return { 'id': video_id, 'title': title, 'description': description, - 'thumbnail': thumbnail, + 'thumbnail': data.get('thumbnail_url'), 'upload_date': release_date, - 'duration': duration, + 'duration': parse_duration(data.get('duration')), 'formats': formats, } From e7e62441cdde6dca6211c073be73677f195a0dff Mon Sep 17 00:00:00 2001 From: remitamine Date: Sun, 3 Mar 2019 13:23:59 +0100 Subject: [PATCH 189/362] [utils] strip #HttpOnly_ prefix from cookies files (#20219) --- test/test_YoutubeDLCookieJar.py | 10 ++++++++++ test/testdata/cookies/httponly_cookies.txt | 6 ++++++ youtube_dl/utils.py | 18 +++++++++++++++++- 3 files changed, 33 insertions(+), 1 deletion(-) create mode 100644 test/testdata/cookies/httponly_cookies.txt diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py index 6a8243590..f959798de 100644 --- a/test/test_YoutubeDLCookieJar.py +++ b/test/test_YoutubeDLCookieJar.py @@ -29,6 +29,16 @@ class TestYoutubeDLCookieJar(unittest.TestCase): tf.close() os.remove(tf.name) + def test_strip_httponly_prefix(self): + cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt') + cookiejar.load(ignore_discard=True, ignore_expires=True) + + def assert_cookie_has_value(key): + self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE') + + assert_cookie_has_value('HTTPONLY_COOKIE') + assert_cookie_has_value('JS_ACCESSIBLE_COOKIE') + if __name__ == '__main__': unittest.main() diff --git a/test/testdata/cookies/httponly_cookies.txt b/test/testdata/cookies/httponly_cookies.txt new file mode 100644 index 000000000..c46541d6b --- /dev/null +++ b/test/testdata/cookies/httponly_cookies.txt @@ -0,0 +1,6 @@ +# Netscape HTTP Cookie File +# http://curl.haxx.se/rfc/cookie_spec.html +# This is a generated file! Do not edit. + +#HttpOnly_www.foobar.foobar FALSE / TRUE 2147483647 HTTPONLY_COOKIE HTTPONLY_COOKIE_VALUE +www.foobar.foobar FALSE / TRUE 2147483647 JS_ACCESSIBLE_COOKIE JS_ACCESSIBLE_COOKIE_VALUE diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index f5a0bb4b0..a71eda85d 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1141,6 +1141,8 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + _HTTPONLY_PREFIX = '#HttpOnly_' + def save(self, filename=None, ignore_discard=False, ignore_expires=False): # Store session cookies with `expires` set to 0 instead of an empty # string @@ -1150,7 +1152,21 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires) def load(self, filename=None, ignore_discard=False, ignore_expires=False): - compat_cookiejar.MozillaCookieJar.load(self, filename, ignore_discard, ignore_expires) + """Load cookies from a file.""" + if filename is None: + if self.filename is not None: + filename = self.filename + else: + raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT) + + cf = io.StringIO() + with open(filename) as f: + for line in f: + if line.startswith(self._HTTPONLY_PREFIX): + line = line[len(self._HTTPONLY_PREFIX):] + cf.write(compat_str(line)) + cf.seek(0) + self._really_load(cf, filename, ignore_discard, ignore_expires) # Session cookies are denoted by either `expires` field set to # an empty string or 0. MozillaCookieJar only recognizes the former # (see [1]). So we need force the latter to be recognized as session From 39c780fdec2c62135f37e3565efedf7dcad605ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Mar 2019 00:37:39 +0700 Subject: [PATCH 190/362] [extractor/common] Return MPD manifest as format's url meta field (#20242) For symmetry with other segmented media --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index c3b0586a0..1fa8048b8 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2120,7 +2120,7 @@ class InfoExtractor(object): bandwidth = int_or_none(representation_attrib.get('bandwidth')) f = { 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, - 'url': base_url, + 'url': mpd_url, 'manifest_url': mpd_url, 'ext': mimetype2ext(mime_type), 'width': int_or_none(representation_attrib.get('width')), From c790e93ab5db5f318fb094b8a45f9160cdf4bd9b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Mar 2019 00:39:15 +0700 Subject: [PATCH 191/362] [extractor/common] Clarify url and manifest_url meta fields --- youtube_dl/extractor/common.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 1fa8048b8..641e50f3c 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -102,10 +102,20 @@ class InfoExtractor(object): from worst to best quality. Potential fields: - * url Mandatory. The URL of the video file + * url The mandatory URL representing the media: + for plain file media - HTTP URL of this file, + for RTMP - RTMP URL, + for HLS - URL of the M3U8 media playlist, + for HDS - URL of the F4M manifest, + for DASH - URL of the MPD manifest, + for MSS - URL of the ISM manifest. * manifest_url The URL of the manifest file in case of - fragmented media (DASH, hls, hds) + fragmented media: + for HLS - URL of the M3U8 master playlist, + for HDS - URL of the F4M manifest, + for DASH - URL of the MPD manifest, + for MSS - URL of the ISM manifest. * ext Will be calculated from URL if missing * format A human-readable description of the format ("mp4 container with h264/opus"). From 5dcd630dca9b75ec2ca920ae7799252e0e0bb599 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 4 Mar 2019 22:26:32 +0100 Subject: [PATCH 192/362] [paramountnetwork] fix mgid extraction(closes #20241) --- youtube_dl/extractor/spike.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py index 6090e0066..21b93a5b3 100644 --- a/youtube_dl/extractor/spike.py +++ b/youtube_dl/extractor/spike.py @@ -46,8 +46,12 @@ class ParamountNetworkIE(MTVServicesInfoExtractor): _GEO_COUNTRIES = ['US'] def _extract_mgid(self, webpage): - cs = self._parse_json(self._search_regex( + root_data = self._parse_json(self._search_regex( r'window\.__DATA__\s*=\s*({.+})', - webpage, 'data'), None)['children'] - c = next(c for c in cs if c.get('type') == 'VideoPlayer') + webpage, 'data'), None) + + def find_sub_data(data, data_type): + return next(c for c in data['children'] if c.get('type') == data_type) + + c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer') return c['props']['media']['video']['config']['uri'] From d9eb580a796ef6c9a248fdd8896ccf85349c35eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Mar 2019 23:45:40 +0700 Subject: [PATCH 193/362] [extractor/common] Do not fail on invalid data while parsing F4M manifest in non fatal mode --- youtube_dl/extractor/common.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 641e50f3c..55ce1a888 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -13,6 +13,7 @@ import socket import sys import time import math +import xml from ..compat import ( compat_cookiejar, @@ -1464,6 +1465,9 @@ class InfoExtractor(object): def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), fatal=True, m3u8_id=None): + if not isinstance(manifest, xml.etree.ElementTree.Element) and not fatal: + return [] + # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0') if akamai_pv is not None and ';' in akamai_pv.text: From c17eb5b4b06cfa2c8bffb378b0a5c84d4c5a6834 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Mar 2019 23:54:25 +0700 Subject: [PATCH 194/362] [rai] Improve extraction (closes #20253) --- youtube_dl/extractor/rai.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 149153b8f..207a6c247 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -74,11 +74,11 @@ class RaiBaseIE(InfoExtractor): if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'): continue - if ext == 'm3u8': + if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon': formats.extend(self._extract_m3u8_formats( media_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - elif ext == 'f4m': + elif ext == 'f4m' or platform == 'flash': manifest_url = update_url_query( media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'), {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'}) From bb6f112d9d57d7c6260de132cad604c1c05bc5a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Mar 2019 23:57:39 +0700 Subject: [PATCH 195/362] [npo] Improve ISM extraction --- youtube_dl/extractor/npo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 857845d35..ad62f8ec6 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -238,7 +238,7 @@ class NPOIE(NPOBaseIE): formats.extend(self._extract_m3u8_formats( stream_url, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) - elif '.ism/Manifest' in stream_url: + elif re.search(r'\.isml?/Manifest', stream_url): formats.extend(self._extract_ism_formats( stream_url, video_id, ism_id='mss', fatal=False)) else: From e5ada4f3ad771d4cf3f533efb2597a3f1618ce75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 6 Mar 2019 00:33:08 +0700 Subject: [PATCH 196/362] [extractor/common] Fallback url to base URL for DASH formats --- youtube_dl/extractor/common.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 55ce1a888..a17f7cbc4 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -108,7 +108,10 @@ class InfoExtractor(object): for RTMP - RTMP URL, for HLS - URL of the M3U8 media playlist, for HDS - URL of the F4M manifest, - for DASH - URL of the MPD manifest, + for DASH - URL of the MPD manifest or + base URL representing the media + if MPD manifest is parsed from + a string, for MSS - URL of the ISM manifest. * manifest_url The URL of the manifest file in case of @@ -2134,7 +2137,8 @@ class InfoExtractor(object): bandwidth = int_or_none(representation_attrib.get('bandwidth')) f = { 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, - 'url': mpd_url, + # NB: mpd_url may be empty when MPD manifest is parsed from a string + 'url': mpd_url or base_url, 'manifest_url': mpd_url, 'ext': mimetype2ext(mime_type), 'width': int_or_none(representation_attrib.get('width')), From 399f76870d7dc72631e7da1f54a46ed8a039c838 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 6 Mar 2019 01:18:52 +0700 Subject: [PATCH 197/362] [compat] Introduce compat_etree_Element --- test/test_compat.py | 7 +++++++ youtube_dl/compat.py | 10 ++++++++++ 2 files changed, 17 insertions(+) diff --git a/test/test_compat.py b/test/test_compat.py index 51fe6aa0b..4822260ac 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -13,6 +13,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from youtube_dl.compat import ( compat_getenv, compat_setenv, + compat_etree_Element, compat_etree_fromstring, compat_expanduser, compat_shlex_split, @@ -90,6 +91,12 @@ class TestCompat(unittest.TestCase): self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag']) self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文']) + def test_compat_etree_Element(self): + try: + compat_etree_Element.text + except AttributeError: + self.fail('compat_etree_Element is not a type') + def test_compat_etree_fromstring(self): xml = ''' diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 7b770340f..b2fe62f12 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2508,6 +2508,15 @@ class _TreeBuilder(etree.TreeBuilder): pass +try: + # xml.etree.ElementTree.Element is a method in Python <=2.6 and + # the following will crash with: + # TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types + isinstance(None, xml.etree.ElementTree.Element) + from xml.etree.ElementTree import Element as compat_etree_Element +except TypeError: # Python <=2.6 + from xml.etree.ElementTree import _ElementInterface as compat_etree_Element + if sys.version_info[0] >= 3: def compat_etree_fromstring(text): return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder())) @@ -2969,6 +2978,7 @@ __all__ = [ 'compat_cookiejar', 'compat_cookies', 'compat_ctypes_WINFUNCTYPE', + 'compat_etree_Element', 'compat_etree_fromstring', 'compat_etree_register_namespace', 'compat_expanduser', From ee0ba927aac067dec533a618540e43ed3deebaba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 6 Mar 2019 01:21:57 +0700 Subject: [PATCH 198/362] Use compat_etree_Element --- youtube_dl/extractor/bbc.py | 4 ++-- youtube_dl/extractor/common.py | 8 ++++---- youtube_dl/extractor/crunchyroll.py | 10 +++++----- 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 13340ec64..d479d2577 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import itertools import re -import xml from .common import InfoExtractor from ..utils import ( @@ -23,6 +22,7 @@ from ..utils import ( urljoin, ) from ..compat import ( + compat_etree_Element, compat_HTTPError, compat_urlparse, ) @@ -317,7 +317,7 @@ class BBCCoUkIE(InfoExtractor): continue captions = self._download_xml( cc_url, programme_id, 'Downloading captions', fatal=False) - if not isinstance(captions, xml.etree.ElementTree.Element): + if not isinstance(captions, compat_etree_Element): continue lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') subtitles[lang] = [ diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index a17f7cbc4..4839edbf7 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -13,11 +13,11 @@ import socket import sys import time import math -import xml from ..compat import ( compat_cookiejar, compat_cookies, + compat_etree_Element, compat_etree_fromstring, compat_getpass, compat_integer_types, @@ -802,7 +802,7 @@ class InfoExtractor(object): fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None): """ - Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle). + Return a tuple (xml as an compat_etree_Element, URL handle). See _download_webpage docstring for arguments specification. """ @@ -823,7 +823,7 @@ class InfoExtractor(object): transform_source=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None): """ - Return the xml as an xml.etree.ElementTree.Element. + Return the xml as an compat_etree_Element. See _download_webpage docstring for arguments specification. """ @@ -1468,7 +1468,7 @@ class InfoExtractor(object): def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), fatal=True, m3u8_id=None): - if not isinstance(manifest, xml.etree.ElementTree.Element) and not fatal: + if not isinstance(manifest, compat_etree_Element) and not fatal: return [] # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index fd1e7afad..5948154f8 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re import json -import xml.etree.ElementTree as etree import zlib from hashlib import sha1 @@ -12,6 +11,7 @@ from .common import InfoExtractor from .vrv import VRVIE from ..compat import ( compat_b64decode, + compat_etree_Element, compat_etree_fromstring, compat_urllib_parse_urlencode, compat_urllib_request, @@ -390,7 +390,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'Downloading subtitles for ' + sub_name, data={ 'subtitle_script_id': sub_id, }) - if not isinstance(sub_doc, etree.Element): + if not isinstance(sub_doc, compat_etree_Element): continue sid = sub_doc.get('id') iv = xpath_text(sub_doc, 'iv', 'subtitle iv') @@ -507,7 +507,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_quality': stream_quality, 'current_page': url, }) - if isinstance(streamdata, etree.Element): + if isinstance(streamdata, compat_etree_Element): stream_info = streamdata.find('./{default}preload/stream_info') if stream_info is not None: stream_infos.append(stream_info) @@ -518,7 +518,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_format': stream_format, 'video_encode_quality': stream_quality, }) - if isinstance(stream_info, etree.Element): + if isinstance(stream_info, compat_etree_Element): stream_infos.append(stream_info) for stream_info in stream_infos: video_encode_id = xpath_text(stream_info, './video_encode_id') @@ -593,7 +593,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text season = episode = episode_number = duration = thumbnail = None - if isinstance(metadata, etree.Element): + if isinstance(metadata, compat_etree_Element): season = xpath_text(metadata, 'series_title') episode = xpath_text(metadata, 'episode_title') episode_number = int_or_none(xpath_text(metadata, 'episode_number')) From a551768acfd177e425f518c43a2992a50a2ff69f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 6 Mar 2019 01:27:22 +0700 Subject: [PATCH 199/362] [facebook] Improve uploader extraction (closes #20250) --- youtube_dl/extractor/facebook.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 74954049d..789dd79d5 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -424,7 +424,7 @@ class FacebookIE(InfoExtractor): uploader = clean_html(get_element_by_id( 'fbPhotoPageAuthorName', webpage)) or self._search_regex( r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', - fatal=False) or self._og_search_title(webpage, fatal=False) + default=None) or self._og_search_title(webpage, fatal=False) timestamp = int_or_none(self._search_regex( r']+data-utime=["\'](\d+)', webpage, 'timestamp', default=None)) From 97157c692c94e3853a6ad1b8a220f064815b6957 Mon Sep 17 00:00:00 2001 From: yonaikerlol Date: Tue, 5 Mar 2019 14:34:34 -0400 Subject: [PATCH 200/362] [openload] Add support for oload.space --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index c1dcbb7eb..bae7c7ee7 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link|pw)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space) ) )/ (?:f|embed)/ @@ -349,6 +349,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.live/f/-Z58UZ-GR4M', 'only_matching': True, + }, { + 'url': 'https://oload.space/f/IY4eZSst3u8/', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From d347b52b63282b3276815fd03fc63a1bc8b82cf5 Mon Sep 17 00:00:00 2001 From: 0x9fff00 <0x9fff00+git@protonmail.ch> Date: Tue, 5 Mar 2019 20:11:32 +0100 Subject: [PATCH 201/362] [urplay] Extract timestamp (#20235) --- youtube_dl/extractor/urplay.py | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/urplay.py b/youtube_dl/extractor/urplay.py index 8e6fd4731..6030b7cb5 100644 --- a/youtube_dl/extractor/urplay.py +++ b/youtube_dl/extractor/urplay.py @@ -2,18 +2,31 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import unified_timestamp class URPlayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P[0-9]+)' _TESTS = [{ - 'url': 'http://urplay.se/program/190031-tripp-trapp-trad-sovkudde', - 'md5': 'ad5f0de86f16ca4c8062cd103959a9eb', + 'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand', + 'md5': 'ff5b0c89928f8083c74bbd5099c9292d', + 'info_dict': { + 'id': '203704', + 'ext': 'mp4', + 'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd', + 'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a', + 'timestamp': 1513512768, + 'upload_date': '20171217', + }, + }, { + 'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde', 'info_dict': { 'id': '190031', 'ext': 'mp4', 'title': 'Tripp, Trapp, Träd : Sovkudde', 'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1', + 'timestamp': 1440093600, + 'upload_date': '20150820', }, }, { 'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden', @@ -51,6 +64,7 @@ class URPlayIE(InfoExtractor): 'title': urplayer_data['title'], 'description': self._og_search_description(webpage), 'thumbnail': urplayer_data.get('image'), + 'timestamp': unified_timestamp(self._html_search_meta(('uploadDate', 'schema:uploadDate'), webpage, 'timestamp')), 'series': urplayer_data.get('series_title'), 'subtitles': subtitles, 'formats': formats, From fca9baf0da9720bac25d160924204395930191fe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 6 Mar 2019 02:45:33 +0700 Subject: [PATCH 202/362] [test] Fix test_compat_etree_Element --- test/test_compat.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/test_compat.py b/test/test_compat.py index 4822260ac..86ff389fd 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -93,7 +93,7 @@ class TestCompat(unittest.TestCase): def test_compat_etree_Element(self): try: - compat_etree_Element.text + compat_etree_Element.items except AttributeError: self.fail('compat_etree_Element is not a type') From 829685b88a0c7610a874b980bc25b308c4f34590 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 6 Mar 2019 09:20:27 +0100 Subject: [PATCH 203/362] [toutv] fix authentication(closes #20261) --- youtube_dl/extractor/toutv.py | 53 +++++++++-------------------------- 1 file changed, 14 insertions(+), 39 deletions(-) diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index f1ab91cf2..124ca064c 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -1,14 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import json from .radiocanada import RadioCanadaIE from ..utils import ( - extract_attributes, int_or_none, merge_dicts, - urlencode_postdata, ) @@ -38,47 +36,24 @@ class TouTvIE(RadioCanadaIE): 'url': 'https://ici.tou.tv/l-age-adulte/S01C501', 'only_matching': True, }] + _CLIENT_KEY = '4dd36440-09d5-4468-8923-b6d91174ad36' def _real_initialize(self): email, password = self._get_login_info() if email is None: return - login_webpage = self._download_webpage( - 'https://services.radio-canada.ca/auth/oauth/v2/authorize', - None, 'Downloading login page', query={ - 'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36', - 'redirect_uri': 'https://ici.tou.tv/logincallback', - 'response_type': 'token', - 'scope': 'id.write media-validation.read', - 'state': '/', - }) - - def extract_form_url_and_data(wp, default_form_url, form_spec_re=''): - form, form_elem = re.search( - r'(?s)((]+?%s[^>]*?>).+?)' % form_spec_re, wp).groups() - form_data = self._hidden_inputs(form) - form_url = extract_attributes(form_elem).get('action') or default_form_url - return form_url, form_data - - post_url, form_data = extract_form_url_and_data( - login_webpage, - 'https://services.radio-canada.ca/auth/oauth/v2/authorize/login', - r'(?:id|name)="Form-login"') - form_data.update({ - 'login-email': email, - 'login-password': password, - }) - consent_webpage = self._download_webpage( - post_url, None, 'Logging in', data=urlencode_postdata(form_data)) - post_url, form_data = extract_form_url_and_data( - consent_webpage, - 'https://services.radio-canada.ca/auth/oauth/v2/authorize/consent') - _, urlh = self._download_webpage_handle( - post_url, None, 'Following Redirection', - data=urlencode_postdata(form_data)) - self._access_token = self._search_regex( - r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', - urlh.geturl(), 'access token') + self._access_token = self._download_json( + 'https://services.radio-canada.ca/toutv/profiling/accounts/login', + None, 'Logging in', data=json.dumps({ + 'ClientId': self._CLIENT_KEY, + 'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20', + 'Email': email, + 'Password': password, + 'Scope': 'id.write media-validation.read', + }).encode(), headers={ + 'Authorization': 'client-key ' + self._CLIENT_KEY, + 'Content-Type': 'application/json;charset=utf-8', + })['access_token'] self._claims = self._call_api('validation/v2/getClaims')['claims'] def _real_extract(self, url): From 7b6e76087080eac54e14cdead4e3bc0225c654b5 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 6 Mar 2019 09:28:14 +0100 Subject: [PATCH 204/362] [toutv] detect invalid login error --- youtube_dl/extractor/toutv.py | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index 124ca064c..25e1fd46d 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -4,7 +4,9 @@ from __future__ import unicode_literals import json from .radiocanada import RadioCanadaIE +from ..compat import compat_HTTPError from ..utils import ( + ExtractorError, int_or_none, merge_dicts, ) @@ -42,18 +44,24 @@ class TouTvIE(RadioCanadaIE): email, password = self._get_login_info() if email is None: return - self._access_token = self._download_json( - 'https://services.radio-canada.ca/toutv/profiling/accounts/login', - None, 'Logging in', data=json.dumps({ - 'ClientId': self._CLIENT_KEY, - 'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20', - 'Email': email, - 'Password': password, - 'Scope': 'id.write media-validation.read', - }).encode(), headers={ - 'Authorization': 'client-key ' + self._CLIENT_KEY, - 'Content-Type': 'application/json;charset=utf-8', - })['access_token'] + try: + self._access_token = self._download_json( + 'https://services.radio-canada.ca/toutv/profiling/accounts/login', + None, 'Logging in', data=json.dumps({ + 'ClientId': self._CLIENT_KEY, + 'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20', + 'Email': email, + 'Password': password, + 'Scope': 'id.write media-validation.read', + }).encode(), headers={ + 'Authorization': 'client-key ' + self._CLIENT_KEY, + 'Content-Type': 'application/json;charset=utf-8', + })['access_token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + error = self._parse_json(e.cause.read().decode(), None)['Message'] + raise ExtractorError(error, expected=True) + raise self._claims = self._call_api('validation/v2/getClaims')['claims'] def _real_extract(self, url): From 9d74ea6d36696396392974e94a40dce1e5a881a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 8 Mar 2019 23:26:59 +0700 Subject: [PATCH 205/362] [francetv:site] Relax video id regex and update test (closes #20268) --- youtube_dl/extractor/francetv.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 3c4ef08a8..6101fb6bd 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -215,7 +215,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor): _TESTS = [{ 'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html', 'info_dict': { - 'id': '162311093', + 'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1', 'ext': 'mp4', 'title': '13h15, le dimanche... - Les mystères de Jésus', 'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42', @@ -271,7 +271,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor): catalogue = None video_id = self._search_regex( - r'(?:data-main-video\s*=|videoId\s*:)\s*(["\'])(?P(?:(?!\1).)+)\1', + r'(?:data-main-video\s*=|videoId["\']?\s*[:=])\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video id', default=None, group='id') if not video_id: From bba35695eb4ab9cc70624583375ba3d15b4e6cc2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Mar 2019 02:52:08 +0700 Subject: [PATCH 206/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/ChangeLog b/ChangeLog index 018a30641..272191a01 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,34 @@ +version + +Core +* [extractor/common] Use compat_etree_Element ++ [compat] Introduce compat_etree_Element +* [extractor/common] Fallback url to base URL for DASH formats +* [extractor/common] Do not fail on invalid data while parsing F4M manifest + in non fatal mode +* [extractor/common] Return MPD manifest as format's url meta field (#20242) +* [utils] Strip #HttpOnly_ prefix from cookies files (#20219) + +Extractors +* [francetv:site] Relax video id regular expression (#20268) +* [toutv] Detect invalid login error +* [toutv] Fix authentication (#20261) ++ [urplay] Extract timestamp (#20235) ++ [openload] Add support for oload.space (#20246) +* [facebook] Improve uploader extraction (#20250) +* [bbc] Use compat_etree_Element +* [crunchyroll] Use compat_etree_Element +* [npo] Improve ISM extraction +* [rai] Improve extraction (#20253) +* [paramountnetwork] Fix mgid extraction (#20241) +* [libsyn] Improve extraction (#20229) ++ [youtube] Add more invidious instances to URL regular expression (#20228) +* [spankbang] Fix extraction (#20023) +* [espn] Extend URL regular expression (#20013) +* [sixplay] Handle videos with empty assets (#20016) ++ [vimeo] Add support for Vimeo Pro portfolio protected videos (#20070) + + version 2019.03.01 Core From 10734553feef497e2810a23bbe62a0b3d630e78d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Mar 2019 02:53:18 +0700 Subject: [PATCH 207/362] release 2019.03.09 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 71a500f04..5f97e2cbe 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.01*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.01** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.09** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.03.01 +[debug] youtube-dl version 2019.03.09 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 272191a01..eda94ad33 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.03.09 Core * [extractor/common] Use compat_etree_Element diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 42ba37f15..f72fee57f 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.03.01' +__version__ = '2019.03.09' From 0d08bcdb70008f0d500afbd19059b3c0971a4776 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 10 Mar 2019 09:37:28 +0100 Subject: [PATCH 208/362] [fox] detect geo restriction and authentication errors(#20208) --- youtube_dl/extractor/fox.py | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 0ffceeb7c..f30d3cba8 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -6,10 +6,12 @@ import uuid from .adobepass import AdobePassIE from ..compat import ( + compat_HTTPError, compat_str, compat_urllib_parse_unquote, ) from ..utils import ( + ExtractorError, int_or_none, parse_age_limit, parse_duration, @@ -48,6 +50,7 @@ class FOXIE(AdobePassIE): 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, }] + _GEO_BYPASS = False _HOME_PAGE_URL = 'https://www.fox.com/' _API_KEY = 'abdcbed02c124d393b39e818a4312055' _access_token = None @@ -58,9 +61,22 @@ class FOXIE(AdobePassIE): } if self._access_token: headers['Authorization'] = 'Bearer ' + self._access_token - return self._download_json( - 'https://api2.fox.com/v2.0/' + path, - video_id, data=data, headers=headers) + try: + return self._download_json( + 'https://api2.fox.com/v2.0/' + path, + video_id, data=data, headers=headers) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.status == 403: + entitlement_issues = self._parse_json( + e.cause.read().decode(), video_id)['entitlementIssues'] + for e in entitlement_issues: + if e.get('errorCode') == 1005: + raise ExtractorError( + 'This video is only available via cable service provider ' + 'subscription. You may want to use --cookies.', expected=True) + messages = ', '.join([e['message'] for e in entitlement_issues]) + raise ExtractorError(messages, expected=True) + raise def _real_initialize(self): if not self._access_token: @@ -81,7 +97,15 @@ class FOXIE(AdobePassIE): title = video['name'] release_url = video['url'] - m3u8_url = self._download_json(release_url, video_id)['playURL'] + try: + m3u8_url = self._download_json(release_url, video_id)['playURL'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.status == 403: + error = self._parse_json(e.cause.read().decode(), video_id) + if error.get('exception') == 'GeoLocationBlocked': + self.raise_geo_restricted(countries=['US']) + raise ExtractorError(error['description'], expected=True) + raise formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') From 276550371313dbfe7d94ceb294bd1284c1e7c404 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 10 Mar 2019 15:03:32 +0100 Subject: [PATCH 209/362] [vimeo:review] improve config url extraction and extract original format(closes #20305) --- youtube_dl/extractor/vimeo.py | 64 +++++++++++++++++++++-------------- 1 file changed, 38 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 6f32ea6f1..e3ec550f0 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -195,6 +195,32 @@ class VimeoBaseInfoExtractor(InfoExtractor): 'subtitles': subtitles, } + def _extract_original_format(self, url, video_id): + download_data = self._download_json( + url, video_id, fatal=False, + query={'action': 'load_download_config'}, + headers={'X-Requested-With': 'XMLHttpRequest'}) + if download_data: + source_file = download_data.get('source_file') + if isinstance(source_file, dict): + download_url = source_file.get('download_url') + if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'): + source_name = source_file.get('public_name', 'Original') + if self._is_valid_url(download_url, video_id, '%s video' % source_name): + ext = (try_get( + source_file, lambda x: x['extension'], + compat_str) or determine_ext( + download_url, None) or 'mp4').lower() + return { + 'url': download_url, + 'ext': ext, + 'width': int_or_none(source_file.get('width')), + 'height': int_or_none(source_file.get('height')), + 'filesize': parse_filesize(source_file.get('size')), + 'format_id': source_name, + 'preference': 1, + } + class VimeoIE(VimeoBaseInfoExtractor): """Information extractor for vimeo.com.""" @@ -659,29 +685,11 @@ class VimeoIE(VimeoBaseInfoExtractor): comment_count = None formats = [] - download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={ - 'X-Requested-With': 'XMLHttpRequest'}) - download_data = self._download_json(download_request, video_id, fatal=False) - if download_data: - source_file = download_data.get('source_file') - if isinstance(source_file, dict): - download_url = source_file.get('download_url') - if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'): - source_name = source_file.get('public_name', 'Original') - if self._is_valid_url(download_url, video_id, '%s video' % source_name): - ext = (try_get( - source_file, lambda x: x['extension'], - compat_str) or determine_ext( - download_url, None) or 'mp4').lower() - formats.append({ - 'url': download_url, - 'ext': ext, - 'width': int_or_none(source_file.get('width')), - 'height': int_or_none(source_file.get('height')), - 'filesize': parse_filesize(source_file.get('size')), - 'format_id': source_name, - 'preference': 1, - }) + + source_format = self._extract_original_format( + 'https://vimeo.com/' + video_id, video_id) + if source_format: + formats.append(source_format) info_dict_config = self._parse_config(config, video_id) formats.extend(info_dict_config['formats']) @@ -940,7 +948,7 @@ class VimeoGroupsIE(VimeoAlbumIE): class VimeoReviewIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P[^/]+)' + _VALID_URL = r'(?Phttps://vimeo\.com/[^/]+/review/(?P[^/]+)/[0-9a-f]{10})' _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'md5': 'c507a72f780cacc12b2248bb4006d253', @@ -992,7 +1000,8 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): data = self._parse_json(self._search_regex( r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data', default=NO_DEFAULT if video_password_verified else '{}'), video_id) - config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl') + config = data.get('vimeo_esi', {}).get('config', {}) + config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl']) if config_url is None: self._verify_video_password(webpage_url, video_id, webpage) config_url = self._get_config_url( @@ -1000,10 +1009,13 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): return config_url def _real_extract(self, url): - video_id = self._match_id(url) + page_url, video_id = re.match(self._VALID_URL, url).groups() config_url = self._get_config_url(url, video_id) config = self._download_json(config_url, video_id) info_dict = self._parse_config(config, video_id) + source_format = self._extract_original_format(page_url, video_id) + if source_format: + info_dict['formats'].append(source_format) self._vimeo_sort_formats(info_dict['formats']) info_dict['id'] = video_id return info_dict From 067aa17edf5a46a8cbc4d6b90864eddf051fa2bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Mar 2019 19:14:41 +0700 Subject: [PATCH 210/362] Start moving to ytdl-org --- .github/ISSUE_TEMPLATE.md | 10 +++--- .github/ISSUE_TEMPLATE_tmpl.md | 10 +++--- .github/PULL_REQUEST_TEMPLATE.md | 4 +-- CONTRIBUTING.md | 20 +++++------ README.md | 42 +++++++++++------------ devscripts/buildserver.py | 2 +- devscripts/create-github-release.py | 4 +-- devscripts/gh-pages/update-feed.py | 4 +-- devscripts/release.sh | 2 +- devscripts/show-downloads-statistics.py | 2 +- setup.py | 2 +- test/test_InfoExtractor.py | 16 ++++----- test/test_YoutubeDL.py | 6 ++-- test/test_all_urls.py | 6 ++-- youtube-dl.plugin.zsh | 2 +- youtube_dl/YoutubeDL.py | 16 ++++----- youtube_dl/__init__.py | 2 +- youtube_dl/compat.py | 6 ++-- youtube_dl/downloader/external.py | 4 +-- youtube_dl/downloader/f4m.py | 6 ++-- youtube_dl/downloader/hls.py | 4 +-- youtube_dl/downloader/http.py | 2 +- youtube_dl/extractor/arkena.py | 2 +- youtube_dl/extractor/bambuser.py | 4 +-- youtube_dl/extractor/bbc.py | 2 +- youtube_dl/extractor/brightcove.py | 6 ++-- youtube_dl/extractor/ceskatelevize.py | 2 +- youtube_dl/extractor/common.py | 20 +++++------ youtube_dl/extractor/commonmistakes.py | 2 +- youtube_dl/extractor/crunchyroll.py | 4 +-- youtube_dl/extractor/dailymotion.py | 4 +-- youtube_dl/extractor/dreisat.py | 2 +- youtube_dl/extractor/francetv.py | 2 +- youtube_dl/extractor/generic.py | 10 +++--- youtube_dl/extractor/googledrive.py | 2 +- youtube_dl/extractor/kuwo.py | 2 +- youtube_dl/extractor/liveleak.py | 6 ++-- youtube_dl/extractor/msn.py | 2 +- youtube_dl/extractor/nhl.py | 2 +- youtube_dl/extractor/noco.py | 2 +- youtube_dl/extractor/once.py | 2 +- youtube_dl/extractor/pbs.py | 6 ++-- youtube_dl/extractor/pluralsight.py | 6 ++-- youtube_dl/extractor/pornhub.py | 2 +- youtube_dl/extractor/prosiebensat1.py | 4 +-- youtube_dl/extractor/radiocanada.py | 2 +- youtube_dl/extractor/rtlnl.py | 2 +- youtube_dl/extractor/theplatform.py | 4 +-- youtube_dl/extractor/toutv.py | 2 +- youtube_dl/extractor/udemy.py | 2 +- youtube_dl/extractor/ustream.py | 2 +- youtube_dl/extractor/veehd.py | 2 +- youtube_dl/extractor/vevo.py | 2 +- youtube_dl/extractor/vimeo.py | 4 +-- youtube_dl/extractor/vk.py | 2 +- youtube_dl/extractor/vlive.py | 2 +- youtube_dl/extractor/yandexmusic.py | 4 +-- youtube_dl/extractor/youtube.py | 44 ++++++++++++------------- youtube_dl/options.py | 2 +- youtube_dl/update.py | 2 +- youtube_dl/utils.py | 18 +++++----- 61 files changed, 182 insertions(+), 182 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 5f97e2cbe..911e912a4 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,12 +6,12 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.09*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. - [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.09** ### Before submitting an *issue* make sure you have: -- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections -- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones +- [ ] At least skimmed through the [README](https://github.com/ytdl-org/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/ytdl-org/youtube-dl#faq) and [BUGS](https://github.com/ytdl-org/youtube-dl#bugs) sections +- [ ] [Searched](https://github.com/ytdl-org/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones - [ ] Checked that provided video/audio/playlist URLs (if any) are alive and playable in a browser ### What is the purpose of your *issue*? @@ -51,11 +51,11 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl - Single video: https://youtu.be/BaW_jenozKc - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc -Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights. +Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights. --- ### Description of your *issue*, suggested solution and other information -Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible. +Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible. If work on your *issue* requires account credentials please provide them or explain how one can obtain them. diff --git a/.github/ISSUE_TEMPLATE_tmpl.md b/.github/ISSUE_TEMPLATE_tmpl.md index 8edbd5a0f..8b7e73417 100644 --- a/.github/ISSUE_TEMPLATE_tmpl.md +++ b/.github/ISSUE_TEMPLATE_tmpl.md @@ -6,12 +6,12 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *%(version)s*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *%(version)s*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. - [ ] I've **verified** and **I assure** that I'm running youtube-dl **%(version)s** ### Before submitting an *issue* make sure you have: -- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections -- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones +- [ ] At least skimmed through the [README](https://github.com/ytdl-org/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/ytdl-org/youtube-dl#faq) and [BUGS](https://github.com/ytdl-org/youtube-dl#bugs) sections +- [ ] [Searched](https://github.com/ytdl-org/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones - [ ] Checked that provided video/audio/playlist URLs (if any) are alive and playable in a browser ### What is the purpose of your *issue*? @@ -51,11 +51,11 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl - Single video: https://youtu.be/BaW_jenozKc - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc -Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights. +Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights. --- ### Description of your *issue*, suggested solution and other information -Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible. +Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible. If work on your *issue* requires account credentials please provide them or explain how one can obtain them. diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index ba4ca7553..e69b907d8 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -7,8 +7,8 @@ --- ### Before submitting a *pull request* make sure you have: -- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections -- [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests +- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/ytdl-org/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/ytdl-org/youtube-dl#youtube-dl-coding-conventions) sections +- [ ] [Searched](https://github.com/ytdl-org/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests - [ ] Checked the code with [flake8](https://pypi.python.org/pypi/flake8) ### In order to be accepted and merged into youtube-dl each piece of code must be in public domain or released under [Unlicense](http://unlicense.org/). Check one of the following options: diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 6c1739860..cd9ccbe96 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -42,11 +42,11 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're ### Is the issue already documented? -Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. +Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/ytdl-org/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. ### Why are existing options not enough? -Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. +Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. ### Is there enough context in your bug report? @@ -70,7 +70,7 @@ It may sound strange, but some bug reports we receive are completely unrelated t # DEVELOPER INSTRUCTIONS -Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution. +Most users do not need to build youtube-dl and can [download the builds](https://ytdl-org.github.io/youtube-dl/download.html) or get them from their distribution. To run youtube-dl as a developer, you don't need to build anything either. Simply execute @@ -98,7 +98,7 @@ If you want to add support for a new site, first of all **make sure** this site After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`): -1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) +1. [Fork this repository](https://github.com/ytdl-org/youtube-dl/fork) 2. Check out the source code with: git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git @@ -150,9 +150,9 @@ After you have ensured this site is distributing its content legally, you can fo # TODO more properties (see youtube_dl/extractor/common.py) } ``` -5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). +5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. 8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): $ flake8 youtube_dl/extractor/yourextractor.py @@ -177,7 +177,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou ### Mandatory and optional metafields -For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: - `id` (media identifier) - `title` (media title) @@ -185,7 +185,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. -[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. +[Any field](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. #### Example @@ -341,7 +341,7 @@ Incorrect: ### Use convenience conversion and parsing functions -Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. +Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. Use `url_or_none` for safe URL processing. @@ -349,7 +349,7 @@ Use `try_get` for safe metadata extraction from parsed JSON. Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. -Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. +Explore [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples diff --git a/README.md b/README.md index c1572f771..e476045b2 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -[![Build Status](https://travis-ci.org/rg3/youtube-dl.svg?branch=master)](https://travis-ci.org/rg3/youtube-dl) +[![Build Status](https://travis-ci.org/ytdl-org/youtube-dl.svg?branch=master)](https://travis-ci.org/ytdl-org/youtube-dl) youtube-dl - download videos from youtube.com or other video platforms @@ -43,7 +43,7 @@ Or with [MacPorts](https://www.macports.org/): sudo port install youtube-dl -Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html). +Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://ytdl-org.github.io/youtube-dl/download.html). # DESCRIPTION **youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. @@ -685,7 +685,7 @@ You can merge the video and audio of two formats into a single file using `-f . Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](https://webchat.freenode.net/?randomnick=1&channels=youtube-dl)). +Bugs and suggestions should be reported at: . Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](https://webchat.freenode.net/?randomnick=1&channels=youtube-dl)). **Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this: ``` @@ -1342,11 +1342,11 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're ### Is the issue already documented? -Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. +Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/ytdl-org/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. ### Why are existing options not enough? -Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. +Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. ### Is there enough context in your bug report? diff --git a/devscripts/buildserver.py b/devscripts/buildserver.py index 1344b4d87..4a4295ba9 100644 --- a/devscripts/buildserver.py +++ b/devscripts/buildserver.py @@ -322,7 +322,7 @@ class GITBuilder(GITInfoBuilder): class YoutubeDLBuilder(object): - authorizedUsers = ['fraca7', 'phihag', 'rg3', 'FiloSottile'] + authorizedUsers = ['fraca7', 'phihag', 'rg3', 'FiloSottile', 'ytdl-org'] def __init__(self, **kwargs): if self.repoName != 'youtube-dl': diff --git a/devscripts/create-github-release.py b/devscripts/create-github-release.py index 30716ad8e..428111b3f 100644 --- a/devscripts/create-github-release.py +++ b/devscripts/create-github-release.py @@ -27,8 +27,8 @@ from youtube_dl.utils import ( class GitHubReleaser(object): - _API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases' - _UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s' + _API_URL = 'https://api.github.com/repos/ytdl-org/youtube-dl/releases' + _UPLOADS_URL = 'https://uploads.github.com/repos/ytdl-org/youtube-dl/releases/%s/assets?name=%s' _NETRC_MACHINE = 'github.com' def __init__(self, debuglevel=0): diff --git a/devscripts/gh-pages/update-feed.py b/devscripts/gh-pages/update-feed.py index e93eb60fb..506a62377 100755 --- a/devscripts/gh-pages/update-feed.py +++ b/devscripts/gh-pages/update-feed.py @@ -10,7 +10,7 @@ import textwrap atom_template = textwrap.dedent("""\ - + youtube-dl releases https://yt-dl.org/feed/youtube-dl-updates-feed @TIMESTAMP@ @@ -21,7 +21,7 @@ entry_template = textwrap.dedent(""" https://yt-dl.org/feed/youtube-dl-updates-feed/youtube-dl-@VERSION@ New version @VERSION@ - +
Downloads available at https://yt-dl.org/downloads/@VERSION@/ diff --git a/devscripts/release.sh b/devscripts/release.sh index 4db5def5d..4c413bf6d 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -96,7 +96,7 @@ git push origin "$version" REV=$(git rev-parse HEAD) make youtube-dl youtube-dl.tar.gz read -p "VM running? (y/n) " -n 1 -wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe +wget "http://$buildserver/build/ytdl-org/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe mkdir -p "build/$version" mv youtube-dl youtube-dl.exe "build/$version" mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz" diff --git a/devscripts/show-downloads-statistics.py b/devscripts/show-downloads-statistics.py index e25d28411..6c8d1cc2d 100644 --- a/devscripts/show-downloads-statistics.py +++ b/devscripts/show-downloads-statistics.py @@ -24,7 +24,7 @@ total_bytes = 0 for page in itertools.count(1): releases = json.loads(compat_urllib_request.urlopen( - 'https://api.github.com/repos/rg3/youtube-dl/releases?page=%s' % page + 'https://api.github.com/repos/ytdl-org/youtube-dl/releases?page=%s' % page ).read().decode('utf-8')) if not releases: diff --git a/setup.py b/setup.py index dfb669ad2..af68b485e 100644 --- a/setup.py +++ b/setup.py @@ -104,7 +104,7 @@ setup( version=__version__, description=DESCRIPTION, long_description=LONG_DESCRIPTION, - url='https://github.com/rg3/youtube-dl', + url='https://github.com/ytdl-org/youtube-dl', author='Ricardo Garcia', author_email='ytdl@yt-dl.org', maintainer='Sergey M.', diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index f0aa8466b..da6cd39b6 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -201,7 +201,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ def test_parse_m3u8_formats(self): _TEST_CASES = [ ( - # https://github.com/rg3/youtube-dl/issues/11507 + # https://github.com/ytdl-org/youtube-dl/issues/11507 # http://pluzz.francetv.fr/videos/le_ministere.html 'pluzz_francetv_11507', 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais', @@ -263,7 +263,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ }] ), ( - # https://github.com/rg3/youtube-dl/issues/11995 + # https://github.com/ytdl-org/youtube-dl/issues/11995 # http://teamcoco.com/video/clueless-gamer-super-bowl-for-honor 'teamcoco_11995', 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8', @@ -337,7 +337,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ }] ), ( - # https://github.com/rg3/youtube-dl/issues/12211 + # https://github.com/ytdl-org/youtube-dl/issues/12211 # http://video.toggle.sg/en/series/whoopie-s-world/ep3/478601 'toggle_mobile_12211', 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8', @@ -501,7 +501,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ }] ), ( - # https://github.com/rg3/youtube-dl/issues/18923 + # https://github.com/ytdl-org/youtube-dl/issues/18923 # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa 'ted_18923', 'http://hls.ted.com/talks/31241.m3u8', @@ -570,9 +570,9 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ def test_parse_mpd_formats(self): _TEST_CASES = [ ( - # https://github.com/rg3/youtube-dl/issues/13919 + # https://github.com/ytdl-org/youtube-dl/issues/13919 # Also tests duplicate representation ids, see - # https://github.com/rg3/youtube-dl/issues/15111 + # https://github.com/ytdl-org/youtube-dl/issues/15111 'float_duration', 'http://unknown/manifest.mpd', [{ @@ -652,7 +652,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ 'height': 1080, }] ), ( - # https://github.com/rg3/youtube-dl/pull/14844 + # https://github.com/ytdl-org/youtube-dl/pull/14844 'urls_only', 'http://unknown/manifest.mpd', [{ @@ -748,7 +748,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ def test_parse_f4m_formats(self): _TEST_CASES = [ ( - # https://github.com/rg3/youtube-dl/issues/14660 + # https://github.com/ytdl-org/youtube-dl/issues/14660 'custom_base_url', 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m', [{ diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 1d7452744..ce9666171 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -411,7 +411,7 @@ class TestFormatSelection(unittest.TestCase): # For extractors with incomplete formats (all formats are audio-only or # video-only) best and worst should fallback to corresponding best/worst # video-only or audio-only formats (as per - # https://github.com/rg3/youtube-dl/pull/5556) + # https://github.com/ytdl-org/youtube-dl/pull/5556) formats = [ {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL}, {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL}, @@ -442,7 +442,7 @@ class TestFormatSelection(unittest.TestCase): self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) def test_format_selection_issue_10083(self): - # See https://github.com/rg3/youtube-dl/issues/10083 + # See https://github.com/ytdl-org/youtube-dl/issues/10083 formats = [ {'format_id': 'regular', 'height': 360, 'url': TEST_URL}, {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL}, @@ -853,7 +853,7 @@ class TestYoutubeDL(unittest.TestCase): self.assertEqual(result, [2, 3, 4]) def test_urlopen_no_file_protocol(self): - # see https://github.com/rg3/youtube-dl/issues/8227 + # see https://github.com/ytdl-org/youtube-dl/issues/8227 ydl = YDL() self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd') diff --git a/test/test_all_urls.py b/test/test_all_urls.py index cd1cd4b24..465ce0050 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -110,7 +110,7 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user']) self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review']) - # https://github.com/rg3/youtube-dl/issues/1930 + # https://github.com/ytdl-org/youtube-dl/issues/1930 def test_soundcloud_not_matching_sets(self): self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set']) @@ -119,12 +119,12 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr']) def test_pbs(self): - # https://github.com/rg3/youtube-dl/issues/2350 + # https://github.com/ytdl-org/youtube-dl/issues/2350 self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs']) self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs']) def test_yahoo_https(self): - # https://github.com/rg3/youtube-dl/issues/2701 + # https://github.com/ytdl-org/youtube-dl/issues/2701 self.assertMatch( 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', ['Yahoo']) diff --git a/youtube-dl.plugin.zsh b/youtube-dl.plugin.zsh index 4edab5214..17ab1341a 100644 --- a/youtube-dl.plugin.zsh +++ b/youtube-dl.plugin.zsh @@ -7,7 +7,7 @@ # https://github.com/zsh-users/antigen # Install youtube-dl: -# antigen bundle rg3/youtube-dl +# antigen bundle ytdl-org/youtube-dl # Bundles installed by antigen are available for use immediately. # Update youtube-dl (and all other antigen bundles): diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index bc9fc270c..3b92acd97 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -889,7 +889,7 @@ class YoutubeDL(object): # url_transparent. In such cases outer metadata (from ie_result) # should be propagated to inner one (info). For this to happen # _type of info should be overridden with url_transparent. This - # fixes issue from https://github.com/rg3/youtube-dl/pull/11163. + # fixes issue from https://github.com/ytdl-org/youtube-dl/pull/11163. if new_result.get('_type') == 'url': new_result['_type'] = 'url_transparent' @@ -1606,7 +1606,7 @@ class YoutubeDL(object): # by extractor are incomplete or not (i.e. whether extractor provides only # video-only or audio-only formats) for proper formats selection for # extractors with such incomplete formats (see - # https://github.com/rg3/youtube-dl/pull/5556). + # https://github.com/ytdl-org/youtube-dl/pull/5556). # Since formats may be filtered during format selection and may not match # the original formats the results may be incorrect. Thus original formats # or pre-calculated metrics should be passed to format selection routines @@ -1614,7 +1614,7 @@ class YoutubeDL(object): # We will pass a context object containing all necessary additional data # instead of just formats. # This fixes incorrect format selection issue (see - # https://github.com/rg3/youtube-dl/issues/10083). + # https://github.com/ytdl-org/youtube-dl/issues/10083). incomplete_formats = ( # All formats are video-only or all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or @@ -1810,7 +1810,7 @@ class YoutubeDL(object): if sub_info.get('data') is not None: try: # Use newline='' to prevent conversion of newline characters - # See https://github.com/rg3/youtube-dl/issues/10268 + # See https://github.com/ytdl-org/youtube-dl/issues/10268 with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile: subfile.write(sub_info['data']) except (OSError, IOError): @@ -2229,7 +2229,7 @@ class YoutubeDL(object): return if type('') is not compat_str: - # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326) + # Python 2.6 on SLES11 SP1 (https://github.com/ytdl-org/youtube-dl/issues/3326) self.report_warning( 'Your Python is broken! Update to a newer and supported version') @@ -2323,7 +2323,7 @@ class YoutubeDL(object): proxies = {'http': opts_proxy, 'https': opts_proxy} else: proxies = compat_urllib_request.getproxies() - # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) + # Set HTTPS proxy to HTTP one if given (https://github.com/ytdl-org/youtube-dl/issues/805) if 'http' in proxies and 'https' not in proxies: proxies['https'] = proxies['http'] proxy_handler = PerRequestProxyHandler(proxies) @@ -2336,7 +2336,7 @@ class YoutubeDL(object): # When passing our own FileHandler instance, build_opener won't add the # default FileHandler and allows us to disable the file protocol, which # can be used for malicious purposes (see - # https://github.com/rg3/youtube-dl/issues/8227) + # https://github.com/ytdl-org/youtube-dl/issues/8227) file_handler = compat_urllib_request.FileHandler() def file_open(*args, **kwargs): @@ -2348,7 +2348,7 @@ class YoutubeDL(object): # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play - # (See https://github.com/rg3/youtube-dl/issues/1309 for details) + # (See https://github.com/ytdl-org/youtube-dl/issues/1309 for details) opener.addheaders = [] self._opener = opener diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index ba435ea42..94788d936 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -48,7 +48,7 @@ from .YoutubeDL import YoutubeDL def _real_main(argv=None): # Compatibility fixes for Windows if sys.platform == 'win32': - # https://github.com/rg3/youtube-dl/issues/820 + # https://github.com/ytdl-org/youtube-dl/issues/820 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None) workaround_optparse_bug9161() diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index b2fe62f12..7992a23ca 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2364,7 +2364,7 @@ except ImportError: # Python 2 # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus # implementations from cpython 3.4.3's stdlib. Python 2's version - # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244) + # is apparently broken (see https://github.com/ytdl-org/youtube-dl/pull/6244) def compat_urllib_parse_unquote_to_bytes(string): """unquote_to_bytes('abc%20def') -> b'abc def'.""" @@ -2828,7 +2828,7 @@ else: compat_socket_create_connection = socket.create_connection -# Fix https://github.com/rg3/youtube-dl/issues/4223 +# Fix https://github.com/ytdl-org/youtube-dl/issues/4223 # See http://bugs.python.org/issue9161 for what is broken def workaround_optparse_bug9161(): op = optparse.OptionParser() @@ -2953,7 +2953,7 @@ if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, # PyPy2 prior to version 5.4.0 expects byte strings as Windows function # names, see the original PyPy issue [1] and the youtube-dl one [2]. # 1. https://bitbucket.org/pypy/pypy/issues/2360/windows-ctypescdll-typeerror-function-name - # 2. https://github.com/rg3/youtube-dl/pull/4392 + # 2. https://github.com/ytdl-org/youtube-dl/pull/4392 def compat_ctypes_WINFUNCTYPE(*args, **kwargs): real = ctypes.WINFUNCTYPE(*args, **kwargs) diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 22e6093b3..5f73f7f0f 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -239,7 +239,7 @@ class FFmpegFD(ExternalFD): # setting -seekable prevents ffmpeg from guessing if the server # supports seeking(by adding the header `Range: bytes=0-`), which # can cause problems in some cases - # https://github.com/rg3/youtube-dl/issues/11800#issuecomment-275037127 + # https://github.com/ytdl-org/youtube-dl/issues/11800#issuecomment-275037127 # http://trac.ffmpeg.org/ticket/6125#comment:10 args += ['-seekable', '1' if seekable else '0'] @@ -334,7 +334,7 @@ class FFmpegFD(ExternalFD): # mp4 file couldn't be played, but if we ask ffmpeg to quit it # produces a file that is playable (this is mostly useful for live # streams). Note that Windows is not affected and produces playable - # files (see https://github.com/rg3/youtube-dl/issues/8300). + # files (see https://github.com/ytdl-org/youtube-dl/issues/8300). if sys.platform != 'win32': proc.communicate(b'q') raise diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 15e71be9a..9b15a0e15 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -324,8 +324,8 @@ class F4mFD(FragmentFD): urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url)) man_url = urlh.geturl() # Some manifests may be malformed, e.g. prosiebensat1 generated manifests - # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244 - # and https://github.com/rg3/youtube-dl/issues/7823) + # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244 + # and https://github.com/ytdl-org/youtube-dl/issues/7823) manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip() doc = compat_etree_fromstring(manifest) @@ -409,7 +409,7 @@ class F4mFD(FragmentFD): # In tests, segments may be truncated, and thus # FlvReader may not be able to parse the whole # chunk. If so, write the segment as is - # See https://github.com/rg3/youtube-dl/issues/9214 + # See https://github.com/ytdl-org/youtube-dl/issues/9214 dest_stream.write(down_data) break raise diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 4def8e2d5..419e73576 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -152,8 +152,8 @@ class HlsFD(FragmentFD): except compat_urllib_error.HTTPError as err: # Unavailable (possibly temporary) fragments may be served. # First we try to retry then either skip or abort. - # See https://github.com/rg3/youtube-dl/issues/10165, - # https://github.com/rg3/youtube-dl/issues/10448). + # See https://github.com/ytdl-org/youtube-dl/issues/10165, + # https://github.com/ytdl-org/youtube-dl/issues/10448). count += 1 if count <= fragment_retries: self.report_retry_fragment(err, frag_index, count, fragment_retries) diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 5b1e96013..08670ee3c 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -111,7 +111,7 @@ class HttpFD(FileDownloader): # to match the value of requested Range HTTP header. This is due to a webservers # that don't support resuming and serve a whole file with no Content-Range # set in response despite of requested Range (see - # https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799) + # https://github.com/ytdl-org/youtube-dl/issues/6057#issuecomment-126129799) if has_range: content_range = ctx.data.headers.get('Content-Range') if content_range: diff --git a/youtube_dl/extractor/arkena.py b/youtube_dl/extractor/arkena.py index 4495ddbb0..854f58767 100644 --- a/youtube_dl/extractor/arkena.py +++ b/youtube_dl/extractor/arkena.py @@ -103,7 +103,7 @@ class ArkenaIE(InfoExtractor): f_url, video_id, mpd_id=kind, fatal=False)) elif kind == 'silverlight': # TODO: process when ism is supported (see - # https://github.com/rg3/youtube-dl/issues/8118) + # https://github.com/ytdl-org/youtube-dl/issues/8118) continue else: tbr = float_or_none(f.get('Bitrate'), 1000) diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index 34f1b3d83..4400ff9c1 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -23,7 +23,7 @@ class BambuserIE(InfoExtractor): _TEST = { 'url': 'http://bambuser.com/v/4050584', - # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388 + # MD5 seems to be flaky, see https://travis-ci.org/ytdl-org/youtube-dl/jobs/14051016#L388 # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641', 'info_dict': { 'id': '4050584', @@ -38,7 +38,7 @@ class BambuserIE(InfoExtractor): }, 'params': { # It doesn't respect the 'Range' header, it would download the whole video - # caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59 + # caused the travis builds to fail: https://travis-ci.org/ytdl-org/youtube-dl/jobs/14493845#L59 'skip_download': True, }, } diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index d479d2577..e76507951 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -208,7 +208,7 @@ class BBCCoUkIE(InfoExtractor): }, 'skip': 'Now it\'s really geo-restricted', }, { - # compact player (https://github.com/rg3/youtube-dl/issues/8147) + # compact player (https://github.com/ytdl-org/youtube-dl/issues/8147) 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', 'info_dict': { 'id': 'p028bfkj', diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 465ae396e..c0345e2c3 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -126,7 +126,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'playlist_mincount': 7, }, { - # playlist with 'playlistTab' (https://github.com/rg3/youtube-dl/issues/9965) + # playlist with 'playlistTab' (https://github.com/ytdl-org/youtube-dl/issues/9965) 'url': 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=AQ%7E%7E,AAABXlLMdok%7E,NJ4EoMlZ4rZdx9eU1rkMVd8EaYPBBUlg', 'info_dict': { 'id': '1522758701001', @@ -155,10 +155,10 @@ class BrightcoveLegacyIE(InfoExtractor): {params} """ - # Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553 + # Fix up some stupid HTML, see https://github.com/ytdl-org/youtube-dl/issues/1553 object_str = re.sub(r'(', lambda m: m.group(1) + '/>', object_str) - # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608 + # Fix up some stupid XML, see https://github.com/ytdl-org/youtube-dl/issues/1608 object_str = object_str.replace('<--', ' %s' % ( - srt_subtitles_timecode(start), - srt_subtitles_timecode(end)), - text, - os.linesep, - )) + alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0) + ssa += os.linesep + 'Dialogue:Marked=0,%s,%s,Default,%s%s' % ( + self._ass_subtitles_timecode(start), + self._ass_subtitles_timecode(end), + '{\\a%d}' % alignment if alignment != 2 else '', + text.replace('\n', '\\N').replace('', '{\\i1}').replace('', '{\\i0}')) if sub_lang == 'vostf': sub_lang = 'fr' @@ -91,8 +106,8 @@ class ADNIE(InfoExtractor): 'ext': 'json', 'data': json.dumps(sub), }, { - 'ext': 'srt', - 'data': srt, + 'ext': 'ssa', + 'data': ssa, }]) return subtitles @@ -100,7 +115,15 @@ class ADNIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) player_config = self._parse_json(self._search_regex( - r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id) + r'playerConfig\s*=\s*({.+});', webpage, + 'player config', default='{}'), video_id, fatal=False) + if not player_config: + config_url = urljoin(self._BASE_URL, self._search_regex( + r'(?:id="player"|class="[^"]*adn-player-container[^"]*")[^>]+data-url="([^"]+)"', + webpage, 'config url')) + player_config = self._download_json( + config_url, video_id, + 'Downloading player config JSON metadata')['player'] video_info = {} video_info_str = self._search_regex( @@ -129,12 +152,15 @@ class ADNIE(InfoExtractor): encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n)) authorization = base64.b64encode(encrypted_message).decode() links_data = self._download_json( - urljoin(self._BASE_URL, links_url), video_id, headers={ + urljoin(self._BASE_URL, links_url), video_id, + 'Downloading links JSON metadata', headers={ 'Authorization': 'Bearer ' + authorization, }) links = links_data.get('links') or {} metas = metas or links_data.get('meta') or {} - sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token + sub_path = sub_path or links_data.get('subtitles') or \ + 'index.php?option=com_vodapi&task=subtitles.getJSON&format=json&id=' + video_id + sub_path += '&token=' + token error = links_data.get('error') title = metas.get('title') or video_info['title'] @@ -142,9 +168,11 @@ class ADNIE(InfoExtractor): for format_id, qualities in links.items(): if not isinstance(qualities, dict): continue - for load_balancer_url in qualities.values(): + for quality, load_balancer_url in qualities.items(): load_balancer_data = self._download_json( - load_balancer_url, video_id, fatal=False) or {} + load_balancer_url, video_id, + 'Downloading %s %s JSON metadata' % (format_id, quality), + fatal=False) or {} m3u8_url = load_balancer_data.get('location') if not m3u8_url: continue From 2bbde1d09afb2225fb7bd245bcf77a0715a58f29 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 4 Apr 2019 17:59:20 +0100 Subject: [PATCH 266/362] [adn] fix subtitle compatibility with ffmpeg --- youtube_dl/extractor/adn.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/adn.py b/youtube_dl/extractor/adn.py index 2eb4d1dc7..1e04a55a6 100644 --- a/youtube_dl/extractor/adn.py +++ b/youtube_dl/extractor/adn.py @@ -81,10 +81,10 @@ class ADNIE(InfoExtractor): ssa = '''[Script Info] ScriptType:V4.00 [V4 Styles] -Format:Name,Fontname,Fontsize,PrimaryColour,Bold,BorderStyle,Outline,Alignment,MarginL,MarginR,MarginV -Style:Default,Arial,18,16777215,-1,1,1,2,20,20,20 +Format: Name,Fontname,Fontsize,PrimaryColour,SecondaryColour,TertiaryColour,BackColour,Bold,Italic,BorderStyle,Outline,Shadow,Alignment,MarginL,MarginR,MarginV,AlphaLevel,Encoding +Style: Default,Arial,18,16777215,16777215,16777215,0,-1,0,1,1,0,2,20,20,20,0,0 [Events] -Format:Marked,Start,End,Style,Text''' +Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text''' for current in sub: start, end, text, line_align, position_align = ( float_or_none(current.get('startTime')), @@ -94,7 +94,7 @@ Format:Marked,Start,End,Style,Text''' if start is None or end is None or text is None: continue alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0) - ssa += os.linesep + 'Dialogue:Marked=0,%s,%s,Default,%s%s' % ( + ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % ( self._ass_subtitles_timecode(start), self._ass_subtitles_timecode(end), '{\\a%d}' % alignment if alignment != 2 else '', From 69e6efac1669da68c0746419657160311cde2671 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 5 Apr 2019 08:26:04 +0100 Subject: [PATCH 267/362] [teamcoco] fix extraction and add suport for subdomains(closes #17099)(closes #20339) --- youtube_dl/extractor/teamcoco.py | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 73469cc5d..7640cf00a 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -16,7 +16,7 @@ from ..utils import ( class TeamcocoIE(TurnerBaseIE): - _VALID_URL = r'https?://teamcoco\.com/(?P([^/]+/)*[^/?#]+)' + _VALID_URL = r'https?://(?:\w+\.)?teamcoco\.com/(?P([^/]+/)*[^/?#]+)' _TESTS = [ { 'url': 'http://teamcoco.com/video/mary-kay-remote', @@ -79,15 +79,20 @@ class TeamcocoIE(TurnerBaseIE): }, { 'url': 'http://teamcoco.com/israel/conan-hits-the-streets-beaches-of-tel-aviv', 'only_matching': True, + }, { + 'url': 'https://conan25.teamcoco.com/video/ice-cube-kevin-hart-conan-share-lyft', + 'only_matching': True, } ] def _graphql_call(self, query_template, object_type, object_id): find_object = 'find' + object_type return self._download_json( - 'http://teamcoco.com/graphql/', object_id, data=json.dumps({ + 'https://teamcoco.com/graphql', object_id, data=json.dumps({ 'query': query_template % (find_object, object_id) - }))['data'][find_object] + }).encode(), headers={ + 'Content-Type': 'application/json', + })['data'][find_object] def _real_extract(self, url): display_id = self._match_id(url) @@ -145,7 +150,12 @@ class TeamcocoIE(TurnerBaseIE): 'accessTokenType': 'jws', })) else: - video_sources = self._graphql_call('''{ + d = self._download_json( + 'https://teamcoco.com/_truman/d/' + video_id, + video_id, fatal=False) or {} + video_sources = d.get('meta') or {} + if not video_sources: + video_sources = self._graphql_call('''{ %s(id: "%s") { src } From afb74964162eaee64c5c9b72990837daae945fec Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 5 Apr 2019 11:45:49 +0100 Subject: [PATCH 268/362] [adultswim] fix extraction(closes #18025) --- youtube_dl/extractor/adultswim.py | 194 ++++++++++++++++++------------ 1 file changed, 118 insertions(+), 76 deletions(-) diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 88c96a950..8d1d9ac7d 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -1,13 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .turner import TurnerBaseIE from ..utils import ( + determine_ext, + float_or_none, int_or_none, + mimetype2ext, + parse_age_limit, + parse_iso8601, strip_or_none, - url_or_none, + try_get, ) @@ -21,8 +27,8 @@ class AdultSwimIE(TurnerBaseIE): 'ext': 'mp4', 'title': 'Rick and Morty - Pilot', 'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.', - 'timestamp': 1493267400, - 'upload_date': '20170427', + 'timestamp': 1543294800, + 'upload_date': '20181127', }, 'params': { # m3u8 download @@ -43,6 +49,7 @@ class AdultSwimIE(TurnerBaseIE): # m3u8 download 'skip_download': True, }, + 'skip': '404 Not Found', }, { 'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/', 'info_dict': { @@ -61,9 +68,9 @@ class AdultSwimIE(TurnerBaseIE): }, { 'url': 'http://www.adultswim.com/videos/attack-on-titan', 'info_dict': { - 'id': 'b7A69dzfRzuaXIECdxW8XQ', + 'id': 'attack-on-titan', 'title': 'Attack on Titan', - 'description': 'md5:6c8e003ea0777b47013e894767f5e114', + 'description': 'md5:41caa9416906d90711e31dc00cb7db7e', }, 'playlist_mincount': 12, }, { @@ -78,83 +85,118 @@ class AdultSwimIE(TurnerBaseIE): # m3u8 download 'skip_download': True, }, + 'skip': '404 Not Found', }] def _real_extract(self, url): show_path, episode_path = re.match(self._VALID_URL, url).groups() display_id = episode_path or show_path - webpage = self._download_webpage(url, display_id) - initial_data = self._parse_json(self._search_regex( - r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});', - webpage, 'initial data'), display_id) - - is_stream = show_path == 'streams' - if is_stream: - if not episode_path: - episode_path = 'live-stream' - - video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path) - video_id = video_data.get('stream') - - if not video_id: - entries = [] - for episode in video_data.get('archiveEpisodes', []): - episode_url = url_or_none(episode.get('url')) - if not episode_url: - continue - entries.append(self.url_result( - episode_url, 'AdultSwim', episode.get('id'))) - return self.playlist_result( - entries, video_data.get('id'), video_data.get('title'), - strip_or_none(video_data.get('description'))) + query = '''query { + getShowBySlug(slug:"%s") { + %%s + } +}''' % show_path + if episode_path: + query = query % '''title + getVideoBySlug(slug:"%s") { + _id + auth + description + duration + episodeNumber + launchDate + mediaID + seasonNumber + poster + title + tvRating + }''' % episode_path + ['getVideoBySlug'] else: - show_data = initial_data['show'] + query = query % '''metaDescription + title + videos(first:1000,sort:["episode_number"]) { + edges { + node { + _id + slug + } + } + }''' + show_data = self._download_json( + 'https://www.adultswim.com/api/search', display_id, + data=json.dumps({'query': query}).encode(), + headers={'Content-Type': 'application/json'})['data']['getShowBySlug'] + if episode_path: + video_data = show_data['getVideoBySlug'] + video_id = video_data['_id'] + episode_title = title = video_data['title'] + series = show_data.get('title') + if series: + title = '%s - %s' % (series, title) + info = { + 'id': video_id, + 'title': title, + 'description': strip_or_none(video_data.get('description')), + 'duration': float_or_none(video_data.get('duration')), + 'formats': [], + 'subtitles': {}, + 'age_limit': parse_age_limit(video_data.get('tvRating')), + 'thumbnail': video_data.get('poster'), + 'timestamp': parse_iso8601(video_data.get('launchDate')), + 'series': series, + 'season_number': int_or_none(video_data.get('seasonNumber')), + 'episode': episode_title, + 'episode_number': int_or_none(video_data.get('episodeNumber')), + } - if not episode_path: - entries = [] - for video in show_data.get('videos', []): - slug = video.get('slug') - if not slug: + auth = video_data.get('auth') + media_id = video_data.get('mediaID') + if media_id: + info.update(self._extract_ngtv_info(media_id, { + # CDN_TOKEN_APP_ID from: + # https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js + 'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE', + }, { + 'url': url, + 'site_name': 'AdultSwim', + 'auth_required': auth, + })) + + if not auth: + extract_data = self._download_json( + 'https://www.adultswim.com/api/shows/v1/videos/' + video_id, + video_id, query={'fields': 'stream'}, fatal=False) or {} + assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or [] + for asset in assets: + asset_url = asset.get('url') + if not asset_url: continue - entries.append(self.url_result( - 'http://adultswim.com/videos/%s/%s' % (show_path, slug), - 'AdultSwim', video.get('id'))) - return self.playlist_result( - entries, show_data.get('id'), show_data.get('title'), - strip_or_none(show_data.get('metadata', {}).get('description'))) + ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type'))) + if ext == 'm3u8': + info['formats'].extend(self._extract_m3u8_formats( + asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + elif ext == 'f4m': + continue + # info['formats'].extend(self._extract_f4m_formats( + # asset_url, video_id, f4m_id='hds', fatal=False)) + elif ext in ('scc', 'ttml', 'vtt'): + info['subtitles'].setdefault('en', []).append({ + 'url': asset_url, + }) + self._sort_formats(info['formats']) - video_data = show_data['sluggedVideo'] - video_id = video_data['id'] - - info = self._extract_cvp_info( - 'http://www.adultswim.com/videos/api/v0/assets?platform=desktop&id=' + video_id, - video_id, { - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big', - 'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do', - }, - }, { - 'url': url, - 'site_name': 'AdultSwim', - 'auth_required': video_data.get('auth'), - }) - - info.update({ - 'id': video_id, - 'display_id': display_id, - 'description': info.get('description') or strip_or_none(video_data.get('description')), - }) - if not is_stream: - info.update({ - 'duration': info.get('duration') or int_or_none(video_data.get('duration')), - 'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')), - 'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')), - 'episode': info['title'], - 'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')), - }) - - info['series'] = video_data.get('collection_title') or info.get('series') - if info['series'] and info['series'] != info['title']: - info['title'] = '%s - %s' % (info['series'], info['title']) - - return info + return info + else: + entries = [] + for edge in show_data.get('videos', {}).get('edges', []): + video = edge.get('node') or {} + slug = video.get('slug') + if not slug: + continue + entries.append(self.url_result( + 'http://adultswim.com/videos/%s/%s' % (show_path, slug), + 'AdultSwim', video.get('_id'))) + return self.playlist_result( + entries, show_path, show_data.get('title'), + strip_or_none(show_data.get('metaDescription'))) From 19041a38773b1022480d50587da7db4a0e6fa869 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 5 Apr 2019 16:18:57 +0100 Subject: [PATCH 269/362] [youtube] extract srv[1-3] subtitle formats(#20566) --- youtube_dl/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 886fc1591..132572c88 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -484,7 +484,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # RTMP (unnamed) '_rtmp': {'protocol': 'rtmp'}, } - _SUBTITLE_FORMATS = ('ttml', 'vtt') + _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt') _GEO_BYPASS = False From a7978f8e2acc8c34989b7f289a16180e71902193 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 5 Apr 2019 18:08:43 +0100 Subject: [PATCH 270/362] [hbo] fix extraction and extract subtitles(closes #14629)(closes #13709) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/hbo.py | 102 +++++++++++------------------ 2 files changed, 39 insertions(+), 68 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 254dbc946..c1c5d1953 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -441,10 +441,7 @@ from .goshgay import GoshgayIE from .gputechconf import GPUTechConfIE from .groupon import GrouponIE from .hark import HarkIE -from .hbo import ( - HBOIE, - HBOEpisodeIE, -) +from .hbo import HBOIE from .hearthisat import HearThisAtIE from .heise import HeiseIE from .hellporno import HellPornoIE diff --git a/youtube_dl/extractor/hbo.py b/youtube_dl/extractor/hbo.py index 859ad5429..44440233d 100644 --- a/youtube_dl/extractor/hbo.py +++ b/youtube_dl/extractor/hbo.py @@ -4,16 +4,28 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( xpath_text, xpath_element, int_or_none, parse_duration, + urljoin, ) -class HBOBaseIE(InfoExtractor): +class HBOIE(InfoExtractor): + IE_NAME = 'hbo' + _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?:video|embed)(?:/[^/]+)*/(?P[^/?#]+)' + _TEST = { + 'url': 'https://www.hbo.com/video/game-of-thrones/seasons/season-8/videos/trailer', + 'md5': '8126210656f433c452a21367f9ad85b3', + 'info_dict': { + 'id': '22113301', + 'ext': 'mp4', + 'title': 'Game of Thrones - Trailer', + }, + 'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'], + } _FORMATS_INFO = { 'pro7': { 'width': 1280, @@ -53,10 +65,17 @@ class HBOBaseIE(InfoExtractor): }, } - def _extract_from_id(self, video_id): - video_data = self._download_xml( - 'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id) - title = xpath_text(video_data, 'title', 'title', True) + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + location_path = self._parse_json(self._html_search_regex( + r'data-state="({.+?})"', webpage, 'state'), display_id)['video']['locationUrl'] + video_data = self._download_xml(urljoin(url, location_path), display_id) + video_id = xpath_text(video_data, 'id', fatal=True) + episode_title = title = xpath_text(video_data, 'title', fatal=True) + series = xpath_text(video_data, 'program') + if series: + title = '%s - %s' % (series, title) formats = [] for source in xpath_element(video_data, 'videos', 'sources', True): @@ -128,68 +147,23 @@ class HBOBaseIE(InfoExtractor): 'width': width, }) + subtitles = None + caption_url = xpath_text(video_data, 'captionUrl') + if caption_url: + subtitles = { + 'en': [{ + 'url': caption_url, + 'ext': 'ttml' + }], + } + return { 'id': video_id, 'title': title, 'duration': parse_duration(xpath_text(video_data, 'duration/tv14')), + 'series': series, + 'episode': episode_title, 'formats': formats, 'thumbnails': thumbnails, + 'subtitles': subtitles, } - - -class HBOIE(HBOBaseIE): - IE_NAME = 'hbo' - _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P[0-9]+)' - _TEST = { - 'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839', - 'md5': '2c6a6bc1222c7e91cb3334dad1746e5a', - 'info_dict': { - 'id': '1437839', - 'ext': 'mp4', - 'title': 'Ep. 64 Clip: Encryption', - 'thumbnail': r're:https?://.*\.jpg$', - 'duration': 1072, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - return self._extract_from_id(video_id) - - -class HBOEpisodeIE(HBOBaseIE): - IE_NAME = 'hbo:episode' - _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?P(?!video)(?:(?:[^/]+/)+video|watch-free-episodes)/(?P[0-9a-z-]+))(?:\.html)?' - - _TESTS = [{ - 'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true', - 'md5': '61ead79b9c0dfa8d3d4b07ef4ac556fb', - 'info_dict': { - 'id': '1439518', - 'display_id': 'ep-52-inside-the-episode', - 'ext': 'mp4', - 'title': 'Ep. 52: Inside the Episode', - 'thumbnail': r're:https?://.*\.jpg$', - 'duration': 240, - }, - }, { - 'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true', - 'only_matching': True, - }, { - 'url': 'http://www.hbo.com/watch-free-episodes/last-week-tonight-with-john-oliver', - 'only_matching': True, - }] - - def _real_extract(self, url): - path, display_id = re.match(self._VALID_URL, url).groups() - - content = self._download_json( - 'http://www.hbo.com/api/content/' + path, display_id)['content'] - - video_id = compat_str((content.get('parsed', {}).get( - 'common:FullBleedVideo', {}) or content['selectedEpisode'])['videoId']) - - info_dict = self._extract_from_id(video_id) - info_dict['display_id'] = display_id - - return info_dict From 4810655cd65f9bdde1ad240adf7334828243fb0a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 5 Apr 2019 19:35:35 +0100 Subject: [PATCH 271/362] [bfi:player] Add new extractor(#19235) --- youtube_dl/extractor/bfi.py | 37 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 38 insertions(+) create mode 100644 youtube_dl/extractor/bfi.py diff --git a/youtube_dl/extractor/bfi.py b/youtube_dl/extractor/bfi.py new file mode 100644 index 000000000..60c8944b5 --- /dev/null +++ b/youtube_dl/extractor/bfi.py @@ -0,0 +1,37 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import extract_attributes + + +class BFIPlayerIE(InfoExtractor): + IE_NAME = 'bfi:player' + _VALID_URL = r'https?://player\.bfi\.org\.uk/[^/]+/film/watch-(?P[\w-]+)-online' + _TEST = { + 'url': 'https://player.bfi.org.uk/free/film/watch-computer-doctor-1974-online', + 'md5': 'e8783ebd8e061ec4bc6e9501ed547de8', + 'info_dict': { + 'id': 'htNnhlZjE60C9VySkQEIBtU-cNV1Xx63', + 'ext': 'mp4', + 'title': 'Computer Doctor', + 'description': 'md5:fb6c240d40c4dbe40428bdd62f78203b', + }, + 'skip': 'BFI Player films cannot be played outside of the UK', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + entries = [] + for player_el in re.findall(r'(?s)<[^>]+class="player"[^>]*>', webpage): + player_attr = extract_attributes(player_el) + ooyala_id = player_attr.get('data-video-id') + if not ooyala_id: + continue + entries.append(self.url_result( + 'ooyala:' + ooyala_id, 'Ooyala', + ooyala_id, player_attr.get('data-label'))) + return self.playlist_result(entries) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c1c5d1953..01119f2bb 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -107,6 +107,7 @@ from .behindkink import BehindKinkIE from .bellmedia import BellMediaIE from .beatport import BeatportIE from .bet import BetIE +from .bfi import BFIPlayerIE from .bigflix import BigflixIE from .bild import BildIE from .bilibili import ( From 9f182c23ba74f76ff716940b2a0568f428d6c2b9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 6 Apr 2019 09:22:25 +0100 Subject: [PATCH 272/362] [vrv] add basic support for individual movie links(#19229) --- youtube_dl/extractor/vrv.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 6c060ae76..c11da97de 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -150,9 +150,10 @@ class VRVIE(VRVBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - episode_path = self._get_cms_resource( - 'cms:/episodes/' + video_id, video_id) - video_data = self._call_cms(episode_path, video_id, 'video') + object_data = self._call_cms(self._get_cms_resource( + 'cms:/objects/' + video_id, video_id), video_id, 'object')['items'][0] + resource_path = object_data['__links__']['resource']['href'] + video_data = self._call_cms(resource_path, video_id, 'video') title = video_data['title'] streams_path = video_data['__links__'].get('streams', {}).get('href') From b9aad6c427ea083143d1e53c0f087ad508bd706a Mon Sep 17 00:00:00 2001 From: Jan Friesse Date: Sat, 9 Feb 2019 10:15:53 +0100 Subject: [PATCH 273/362] [dvtv] Fix extraction (closes #18514) --- youtube_dl/extractor/dvtv.py | 120 +++++++++++++++++++++-------------- 1 file changed, 73 insertions(+), 47 deletions(-) diff --git a/youtube_dl/extractor/dvtv.py b/youtube_dl/extractor/dvtv.py index 20996962a..bc68d07d1 100644 --- a/youtube_dl/extractor/dvtv.py +++ b/youtube_dl/extractor/dvtv.py @@ -10,7 +10,9 @@ from ..utils import ( int_or_none, js_to_json, mimetype2ext, + try_get, unescapeHTML, + parse_iso8601, ) @@ -28,6 +30,8 @@ class DVTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně', 'duration': 1484, + 'upload_date': '20141217', + 'timestamp': 1418792400, } }, { 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/', @@ -84,6 +88,8 @@ class DVTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta', 'duration': 1103, + 'upload_date': '20170511', + 'timestamp': 1494514200, }, 'params': { 'skip_download': True, @@ -91,43 +97,62 @@ class DVTVIE(InfoExtractor): }, { 'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/', 'only_matching': True, + }, { + # Test live stream video (liveStarter) parsing + 'url': 'https://video.aktualne.cz/dvtv/zive-mistryne-sveta-eva-samkova-po-navratu-ze-sampionatu/r~182654c2288811e990fd0cc47ab5f122/', + 'md5': '2e552e483f2414851ca50467054f9d5d', + 'info_dict': { + 'id': '8d116360288011e98c840cc47ab5f122', + 'ext': 'mp4', + 'title': 'Živě: Mistryně světa Eva Samková po návratu ze šampionátu', + 'upload_date': '20190204', + 'timestamp': 1549289591, + }, + 'params': { + # Video content is no longer available + 'skip_download': True, + }, }] - def _parse_video_metadata(self, js, video_id, live_js=None): + def _parse_video_metadata(self, js, video_id, timestamp): + data = self._parse_json(js, video_id, transform_source=js_to_json) - if live_js: - data.update(self._parse_json( - live_js, video_id, transform_source=js_to_json)) + + live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict) + if live_starter: + data.update(live_starter) title = unescapeHTML(data['title']) formats = [] - for video in data['sources']: - video_url = video.get('file') - if not video_url: - continue - video_type = video.get('type') - ext = determine_ext(video_url, mimetype2ext(video_type)) - if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - elif video_type == 'application/dash+xml' or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - video_url, video_id, mpd_id='dash', fatal=False)) - else: - label = video.get('label') - height = self._search_regex( - r'^(\d+)[pP]', label or '', 'height', default=None) - format_id = ['http'] - for f in (ext, label): - if f: - format_id.append(f) - formats.append({ - 'url': video_url, - 'format_id': '-'.join(format_id), - 'height': int_or_none(height), - }) + + for tracks in data.get('tracks', {}).values(): + for video in tracks: + video_url = video.get('src') + if not video_url: + continue + video_type = video.get('type') + ext = determine_ext(video_url, mimetype2ext(video_type)) + if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif video_type == 'application/dash+xml' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + video_url, video_id, mpd_id='dash', fatal=False)) + else: + label = video.get('label') + height = self._search_regex( + r'^(\d+)[pP]', label or '', 'height', default=None) + format_id = ['http'] + for f in (ext, label): + if f: + format_id.append(f) + formats.append({ + 'url': video_url, + 'format_id': '-'.join(format_id), + 'height': int_or_none(height), + }) self._sort_formats(formats) return { @@ -136,7 +161,7 @@ class DVTVIE(InfoExtractor): 'description': data.get('description'), 'thumbnail': data.get('image'), 'duration': int_or_none(data.get('duration')), - 'timestamp': int_or_none(data.get('pubtime')), + 'timestamp': int_or_none(timestamp), 'formats': formats } @@ -145,32 +170,33 @@ class DVTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - # live content - live_item = self._search_regex( - r'(?s)embedData[0-9a-f]{32}\.asset\.liveStarter\s*=\s*(\{.+?\});', - webpage, 'video', default=None) - - # single video - item = self._search_regex( - r'(?s)embedData[0-9a-f]{32}\[["\']asset["\']\]\s*=\s*(\{.+?\});', - webpage, 'video', default=None) - - if item: - return self._parse_video_metadata(item, video_id, live_item) + timestamp = parse_iso8601(self._html_search_meta( + 'article:published_time', webpage, 'published time', default=None)) # playlist items = re.findall( - r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);", + r"(?s)playlist\.push\(({.+?})\);", webpage) - if not items: - items = re.findall(r'(?s)var\s+asset\s*=\s*({.+?});\n', webpage) if items: return { '_type': 'playlist', 'id': video_id, 'title': self._og_search_title(webpage), - 'entries': [self._parse_video_metadata(i, video_id) for i in items] + 'entries': [self._parse_video_metadata(i, video_id, timestamp) for i in items] } + # single video + item = self._search_regex( + r'(?s)BBXPlayer.setup\((.+?)\);', + webpage, 'video', default=None) + + if item: + # remove function calls (ex. htmldeentitize) + # TODO this should be fixed in a general way in the js_to_json + item = re.sub(r'\w+?\((.+)\)', r'\1', item) + + if item: + return self._parse_video_metadata(item, video_id, timestamp) + raise ExtractorError('Could not find neither video nor playlist') From 19591facea9abe965a734224bea33948bb57b5f4 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 6 Apr 2019 16:29:30 +0100 Subject: [PATCH 274/362] [dvtv] remove unnecessary comments and spaces --- youtube_dl/extractor/dvtv.py | 32 +++++++------------------------- 1 file changed, 7 insertions(+), 25 deletions(-) diff --git a/youtube_dl/extractor/dvtv.py b/youtube_dl/extractor/dvtv.py index bc68d07d1..de7f6d670 100644 --- a/youtube_dl/extractor/dvtv.py +++ b/youtube_dl/extractor/dvtv.py @@ -19,9 +19,7 @@ from ..utils import ( class DVTVIE(InfoExtractor): IE_NAME = 'dvtv' IE_DESC = 'http://video.aktualne.cz/' - _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P[0-9a-f]{32})' - _TESTS = [{ 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/', 'md5': '67cb83e4a955d36e1b5d31993134a0c2', @@ -36,7 +34,7 @@ class DVTVIE(InfoExtractor): }, { 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/', 'info_dict': { - 'title': r're:^DVTV 16\. 12\. 2014: útok Talibanu, boj o kliniku, uprchlíci', + 'title': r'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci', 'id': '973eb3bc854e11e498be002590604f2e', }, 'playlist': [{ @@ -115,17 +113,14 @@ class DVTVIE(InfoExtractor): }] def _parse_video_metadata(self, js, video_id, timestamp): - data = self._parse_json(js, video_id, transform_source=js_to_json) + title = unescapeHTML(data['title']) live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict) if live_starter: data.update(live_starter) - title = unescapeHTML(data['title']) - formats = [] - for tracks in data.get('tracks', {}).values(): for video in tracks: video_url = video.get('src') @@ -167,36 +162,23 @@ class DVTVIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - timestamp = parse_iso8601(self._html_search_meta( 'article:published_time', webpage, 'published time', default=None)) - # playlist - items = re.findall( - r"(?s)playlist\.push\(({.+?})\);", - webpage) - + items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage) if items: - return { - '_type': 'playlist', - 'id': video_id, - 'title': self._og_search_title(webpage), - 'entries': [self._parse_video_metadata(i, video_id, timestamp) for i in items] - } + return self.playlist_result( + [self._parse_video_metadata(i, video_id, timestamp) for i in items], + video_id, self._html_search_meta('twitter:title', webpage)) - # single video item = self._search_regex( - r'(?s)BBXPlayer.setup\((.+?)\);', + r'(?s)BBXPlayer\.setup\((.+?)\);', webpage, 'video', default=None) - if item: # remove function calls (ex. htmldeentitize) # TODO this should be fixed in a general way in the js_to_json item = re.sub(r'\w+?\((.+)\)', r'\1', item) - - if item: return self._parse_video_metadata(item, video_id, timestamp) raise ExtractorError('Could not find neither video nor playlist') From c701472fc99c90f6ef4fdf0f0169a342f2e9e892 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 02:15:25 +0700 Subject: [PATCH 275/362] [platzi] Add extractor (closes #20562) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/platzi.py | 217 +++++++++++++++++++++++++++++ 2 files changed, 221 insertions(+) create mode 100644 youtube_dl/extractor/platzi.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 01119f2bb..41ab36213 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -868,6 +868,10 @@ from .picarto import ( from .piksel import PikselIE from .pinkbike import PinkbikeIE from .pladform import PladformIE +from .platzi import ( + PlatziIE, + PlatziCourseIE, +) from .playfm import PlayFMIE from .playplustv import PlayPlusTVIE from .plays import PlaysTVIE diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py new file mode 100644 index 000000000..557b2b5ad --- /dev/null +++ b/youtube_dl/extractor/platzi.py @@ -0,0 +1,217 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_str, +) +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + str_or_none, + try_get, + url_or_none, + urlencode_postdata, + urljoin, +) + + +class PlatziIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?: + platzi\.com/clases| # es version + courses\.platzi\.com/classes # en version + )/[^/]+/(?P\d+)-[^/?\#&]+ + ''' + _LOGIN_URL = 'https://platzi.com/login/' + _NETRC_MACHINE = 'platzi' + + _TESTS = [{ + 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/', + 'md5': '8f56448241005b561c10f11a595b37e3', + 'info_dict': { + 'id': '12074', + 'ext': 'mp4', + 'title': 'Creando nuestra primera página', + 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc', + 'duration': 420, + }, + 'skip': 'Requires platzi account credentials', + }, { + 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/', + 'info_dict': { + 'id': '13430', + 'ext': 'mp4', + 'title': 'Background', + 'description': 'md5:49c83c09404b15e6e71defaf87f6b305', + 'duration': 360, + }, + 'skip': 'Requires platzi account credentials', + 'params': { + 'skip_download': True, + }, + }] + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'email': username, + 'password': password, + }) + + urlh = self._request_webpage( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form), + headers={'Referer': self._LOGIN_URL}) + + # login succeeded + if 'platzi.com/login' not in compat_str(urlh.geturl()): + return + + login_error = self._webpage_read_content( + urlh, self._LOGIN_URL, None, 'Downloading login error page') + + login = self._parse_json( + self._search_regex( + r'login\s*=\s*({.+?})(?:\s*;|\s*[^/?\#&]+) + ''' + _TESTS = [{ + 'url': 'https://platzi.com/clases/next-js/', + 'info_dict': { + 'id': '1311', + 'title': 'Curso de Next.js', + }, + 'playlist_count': 22, + }, { + 'url': 'https://courses.platzi.com/classes/communication-codestream/', + 'info_dict': { + 'id': '1367', + 'title': 'Codestream Course', + }, + 'playlist_count': 14, + }] + + @classmethod + def suitable(cls, url): + return False if PlatziIE.suitable(url) else super(PlatziCourseIE, cls).suitable(url) + + def _real_extract(self, url): + course_name = self._match_id(url) + + webpage = self._download_webpage(url, course_name) + + props = self._parse_json( + self._search_regex(r'data\s*=\s*({.+?})\s*;', webpage, 'data'), + course_name)['initialProps'] + + entries = [] + for chapter_num, chapter in enumerate(props['concepts'], 1): + if not isinstance(chapter, dict): + continue + materials = chapter.get('materials') + if not materials or not isinstance(materials, list): + continue + chapter_title = chapter.get('title') + chapter_id = str_or_none(chapter.get('id')) + for material in materials: + if not isinstance(material, dict): + continue + if material.get('material_type') != 'video': + continue + video_url = urljoin(url, material.get('url')) + if not video_url: + continue + entries.append({ + '_type': 'url_transparent', + 'url': video_url, + 'title': str_or_none(material.get('name')), + 'id': str_or_none(material.get('id')), + 'ie_key': PlatziIE.ie_key(), + 'chapter': chapter_title, + 'chapter_number': chapter_num, + 'chapter_id': chapter_id, + }) + + course_id = compat_str(try_get(props, lambda x: x['course']['id'])) + course_title = try_get(props, lambda x: x['course']['name'], compat_str) + + return self.playlist_result(entries, course_id, course_title) From 059cd768b97188fbbf3262696e6511f3aa1795e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 02:17:54 +0700 Subject: [PATCH 276/362] [vk] Remove unused import --- youtube_dl/extractor/vk.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 39376e39f..1072550f1 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -6,10 +6,7 @@ import re import sys from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( clean_html, ExtractorError, From f412970164c349bea81bfd9d95e56fec7d16c8a1 Mon Sep 17 00:00:00 2001 From: Martin Michlmayr Date: Sun, 7 Apr 2019 02:28:31 +0700 Subject: [PATCH 277/362] [README.md] Fix lists formatting (closes #20558) Lists have to be separated from the previous paragraph by a blank line in certain variants of Markdown, otherwise they are not interpreted as lists. This change ensures that that the youtube-dl.1 man page, which is generated from README.md with the help of pandoc, is formatted correctly. --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index e476045b2..92c3a92a1 100644 --- a/README.md +++ b/README.md @@ -642,6 +642,7 @@ The simplest case is requesting a specific format, for example with `-f 22` you You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download the best quality format of a particular file extension served as a single file, e.g. `-f webm` will download the best quality format with the `webm` extension served as a single file. You can also use special names to select particular edge case formats: + - `best`: Select the best quality format represented by a single file with video and audio. - `worst`: Select the worst quality format represented by a single file with video and audio. - `bestvideo`: Select the best quality video-only format (e.g. DASH video). May not be available. @@ -658,6 +659,7 @@ If you want to download several formats of the same video use a comma as a separ You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals): + - `filesize`: The number of bytes, if known in advance - `width`: Width of the video, if known - `height`: Height of the video, if known @@ -668,6 +670,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, ` - `fps`: Frame rate Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields: + - `ext`: File extension - `acodec`: Name of the audio codec in use - `vcodec`: Name of the video codec in use From f4da80803619aea52bb116f6191f78e1bd77d2c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 02:58:40 +0700 Subject: [PATCH 278/362] [xvideos] Extract all thumbnails (closes #20432) --- youtube_dl/extractor/xvideos.py | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index ec2d913fc..166bcf443 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -57,10 +57,17 @@ class XVideosIE(InfoExtractor): webpage, 'title', default=None, group='title') or self._og_search_title(webpage) - thumbnail = self._search_regex( - (r'setThumbUrl\(\s*(["\'])(?P(?:(?!\1).)+)\1', - r'url_bigthumb=(?P.+?)&'), - webpage, 'thumbnail', fatal=False, group='thumbnail') + thumbnails = [] + for preference, thumbnail in enumerate(('', '169')): + thumbnail_url = self._search_regex( + r'setThumbUrl%s\(\s*(["\'])(?P(?:(?!\1).)+)\1' % thumbnail, + webpage, 'thumbnail', default=None, group='thumbnail') + if thumbnail_url: + thumbnails.append({ + 'url': thumbnail_url, + 'preference': preference, + }) + duration = int_or_none(self._og_search_property( 'duration', webpage, default=None)) or parse_duration( self._search_regex( @@ -98,6 +105,6 @@ class XVideosIE(InfoExtractor): 'formats': formats, 'title': title, 'duration': duration, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, 'age_limit': 18, } From 8410653f24ae73e4bc52c11bc0ec595e42567038 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 03:18:10 +0700 Subject: [PATCH 279/362] [ruutu] Add support for audio podcasts (closes #20473, closes #20545) --- youtube_dl/extractor/ruutu.py | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index f530f0083..f05401b36 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -59,6 +59,20 @@ class RuutuIE(InfoExtractor): 'url': 'http://www.ruutu.fi/video/3193728', 'only_matching': True, }, + { + # audio podcast + 'url': 'https://www.supla.fi/supla/3382410', + 'md5': 'b9d7155fed37b2ebf6021d74c4b8e908', + 'info_dict': { + 'id': '3382410', + 'ext': 'mp3', + 'title': 'Mikä ihmeen poltergeist?', + 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52', + 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 0, + }, + 'expected_warnings': ['HTTP Error 502: Bad Gateway'], + } ] def _real_extract(self, url): @@ -94,6 +108,12 @@ class RuutuIE(InfoExtractor): continue formats.extend(self._extract_mpd_formats( video_url, video_id, mpd_id='dash', fatal=False)) + elif ext == 'mp3' or child.tag == 'AudioMediaFile': + formats.append({ + 'format_id': 'audio', + 'url': video_url, + 'vcodec': 'none', + }) else: proto = compat_urllib_parse_urlparse(video_url).scheme if not child.tag.startswith('HTTP') and proto != 'rtmp': From aa5338118e77380c753b397c6f544fcfdef1cb22 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 04:16:45 +0700 Subject: [PATCH 280/362] [ChangeLog] Actualize [ci skip] --- ChangeLog | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/ChangeLog b/ChangeLog index 3a0b6634f..41adb4204 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,29 @@ +version + +Core ++ [downloader/external] Pass rtmp_conn to ffmpeg + +Extractors ++ [ruutu] Add support for audio podcasts (#20473, #20545) ++ [xvideos] Extract all thumbnails (#20432) ++ [platzi] Add support for platzi.com (#20562) +* [dvtv] Fix extraction (#18514, #19174) ++ [vrv] Add basic support for individual movie links (#19229) ++ [bfi:player] Add support for player.bfi.org.uk (#19235) +* [hbo] Fix extraction and extract subtitles (#14629, #13709) +* [youtube] Extract srv[1-3] subtitle formats (#20566) +* [adultswim] Fix extraction (#18025) +* [teamcoco] Fix extraction and add suport for subdomains (#17099, #20339) +* [adn] Fix subtitle compatibility with ffmpeg +* [adn] Fix extraction and add support for positioning styles (#20549) +* [vk] Use unique video id (#17848) +* [newstube] Fix extraction +* [rtl2] Actualize extraction ++ [adobeconnect] Add support for adobeconnect.com (#20283) ++ [gaia] Add support for authentication (#14605) ++ [mediasite] Add support for dashed ids and named catalogs (#20531) + + version 2019.04.01 Core From a46d9e5b41bcfdf23038fa9b36aec5d4ba9c6de0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 04:19:46 +0700 Subject: [PATCH 281/362] release 2019.04.07 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 6 +++++- youtube_dl/version.py | 2 +- 4 files changed, 10 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index cc68279d0..5469c73cf 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.04.01*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.04.01** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.04.07*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.04.07** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/ytdl-org/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/ytdl-org/youtube-dl#faq) and [BUGS](https://github.com/ytdl-org/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.04.01 +[debug] youtube-dl version 2019.04.07 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 41adb4204..421f247fd 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.04.07 Core + [downloader/external] Pass rtmp_conn to ffmpeg diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 12df319eb..df272c479 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -28,6 +28,7 @@ - **acast:channel** - **AddAnime** - **ADN**: Anime Digital Network + - **AdobeConnect** - **AdobeTV** - **AdobeTVChannel** - **AdobeTVShow** @@ -101,6 +102,7 @@ - **Bellator** - **BellMedia** - **Bet** + - **bfi:player** - **Bigflix** - **Bild**: Bild.de - **BiliBili** @@ -345,7 +347,6 @@ - **Groupon** - **Hark** - **hbo** - - **hbo:episode** - **HearThisAt** - **Heise** - **HellPorno** @@ -489,6 +490,7 @@ - **Mediaset** - **Mediasite** - **MediasiteCatalog** + - **MediasiteNamedCatalog** - **Medici** - **megaphone.fm**: megaphone.fm embedded players - **Meipai**: 美拍 @@ -671,6 +673,8 @@ - **Piksel** - **Pinkbike** - **Pladform** + - **Platzi** + - **PlatziCourse** - **play.fm** - **PlayPlusTV** - **PlaysTV** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index f872cd137..5c7d550f5 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.04.01' +__version__ = '2019.04.07' From bf6fb8b9dc921a30df24d9789d5bbb0ac5b370b0 Mon Sep 17 00:00:00 2001 From: ealgase Date: Sat, 6 Apr 2019 23:38:40 -0400 Subject: [PATCH 282/362] [openload] add tests --- youtube_dl/extractor/openload.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 25b3bfdbd..130165b8c 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -350,6 +350,12 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.space/f/IY4eZSst3u8/', 'only_matching': True, + }, { + 'url': 'https://oladblock.services/f/b8NWEgkqNLI/', + 'only_matching': True, + }, { + 'url': 'https://oladblock.xyz/f/b8NWEgkqNLI/', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 9ed06812ec8da6f1364acd00261935c334994e62 Mon Sep 17 00:00:00 2001 From: ealgase Date: Sat, 6 Apr 2019 23:59:41 -0400 Subject: [PATCH 283/362] [streamango] add support for streamcherry.com --- youtube_dl/extractor/streamango.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py index efb259f96..f1e17dd88 100644 --- a/youtube_dl/extractor/streamango.py +++ b/youtube_dl/extractor/streamango.py @@ -14,7 +14,7 @@ from ..utils import ( class StreamangoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4', 'md5': 'e992787515a182f55e38fc97588d802a', @@ -41,6 +41,9 @@ class StreamangoIE(InfoExtractor): }, { 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4', 'only_matching': True, + }, { + 'url': 'https://streamcherry.com/f/clapasobsptpkdfe/', + 'only_matching': True, }] def _real_extract(self, url): From d562cac9dc67bfa2306c6225c261390162527d9e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 7 Apr 2019 12:39:48 +0100 Subject: [PATCH 284/362] [stv:player] Add new extractor(closes #20586) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/stv.py | 94 ++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+) create mode 100644 youtube_dl/extractor/stv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 41ab36213..cc19af5c4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1093,6 +1093,7 @@ from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE from .stretchinternet import StretchInternetIE +from .stv import STVPlayerIE from .sunporno import SunPornoIE from .svt import ( SVTIE, diff --git a/youtube_dl/extractor/stv.py b/youtube_dl/extractor/stv.py new file mode 100644 index 000000000..ccb074cd4 --- /dev/null +++ b/youtube_dl/extractor/stv.py @@ -0,0 +1,94 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse +) +from ..utils import ( + extract_attributes, + float_or_none, + int_or_none, + str_or_none, +) + + +class STVPlayerIE(InfoExtractor): + IE_NAME = 'stv:player' + _VALID_URL = r'https?://player\.stv\.tv/(?Pepisode|video)/(?P[a-z0-9]{4})' + _TEST = { + 'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/', + 'md5': '2ad867d4afd641fa14187596e0fbc91b', + 'info_dict': { + 'id': '6016487034001', + 'ext': 'mp4', + 'upload_date': '20190321', + 'title': 'Interview with the cast ahead of new Victoria', + 'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.', + 'timestamp': 1553179628, + 'uploader_id': '1486976045', + }, + 'skip': 'this resource is unavailable outside of the UK', + } + _PUBLISHER_ID = '1486976045' + _PTYPE_MAP = { + 'episode': 'episodes', + 'video': 'shortform', + } + + def _real_extract(self, url): + ptype, video_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, video_id) + + qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex( + r'itemprop="embedURL"[^>]+href="([^"]+)', + webpage, 'embed URL', default=None)).query) + publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID + + player_attr = extract_attributes(self._search_regex( + r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {} + + info = {} + duration = ref_id = series = video_id = None + api_ref_id = player_attr.get('data-player-api-refid') + if api_ref_id: + resp = self._download_json( + 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id), + api_ref_id, fatal=False) + if resp: + result = resp.get('results') or {} + video = result.get('video') or {} + video_id = str_or_none(video.get('id')) + ref_id = video.get('guid') + duration = video.get('length') + programme = result.get('programme') or {} + series = programme.get('name') or programme.get('shortName') + subtitles = {} + _subtitles = result.get('_subtitles') or {} + for ext, sub_url in _subtitles.items(): + subtitles.setdefault('en', []).append({ + 'ext': 'vtt' if ext == 'webvtt' else ext, + 'url': sub_url, + }) + info.update({ + 'description': result.get('summary'), + 'subtitles': subtitles, + 'view_count': int_or_none(result.get('views')), + }) + if not video_id: + video_id = qs.get('videoId', [None])[0] or self._search_regex( + r' Date: Sun, 7 Apr 2019 21:05:50 +0700 Subject: [PATCH 285/362] [tiktok] Add support for new URL schema (closes #20573) --- youtube_dl/extractor/tiktok.py | 35 +++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py index 083e9f36d..66088b9ab 100644 --- a/youtube_dl/extractor/tiktok.py +++ b/youtube_dl/extractor/tiktok.py @@ -65,8 +65,15 @@ class TikTokBaseIE(InfoExtractor): class TikTokIE(TikTokBaseIE): - _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P\d+)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + (?:m\.)?tiktok\.com/v| + (?:www\.)?tiktok\.com/share/video + ) + /(?P\d+) + ''' + _TESTS = [{ 'url': 'https://m.tiktok.com/v/6606727368545406213.html', 'md5': 'd584b572e92fcd48888051f238022420', 'info_dict': { @@ -81,25 +88,39 @@ class TikTokIE(TikTokBaseIE): 'comment_count': int, 'repost_count': int, } - } + }, { + 'url': 'https://www.tiktok.com/share/video/6606727368545406213', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'https://m.tiktok.com/v/%s.html' % video_id, video_id) data = self._parse_json(self._search_regex( r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id) return self._extract_aweme(data) class TikTokUserIE(TikTokBaseIE): - _VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P\d+)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + (?:m\.)?tiktok\.com/h5/share/usr| + (?:www\.)?tiktok\.com/share/user + ) + /(?P\d+) + ''' + _TESTS = [{ 'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html', 'info_dict': { 'id': '188294915489964032', }, 'playlist_mincount': 24, - } + }, { + 'url': 'https://www.tiktok.com/share/user/188294915489964032', + 'only_matching': True, + }] def _real_extract(self, url): user_id = self._match_id(url) From 9045d28b5e3eba03908a82dcb868bd1649650ddb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 7 Apr 2019 21:31:01 +0100 Subject: [PATCH 286/362] [aol] restrict url regex and improve format extraction --- youtube_dl/extractor/aol.py | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index cb9279193..dffa9733d 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -4,6 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -12,12 +16,12 @@ from ..utils import ( class AolIE(InfoExtractor): - IE_NAME = 'on.aol.com' - _VALID_URL = r'(?:aol-video:|https?://(?:(?:www|on)\.)?aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P[^/?#&]+)' + IE_NAME = 'aol.com' + _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.com/video/(?:[^/]+/)*)(?P[0-9a-f]+)' _TESTS = [{ # video with 5min ID - 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', + 'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/', 'md5': '18ef68f48740e86ae94b98da815eec42', 'info_dict': { 'id': '518167793', @@ -34,7 +38,7 @@ class AolIE(InfoExtractor): } }, { # video with vidible ID - 'url': 'http://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/', + 'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/', 'info_dict': { 'id': '5707d6b8e4b090497b04f706', 'ext': 'mp4', @@ -49,17 +53,17 @@ class AolIE(InfoExtractor): 'skip_download': True, } }, { - 'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944', + 'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/', 'only_matching': True, }, { - 'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763', - 'only_matching': True, - }, { - 'url': 'http://on.aol.com/video/519442220', + 'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/', 'only_matching': True, }, { 'url': 'aol-video:5707d6b8e4b090497b04f706', 'only_matching': True, + }, { + 'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/', + 'only_matching': True, }] def _real_extract(self, url): @@ -73,7 +77,7 @@ class AolIE(InfoExtractor): video_data = response['data'] formats = [] - m3u8_url = video_data.get('videoMasterPlaylist') + m3u8_url = url_or_none(video_data.get('videoMasterPlaylist')) if m3u8_url: formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) @@ -96,6 +100,12 @@ class AolIE(InfoExtractor): 'width': int(mobj.group(1)), 'height': int(mobj.group(2)), }) + else: + qs = compat_parse_qs(compat_urllib_parse_urlparse(video_url).query) + f.update({ + 'width': int_or_none(qs.get('w', [None])[0]), + 'height': int_or_none(qs.get('h', [None])[0]), + }) formats.append(f) self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id')) From 9c017253e83ac3dfd363566ccbb9fc63f4e2ac07 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 8 Apr 2019 16:34:03 +0100 Subject: [PATCH 287/362] [jwplatfom] do not match manifest URLs(#20596) --- youtube_dl/extractor/jwplatform.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index d19a6a774..647b905f1 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,7 +7,7 @@ from .common import InfoExtractor class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P[a-zA-Z0-9]{8})' + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video)s|jw6|v2/media)/|jwplatform:)(?P[a-zA-Z0-9]{8})' _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', From 5ca3459828cc0d752f02dab3e9c02cca85185cbb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 9 Apr 2019 11:20:26 +0100 Subject: [PATCH 288/362] [kaltura] sanitize embed URLs --- youtube_dl/extractor/kaltura.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index fdf7f5bbc..79162f665 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -145,6 +145,8 @@ class KalturaIE(InfoExtractor): ) if mobj: embed_info = mobj.groupdict() + for k, v in embed_info.items(): + embed_info[k] = v.strip() url = 'kaltura:%(partner_id)s:%(id)s' % embed_info escaped_pid = re.escape(embed_info['partner_id']) service_url = re.search( From 4bc12b8f819cd0a393e5800d4dc2ecf24401e199 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 9 Apr 2019 11:21:46 +0100 Subject: [PATCH 289/362] [dispeak] improve mp4 bitrate extraction --- youtube_dl/extractor/dispeak.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/dispeak.py b/youtube_dl/extractor/dispeak.py index c05f601e2..c345e0274 100644 --- a/youtube_dl/extractor/dispeak.py +++ b/youtube_dl/extractor/dispeak.py @@ -58,10 +58,17 @@ class DigitallySpeakingIE(InfoExtractor): stream_name = xpath_text(a_format, 'streamName', fatal=True) video_path = re.match(r'mp4\:(?P.*)', stream_name).group('path') url = video_root + video_path - vbr = xpath_text(a_format, 'bitrate') + bitrate = xpath_text(a_format, 'bitrate') + tbr = int_or_none(bitrate) + vbr = int_or_none(self._search_regex( + r'-(\d+)\.mp4', video_path, 'vbr', default=None)) + abr = tbr - vbr if tbr and vbr else None video_formats.append({ + 'format_id': bitrate, 'url': url, - 'vbr': int_or_none(vbr), + 'tbr': tbr, + 'vbr': vbr, + 'abr': abr, }) return video_formats From 118f7add3b9690884edb4dc887995f3815243c78 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 9 Apr 2019 11:23:47 +0100 Subject: [PATCH 290/362] [gdc] add support for kaltura embeds and update tests(closes #20575) --- youtube_dl/extractor/gdcvault.py | 96 ++++++++++++++++++-------------- 1 file changed, 55 insertions(+), 41 deletions(-) diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index 8806dc48a..2f555c1d4 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -3,22 +3,24 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .kaltura import KalturaIE from ..utils import ( HEADRequest, sanitized_Request, + smuggle_url, urlencode_postdata, ) class GDCVaultIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P\d+)/(?P(\w|-)+)?' + _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P\d+)(?:/(?P[\w-]+))?' _NETRC_MACHINE = 'gdcvault' _TESTS = [ { 'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple', 'md5': '7ce8388f544c88b7ac11c7ab1b593704', 'info_dict': { - 'id': '1019721', + 'id': '201311826596_AWNY', 'display_id': 'Doki-Doki-Universe-Sweet-Simple', 'ext': 'mp4', 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)' @@ -27,7 +29,7 @@ class GDCVaultIE(InfoExtractor): { 'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of', 'info_dict': { - 'id': '1015683', + 'id': '201203272_1330951438328RSXR', 'display_id': 'Embracing-the-Dark-Art-of', 'ext': 'flv', 'title': 'Embracing the Dark Art of Mathematical Modeling in AI' @@ -56,7 +58,7 @@ class GDCVaultIE(InfoExtractor): 'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface', 'md5': 'a8efb6c31ed06ca8739294960b2dbabd', 'info_dict': { - 'id': '1023460', + 'id': '840376_BQRC', 'ext': 'mp4', 'display_id': 'Tenacious-Design-and-The-Interface', 'title': 'Tenacious Design and The Interface of \'Destiny\'', @@ -66,26 +68,38 @@ class GDCVaultIE(InfoExtractor): # Multiple audios 'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC', 'info_dict': { - 'id': '1014631', - 'ext': 'flv', + 'id': '12396_1299111843500GMPX', + 'ext': 'mp4', 'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man', }, - 'params': { - 'skip_download': True, # Requires rtmpdump - 'format': 'jp', # The japanese audio - } + # 'params': { + # 'skip_download': True, # Requires rtmpdump + # 'format': 'jp', # The japanese audio + # } }, { # gdc-player.html 'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo', 'info_dict': { - 'id': '1435', + 'id': '9350_1238021887562UHXB', 'display_id': 'An-American-engine-in-Tokyo', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT', }, + }, + { + # Kaltura Embed + 'url': 'https://www.gdcvault.com/play/1026180/Mastering-the-Apex-of-Scaling', + 'info_dict': { + 'id': '0_h1fg8j3p', + 'ext': 'mp4', + 'title': 'Mastering the Apex of Scaling Game Servers (Presented by Multiplay)', + 'timestamp': 1554401811, + 'upload_date': '20190404', + 'uploader_id': 'joe@blazestreaming.com', + }, 'params': { - 'skip_download': True, # Requires rtmpdump + 'format': 'mp4-408', }, }, ] @@ -114,10 +128,8 @@ class GDCVaultIE(InfoExtractor): return start_page def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - display_id = mobj.group('name') or video_id + video_id, name = re.match(self._VALID_URL, url).groups() + display_id = name or video_id webpage_url = 'http://www.gdcvault.com/play/' + video_id start_page = self._download_webpage(webpage_url, display_id) @@ -127,12 +139,12 @@ class GDCVaultIE(InfoExtractor): start_page, 'url', default=None) if direct_url: title = self._html_search_regex( - r'Session Name\s*(.*?)', + r'Session Name:?\s*(.*?)', start_page, 'title') video_url = 'http://www.gdcvault.com' + direct_url # resolve the url so that we can detect the correct extension - head = self._request_webpage(HEADRequest(video_url), video_id) - video_url = head.geturl() + video_url = self._request_webpage( + HEADRequest(video_url), video_id).geturl() return { 'id': video_id, @@ -141,34 +153,36 @@ class GDCVaultIE(InfoExtractor): 'title': title, } - PLAYER_REGEX = r'' - xml_root = self._html_search_regex( - PLAYER_REGEX, start_page, 'xml root', default=None) - if xml_root is None: - # Probably need to authenticate - login_res = self._login(webpage_url, display_id) - if login_res is None: - self.report_warning('Could not login.') - else: - start_page = login_res - # Grab the url from the authenticated page - xml_root = self._html_search_regex( - PLAYER_REGEX, start_page, 'xml root') + xml_root = self._html_search_regex( + PLAYER_REGEX, start_page, 'xml root', default=None) + if xml_root is None: + # Probably need to authenticate + login_res = self._login(webpage_url, display_id) + if login_res is None: + self.report_warning('Could not login.') + else: + start_page = login_res + # Grab the url from the authenticated page + xml_root = self._html_search_regex( + PLAYER_REGEX, start_page, 'xml root') - xml_name = self._html_search_regex( - r'', + r'