From 641e86e3cf751f1050ca331b9d13152bd0e18558 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 24 Nov 2018 21:47:41 +0700 Subject: [PATCH 01/60] [wistia] Add support for fast.wistia.com (closes #18287) --- youtube_dl/extractor/wistia.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 2182d6fd4..01a51275e 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/embed/iframe/)(?P[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P[a-z0-9]+)' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -35,12 +35,15 @@ class WistiaIE(InfoExtractor): # with hls video 'url': 'wistia:807fafadvk', 'only_matching': True, + }, { + 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt', + 'only_matching': True, }] @staticmethod def _extract_url(webpage): match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) if match: return unescapeHTML(match.group('url')) From d19600df07128c73ef7242af7e1cd8c819951aba Mon Sep 17 00:00:00 2001 From: Alexander Seiler Date: Sat, 24 Nov 2018 16:14:27 +0100 Subject: [PATCH 02/60] [joj] Fix extraction (closes #18280) --- youtube_dl/extractor/joj.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py index d9f8dbfd2..62b28e980 100644 --- a/youtube_dl/extractor/joj.py +++ b/youtube_dl/extractor/joj.py @@ -61,7 +61,7 @@ class JojIE(InfoExtractor): bitrates = self._parse_json( self._search_regex( - r'(?s)bitrates\s*=\s*({.+?});', webpage, 'bitrates', + r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates', default='{}'), video_id, transform_source=js_to_json, fatal=False) From ca01d178844129bd4b6ed74740fbd30e7f84c1c2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 28 Nov 2018 19:53:22 +0100 Subject: [PATCH 03/60] [vimeo] Add support for VHX(Vimeo OTT)(#14835) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/vimeo.py | 85 +++++++++++++++++++++++++++++- 2 files changed, 85 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 60e6175b1..cd91c0fcb 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1303,6 +1303,7 @@ from .vimeo import ( VimeoReviewIE, VimeoUserIE, VimeoWatchLaterIE, + VHXEmbedIE, ) from .vimple import VimpleIE from .vine import ( diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 88f4d9979..6353c6831 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -14,10 +14,13 @@ from ..compat import ( from ..utils import ( determine_ext, ExtractorError, + js_to_json, InAdvancePagedList, int_or_none, merge_dicts, NO_DEFAULT, + parse_filesize, + qualities, RegexNotFoundError, sanitized_Request, smuggle_url, @@ -27,7 +30,6 @@ from ..utils import ( unsmuggle_url, urlencode_postdata, unescapeHTML, - parse_filesize, ) @@ -1063,3 +1065,84 @@ class VimeoLikesIE(InfoExtractor): 'description': description, 'entries': pl, } + + +class VHXEmbedIE(InfoExtractor): + IE_NAME = 'vhx:embed' + _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P\d+)' + + def _call_api(self, video_id, access_token, path='', query=None): + return self._download_json( + 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ + 'Authorization': 'Bearer ' + access_token, + }, query=query) + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + credentials = self._parse_json(self._search_regex( + r'(?s)credentials\s*:\s*({.+?}),', webpage, + 'config'), video_id, js_to_json) + access_token = credentials['access_token'] + + query = {} + for k, v in credentials.items(): + if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': + if k == 'authUserToken': + query['auth_user_token'] = v + else: + query[k] = v + files = self._call_api(video_id, access_token, '/files', query) + + formats = [] + for f in files: + href = try_get(f, lambda x: x['_links']['source']['href']) + if not href: + continue + method = f.get('method') + if method == 'hls': + formats.extend(self._extract_m3u8_formats( + href, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif method == 'dash': + formats.extend(self._extract_mpd_formats( + href, video_id, mpd_id='dash', fatal=False)) + else: + fmt = { + 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), + 'format_id': 'http', + 'preference': 1, + 'url': href, + 'vcodec': f.get('codec'), + } + quality = f.get('quality') + if quality: + fmt.update({ + 'format_id': 'http-' + quality, + 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), + }) + formats.append(fmt) + self._sort_formats(formats) + + video_data = self._call_api(video_id, access_token) + title = video_data.get('title') or video_data['name'] + + q = qualities(['small', 'medium', 'large', 'source']) + thumbnails = [] + for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): + thumbnails.append({ + 'id': thumbnail_id, + 'url': thumbnail_url, + 'preference': q(thumbnail_id), + }) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), + 'formats': formats, + 'thumbnails': thumbnails, + 'timestamp': unified_timestamp(video_data.get('created_at')), + 'view_count': int_or_none(video_data.get('plays_count')), + } From d9df8f120b325766181fb474a8c534e51df78f17 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 28 Nov 2018 20:13:36 +0100 Subject: [PATCH 04/60] [vimeo] extract VHX subtitles --- youtube_dl/extractor/vimeo.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 6353c6831..5e15f060b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1127,6 +1127,17 @@ class VHXEmbedIE(InfoExtractor): video_data = self._call_api(video_id, access_token) title = video_data.get('title') or video_data['name'] + subtitles = {} + for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: + lang = subtitle.get('srclang') or subtitle.get('label') + for _link in subtitle.get('_links', {}).values(): + href = _link.get('href') + if not href: + continue + subtitles.setdefault(lang, []).append({ + 'url': href, + }) + q = qualities(['small', 'medium', 'large', 'source']) thumbnails = [] for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): @@ -1142,6 +1153,7 @@ class VHXEmbedIE(InfoExtractor): 'description': video_data.get('description'), 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), 'formats': formats, + 'subtitles': subtitles, 'thumbnails': thumbnails, 'timestamp': unified_timestamp(video_data.get('created_at')), 'view_count': int_or_none(video_data.get('plays_count')), From 053e5b12b2e38b7d343aafbb7dc13fb8e4933015 Mon Sep 17 00:00:00 2001 From: Alexander Seiler Date: Thu, 29 Nov 2018 18:12:18 +0100 Subject: [PATCH 05/60] [azmedien] Fix extraction (closes #18334) --- youtube_dl/extractor/azmedien.py | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index a57a5f114..fcbdc71b9 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -36,7 +36,6 @@ class AZMedienIE(InfoExtractor): 'id': '1_anruz3wy', 'ext': 'mp4', 'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen', - 'description': 'md5:dd9f96751ec9c35e409a698a328402f3', 'uploader_id': 'TVOnline', 'upload_date': '20180930', 'timestamp': 1538328802, @@ -53,15 +52,12 @@ class AZMedienIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') video_id = mobj.group('id') entry_id = mobj.group('kaltura_id') if not entry_id: - webpage = self._download_webpage(url, video_id) - api_path = self._search_regex( - r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']', - webpage, 'api path') - api_url = 'https://www.%s%s' % (mobj.group('host'), api_path) + api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0]) payload = { 'query': '''query VideoContext($articleId: ID!) { article: node(id: $articleId) { From adbbdefc8126a933d9ff0a6e603fb312e4b4cbdc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 30 Nov 2018 00:48:15 +0700 Subject: [PATCH 06/60] [hotstar] Add support for alternative app state layout (closes #18320) --- youtube_dl/extractor/hotstar.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index bf5717f1b..45aa5e7ea 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -43,6 +43,7 @@ class HotStarIE(HotStarBaseIE): IE_NAME = 'hotstar' _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P\d{10})' _TESTS = [{ + # contentData 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273', 'info_dict': { 'id': '1000076273', @@ -57,6 +58,10 @@ class HotStarIE(HotStarBaseIE): # m3u8 download 'skip_download': True, } + }, { + # contentDetail + 'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157', + 'only_matching': True, }, { 'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583', 'only_matching': True, @@ -74,8 +79,12 @@ class HotStarIE(HotStarBaseIE): r'', webpage, 'app state'), video_id) video_data = {} + getters = ( + lambda x, k=k: x['initialState']['content%s' % k]['content'] + for k in ('Data', 'Detail') + ) for v in app_state.values(): - content = try_get(v, lambda x: x['initialState']['contentData']['content'], dict) + content = try_get(v, getters, dict) if content and content.get('contentId') == video_id: video_data = content From 16597c2f9492651c55e01f441ee9cb5c276209cb Mon Sep 17 00:00:00 2001 From: Jimm Stout Date: Thu, 29 Nov 2018 13:07:07 -0500 Subject: [PATCH 07/60] [gfycat] Update API endpoint (closes #18333) --- youtube_dl/extractor/gfycat.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/gfycat.py b/youtube_dl/extractor/gfycat.py index a0670b645..c1b36a59b 100644 --- a/youtube_dl/extractor/gfycat.py +++ b/youtube_dl/extractor/gfycat.py @@ -53,7 +53,7 @@ class GfycatIE(InfoExtractor): video_id = self._match_id(url) gfy = self._download_json( - 'http://gfycat.com/cajax/get/%s' % video_id, + 'https://api.gfycat.com/v1/gfycats/%s' % video_id, video_id, 'Downloading video info') if 'error' in gfy: raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True) From f012823082c893c0fc1f96afb8a91f5b1c1ae07a Mon Sep 17 00:00:00 2001 From: Hakim Boyles Date: Thu, 29 Nov 2018 14:20:27 -0400 Subject: [PATCH 08/60] [lynda] Fix authentication (closes #18158) --- youtube_dl/extractor/lynda.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 4ba61cd8a..3084c6dff 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -15,7 +15,7 @@ from ..utils import ( class LyndaBaseIE(InfoExtractor): - _SIGNIN_URL = 'https://www.lynda.com/signin' + _SIGNIN_URL = 'https://www.lynda.com/signin/lynda' _PASSWORD_URL = 'https://www.lynda.com/signin/password' _USER_URL = 'https://www.lynda.com/signin/user' _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' From 3430ff9b07d4dc9dd39617af54aeffb381d88737 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 1 Dec 2018 16:45:51 +0700 Subject: [PATCH 09/60] [pornhub] Use actual URL host for requests (closes #18359) --- youtube_dl/extractor/pornhub.py | 34 +++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index c9c884095..e377de196 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -27,7 +27,7 @@ class PornHubIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?Ppornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P[\da-z]+) @@ -129,7 +129,7 @@ class PornHubIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r']+?src=["\'](?P(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)', + r']+?src=["\'](?P(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)', webpage) def _extract_count(self, pattern, webpage, name): @@ -137,14 +137,16 @@ class PornHubIE(InfoExtractor): pattern, webpage, '%s count' % name, fatal=False)) def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') or 'pornhub.com' + video_id = mobj.group('id') - self._set_cookie('pornhub.com', 'age_verified', '1') + self._set_cookie(host, 'age_verified', '1') def dl_webpage(platform): - self._set_cookie('pornhub.com', 'platform', platform) + self._set_cookie(host, 'platform', platform) return self._download_webpage( - 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, + 'http://www.%s/view_video.php?viewkey=%s' % (host, video_id), video_id, 'Downloading %s webpage' % platform) webpage = dl_webpage('pc') @@ -306,7 +308,7 @@ class PornHubIE(InfoExtractor): class PornHubPlaylistBaseIE(InfoExtractor): - def _extract_entries(self, webpage): + 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 # https://github.com/rg3/youtube-dl/issues/11594). @@ -316,7 +318,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): return [ self.url_result( - 'http://www.pornhub.com/%s' % video_url, + 'http://www.%s/%s' % (host, video_url), PornHubIE.ie_key(), video_title=title) for video_url, title in orderedSet(re.findall( r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', @@ -324,11 +326,13 @@ class PornHubPlaylistBaseIE(InfoExtractor): ] def _real_extract(self, url): - playlist_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - entries = self._extract_entries(webpage) + entries = self._extract_entries(webpage, host) playlist = self._parse_json( self._search_regex( @@ -343,7 +347,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/playlist/(?P\d+)' + _VALID_URL = r'https?://(?:[^/]+\.)?(?Ppornhub\.(?:com|net))/playlist/(?P\d+)' _TESTS = [{ 'url': 'http://www.pornhub.com/playlist/4667351', 'info_dict': { @@ -358,7 +362,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?(?Ppornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -399,7 +403,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): }] def _real_extract(self, url): - user_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + user_id = mobj.group('id') entries = [] for page_num in itertools.count(1): @@ -411,7 +417,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: break raise - page_entries = self._extract_entries(webpage) + page_entries = self._extract_entries(webpage, host) if not page_entries: break entries.extend(page_entries) From aa374bc78e5e4dbb8453bd367ae0e3c0db702a7a Mon Sep 17 00:00:00 2001 From: Alexander Seiler Date: Sat, 1 Dec 2018 18:05:15 +0100 Subject: [PATCH 10/60] [utils] Fix random_birthday to generate existing dates only --- youtube_dl/utils.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index e84d35d4d..0b1c7cd6c 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3948,8 +3948,12 @@ def write_xattr(path, key, value): def random_birthday(year_field, month_field, day_field): + start_date = datetime.date(1950, 1, 1) + end_date = datetime.date(1995, 12, 31) + offset = random.randint(0, (end_date - start_date).days) + random_date = start_date + datetime.timedelta(offset) return { - year_field: str(random.randint(1950, 1995)), - month_field: str(random.randint(1, 12)), - day_field: str(random.randint(1, 31)), + year_field: str(random_date.year), + month_field: str(random_date.month), + day_field: str(random_date.day), } From 1ead840d2c18d4add340117f676fd6694f0650d3 Mon Sep 17 00:00:00 2001 From: Ken Swenson Date: Fri, 9 Nov 2018 16:49:20 -0500 Subject: [PATCH 11/60] [tiktok] Add extractor (closes #18108) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tiktok.py | 79 ++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 youtube_dl/extractor/tiktok.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index cd91c0fcb..547331078 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1124,6 +1124,7 @@ from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE from .threeqsdn import ThreeQSDNIE +from .tiktok import TikTokIE from .tinypic import TinyPicIE from .tmz import ( TMZIE, diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py new file mode 100644 index 000000000..d71b09c66 --- /dev/null +++ b/youtube_dl/extractor/tiktok.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + compat_str, + int_or_none, + str_or_none, + try_get, + url_or_none, +) + + +class TikTokIE(InfoExtractor): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P[0-9]+)' + _TEST = { + 'url': 'https://m.tiktok.com/v/6606727368545406213.html', + 'md5': 'd584b572e92fcd48888051f238022420', + 'info_dict': { + 'id': '6606727368545406213', + 'ext': 'mp4', + 'title': 'Zureeal on TikTok', + 'thumbnail': r're:^https?://.*~noop.image', + 'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay', + 'uploader': 'Zureeal', + 'width': 540, + 'height': 960, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + data = self._parse_json( + self._search_regex( + r'var\s+data\s*=\s*({.+?});', webpage, 'data' + ), video_id) + + title = self._og_search_title(webpage) + + description = str_or_none(try_get(data, lambda x: x['desc'])) + width = int_or_none(try_get(data, lambda x: x['video']['width'])) + height = int_or_none(try_get(data, lambda x: x['video']['height'])) + + formats = [] + + for count, (key, label) in enumerate((('play_addr_lowbr', 'Low'), ('play_addr', 'Normal'), ('download_addr', 'Download')), -2): + for format in try_get(data, lambda x: x['video'][key]['url_list']): + format_url = url_or_none(format) + if not format_url: + continue + formats.append({ + 'url': format_url, + 'ext': 'mp4', + 'height': height, + 'width': width, + 'format_note': label, + 'quality': count + }) + + self._sort_formats(formats) + + uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) + + thumbnail = url_or_none( + try_get( + data, lambda x: x['video']['cover']['url_list'][0], compat_str)) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'uploader': uploader, + 'formats': formats, + 'thumbnail': thumbnail, + 'width': width, + 'height': height, + } From ce18a19be9af1e227e7162636cbf6b277adc1b41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 2 Dec 2018 02:39:22 +0700 Subject: [PATCH 12/60] [tiktok] Improve extraction and add support for user pages (closes #18135) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/tiktok.py | 136 ++++++++++++++++++----------- 2 files changed, 91 insertions(+), 50 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 547331078..0baed6b27 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1124,7 +1124,10 @@ from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE from .threeqsdn import ThreeQSDNIE -from .tiktok import TikTokIE +from .tiktok import ( + TikTokIE, + TikTokUserIE, +) from .tinypic import TinyPicIE from .tmz import ( TMZIE, diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py index d71b09c66..083e9f36d 100644 --- a/youtube_dl/extractor/tiktok.py +++ b/youtube_dl/extractor/tiktok.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( compat_str, + ExtractorError, int_or_none, str_or_none, try_get, @@ -11,69 +12,106 @@ from ..utils import ( ) -class TikTokIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P[0-9]+)' +class TikTokBaseIE(InfoExtractor): + def _extract_aweme(self, data): + video = data['video'] + description = str_or_none(try_get(data, lambda x: x['desc'])) + width = int_or_none(try_get(data, lambda x: video['width'])) + height = int_or_none(try_get(data, lambda x: video['height'])) + + format_urls = set() + formats = [] + for format_id in ( + 'play_addr_lowbr', 'play_addr', 'play_addr_h264', + 'download_addr'): + for format in try_get( + video, lambda x: x[format_id]['url_list'], list) or []: + format_url = url_or_none(format) + if not format_url: + continue + if format_url in format_urls: + continue + format_urls.add(format_url) + formats.append({ + 'url': format_url, + 'ext': 'mp4', + 'height': height, + 'width': width, + }) + self._sort_formats(formats) + + thumbnail = url_or_none(try_get( + video, lambda x: x['cover']['url_list'][0], compat_str)) + uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) + timestamp = int_or_none(data.get('create_time')) + comment_count = int_or_none(data.get('comment_count')) or int_or_none( + try_get(data, lambda x: x['statistics']['comment_count'])) + repost_count = int_or_none(try_get( + data, lambda x: x['statistics']['share_count'])) + + aweme_id = data['aweme_id'] + + return { + 'id': aweme_id, + 'title': uploader or aweme_id, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'timestamp': timestamp, + 'comment_count': comment_count, + 'repost_count': repost_count, + 'formats': formats, + } + + +class TikTokIE(TikTokBaseIE): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P\d+)' _TEST = { 'url': 'https://m.tiktok.com/v/6606727368545406213.html', 'md5': 'd584b572e92fcd48888051f238022420', 'info_dict': { 'id': '6606727368545406213', 'ext': 'mp4', - 'title': 'Zureeal on TikTok', - 'thumbnail': r're:^https?://.*~noop.image', + 'title': 'Zureeal', 'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay', + 'thumbnail': r're:^https?://.*~noop.image', 'uploader': 'Zureeal', - 'width': 540, - 'height': 960, + 'timestamp': 1538248586, + 'upload_date': '20180929', + 'comment_count': int, + 'repost_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + data = self._parse_json(self._search_regex( + r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id) + return self._extract_aweme(data) - data = self._parse_json( - self._search_regex( - r'var\s+data\s*=\s*({.+?});', webpage, 'data' - ), video_id) - title = self._og_search_title(webpage) +class TikTokUserIE(TikTokBaseIE): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P\d+)' + _TEST = { + 'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html', + 'info_dict': { + 'id': '188294915489964032', + }, + 'playlist_mincount': 24, + } - description = str_or_none(try_get(data, lambda x: x['desc'])) - width = int_or_none(try_get(data, lambda x: x['video']['width'])) - height = int_or_none(try_get(data, lambda x: x['video']['height'])) - - formats = [] - - for count, (key, label) in enumerate((('play_addr_lowbr', 'Low'), ('play_addr', 'Normal'), ('download_addr', 'Download')), -2): - for format in try_get(data, lambda x: x['video'][key]['url_list']): - format_url = url_or_none(format) - if not format_url: - continue - formats.append({ - 'url': format_url, - 'ext': 'mp4', - 'height': height, - 'width': width, - 'format_note': label, - 'quality': count - }) - - self._sort_formats(formats) - - uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) - - thumbnail = url_or_none( - try_get( - data, lambda x: x['video']['cover']['url_list'][0], compat_str)) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'uploader': uploader, - 'formats': formats, - 'thumbnail': thumbnail, - 'width': width, - 'height': height, - } + def _real_extract(self, url): + user_id = self._match_id(url) + data = self._download_json( + 'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id, + query={'_signature': '_'}) + entries = [] + for aweme in data['aweme_list']: + try: + entry = self._extract_aweme(aweme) + except ExtractorError: + continue + entry['extractor_key'] = TikTokIE.ie_key() + entries.append(entry) + return self.playlist_result(entries, user_id) From 1fa59a928e48ac81e2afb5dfe134fa6c40f64e44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 3 Dec 2018 00:06:54 +0700 Subject: [PATCH 13/60] [ChangeLog] Actualize [ci skip] --- ChangeLog | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/ChangeLog b/ChangeLog index f82c7ea35..ddd4bec14 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,20 @@ +version + +Core +* [utils] Fix random_birthday to generate existing dates only (#18284) + +Extractors ++ [tiktok] Add support for tiktok.com (#18108, #18135) +* [pornhub] Use actual URL host for requests (#18359) +* [lynda] Fix authentication (#18158, #18217) +* [gfycat] Update API endpoint (#18333, #18343) ++ [hotstar] Add support for alternative app state layout (#18320) +* [azmedien] Fix extraction (#18334, #18336) ++ [vimeo] Add support for VHX (Vimeo OTT) (#14835) +* [joj] Fix extraction (#18280, #18281) ++ [wistia] Add support for fast.wistia.com (#18287) + + version 2018.11.23 Core From ab896fa894d2395b886e5bb8168ca0e0e6e9517d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 3 Dec 2018 00:10:20 +0700 Subject: [PATCH 14/60] release 2018.12.03 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 +++ youtube_dl/version.py | 2 +- 4 files changed, 8 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 35cc8d6d0..4b35244a8 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 *2018.11.23*. 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 **2018.11.23** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.03*. 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 **2018.12.03** ### 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 2018.11.23 +[debug] youtube-dl version 2018.12.03 [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 ddd4bec14..689d07826 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.03 Core * [utils] Fix random_birthday to generate existing dates only (#18284) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 7d72ad82d..837b0199b 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -885,6 +885,8 @@ - **ThisAmericanLife** - **ThisAV** - **ThisOldHouse** + - **TikTok** + - **TikTokUser** - **tinypic**: tinypic.com videos - **TMZ** - **TMZArticle** @@ -979,6 +981,7 @@ - **VevoPlaylist** - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet - **vh1.com** + - **vhx:embed** - **Viafree** - **vice** - **vice:article** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 4956365d0..8e1203892 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.11.23' +__version__ = '2018.12.03' From 5547014ad972a4364c4d4a613db6d3a18f25950e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 2 Dec 2018 20:01:36 +0100 Subject: [PATCH 15/60] [gamespot] add support reviews URLs --- youtube_dl/extractor/gamespot.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index ab647dd41..4236a5ed8 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -14,7 +14,7 @@ from ..utils import ( class GameSpotIE(OnceIE): - _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P\d+)' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -41,6 +41,9 @@ class GameSpotIE(OnceIE): }, { 'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/', 'only_matching': True, + }, { + 'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/', + 'only_matching': True, }] def _real_extract(self, url): From 8bb0c9cc16b841ab89e15e620e00ee954ab316ed Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 5 Dec 2018 07:03:00 +0100 Subject: [PATCH 16/60] [tbs] fix info extraction(fixes #18403) --- youtube_dl/extractor/tbs.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index 784f8ed66..e8a7c65e0 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -16,7 +16,7 @@ from ..utils import ( class TBSIE(TurnerBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?Ptbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?(?Ptbs|tntdrama)\.com(?P/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P[^/?#]+))' _TESTS = [{ 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster', 'info_dict': { @@ -40,12 +40,12 @@ class TBSIE(TurnerBaseIE): }] def _real_extract(self, url): - site, display_id = re.match(self._VALID_URL, url).groups() + site, path, display_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) drupal_settings = self._parse_json(self._search_regex( r']+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})', webpage, 'drupal setting'), display_id) - video_data = drupal_settings['turner_playlist'][0] + video_data = next(v for v in drupal_settings['turner_playlist'] if v.get('url') == path) media_id = video_data['mediaID'] title = video_data['title'] From ae9d77dab54630ac480bd4082468d543a15c341e Mon Sep 17 00:00:00 2001 From: v-delta <45652398+v-delta@users.noreply.github.com> Date: Thu, 6 Dec 2018 17:24:35 +0100 Subject: [PATCH 17/60] [yourporn] Fix extraction (closes #18424) --- 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 6602f7c03..a9951f3b8 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -26,7 +26,7 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]) + video_id)[video_id]).replace('/cdn/', '/cdn2/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', From 33cc1ea586480ccc60fd25f2d42cfb44eec605c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 7 Dec 2018 00:00:06 +0700 Subject: [PATCH 18/60] [nrktv] Relax _VALID_URL (closes #18304, closes #18387) --- youtube_dl/extractor/nrk.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index a231735fb..c5001ef48 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -248,7 +248,7 @@ class NRKTVIE(NRKBaseIE): _VALID_URL = r'''(?x) https?:// (?:tv|radio)\.nrk(?:super)?\.no/ - (?:serie/[^/]+|program)/ + (?:serie(?:/[^/]+){1,2}|program)/ (?![Ee]pisodes)%s (?:/\d{2}-\d{2}-\d{4})? (?:\#del=(?P\d+))? @@ -362,6 +362,9 @@ class NRKTVIE(NRKBaseIE): }, { 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller', + 'only_matching': True, }] From 15699ec8b0a9cb8d519b721a5cb8199afe62fc3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 7 Dec 2018 00:49:24 +0700 Subject: [PATCH 19/60] [nrktv:season,series] Fix extraction and update tests (closes #17159, closes #17258) --- youtube_dl/extractor/nrk.py | 68 +++++++++++++++++++++++-------------- 1 file changed, 43 insertions(+), 25 deletions(-) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index c5001ef48..48bc6fd7a 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -211,13 +211,13 @@ class NRKIE(NRKBaseIE): _TESTS = [{ # video 'url': 'http://www.nrk.no/video/PS*150533', - 'md5': '2f7f6eeb2aacdd99885f355428715cfa', + 'md5': '706f34cdf1322577589e369e522b50ef', 'info_dict': { 'id': '150533', 'ext': 'mp4', 'title': 'Dompap og andre fugler i Piip-Show', 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', - 'duration': 263, + 'duration': 262, } }, { # audio @@ -256,14 +256,14 @@ class NRKTVIE(NRKBaseIE): _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') _TESTS = [{ 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'md5': '4e9ca6629f09e588ed240fb11619922a', + 'md5': '9a167e54d04671eb6317a37b7bc8a280', 'info_dict': { 'id': 'MUHH48000314AA', 'ext': 'mp4', 'title': '20 spørsmål 23.05.2014', 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'duration': 1741, - 'series': '20 spørsmål - TV', + 'series': '20 spørsmål', 'episode': '23.05.2014', }, }, { @@ -301,7 +301,7 @@ class NRKTVIE(NRKBaseIE): 'id': 'MSPO40010515AH', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', 'duration': 772, 'series': 'Tour de Ski', 'episode': '06.01.2015', @@ -314,7 +314,7 @@ class NRKTVIE(NRKBaseIE): 'id': 'MSPO40010515BH', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', 'duration': 6175, 'series': 'Tour de Ski', 'episode': '06.01.2015', @@ -326,7 +326,7 @@ class NRKTVIE(NRKBaseIE): 'info_dict': { 'id': 'MSPO40010515', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', }, 'expected_warnings': ['Video is geo restricted'], }, { @@ -406,21 +406,35 @@ class NRKTVSerieBaseIE(InfoExtractor): def _extract_series(self, webpage, display_id, fatal=True): config = self._parse_json( self._search_regex( - r'({.+?})\s*,\s*"[^"]+"\s*\)\s*', webpage, 'config', - default='{}' if not fatal else NO_DEFAULT), + (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;', + r'({.+?})\s*,\s*"[^"]+"\s*\)\s*'), + webpage, 'config', default='{}' if not fatal else NO_DEFAULT), display_id, fatal=False) if not config: return - return try_get(config, lambda x: x['series'], dict) + return try_get( + config, + (lambda x: x['initialState']['series'], lambda x: x['series']), + dict) + + def _extract_seasons(self, seasons): + if not isinstance(seasons, list): + return [] + entries = [] + for season in seasons: + entries.extend(self._extract_episodes(season)) + return entries def _extract_episodes(self, season): - entries = [] if not isinstance(season, dict): - return entries - episodes = season.get('episodes') - if not isinstance(episodes, list): - return entries - for episode in episodes: + return [] + return self._extract_entries(season.get('episodes')) + + def _extract_entries(self, entry_list): + if not isinstance(entry_list, list): + return [] + entries = [] + for episode in entry_list: nrk_id = episode.get('prfId') if not nrk_id or not isinstance(nrk_id, compat_str): continue @@ -465,7 +479,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P[^/]+)' _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P\d+)' _TESTS = [{ - # new layout + # new layout, seasons 'url': 'https://tv.nrk.no/serie/backstage', 'info_dict': { 'id': 'backstage', @@ -474,20 +488,21 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): }, 'playlist_mincount': 60, }, { - # old layout + # new layout, instalments 'url': 'https://tv.nrk.no/serie/groenn-glede', 'info_dict': { 'id': 'groenn-glede', 'title': 'Grønn glede', 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', }, - 'playlist_mincount': 9, + 'playlist_mincount': 10, }, { - 'url': 'http://tv.nrksuper.no/serie/labyrint', + # old layout + 'url': 'https://tv.nrksuper.no/serie/labyrint', 'info_dict': { 'id': 'labyrint', 'title': 'Labyrint', - 'description': 'md5:58afd450974c89e27d5a19212eee7115', + 'description': 'md5:318b597330fdac5959247c9b69fdb1ec', }, 'playlist_mincount': 3, }, { @@ -520,11 +535,11 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): description = try_get( series, lambda x: x['titles']['subtitle'], compat_str) entries = [] - for season in series['seasons']: - entries.extend(self._extract_episodes(season)) + entries.extend(self._extract_seasons(series.get('seasons'))) + entries.extend(self._extract_entries(series.get('instalments'))) return self.playlist_result(entries, series_id, title, description) - # Old layout (e.g. https://tv.nrk.no/serie/groenn-glede) + # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint) entries = [ self.url_result( 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format( @@ -536,6 +551,9 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): 'seriestitle', webpage, 'title', default=None) or self._og_search_title( webpage, fatal=False) + if title: + title = self._search_regex( + r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title) description = self._html_search_meta( 'series_description', webpage, @@ -596,7 +614,7 @@ class NRKPlaylistIE(NRKPlaylistBaseIE): 'title': 'Rivertonprisen til Karin Fossum', 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', }, - 'playlist_count': 5, + 'playlist_count': 2, }] def _extract_title(self, webpage): From c976873c5b2912c06ff53e5193640ee8627edee4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 7 Dec 2018 00:54:58 +0700 Subject: [PATCH 20/60] [nrktv:series] Add support for extra materials --- youtube_dl/extractor/nrk.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 48bc6fd7a..072f920a9 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -537,6 +537,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): entries = [] entries.extend(self._extract_seasons(series.get('seasons'))) entries.extend(self._extract_entries(series.get('instalments'))) + entries.extend(self._extract_episodes(series.get('extraMaterial'))) return self.playlist_result(entries, series_id, title, description) # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint) From dfe0a3a9d2e07ac1e5ad221912d03b999ebb4d75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 7 Dec 2018 03:27:11 +0700 Subject: [PATCH 21/60] [lecturio] Add extractor (closes #18405) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/lecturio.py | 186 +++++++++++++++++++++++++++++ 2 files changed, 190 insertions(+) create mode 100644 youtube_dl/extractor/lecturio.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 0baed6b27..e5f18a75d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -553,6 +553,10 @@ from .lcp import ( ) from .learnr import LearnrIE from .lecture2go import Lecture2GoIE +from .lecturio import ( + LecturioIE, + LecturioCourseIE, +) from .leeco import ( LeIE, LePlaylistIE, diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py new file mode 100644 index 000000000..62ff28e02 --- /dev/null +++ b/youtube_dl/extractor/lecturio.py @@ -0,0 +1,186 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + extract_attributes, + ExtractorError, + float_or_none, + int_or_none, + str_or_none, + url_or_none, + urlencode_postdata, + urljoin, +) + + +class LecturioBaseIE(InfoExtractor): + _LOGIN_URL = 'https://app.lecturio.com/en/login' + _NETRC_MACHINE = 'lecturio' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + # Sets some cookies + _, urlh = self._download_webpage_handle( + self._LOGIN_URL, None, 'Downloading login popup') + + def is_logged(url_handle): + return self._LOGIN_URL not in compat_str(url_handle.geturl()) + + # Already logged in + if is_logged(urlh): + return + + login_form = { + 'signin[email]': username, + 'signin[password]': password, + 'signin[remember]': 'on', + } + + response, urlh = self._download_webpage_handle( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form)) + + # Logged in successfully + if is_logged(urlh): + return + + errors = self._html_search_regex( + r'(?s)]+class=["\']error_list[^>]+>(.+?)', response, + 'errors', default=None) + if errors: + raise ExtractorError('Unable to login: %s' % errors, expected=True) + raise ExtractorError('Unable to log in') + + +class LecturioIE(LecturioBaseIE): + _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P[^/?#&]+)\.lecture' + _TEST = { + 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos', + 'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870', + 'info_dict': { + 'id': '39634', + 'ext': 'mp4', + 'title': 'Important Concepts and Terms – Introduction to Microbiology', + }, + 'skip': 'Requires lecturio account credentials', + } + + _CC_LANGS = { + 'German': 'de', + 'English': 'en', + 'Spanish': 'es', + 'French': 'fr', + 'Polish': 'pl', + 'Russian': 'ru', + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://app.lecturio.com/en/lecture/%s/player.html' % display_id, + display_id) + + lecture_id = self._search_regex( + r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id') + + api_url = self._search_regex( + r'lectureDataLink\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'api url', group='url') + + video = self._download_json(api_url, display_id) + + title = video['title'].strip() + + formats = [] + for format_ in video['content']['media']: + if not isinstance(format_, dict): + continue + file_ = format_.get('file') + if not file_: + continue + ext = determine_ext(file_) + if ext == 'smil': + # smil contains only broken RTMP formats anyway + continue + file_url = url_or_none(file_) + if not file_url: + continue + label = str_or_none(format_.get('label')) + filesize = int_or_none(format_.get('fileSize')) + formats.append({ + 'url': file_url, + 'format_id': label, + 'filesize': float_or_none(filesize, invscale=1000) + }) + self._sort_formats(formats) + + subtitles = {} + automatic_captions = {} + cc = self._parse_json( + self._search_regex( + r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles', + default='{}'), display_id, fatal=False) + for cc_label, cc_url in cc.items(): + cc_url = url_or_none(cc_url) + if not cc_url: + continue + sub_dict = automatic_captions if 'auto-translated' in cc_label else subtitles + lang = self._search_regex( + r'/([a-z]{2})_', cc_url, 'lang', default=cc_label.split()[0]) + sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({ + 'url': cc_url, + }) + + return { + 'id': lecture_id, + 'title': title, + 'formats': formats, + 'subtitles': subtitles, + 'automatic_captions': automatic_captions, + } + + +class LecturioCourseIE(LecturioBaseIE): + _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P[^/?#&]+)\.course' + _TEST = { + 'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/', + 'info_dict': { + 'id': 'microbiology-introduction', + 'title': 'Microbiology: Introduction', + }, + 'playlist_count': 45, + 'skip': 'Requires lecturio account credentials', + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>', + webpage): + params = extract_attributes(mobj.group(0)) + lecture_url = urljoin(url, params.get('data-url')) + lecture_id = params.get('data-id') + entries.append(self.url_result( + lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id)) + + title = self._search_regex( + r']+class=["\']content-title[^>]+>([^<]+)', webpage, + 'title', default=None) + + return self.playlist_result(entries, display_id, title) From ebb0449049c198f04103502c95a13171b854d1c7 Mon Sep 17 00:00:00 2001 From: ealgase Date: Thu, 6 Dec 2018 15:36:08 -0500 Subject: [PATCH 22/60] [xvideos] Switch to HTTPS (closes #18422) --- youtube_dl/extractor/xvideos.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index efee95651..ec2d913fc 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -45,7 +45,7 @@ class XVideosIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - 'http://www.xvideos.com/video%s/' % video_id, video_id) + 'https://www.xvideos.com/video%s/' % video_id, video_id) mobj = re.search(r'

(.+?)

', webpage) if mobj: From 8c5879715f4d979b83c49d44a9094307247097ba Mon Sep 17 00:00:00 2001 From: Alexander Seiler Date: Thu, 6 Dec 2018 21:41:02 +0100 Subject: [PATCH 23/60] [ard:mediathek] Fix title and description extraction (closes #18349) --- youtube_dl/extractor/ard.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 6bf8f61eb..84e96f769 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -173,13 +173,18 @@ class ARDMediathekIE(InfoExtractor): title = self._html_search_regex( [r'(.*?)', r'', - r'

(.*?)

'], + r'

(.*?)

', + r']*>(.*?)'], webpage, 'title') description = self._html_search_meta( 'dcterms.abstract', webpage, 'description', default=None) if description is None: description = self._html_search_meta( - 'description', webpage, 'meta description') + 'description', webpage, 'meta description', default=None) + if description is None: + description = self._html_search_regex( + r'(.+?)

', + webpage, 'teaser text', default=None) # Thumbnail is sometimes not present. # It is in the mobile version, but that seems to use a different URL From c3c098dcf2826ab4d668a92c9137cca2c0c42a4f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 7 Dec 2018 18:52:01 +0100 Subject: [PATCH 24/60] [hotstar] fix video data extraction(closes #18386) --- youtube_dl/extractor/hotstar.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index 45aa5e7ea..8de9c4faf 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -79,7 +79,7 @@ class HotStarIE(HotStarBaseIE): r'', webpage, 'app state'), video_id) video_data = {} - getters = ( + getters = list( lambda x, k=k: x['initialState']['content%s' % k]['content'] for k in ('Data', 'Detail') ) @@ -87,6 +87,7 @@ class HotStarIE(HotStarBaseIE): content = try_get(v, getters, dict) if content and content.get('contentId') == video_id: video_data = content + break title = video_data['title'] From 9235b5091cedcc21c8dc32d4b292340edeee4ed0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Dec 2018 23:57:40 +0700 Subject: [PATCH 25/60] [iprima] Relax _VALID_URL (closes #18453) --- youtube_dl/extractor/iprima.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 1d58d6e85..11a6629d2 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -12,7 +12,7 @@ from ..utils import ( class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P[^?#]+)' + _VALID_URL = r'https?://(?:play|prima|www)\.iprima\.cz/(?:[^/]+/)*(?P[^/?#&]+)' _GEO_BYPASS = False _TESTS = [{ @@ -41,6 +41,9 @@ class IPrimaIE(InfoExtractor): # iframe prima.iprima.cz 'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha', 'only_matching': True, + }, { + 'url': 'http://www.iprima.cz/filmy/desne-rande', + 'only_matching': True, }] def _real_extract(self, url): From 1d88b3e6e6e59e4b52305faf6c1bf1fd69c555ee Mon Sep 17 00:00:00 2001 From: aegamesi Date: Sat, 29 Apr 2017 22:56:33 -0700 Subject: [PATCH 26/60] [YoutubeDL] Recognize expires=0 as session cookies and send session cookies with requests --- youtube_dl/YoutubeDL.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 38ba43a97..2433f74f4 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -2300,7 +2300,13 @@ class YoutubeDL(object): self.cookiejar = compat_cookiejar.MozillaCookieJar( opts_cookiefile) if os.access(opts_cookiefile, os.R_OK): - self.cookiejar.load() + self.cookiejar.load(ignore_discard=True, ignore_expires=True) + # Force CookieJar to treat 'expires=0' cookies as session/discard cookies + # Fixes https://bugs.python.org/issue17164 + for cookie in self.cookiejar: + if cookie.expires == 0: + cookie.expires = None + cookie.discard = True cookie_processor = YoutubeDLCookieProcessor(self.cookiejar) if opts_proxy is not None: From 1bab3437046646da4ebe2b8e0c7fdc25aa1072ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 06:00:32 +0700 Subject: [PATCH 27/60] [YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929) --- youtube_dl/YoutubeDL.py | 12 +++--------- youtube_dl/utils.py | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 9 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 2433f74f4..4493fd0e1 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -88,6 +88,7 @@ from .utils import ( version_tuple, write_json_file, write_string, + YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, ) @@ -558,7 +559,7 @@ class YoutubeDL(object): self.restore_console_title() if self.params.get('cookiefile') is not None: - self.cookiejar.save() + self.cookiejar.save(ignore_discard=True, ignore_expires=True) def trouble(self, message=None, tb=None): """Determine action to take when a download problem appears. @@ -2297,16 +2298,9 @@ class YoutubeDL(object): self.cookiejar = compat_cookiejar.CookieJar() else: opts_cookiefile = expand_path(opts_cookiefile) - self.cookiejar = compat_cookiejar.MozillaCookieJar( - opts_cookiefile) + self.cookiejar = YoutubeDLCookieJar(opts_cookiefile) if os.access(opts_cookiefile, os.R_OK): self.cookiejar.load(ignore_discard=True, ignore_expires=True) - # Force CookieJar to treat 'expires=0' cookies as session/discard cookies - # Fixes https://bugs.python.org/issue17164 - for cookie in self.cookiejar: - if cookie.expires == 0: - cookie.expires = None - cookie.discard = True cookie_processor = YoutubeDLCookieProcessor(self.cookiejar) if opts_proxy is not None: diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 0b1c7cd6c..62e769fd5 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -39,6 +39,7 @@ from .compat import ( compat_HTMLParser, compat_basestring, compat_chr, + compat_cookiejar, compat_ctypes_WINFUNCTYPE, compat_etree_fromstring, compat_expanduser, @@ -1139,6 +1140,33 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): req, **kwargs) +class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + def save(self, filename=None, ignore_discard=False, ignore_expires=False): + # Store session cookies with `expires` set to 0 instead of an empty + # string + for cookie in self: + if cookie.expires is None: + cookie.expires = 0 + 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) + # 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 + # cookies on our own. + # Session cookies may be important for cookies-based authentication, + # e.g. usually, when user does not check 'Remember me' check box while + # logging in on a site, some important cookies are stored as session + # cookies so that not recognizing them will result in failed login. + # 1. https://bugs.python.org/issue17164 + for cookie in self: + # Treat `expires=0` cookies as session cookies + if cookie.expires == 0: + cookie.expires = None + cookie.discard = True + + class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): def __init__(self, cookiejar=None): compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar) From 5f47a60c5d66d65b505131a672a3bad67ddaa00f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 9 Dec 2018 09:35:17 +0100 Subject: [PATCH 28/60] [imgur] improve gallery and album detection and extraction(closes #9133)(closes #16577)(closes #17223)(closes #18404) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/imgur.py | 86 +++++++++++++++--------------- 2 files changed, 44 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e5f18a75d..e28db6968 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -483,6 +483,7 @@ from .imdb import ( from .imgur import ( ImgurIE, ImgurAlbumIE, + ImgurGalleryIE, ) from .ina import InaIE from .inc import IncIE diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index ecc958a17..0eb54db3f 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -12,7 +12,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -20,28 +20,9 @@ class ImgurIE(InfoExtractor): 'id': 'A61SaA1', 'ext': 'mp4', 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 'Imgur: The magic of the Internet', }, }, { 'url': 'https://imgur.com/A61SaA1', - 'info_dict': { - 'id': 'A61SaA1', - 'ext': 'mp4', - 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 'Imgur: The magic of the Internet', - }, - }, { - 'url': 'https://imgur.com/gallery/YcAQlkx', - 'info_dict': { - 'id': 'YcAQlkx', - 'ext': 'mp4', - 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', - } - }, { - 'url': 'http://imgur.com/topic/Funny/N8rOudd', - 'only_matching': True, - }, { - 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, }, { 'url': 'https://i.imgur.com/crGpqCV.mp4', @@ -50,8 +31,8 @@ class ImgurIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - gifv_url = 'https://i.imgur.com/{id}.gifv'.format(id=video_id) - webpage = self._download_webpage(gifv_url, video_id) + webpage = self._download_webpage( + 'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id) width = int_or_none(self._og_search_property( 'video:width', webpage, default=None)) @@ -72,7 +53,6 @@ class ImgurIE(InfoExtractor): 'format_id': m.group('type').partition('/')[2], 'url': self._proto_relative_url(m.group('src')), 'ext': mimetype2ext(m.group('type')), - 'acodec': 'none', 'width': width, 'height': height, 'http_headers': { @@ -107,44 +87,64 @@ class ImgurIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'description': self._og_search_description(webpage, default=None), 'title': self._og_search_title(webpage), } -class ImgurAlbumIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P[a-zA-Z0-9]{5})(?:[/?#&]+)?$' +class ImgurGalleryIE(InfoExtractor): + IE_NAME = 'imgur:gallery' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'http://imgur.com/gallery/Q95ko', 'info_dict': { 'id': 'Q95ko', + 'title': 'Adding faces make every GIF better', }, 'playlist_count': 25, }, { - 'url': 'http://imgur.com/a/j6Orj', + 'url': 'http://imgur.com/topic/Aww/ll5Vk', 'only_matching': True, }, { - 'url': 'http://imgur.com/topic/Aww/ll5Vk', + 'url': 'https://imgur.com/gallery/YcAQlkx', + 'info_dict': { + 'id': 'YcAQlkx', + 'ext': 'mp4', + 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', + } + }, { + 'url': 'http://imgur.com/topic/Funny/N8rOudd', + 'only_matching': True, + }, { + 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, }] def _real_extract(self, url): - album_id = self._match_id(url) + gallery_id = self._match_id(url) - album_images = self._download_json( - 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, - album_id, fatal=False) + data = self._download_json( + 'https://imgur.com/gallery/%s.json' % gallery_id, + gallery_id)['data']['image'] - if album_images: - data = album_images.get('data') - if data and isinstance(data, dict): - images = data.get('images') - if images and isinstance(images, list): - entries = [ - self.url_result('http://imgur.com/%s' % image['hash']) - for image in images if image.get('hash')] - return self.playlist_result(entries, album_id) + if data.get('is_album'): + entries = [ + self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash']) + for image in data['album_images']['images'] if image.get('hash')] + return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description')) - # Fallback to single video - return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key()) + return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id) + + +class ImgurAlbumIE(ImgurGalleryIE): + IE_NAME = 'imgur:album' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P[a-zA-Z0-9]+)' + + _TESTS = [{ + 'url': 'http://imgur.com/a/j6Orj', + 'info_dict': { + 'id': 'j6Orj', + 'title': 'A Literary Analysis of "Star Wars: The Force Awakens"', + }, + 'playlist_count': 12, + }] From 3ad6dabd33307c0125fd462c4988083e360c40ad Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 9 Dec 2018 10:04:00 +0100 Subject: [PATCH 29/60] [aenetworks] add support for History Vault(closes #18460) --- youtube_dl/extractor/aenetworks.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 398e56ea3..85ec6392d 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -22,18 +22,19 @@ class AENetworksBaseIE(ThePlatformIE): class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' - IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' + IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault' _VALID_URL = r'''(?x) https?:// (?:www\.)? (?P - (?:history|aetv|mylifetime|lifetimemovieclub)\.com| + (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com| fyi\.tv )/ (?: shows/(?P[^/]+(?:/[^/]+){0,2})| movies/(?P[^/]+)(?:/full-movie)?| - specials/(?P[^/]+)/full-special + specials/(?P[^/]+)/full-special| + collections/[^/]+/(?P[^/]+) ) ''' _TESTS = [{ @@ -80,6 +81,9 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special', 'only_matching': True + }, { + 'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', @@ -90,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE): } def _real_extract(self, url): - domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups() - display_id = show_path or movie_display_id or special_display_id - webpage = self._download_webpage(url, display_id) + domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id or special_display_id or collection_display_id + webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers()) if show_path: url_parts = show_path.split('/') url_parts_len = len(url_parts) From 5ee7ae5c7577c9c137a7b38edd5ad01ae3a40376 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 22:28:24 +0700 Subject: [PATCH 30/60] [teachable] Add support for teachable based platform sites (closes #5451, closes #18150, closes #18272) --- youtube_dl/extractor/extractors.py | 8 +- youtube_dl/extractor/generic.py | 5 + .../extractor/{upskill.py => teachable.py} | 129 ++++++++++++++---- 3 files changed, 115 insertions(+), 27 deletions(-) rename youtube_dl/extractor/{upskill.py => teachable.py} (52%) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e28db6968..6a5d12ab1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1091,6 +1091,10 @@ from .tass import TassIE from .tastytrade import TastyTradeIE from .tbs import TBSIE from .tdslifeway import TDSLifewayIE +from .teachable import ( + TeachableIE, + TeachableCourseIE, +) from .teachertube import ( TeacherTubeIE, TeacherTubeUserIE, @@ -1240,10 +1244,6 @@ from .uplynk import ( UplynkIE, UplynkPreplayIE, ) -from .upskill import ( - UpskillIE, - UpskillCourseIE, -) from .urort import UrortIE from .urplay import URPlayIE from .usanetwork import USANetworkIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 59cf03faf..65b482333 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -109,6 +109,7 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .teachable import TeachableIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE @@ -3112,6 +3113,10 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( diff --git a/youtube_dl/extractor/upskill.py b/youtube_dl/extractor/teachable.py similarity index 52% rename from youtube_dl/extractor/upskill.py rename to youtube_dl/extractor/teachable.py index 30297b4dd..a0c46b2e6 100644 --- a/youtube_dl/extractor/upskill.py +++ b/youtube_dl/extractor/teachable.py @@ -14,20 +14,38 @@ from ..utils import ( ) -class UpskillBaseIE(InfoExtractor): - _LOGIN_URL = 'http://upskillcourses.com/sign_in' - _NETRC_MACHINE = 'upskill' +class TeachableBaseIE(InfoExtractor): + _NETRC_MACHINE = 'teachable' + _URL_PREFIX = 'teachable:' + + _SITES = { + # Only notable ones here + 'upskillcourses.com': 'upskill', + 'academy.gns3.com': 'gns3', + 'academyhacker.com': 'academyhacker', + 'stackskills.com': 'stackskills', + 'market.saleshacker.com': 'saleshacker', + 'learnability.org': 'learnability', + 'edurila.com': 'edurila', + } + + _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys())) def _real_initialize(self): - self._login() + self._logged_in = False - def _login(self): - username, password = self._get_login_info() + def _login(self, site): + if self._logged_in: + return + + username, password = self._get_login_info( + netrc_machine=self._SITES.get(site, site)) if username is None: return login_page, urlh = self._download_webpage_handle( - self._LOGIN_URL, None, 'Downloading login page') + 'https://%s/sign_in' % site, None, + 'Downloading %s login page' % site) login_url = compat_str(urlh.geturl()) @@ -46,18 +64,24 @@ class UpskillBaseIE(InfoExtractor): post_url = urljoin(login_url, post_url) response = self._download_webpage( - post_url, None, 'Logging in', + post_url, None, 'Logging in to %s' % site, data=urlencode_postdata(login_form), headers={ 'Content-Type': 'application/x-www-form-urlencoded', 'Referer': login_url, }) + if '>I accept the new Privacy Policy<' in response: + raise ExtractorError( + 'Unable to login: %s asks you to accept new Privacy Policy. ' + 'Go to https://%s/ and accept.' % (site, site), expected=True) + # Successful login if any(re.search(p, response) for p in ( r'class=["\']user-signout', r']+\bhref=["\']/sign_out', r'>\s*Log out\s*<')): + self._logged_in = True return message = get_element_by_class('alert', response) @@ -68,8 +92,14 @@ class UpskillBaseIE(InfoExtractor): raise ExtractorError('Unable to log in') -class UpskillIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P\d+)' +class TeachableIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P[^/]+)| + https?://(?:www\.)?(?P%s) + ) + /courses/[^/]+/lectures/(?P\d+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', @@ -77,7 +107,7 @@ class UpskillIE(UpskillBaseIE): 'id': 'uzw6zw58or', 'ext': 'mp4', 'title': 'Welcome to the Course!', - 'description': 'md5:8d66c13403783370af62ca97a7357bdd', + 'description': 'md5:65edb0affa582974de4625b9cdea1107', 'duration': 138.763, 'timestamp': 1479846621, 'upload_date': '20161122', @@ -88,10 +118,38 @@ class UpskillIE(UpskillBaseIE): }, { 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', + 'only_matching': True, + }, { + 'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'only_matching': True, }] + @staticmethod + def _is_teachable(webpage): + return 'teachableTracker.linker:autoLink' in webpage and re.search( + r']+href=["\']https?://process\.fs\.teachablecdn\.com', + webpage) + + @staticmethod + def _extract_url(webpage, source_url): + if not TeachableIE._is_teachable(webpage): + print('NOT TEACHABLE') + return + if re.match(r'https?://[^/]+/(?:courses|p)', source_url): + return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url) + def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') or mobj.group('site_t') + video_id = mobj.group('id') + + self._login(site) + + prefixed = url.startswith(self._URL_PREFIX) + if prefixed: + url = url[len(self._URL_PREFIX):] webpage = self._download_webpage(url, video_id) @@ -113,12 +171,18 @@ class UpskillIE(UpskillBaseIE): } -class UpskillCourseIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P[^/?#&]+)' +class TeachableCourseIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P[^/]+)| + https?://(?:www\.)?(?P%s) + ) + /(?:courses|p)/(?:enrolled/)?(?P[^/?#&]+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/', 'info_dict': { - 'id': '119763', + 'id': 'essential-web-developer-course', 'title': 'The Essential Web Developer Course (Free)', }, 'playlist_count': 192, @@ -128,21 +192,37 @@ class UpskillCourseIE(UpskillBaseIE): }, { 'url': 'http://upskillcourses.com/courses/enrolled/119763', 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/enrolled/423415', + 'only_matching': True, + }, { + 'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini', + 'only_matching': True, + }, { + 'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course', + 'only_matching': True, }] @classmethod def suitable(cls, url): - return False if UpskillIE.suitable(url) else super( - UpskillCourseIE, cls).suitable(url) + return False if TeachableIE.suitable(url) else super( + TeachableCourseIE, cls).suitable(url) def _real_extract(self, url): - course_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') or mobj.group('site_t') + course_id = mobj.group('id') + + self._login(site) + + prefixed = url.startswith(self._URL_PREFIX) + if prefixed: + prefix = self._URL_PREFIX + url = url[len(prefix):] webpage = self._download_webpage(url, course_id) - course_id = self._search_regex( - r'data-course-id=["\'](\d+)', webpage, 'course id', - default=course_id) + url_base = 'https://%s/' % site entries = [] @@ -162,10 +242,13 @@ class UpskillCourseIE(UpskillBaseIE): title = self._html_search_regex( r']+class=["\']lecture-name[^>]+>([^<]+)', li, 'title', default=None) + entry_url = urljoin(url_base, lecture_url) + if prefixed: + entry_url = self._URL_PREFIX + entry_url entries.append( self.url_result( - urljoin('http://upskillcourses.com/', lecture_url), - ie=UpskillIE.ie_key(), video_id=lecture_id, + entry_url, + ie=TeachableIE.ie_key(), video_id=lecture_id, video_title=clean_html(title))) course_title = self._html_search_regex( From 9e02c2c704d15d56b92ebe2fc8d481f99f5d106d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 22:56:33 +0700 Subject: [PATCH 31/60] [YoutubeDLCookieJar] Add test for keeping session cookies --- test/test_YoutubeDLCookieJar.py | 34 +++++++++++++++++++++++ test/testdata/cookies/session_cookies.txt | 6 ++++ 2 files changed, 40 insertions(+) create mode 100644 test/test_YoutubeDLCookieJar.py create mode 100644 test/testdata/cookies/session_cookies.txt diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py new file mode 100644 index 000000000..6a8243590 --- /dev/null +++ b/test/test_YoutubeDLCookieJar.py @@ -0,0 +1,34 @@ +#!/usr/bin/env python +# coding: utf-8 + +from __future__ import unicode_literals + +import os +import re +import sys +import tempfile +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.utils import YoutubeDLCookieJar + + +class TestYoutubeDLCookieJar(unittest.TestCase): + def test_keep_session_cookies(self): + cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt') + cookiejar.load(ignore_discard=True, ignore_expires=True) + tf = tempfile.NamedTemporaryFile(delete=False) + try: + cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True) + temp = tf.read().decode('utf-8') + self.assertTrue(re.search( + r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp)) + self.assertTrue(re.search( + r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpires0\s+YoutubeDLExpires0Value', temp)) + finally: + tf.close() + os.remove(tf.name) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/testdata/cookies/session_cookies.txt b/test/testdata/cookies/session_cookies.txt new file mode 100644 index 000000000..91e5c9231 --- /dev/null +++ b/test/testdata/cookies/session_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. + +www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value +www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue From 24cc64254c03c56229654b13d833c600d7048bbb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 23:08:16 +0700 Subject: [PATCH 32/60] [ChangeLog] Actualize [ci skip] --- ChangeLog | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/ChangeLog b/ChangeLog index 689d07826..6afee3a28 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,27 @@ +version + +Core +* [YoutubeDL] Keep session cookies in cookie file between runs +* [YoutubeDL] Recognize session cookies with expired set to 0 (#12929) + +Extractors ++ [teachable] Add support for teachable platform sites (#5451, #18150, #18272) ++ [aenetworks] Add support for historyvault.com (#18460) +* [imgur] Improve gallery and album detection and extraction (#9133, #16577, + #17223, #18404) +* [iprima] Relax URL regular expression (#18453) +* [hotstar] Fix video data extraction (#18386) +* [ard:mediathek] Fix title and description extraction (#18349, #18371) +* [xvideos] Switch to HTTPS (#18422, #18427) ++ [lecturio] Add support for lecturio.com (#18405) ++ [nrktv:series] Add support for extra materials +* [nrktv:season,series] Fix extraction (#17159, #17258) +* [nrktv] Relax URL regular expression (#18304, #18387) +* [yourporn] Fix extraction (#18424, #18425) +* [tbs] Fix info extraction (#18403) ++ [gamespot] Add support for review URLs + + version 2018.12.03 Core From cefe42c412168e95b78dcefc5cdba608dba7dd02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 23:11:32 +0700 Subject: [PATCH 33/60] release 2018.12.09 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 11 +++++++---- youtube_dl/version.py | 2 +- 4 files changed, 12 insertions(+), 9 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 4b35244a8..1ccf410a7 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 *2018.12.03*. 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 **2018.12.03** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.09*. 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 **2018.12.09** ### 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 2018.12.03 +[debug] youtube-dl version 2018.12.09 [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 6afee3a28..9aef67b52 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.09 Core * [YoutubeDL] Keep session cookies in cookie file between runs diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 837b0199b..31d20f255 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -33,7 +33,7 @@ - **AdobeTVShow** - **AdobeTVVideo** - **AdultSwim** - - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network + - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault - **afreecatv**: afreecatv.com - **AirMozilla** - **AliExpressLive** @@ -376,7 +376,8 @@ - **imdb**: Internet Movie Database trailers - **imdb:list**: Internet Movie Database lists - **Imgur** - - **ImgurAlbum** + - **imgur:album** + - **imgur:gallery** - **Ina** - **Inc** - **IndavideoEmbed** @@ -435,6 +436,8 @@ - **Le**: 乐视网 - **Learnr** - **Lecture2Go** + - **Lecturio** + - **LecturioCourse** - **LEGO** - **Lemonde** - **Lenta** @@ -853,6 +856,8 @@ - **TastyTrade** - **TBS** - **TDSLifeway** + - **Teachable** + - **TeachableCourse** - **teachertube**: teachertube.com videos - **teachertube:user:collection**: teachertube.com user and collection videos - **TeachingChannel** @@ -961,8 +966,6 @@ - **uol.com.br** - **uplynk** - **uplynk:preplay** - - **Upskill** - - **UpskillCourse** - **Urort**: NRK P3 Urørt - **URPlay** - **USANetwork** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 8e1203892..d15b9583f 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.03' +__version__ = '2018.12.09' From 59c3940165efaee6705ff06ef4fc4ac2c701107d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 10 Dec 2018 01:37:10 +0700 Subject: [PATCH 34/60] [ard:mediathek] Add support for classic.ardmediathek.de (closes #18473) --- youtube_dl/extractor/ard.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 84e96f769..2e1536a1b 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -21,7 +21,7 @@ from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ # available till 26.07.2022 @@ -51,6 +51,9 @@ class ARDMediathekIE(InfoExtractor): # audio 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', 'only_matching': True, + }, { + 'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698', + 'only_matching': True, }] def _extract_media_info(self, media_info_url, webpage, video_id): From 6e29458f2479c4535f8605032b9492f52bb37f17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 10 Dec 2018 04:30:00 +0700 Subject: [PATCH 35/60] [test/testdata/cookies/session_cookies.txt] Fix empty expires test data --- test/testdata/cookies/session_cookies.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/testdata/cookies/session_cookies.txt b/test/testdata/cookies/session_cookies.txt index 91e5c9231..f6996f031 100644 --- a/test/testdata/cookies/session_cookies.txt +++ b/test/testdata/cookies/session_cookies.txt @@ -2,5 +2,5 @@ # http://curl.haxx.se/rfc/cookie_spec.html # This is a generated file! Do not edit. +www.foobar.foobar FALSE / TRUE YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value -www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue From 102a4e54c5c0819233773cc15398bc901a218f4c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 10 Dec 2018 10:10:28 +0700 Subject: [PATCH 36/60] [teachable] Remove debug output --- youtube_dl/extractor/teachable.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index a0c46b2e6..47ac95ee8 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -135,7 +135,6 @@ class TeachableIE(TeachableBaseIE): @staticmethod def _extract_url(webpage, source_url): if not TeachableIE._is_teachable(webpage): - print('NOT TEACHABLE') return if re.match(r'https?://[^/]+/(?:courses|p)', source_url): return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url) From 13e17cd28e7f9e3bd8be4fa7b073a5cb96f5959f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 10 Dec 2018 14:59:57 +0100 Subject: [PATCH 37/60] [uol] fix format url extraction(closes 18480) --- youtube_dl/extractor/uol.py | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/uol.py b/youtube_dl/extractor/uol.py index e67083004..08f0c072e 100644 --- a/youtube_dl/extractor/uol.py +++ b/youtube_dl/extractor/uol.py @@ -61,7 +61,7 @@ class UOLIE(InfoExtractor): 'height': 360, }, '5': { - 'width': 1080, + 'width': 1280, 'height': 720, }, '6': { @@ -80,6 +80,10 @@ class UOLIE(InfoExtractor): 'width': 568, 'height': 320, }, + '11': { + 'width': 640, + 'height': 360, + } } def _real_extract(self, url): @@ -111,19 +115,31 @@ class UOLIE(InfoExtractor): 'ver': video_data.get('numRevision', 2), 'r': 'http://mais.uol.com.br', } + for k in ('token', 'sign'): + v = video_data.get(k) + if v: + query[k] = v + formats = [] for f in video_data.get('formats', []): f_url = f.get('url') or f.get('secureUrl') if not f_url: continue + f_url = update_url_query(f_url, query) format_id = str_or_none(f.get('id')) + if format_id == '10': + formats.extend(self._extract_m3u8_formats( + f_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + continue fmt = { 'format_id': format_id, - 'url': update_url_query(f_url, query), + 'url': f_url, + 'source_preference': 1, } fmt.update(self._FORMATS.get(format_id, {})) formats.append(fmt) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext')) tags = [] for tag in video_data.get('tags', []): From 0a05cfabb6338be750474a7286ce0d72a4d7c142 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 11 Dec 2018 23:45:02 +0700 Subject: [PATCH 38/60] [lecturio] Improve subtitles extraction (closes #18488) --- youtube_dl/extractor/lecturio.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 62ff28e02..0f1265cdf 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -136,9 +136,15 @@ class LecturioIE(LecturioBaseIE): cc_url = url_or_none(cc_url) if not cc_url: continue - sub_dict = automatic_captions if 'auto-translated' in cc_label else subtitles lang = self._search_regex( - r'/([a-z]{2})_', cc_url, 'lang', default=cc_label.split()[0]) + r'/([a-z]{2})_', cc_url, 'lang', + default=cc_label.split()[0] if cc_label else 'en') + original_lang = self._search_regex( + r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang', + default=None) + sub_dict = (automatic_captions + if 'auto-translated' in cc_label or original_lang + else subtitles) sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({ 'url': cc_url, }) From 8fe104947d6b772ccacd0b8af51d1adb16865e99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Dec 2018 22:25:12 +0700 Subject: [PATCH 39/60] [youtube] Fix multifeed extraction (closes #18531) --- youtube_dl/extractor/youtube.py | 52 ++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3f49f3889..c582ab2ff 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1712,30 +1712,36 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: video_description = '' - if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False): + if not smuggled_data.get('force_singlefeed', False): if not self._downloader.params.get('noplaylist'): - entries = [] - feed_ids = [] - multifeed_metadata_list = video_info['multifeed_metadata_list'][0] - for feed in multifeed_metadata_list.split(','): - # Unquote should take place before split on comma (,) since textual - # fields may contain comma as well (see - # https://github.com/rg3/youtube-dl/issues/8536) - feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) - entries.append({ - '_type': 'url_transparent', - 'ie_key': 'Youtube', - 'url': smuggle_url( - '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), - {'force_singlefeed': True}), - 'title': '%s (%s)' % (video_title, feed_data['title'][0]), - }) - feed_ids.append(feed_data['id'][0]) - self.to_screen( - 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' - % (', '.join(feed_ids), video_id)) - return self.playlist_result(entries, video_id, video_title, video_description) - self.to_screen('Downloading just video %s because of --no-playlist' % video_id) + multifeed_metadata_list = try_get( + player_response, + lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], + compat_str) or try_get( + video_info, lambda x: x['multifeed_metadata_list'][0], compat_str) + if multifeed_metadata_list: + entries = [] + feed_ids = [] + for feed in multifeed_metadata_list.split(','): + # Unquote should take place before split on comma (,) since textual + # fields may contain comma as well (see + # https://github.com/rg3/youtube-dl/issues/8536) + feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) + entries.append({ + '_type': 'url_transparent', + 'ie_key': 'Youtube', + 'url': smuggle_url( + '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), + {'force_singlefeed': True}), + 'title': '%s (%s)' % (video_title, feed_data['title'][0]), + }) + feed_ids.append(feed_data['id'][0]) + self.to_screen( + 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' + % (', '.join(feed_ids), video_id)) + return self.playlist_result(entries, video_id, video_title, video_description) + else: + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) if view_count is None: view_count = extract_view_count(video_info) From 7f41a598b3fba1bcab2817de64a08941200aa3c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Dec 2018 23:08:14 +0700 Subject: [PATCH 40/60] [safari] Add support for learning.oreilly.com (closes #18510) --- youtube_dl/extractor/safari.py | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 30e2a38b4..c0d32a1b9 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -15,10 +15,10 @@ from ..utils import ( class SafariBaseIE(InfoExtractor): - _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' + _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1' + _API_BASE = 'https://learning.oreilly.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False @@ -76,7 +76,7 @@ class SafariIE(SafariBaseIE): IE_DESC = 'safaribooksonline.com online video' _VALID_URL = r'''(?x) https?:// - (?:www\.)?safaribooksonline\.com/ + (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ (?: library/view/[^/]+/(?P[^/]+)/(?P[^/?\#&]+)\.html| videos/[^/]+/[^/]+/(?P[^-]+-[^/?\#&]+) @@ -104,6 +104,9 @@ class SafariIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00', 'only_matching': True, + }, { + 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro', + 'only_matching': True, }] _PARTNER_ID = '1926081' @@ -160,7 +163,7 @@ class SafariIE(SafariBaseIE): class SafariApiIE(SafariBaseIE): IE_NAME = 'safari:api' - _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P[^/]+)/chapter(?:-content)?/(?P[^/?#&]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P[^/]+)/chapter(?:-content)?/(?P[^/?#&]+)\.html' _TESTS = [{ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', @@ -185,7 +188,7 @@ class SafariCourseIE(SafariBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?safaribooksonline\.com/ + (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ (?: library/view/[^/]+| api/v1/book| @@ -213,6 +216,9 @@ class SafariCourseIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314', 'only_matching': True, + }, { + 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838', + 'only_matching': True, }] @classmethod From c984196cf1c9eb34725091e07a4f094b7eea1d4f Mon Sep 17 00:00:00 2001 From: Sergey M Date: Sat, 15 Dec 2018 23:59:17 +0700 Subject: [PATCH 41/60] [README.md] Bind info dict URLs to a fixed blob (closes #18492) --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 35c3de512..a1d2904c0 100644 --- a/README.md +++ b/README.md @@ -1024,7 +1024,7 @@ 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/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +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: @@ -1045,7 +1045,7 @@ 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/master/youtube_dl/extractor/common.py#L75-L257) 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/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: - `id` (media identifier) - `title` (media title) @@ -1053,7 +1053,7 @@ 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/master/youtube_dl/extractor/common.py#L149-L257) 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/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. #### Example From 21c340b83fb41094ef59b87d52c4eb1d90d1df04 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 16 Dec 2018 19:35:48 +0700 Subject: [PATCH 42/60] [youtube] Fix mark watched (closes #18546) --- youtube_dl/extractor/youtube.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index c582ab2ff..44c25c11c 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -48,6 +48,7 @@ from ..utils import ( unified_strdate, unsmuggle_url, uppercase_escape, + url_or_none, urlencode_postdata, ) @@ -1386,8 +1387,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._downloader.report_warning(err_msg) return {} - def _mark_watched(self, video_id, video_info): - playback_url = video_info.get('videostats_playback_base_url', [None])[0] + def _mark_watched(self, video_id, video_info, player_response): + playback_url = url_or_none(try_get( + player_response, + lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get( + video_info, lambda x: x['videostats_playback_base_url'][0])) if not playback_url: return parsed_playback_url = compat_urlparse.urlparse(playback_url) @@ -2122,7 +2126,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._sort_formats(formats) - self.mark_watched(video_id, video_info) + self.mark_watched(video_id, video_info, player_response) return { 'id': video_id, From c8b37510868b20b0829583557899d70db2ea6243 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 16 Dec 2018 14:28:40 +0100 Subject: [PATCH 43/60] [vrv] fix initial state extraction --- youtube_dl/extractor/vrv.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index ac0819c7c..483a3be3a 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -120,8 +120,10 @@ class VRVIE(VRVBaseIE): url, video_id, headers=self.geo_verification_headers()) media_resource = self._parse_json(self._search_regex( - r'window\.__INITIAL_STATE__\s*=\s*({.+?})', - webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {} + [ + r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:|;)', + 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: From 90046d77616f8f24e3716c64443118a9dcbec996 Mon Sep 17 00:00:00 2001 From: yonaikerlol Date: Sun, 16 Dec 2018 17:10:36 -0400 Subject: [PATCH 44/60] [iprima] Relax _VALID_URL (closes #18515) --- youtube_dl/extractor/iprima.py | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 11a6629d2..11bbeb592 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -12,7 +12,7 @@ from ..utils import ( class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://(?:play|prima|www)\.iprima\.cz/(?:[^/]+/)*(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P[^/?#&]+)' _GEO_BYPASS = False _TESTS = [{ @@ -44,6 +44,21 @@ class IPrimaIE(InfoExtractor): }, { 'url': 'http://www.iprima.cz/filmy/desne-rande', 'only_matching': True, + }, { + 'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby', + 'only_matching': True, + }, { + 'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy', + 'only_matching': True, + }, { + 'url': 'https://cool.iprima.cz/derava-silnice-nevadi', + 'only_matching': True, + }, { + 'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi', + 'only_matching': True, + }, { + 'url': 'https://autosalon.iprima.cz/motorsport/7-epizoda-1', + 'only_matching': True, }] def _real_extract(self, url): From 252e172dea96b90191682afac837535de4d33107 Mon Sep 17 00:00:00 2001 From: Tim Landscheidt Date: Sun, 16 Dec 2018 21:29:12 +0000 Subject: [PATCH 45/60] [acast] Add support for embed.acast.com --- youtube_dl/extractor/acast.py | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 6d846ea7a..1fbff705d 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -17,25 +17,8 @@ from ..utils import ( class ACastIE(InfoExtractor): IE_NAME = 'acast' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' + _VALID_URL = r'https?://(?:(?:embed|www)\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' _TESTS = [{ - # test with one bling - 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', - 'md5': 'ada3de5a1e3a2a381327d749854788bb', - 'info_dict': { - 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', - 'ext': 'mp3', - 'title': '"Where Are You?": Taipei 101, Taiwan', - 'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e', - 'timestamp': 1196172000, - 'upload_date': '20071127', - 'duration': 211, - 'creator': 'Concierge', - 'series': 'Condé Nast Traveler Podcast', - 'episode': '"Where Are You?": Taipei 101, Taiwan', - } - }, { - # test with multiple blings 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', 'md5': 'a02393c74f3bdb1801c3ec2695577ce0', 'info_dict': { @@ -50,6 +33,9 @@ class ACastIE(InfoExtractor): 'series': 'Spår', 'episode': '2. Raggarmordet - Röster ur det förflutna', } + }, { + 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015', + 'only_matching': True, }] def _real_extract(self, url): From 50a498a68e2f6754f5b26e5ad1f6eabfd9aeeb14 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 04:32:59 +0700 Subject: [PATCH 46/60] [acast] Extend _VALID_URL --- youtube_dl/extractor/acast.py | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 1fbff705d..b32f74a37 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -17,7 +17,14 @@ from ..utils import ( class ACastIE(InfoExtractor): IE_NAME = 'acast' - _VALID_URL = r'https?://(?:(?:embed|www)\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?:embed|www)\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/]+)/(?P[^/#?]+) + ''' _TESTS = [{ 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', 'md5': 'a02393c74f3bdb1801c3ec2695577ce0', @@ -36,6 +43,9 @@ class ACastIE(InfoExtractor): }, { 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015', 'only_matching': True, + }, { + 'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22', + 'only_matching': True, }] def _real_extract(self, url): From 1c82122741783adf6653df25fa81ef0f95a22279 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 04:51:57 +0700 Subject: [PATCH 47/60] [ard:beta] Relax _VALID_URL (closes #18441) --- youtube_dl/extractor/ard.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 2e1536a1b..a5df7f0f9 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -56,6 +56,10 @@ class ARDMediathekIE(InfoExtractor): 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url) + def _extract_media_info(self, media_info_url, webpage, video_id): media_info = self._download_json( media_info_url, video_id, 'Downloading media JSON') @@ -296,7 +300,7 @@ class ARDIE(InfoExtractor): class ARDBetaMediathekIE(InfoExtractor): - _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P[a-zA-Z0-9]+)/(?P[^/?#]+)' + _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P[a-zA-Z0-9]+)(?:/(?P[^/?#]+))?' _TESTS = [{ 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', @@ -310,12 +314,18 @@ class ARDBetaMediathekIE(InfoExtractor): 'upload_date': '20180826', 'ext': 'mp4', }, + }, { + 'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/', + 'only_matching': True, + }, { + 'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id webpage = self._download_webpage(url, display_id) data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json') From 752582183a1942b12880139039137b3a60962611 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 05:29:59 +0700 Subject: [PATCH 48/60] [ard:beta] Improve extraction robustness, fix subtitles extraction, improve geo restricted videos extraction --- youtube_dl/extractor/ard.py | 58 +++++++++++++++++++++++++------------ 1 file changed, 40 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index a5df7f0f9..8adae4644 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,13 +8,16 @@ from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, - qualities, int_or_none, parse_duration, + qualities, + str_or_none, + try_get, unified_strdate, - xpath_text, + unified_timestamp, update_url_query, url_or_none, + xpath_text, ) from ..compat import compat_etree_fromstring @@ -336,43 +339,62 @@ class ARDBetaMediathekIE(InfoExtractor): 'display_id': display_id, } formats = [] + subtitles = {} + geoblocked = False for widget in data.values(): - if widget.get('_geoblocked'): - raise ExtractorError('This video is not available due to geoblocking', expected=True) - + if widget.get('_geoblocked') is True: + geoblocked = True if '_duration' in widget: - res['duration'] = widget['_duration'] + res['duration'] = int_or_none(widget['_duration']) if 'clipTitle' in widget: res['title'] = widget['clipTitle'] if '_previewImage' in widget: res['thumbnail'] = widget['_previewImage'] if 'broadcastedOn' in widget: - res['upload_date'] = unified_strdate(widget['broadcastedOn']) + res['timestamp'] = unified_timestamp(widget['broadcastedOn']) if 'synopsis' in widget: res['description'] = widget['synopsis'] - if '_subtitleUrl' in widget: - res['subtitles'] = {'de': [{ + subtitle_url = url_or_none(widget.get('_subtitleUrl')) + if subtitle_url: + subtitles.setdefault('de', []).append({ 'ext': 'ttml', - 'url': widget['_subtitleUrl'], - }]} + 'url': subtitle_url, + }) if '_quality' in widget: - format_url = widget['_stream']['json'][0] - - if format_url.endswith('.f4m'): + format_url = url_or_none(try_get( + widget, lambda x: x['_stream']['json'][0])) + if not format_url: + continue + ext = determine_ext(format_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( format_url + '?hdcore=3.11.0', video_id, f4m_id='hds', fatal=False)) - elif format_url.endswith('m3u8'): + elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + format_url, video_id, 'mp4', m3u8_id='hls', + fatal=False)) else: + # HTTP formats are not available when geoblocked is True, + # other formats are fine though + if geoblocked: + continue + quality = str_or_none(widget.get('_quality')) formats.append({ - 'format_id': 'http-' + widget['_quality'], + 'format_id': ('http-' + quality) if quality else 'http', 'url': format_url, 'preference': 10, # Plain HTTP, that's nice }) + if not formats and geoblocked: + self.raise_geo_restricted( + msg='This video is not available due to geoblocking', + countries=['DE']) + self._sort_formats(formats) - res['formats'] = formats + res.update({ + 'subtitles': subtitles, + 'formats': formats, + }) return res From cbb3e4b14f59fe2dba5983f7e55308eba2ea025b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 05:34:55 +0700 Subject: [PATCH 49/60] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index 9aef67b52..291ae42bb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version + +Extractors +* [ard:beta] Improve geo restricted videos extraction +* [ard:beta] Fix subtitles extraction +* [ard:beta] Improve extraction robustness +* [ard:beta] Relax URL regular expression (#18441) +* [acast] Add support for embed.acast.com and play.acast.com (#18483) +* [iprima] Relax URL regular expression (#18515, #18540) +* [vrv] Fix initial state extraction (#18553) +* [youtube] Fix mark watched (#18546) ++ [safari] Add support for learning.oreilly.com (#18510) +* [youtube] Fix multifeed extraction (#18531) +* [lecturio] Improve subtitles extraction (#18488) +* [uol] Fix format URL extraction (#18480) ++ [ard:mediathek] Add support for classic.ardmediathek.de (#18473) + + version 2018.12.09 Core From 4cee62ade0d991eedb2feae927c44370be3c389e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 05:37:50 +0700 Subject: [PATCH 50/60] release 2018.12.17 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 1ccf410a7..b84559932 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 *2018.12.09*. 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 **2018.12.09** +### 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** ### 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 2018.12.09 +[debug] youtube-dl version 2018.12.17 [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/CONTRIBUTING.md b/CONTRIBUTING.md index bbcb78808..cba87190d 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -152,7 +152,7 @@ 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/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +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: @@ -173,7 +173,7 @@ 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/master/youtube_dl/extractor/common.py#L75-L257) 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/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: - `id` (media identifier) - `title` (media title) @@ -181,7 +181,7 @@ 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/master/youtube_dl/extractor/common.py#L149-L257) 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/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. #### Example diff --git a/ChangeLog b/ChangeLog index 291ae42bb..510013e89 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.17 Extractors * [ard:beta] Improve geo restricted videos extraction diff --git a/youtube_dl/version.py b/youtube_dl/version.py index d15b9583f..0461aac0c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.09' +__version__ = '2018.12.17' From 7216e9bff71b4c537bb8d56386d789bb83f921f9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 17 Dec 2018 16:34:51 +0100 Subject: [PATCH 51/60] [discovery] Add support for Scripps Networks watch domains(closes #17947) --- youtube_dl/extractor/discovery.py | 35 +++++++++++++++++-------- youtube_dl/extractor/scrippsnetworks.py | 29 +++++--------------- 2 files changed, 31 insertions(+), 33 deletions(-) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 3589bd428..44fbc41bb 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -17,16 +17,29 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?P - discovery| - investigationdiscovery| - discoverylife| - animalplanet| - ahctv| - destinationamerica| - sciencechannel| - tlc| - velocity + _VALID_URL = r'''(?x)https?:// + (?P + (?:www\.)? + (?: + discovery| + investigationdiscovery| + discoverylife| + animalplanet| + ahctv| + destinationamerica| + sciencechannel| + tlc| + velocity + )| + watch\. + (?: + hgtv| + foodnetwork| + travelchannel| + diynetwork| + cookingchanneltv| + motortrend + ) )\.com(?P/tv-shows/[^/]+/(?:video|full-episode)s/(?P[^./?#]+))''' _TESTS = [{ 'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley', @@ -71,7 +84,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): if not access_token: access_token = self._download_json( - 'https://www.%s.com/anonymous' % site, display_id, query={ + 'https://%s.com/anonymous' % site, display_id, query={ 'authRel': 'authorization', 'client_id': try_get( react_data, lambda x: x['application']['apiClientId'], diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index 4023aeef8..8b3275735 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -19,7 +19,7 @@ class ScrippsNetworksWatchIE(AWSIE): _VALID_URL = r'''(?x) https?:// watch\. - (?Phgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv|geniuskitchen)\.com/ + (?Pgeniuskitchen)\.com/ (?: player\.[A-Z0-9]+\.html\#| show/(?:[^/]+/){2}| @@ -28,38 +28,23 @@ class ScrippsNetworksWatchIE(AWSIE): (?P\d+) ''' _TESTS = [{ - 'url': 'http://watch.hgtv.com/show/HGTVE/Best-Ever-Treehouses/2241515/Best-Ever-Treehouses/', - 'md5': '26545fd676d939954c6808274bdb905a', + 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', 'info_dict': { - 'id': '4173834', + 'id': '4194875', 'ext': 'mp4', - 'title': 'Best Ever Treehouses', - 'description': "We're searching for the most over the top treehouses.", + 'title': 'Ample Hills Ice Cream Bike', + 'description': 'Courtney Rada churns up a signature GK Now ice cream with The Scoopmaster.', 'uploader': 'ANV', - 'upload_date': '20170922', - 'timestamp': 1506056400, + 'upload_date': '20171011', + 'timestamp': 1507698000, }, 'params': { 'skip_download': True, }, 'add_ie': [AnvatoIE.ie_key()], - }, { - 'url': 'http://watch.diynetwork.com/show/DSAL/Salvage-Dawgs/2656646/Covington-Church/', - 'only_matching': True, - }, { - 'url': 'http://watch.diynetwork.com/player.HNT.html#2656646', - 'only_matching': True, - }, { - 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', - 'only_matching': True, }] _SNI_TABLE = { - 'hgtv': 'hgtv', - 'diynetwork': 'diy', - 'foodnetwork': 'food', - 'cookingchanneltv': 'cook', - 'travelchannel': 'trav', 'geniuskitchen': 'genius', } From 386d1fea79e861b11c77a7353c07eb162fbb4dae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 23:43:12 +0700 Subject: [PATCH 52/60] [lecturio] Add support for lecturio.de (closes #18562) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/lecturio.py | 45 +++++++++++++++++++++++++++--- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6a5d12ab1..d72f52e36 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -557,6 +557,7 @@ from .lecture2go import Lecture2GoIE from .lecturio import ( LecturioIE, LecturioCourseIE, + LecturioDeCourseIE, ) from .leeco import ( LeIE, diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 0f1265cdf..24f78d928 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -64,8 +64,14 @@ class LecturioBaseIE(InfoExtractor): class LecturioIE(LecturioBaseIE): - _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P[^/?#&]+)\.lecture' - _TEST = { + _VALID_URL = r'''(?x) + https:// + (?: + app\.lecturio\.com/[^/]+/(?P[^/?#&]+)\.lecture| + (?:www\.)?lecturio\.de/[^/]+/(?P[^/?#&]+)\.vortrag + ) + ''' + _TESTS = [{ 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos', 'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870', 'info_dict': { @@ -74,7 +80,10 @@ class LecturioIE(LecturioBaseIE): 'title': 'Important Concepts and Terms – Introduction to Microbiology', }, 'skip': 'Requires lecturio account credentials', - } + }, { + 'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag', + 'only_matching': True, + }] _CC_LANGS = { 'German': 'de', @@ -86,7 +95,8 @@ class LecturioIE(LecturioBaseIE): } def _real_extract(self, url): - display_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') or mobj.group('id_de') webpage = self._download_webpage( 'https://app.lecturio.com/en/lecture/%s/player.html' % display_id, @@ -190,3 +200,30 @@ class LecturioCourseIE(LecturioBaseIE): 'title', default=None) return self.playlist_result(entries, display_id, title) + + +class LecturioDeCourseIE(LecturioBaseIE): + _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P[^/?#&]+)\.kurs' + _TEST = { + 'url': 'https://www.lecturio.de/jura/grundrechte.kurs', + 'only_matching': True, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'(?s)]+\bdata-lecture-id=["\'](?P\d+).+?\bhref=(["\'])(?P(?:(?!\2).)+\.vortrag)\b[^>]+>', + webpage): + lecture_url = urljoin(url, mobj.group('url')) + lecture_id = mobj.group('id') + entries.append(self.url_result( + lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id)) + + title = self._search_regex( + r']*>([^<]+)', webpage, 'title', default=None) + + return self.playlist_result(entries, display_id, title) From cfd13c4c45f63c408a3e53ac31561c286c9a3acc Mon Sep 17 00:00:00 2001 From: Daan van Vugt Date: Mon, 17 Dec 2018 18:03:00 +0100 Subject: [PATCH 53/60] [mediasite] Relax _VALID_URL --- youtube_dl/extractor/mediasite.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 84876b883..de37df0c6 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -21,7 +21,7 @@ from ..utils import ( class MediasiteIE(InfoExtractor): - _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' + _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/livebroadcast/Presentation)/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' _TESTS = [ { 'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d', @@ -84,7 +84,11 @@ class MediasiteIE(InfoExtractor): 'timestamp': 1333983600, 'duration': 7794, } - } + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d', + 'only_matching': True, + }, ] # look in Mediasite.Core.js (Mediasite.ContentStreamType[*]) From 4ee184545455d1ebf4a9f97f86ade2c4a3b3e03b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 18 Dec 2018 01:55:13 +0700 Subject: [PATCH 54/60] [mediasite] Extend _VALID_URL even more --- youtube_dl/extractor/mediasite.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index de37df0c6..ef9628e65 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -21,7 +21,7 @@ from ..utils import ( class MediasiteIE(InfoExtractor): - _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/livebroadcast/Presentation)/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' + _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' _TESTS = [ { 'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d', @@ -89,6 +89,10 @@ class MediasiteIE(InfoExtractor): 'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d', 'only_matching': True, }, + { + 'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d', + 'only_matching': True, + }, ] # look in Mediasite.Core.js (Mediasite.ContentStreamType[*]) From 65e29cdac3f3ee14e07c200293438426b1135719 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 18 Dec 2018 22:46:19 +0100 Subject: [PATCH 55/60] [twitter] pass referer with card request(closes #18579) --- youtube_dl/extractor/twitter.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index de41065d6..41d0b6be8 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -171,7 +171,8 @@ class TwitterCardIE(TwitterBaseIE): urls.append('https://twitter.com/i/videos/' + video_id) for u in urls: - webpage = self._download_webpage(u, video_id) + webpage = self._download_webpage( + u, video_id, headers={'Referer': 'https://twitter.com/'}) iframe_url = self._html_search_regex( r']+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', From 904bb599be0fcf5fa861f17eee757c3c9494208b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Elan=20Ruusam=C3=A4e?= Date: Wed, 19 Dec 2018 22:22:10 +0200 Subject: [PATCH 56/60] [README.md] Add flake8 instructions --- README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index a1d2904c0..b3c39bf66 100644 --- a/README.md +++ b/README.md @@ -1025,15 +1025,19 @@ 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! From 835e45abab88e2a1661b86be255e06323e88ec7a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 19 Dec 2018 22:07:37 +0100 Subject: [PATCH 57/60] [crackle] extract ism and http formats --- youtube_dl/extractor/crackle.py | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index 8dd9d6687..f73ef6b63 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -48,6 +48,21 @@ class CrackleIE(InfoExtractor): 'only_matching': True, }] + _MEDIA_FILE_SLOTS = { + '360p.mp4': { + 'width': 640, + 'height': 360, + }, + '480p.mp4': { + 'width': 768, + 'height': 432, + }, + '480p_1mbps.mp4': { + 'width': 852, + 'height': 480, + }, + } + def _real_extract(self, url): video_id = self._match_id(url) @@ -95,6 +110,20 @@ class CrackleIE(InfoExtractor): elif ext == 'mpd': formats.extend(self._extract_mpd_formats( format_url, video_id, mpd_id='dash', fatal=False)) + elif format_url.endswith('.ism/Manifest'): + formats.extend(self._extract_ism_formats( + format_url, video_id, ism_id='mss', fatal=False)) + else: + mfs_path = e.get('Type') + mfs_info = self._MEDIA_FILE_SLOTS.get(mfs_path) + if not mfs_info: + continue + formats.append({ + 'url': format_url, + 'format_id': 'http-' + mfs_path.split('.')[0], + 'width': mfs_info['width'], + 'height': mfs_info['height'], + }) self._sort_formats(formats) description = media.get('Description') From e1a0628797e2dc7e5e032f853ab4ddc6a7a08020 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 20 Dec 2018 23:22:51 +0100 Subject: [PATCH 58/60] [liveleak] add support for another embed type and restore original format extraction --- youtube_dl/extractor/liveleak.py | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index 26671753c..22a067e40 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -87,7 +87,7 @@ class LiveLeakIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r']+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"', + r']+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"', webpage) def _real_extract(self, url): @@ -120,13 +120,27 @@ class LiveLeakIE(InfoExtractor): } for idx, info_dict in enumerate(entries): + formats = [] for a_format in info_dict['formats']: if not a_format.get('height'): a_format['height'] = int_or_none(self._search_regex( r'([0-9]+)p\.mp4', a_format['url'], 'height label', default=None)) + formats.append(a_format) - self._sort_formats(info_dict['formats']) + # Removing '.*.mp4' gives the raw video, which is essentially + # the same video without the LiveLeak logo at the top (see + # https://github.com/rg3/youtube-dl/pull/4768) + orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url']) + if a_format['url'] != orig_url: + format_id = a_format.get('format_id') + formats.append({ + 'format_id': 'original' + ('-' + format_id if format_id else ''), + 'url': orig_url, + 'preference': 1, + }) + self._sort_formats(formats) + info_dict['formats'] = formats # Don't append entry ID for one-video pages to keep backward compatibility if len(entries) > 1: @@ -146,7 +160,7 @@ class LiveLeakIE(InfoExtractor): class LiveLeakEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P[if])=(?P[\w_]+)' + _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P[ift])=(?P[\w_]+)' # See generic.py for actual test cases _TESTS = [{ @@ -158,15 +172,14 @@ class LiveLeakEmbedIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - kind, video_id = mobj.group('kind', 'id') + kind, video_id = re.match(self._VALID_URL, url).groups() if kind == 'f': webpage = self._download_webpage(url, video_id) liveleak_url = self._search_regex( - r'logourl\s*:\s*(?P[\'"])(?P%s)(?P=q1)' % LiveLeakIE._VALID_URL, + r'(?:logourl\s*:\s*|window\.open\()(?P[\'"])(?P%s)(?P=q1)' % LiveLeakIE._VALID_URL, webpage, 'LiveLeak URL', group='url') - elif kind == 'i': - liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id + else: + liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id) return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key()) From 4273caf5c7e4a79783106938802c1f4e1aa9c950 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Dec 2018 16:38:16 +0700 Subject: [PATCH 59/60] [youtube] Extend html5 player regex (closes #17516) --- 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 44c25c11c..906774875 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1834,7 +1834,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version From 63529e935cf5f87e6080607ef9d9196fe435e092 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Dec 2018 16:57:10 +0700 Subject: [PATCH 60/60] [youtube] Relax html5 player regexes (closes #18465, closes #18466) --- 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 906774875..954853e00 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1105,7 +1105,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P[a-z]+)$', + r'.*?-(?P[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -1834,7 +1834,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version