diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 97b8afcf9..0721d49c3 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.01.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [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 2020.01.01 + [debug] youtube-dl version 2020.03.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index de6c44a65..1e67f724d 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.01.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index a9dd5ca52..1290b55c4 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.01.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 8347903ea..3f006bef8 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.01.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [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 2020.01.01 + [debug] youtube-dl version 2020.03.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 92228513c..202bb9b2f 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.01.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/.travis.yml b/.travis.yml index 14d95fa84..51afd469a 100644 --- a/.travis.yml +++ b/.travis.yml @@ -13,7 +13,7 @@ dist: trusty env: - YTDL_TEST_SET=core - YTDL_TEST_SET=download -matrix: +jobs: include: - python: 3.7 dist: xenial @@ -35,6 +35,11 @@ matrix: env: YTDL_TEST_SET=download - env: JYTHON=true; YTDL_TEST_SET=core - env: JYTHON=true; YTDL_TEST_SET=download + - name: flake8 + python: 3.8 + dist: xenial + install: pip install flake8 + script: flake8 . fast_finish: true allow_failures: - env: YTDL_TEST_SET=download diff --git a/ChangeLog b/ChangeLog index c33169cd8..1a676f4f2 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,114 @@ +version 2020.03.01 + +Core +* [YoutubeDL] Force redirect URL to unicode on python 2 +- [options] Remove duplicate short option -v for --version (#24162) + +Extractors +* [xhamster] Fix extraction (#24205) +* [franceculture] Fix extraction (#24204) ++ [telecinco] Add support for article opening videos +* [telecinco] Fix extraction (#24195) +* [xtube] Fix metadata extraction (#21073, #22455) +* [youjizz] Fix extraction (#24181) +- Remove no longer needed compat_str around geturl +* [pornhd] Fix extraction (#24128) ++ [teachable] Add support for multiple videos per lecture (#24101) ++ [wistia] Add support for multiple generic embeds (#8347, 11385) +* [imdb] Fix extraction (#23443) +* [tv2dk:bornholm:play] Fix extraction (#24076) + + +version 2020.02.16 + +Core +* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591, + #10622) +* [update] Fix updating via symlinks (#23991) ++ [compat] Introduce compat_realpath (#23991) + +Extractors ++ [npr] Add support for streams (#24042) ++ [24video] Add support for porn.24video.net (#23779, #23784) +- [jpopsuki] Remove extractor (#23858) +* [nova] Improve extraction (#23690) +* [nova:embed] Improve (#23690) +* [nova:embed] Fix extraction (#23672) ++ [abc:iview] Add support for 720p (#22907, #22921) +* [nytimes] Improve format sorting (#24010) ++ [toggle] Add support for mewatch.sg (#23895, #23930) +* [thisoldhouse] Fix extraction (#23951) ++ [popcorntimes] Add support for popcorntimes.tv (#23949) +* [sportdeutschland] Update to new API +* [twitch:stream] Lowercase channel id for stream request (#23917) +* [tv5mondeplus] Fix extraction (#23907, #23911) +* [tva] Relax URL regular expression (#23903) +* [vimeo] Fix album extraction (#23864) +* [viewlift] Improve extraction + * Fix extraction (#23851) + + Add support for authentication + + Add support for more domains +* [svt] Fix series extraction (#22297) +* [svt] Fix article extraction (#22897, #22919) +* [soundcloud] Imporve private playlist/set tracks extraction (#3707) + + +version 2020.01.24 + +Extractors +* [youtube] Fix sigfunc name extraction (#23819) +* [stretchinternet] Fix extraction (#4319) +* [voicerepublic] Fix extraction +* [azmedien] Fix extraction (#23783) +* [businessinsider] Fix jwplatform id extraction (#22929, #22954) ++ [24video] Add support for 24video.vip (#23753) +* [ivi:compilation] Fix entries extraction (#23770) +* [ard] Improve extraction (#23761) + * Simplify extraction + + Extract age limit and series + * Bypass geo-restriction ++ [nbc] Add support for nbc multi network URLs (#23049) +* [americastestkitchen] Fix extraction +* [zype] Improve extraction + + Extract subtitles (#21258) + + Support URLs with alternative keys/tokens (#21258) + + Extract more metadata +* [orf:tvthek] Improve geo restricted videos detection (#23741) +* [soundcloud] Restore previews extraction (#23739) + + +version 2020.01.15 + +Extractors +* [yourporn] Fix extraction (#21645, #22255, #23459) ++ [canvas] Add support for new API endpoint (#17680, #18629) +* [ndr:base:embed] Improve thumbnails extraction (#23731) ++ [vodplatform] Add support for embed.kwikmotion.com domain ++ [twitter] Add support for promo_video_website cards (#23711) +* [orf:radio] Clean description and improve extraction +* [orf:fm4] Fix extraction (#23599) +* [safari] Fix kaltura session extraction (#23679, #23670) +* [lego] Fix extraction and extract subtitle (#23687) +* [cloudflarestream] Improve extraction + + Add support for bytehighway.net domain + + Add support for signed URLs + + Extract thumbnail +* [naver] Improve extraction + * Improve geo-restriction handling + + Extract automatic captions + + Extract uploader metadata + + Extract VLive HLS formats + * Improve metadata extraction +- [pandatv] Remove extractor (#23630) +* [dctp] Fix format extraction (#23656) ++ [scrippsnetworks] Add support for www.discovery.com videos +* [discovery] Fix anonymous token extraction (#23650) +* [nrktv:seriebase] Fix extraction (#23625, #23537) +* [wistia] Improve format extraction and extract subtitles (#22590) +* [vice] Improve extraction (#23631) +* [redtube] Detect private videos (#23518) + + version 2020.01.01 Extractors diff --git a/devscripts/create-github-release.py b/devscripts/create-github-release.py index 6464ef322..2ddfa1096 100644 --- a/devscripts/create-github-release.py +++ b/devscripts/create-github-release.py @@ -1,7 +1,6 @@ #!/usr/bin/env python from __future__ import unicode_literals -import base64 import io import json import mimetypes diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e471aa79a..02bc088ab 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -389,7 +389,6 @@ - **JeuxVideo** - **Joj** - **Jove** - - **jpopsuki.tv** - **JWPlatform** - **Kakao** - **Kaltura** @@ -628,7 +627,6 @@ - **OutsideTV** - **PacktPub** - **PacktPubCourse** - - **PandaTV**: 熊猫TV - **pandora.tv**: 판도라TV - **ParamountNetwork** - **parliamentlive.tv**: UK parliament videos @@ -664,6 +662,7 @@ - **Pokemon** - **PolskieRadio** - **PolskieRadioCategory** + - **Popcorntimes** - **PopcornTV** - **PornCom** - **PornerBros** @@ -1005,8 +1004,8 @@ - **Vidzi** - **vier**: vier.be and vijf.be - **vier:videos** - - **ViewLift** - - **ViewLiftEmbed** + - **viewlift** + - **viewlift:embed** - **Viidea** - **viki** - **viki:channel** diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index ce9666171..1e204e551 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -816,11 +816,15 @@ class TestYoutubeDL(unittest.TestCase): 'webpage_url': 'http://example.com', } - def get_ids(params): + def get_downloaded_info_dicts(params): ydl = YDL(params) - # make a copy because the dictionary can be modified - ydl.process_ie_result(playlist.copy()) - return [int(v['id']) for v in ydl.downloaded_info_dicts] + # make a deep copy because the dictionary and nested entries + # can be modified + ydl.process_ie_result(copy.deepcopy(playlist)) + return ydl.downloaded_info_dicts + + def get_ids(params): + return [int(v['id']) for v in get_downloaded_info_dicts(params)] result = get_ids({}) self.assertEqual(result, [1, 2, 3, 4]) @@ -852,6 +856,22 @@ class TestYoutubeDL(unittest.TestCase): result = get_ids({'playlist_items': '2-4,3-4,3'}) self.assertEqual(result, [2, 3, 4]) + # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591 + # @{ + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + self.assertEqual(result[2]['playlist_index'], 4) + + result = get_downloaded_info_dicts({'playlist_items': '4,2'}) + self.assertEqual(result[0]['playlist_index'], 4) + self.assertEqual(result[1]['playlist_index'], 2) + # @} + def test_urlopen_no_file_protocol(self): # see https://github.com/ytdl-org/youtube-dl/issues/8227 ydl = YDL() diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 7d57a628e..17aaaf20d 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -26,7 +26,6 @@ from youtube_dl.extractor import ( ThePlatformIE, ThePlatformFeedIE, RTVEALaCartaIE, - FunnyOrDieIE, DemocracynowIE, ) @@ -322,18 +321,6 @@ class TestRtveSubtitles(BaseTestSubtitles): self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca') -class TestFunnyOrDieSubtitles(BaseTestSubtitles): - url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine' - IE = FunnyOrDieIE - - def test_allsubtitles(self): - self.DL.params['writesubtitles'] = True - self.DL.params['allsubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(set(subtitles.keys()), set(['en'])) - self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4') - - class TestDemocracynowSubtitles(BaseTestSubtitles): url = 'http://www.democracynow.org/shows/2015/7/3' IE = DemocracynowIE diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index f5cb46308..19370f62b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -92,6 +92,7 @@ from .utils import ( YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, + YoutubeDLRedirectHandler, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER @@ -990,7 +991,7 @@ class YoutubeDL(object): 'playlist_title': ie_result.get('title'), 'playlist_uploader': ie_result.get('uploader'), 'playlist_uploader_id': ie_result.get('uploader_id'), - 'playlist_index': i + playliststart, + 'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], 'webpage_url_basename': url_basename(ie_result['webpage_url']), @@ -2343,6 +2344,7 @@ class YoutubeDL(object): debuglevel = 1 if self.params.get('debug_printtraffic') else 0 https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) + redirect_handler = YoutubeDLRedirectHandler() data_handler = compat_urllib_request_DataHandler() # When passing our own FileHandler instance, build_opener won't add the @@ -2356,7 +2358,7 @@ class YoutubeDL(object): file_handler.file_open = file_open opener = compat_urllib_request.build_opener( - proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler) + proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler) # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index c75ab131b..d1b86bd13 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2754,6 +2754,17 @@ else: compat_expanduser = os.path.expanduser +if compat_os_name == 'nt' and sys.version_info < (3, 8): + # os.path.realpath on Windows does not follow symbolic links + # prior to Python 3.8 (see https://bugs.python.org/issue9949) + def compat_realpath(path): + while os.path.islink(path): + path = os.path.abspath(os.readlink(path)) + return path +else: + compat_realpath = os.path.realpath + + if sys.version_info < (3, 0): def compat_print(s): from .utils import preferredencoding @@ -2998,6 +3009,7 @@ __all__ = [ 'compat_os_name', 'compat_parse_qs', 'compat_print', + 'compat_realpath', 'compat_setenv', 'compat_shlex_quote', 'compat_shlex_split', diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 4ac323bf6..6637f4f35 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor): # ABC iview programs are normally available for 14 days only. _TESTS = [{ - 'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00', - 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', + 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00', + 'md5': '67715ce3c78426b11ba167d875ac6abf', 'info_dict': { - 'id': 'ZX9371A050S00', + 'id': 'LE1927H001S00', 'ext': 'mp4', - 'title': "Gaston's Birthday", - 'series': "Ben And Holly's Little Kingdom", - 'description': 'md5:f9de914d02f226968f598ac76f105bcf', - 'upload_date': '20180604', - 'uploader_id': 'abc4kids', - 'timestamp': 1528140219, + 'title': "Series 11 Ep 1", + 'series': "Gruen", + 'description': 'md5:52cc744ad35045baf6aded2ce7287f67', + 'upload_date': '20190925', + 'uploader_id': 'abc1', + 'timestamp': 1569445289, }, 'params': { 'skip_download': True, @@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor): 'hdnea': token, }) - for sd in ('sd', 'sd-low'): + for sd in ('720', 'sd', 'sd-low'): sd_url = try_get( stream, lambda x: x['streams']['hls'][sd], compat_str) if not sd_url: diff --git a/youtube_dl/extractor/americastestkitchen.py b/youtube_dl/extractor/americastestkitchen.py index 8b32aa886..9c9d77ae1 100644 --- a/youtube_dl/extractor/americastestkitchen.py +++ b/youtube_dl/extractor/americastestkitchen.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..utils import ( clean_html, int_or_none, + js_to_json, try_get, unified_strdate, ) @@ -13,22 +14,21 @@ from ..utils import ( class AmericasTestKitchenIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P\d+)' _TESTS = [{ - 'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party', + 'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers', 'md5': 'b861c3e365ac38ad319cfd509c30577f', 'info_dict': { - 'id': '1_5g5zua6e', - 'title': 'Summer Dinner Party', + 'id': '5b400b9ee338f922cb06450c', + 'title': 'Weeknight Japanese Suppers', 'ext': 'mp4', - 'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec', - 'thumbnail': r're:^https?://.*\.jpg', - 'timestamp': 1497285541, - 'upload_date': '20170612', - 'uploader_id': 'roger.metcalf@americastestkitchen.com', - 'release_date': '20170617', + 'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8', + 'thumbnail': r're:^https?://', + 'timestamp': 1523664000, + 'upload_date': '20180414', + 'release_date': '20180414', 'series': "America's Test Kitchen", - 'season_number': 17, - 'episode': 'Summer Dinner Party', - 'episode_number': 24, + 'season_number': 18, + 'episode': 'Weeknight Japanese Suppers', + 'episode_number': 15, }, 'params': { 'skip_download': True, @@ -47,7 +47,7 @@ class AmericasTestKitchenIE(InfoExtractor): self._search_regex( r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*', webpage, 'initial context'), - video_id) + video_id, js_to_json) ep_data = try_get( video_data, @@ -55,17 +55,7 @@ class AmericasTestKitchenIE(InfoExtractor): lambda x: x['videoDetail']['content']['data']), dict) ep_meta = ep_data.get('full_video', {}) - zype_id = ep_meta.get('zype_id') - if zype_id: - embed_url = 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id - ie_key = 'Zype' - else: - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id') - external_id = ep_data.get('external_id') or ep_meta['external_id'] - embed_url = 'kaltura:%s:%s' % (partner_id, external_id) - ie_key = 'Kaltura' + zype_id = ep_data.get('zype_id') or ep_meta['zype_id'] title = ep_data.get('title') or ep_meta.get('title') description = clean_html(ep_meta.get('episode_description') or ep_data.get( @@ -79,8 +69,8 @@ class AmericasTestKitchenIE(InfoExtractor): return { '_type': 'url_transparent', - 'url': embed_url, - 'ie_key': ie_key, + 'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id, + 'ie_key': 'Zype', 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 8adae4644..2f47e21c3 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor @@ -22,7 +23,101 @@ from ..utils import ( from ..compat import compat_etree_fromstring -class ARDMediathekIE(InfoExtractor): +class ARDMediathekBaseIE(InfoExtractor): + _GEO_COUNTRIES = ['DE'] + + def _extract_media_info(self, media_info_url, webpage, video_id): + media_info = self._download_json( + media_info_url, video_id, 'Downloading media JSON') + return self._parse_media_info(media_info, video_id, '"fsk"' in webpage) + + def _parse_media_info(self, media_info, video_id, fsk): + formats = self._extract_formats(media_info, video_id) + + if not formats: + if fsk: + raise ExtractorError( + 'This video is only available after 20:00', expected=True) + elif media_info.get('_geoblocked'): + self.raise_geo_restricted( + 'This video is not available due to geoblocking', + countries=self._GEO_COUNTRIES) + + self._sort_formats(formats) + + subtitles = {} + subtitle_url = media_info.get('_subtitleUrl') + if subtitle_url: + subtitles['de'] = [{ + 'ext': 'ttml', + 'url': subtitle_url, + }] + + return { + 'id': video_id, + 'duration': int_or_none(media_info.get('_duration')), + 'thumbnail': media_info.get('_previewImage'), + 'is_live': media_info.get('_isLive') is True, + 'formats': formats, + 'subtitles': subtitles, + } + + def _extract_formats(self, media_info, video_id): + type_ = media_info.get('_type') + media_array = media_info.get('_mediaArray', []) + formats = [] + for num, media in enumerate(media_array): + for stream in media.get('_mediaStreamArray', []): + stream_urls = stream.get('_stream') + if not stream_urls: + continue + if not isinstance(stream_urls, list): + stream_urls = [stream_urls] + quality = stream.get('_quality') + server = stream.get('_server') + for stream_url in stream_urls: + if not url_or_none(stream_url): + continue + ext = determine_ext(stream_url) + if quality != 'auto' and ext in ('f4m', 'm3u8'): + continue + if ext == 'f4m': + formats.extend(self._extract_f4m_formats( + update_url_query(stream_url, { + 'hdcore': '3.1.1', + 'plugin': 'aasp-3.1.1.69.124' + }), video_id, f4m_id='hds', fatal=False)) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + else: + if server and server.startswith('rtmp'): + f = { + 'url': server, + 'play_path': stream_url, + 'format_id': 'a%s-rtmp-%s' % (num, quality), + } + else: + f = { + 'url': stream_url, + 'format_id': 'a%s-%s-%s' % (num, ext, quality) + } + m = re.search( + r'_(?P\d+)x(?P\d+)\.mp4$', + stream_url) + if m: + f.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + if type_ == 'audio': + f['vcodec'] = 'none' + formats.append(f) + return formats + + +class ARDMediathekIE(ARDMediathekBaseIE): IE_NAME = 'ARD:mediathek' _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' @@ -63,94 +158,6 @@ class ARDMediathekIE(InfoExtractor): 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') - - formats = self._extract_formats(media_info, video_id) - - if not formats: - if '"fsk"' in webpage: - raise ExtractorError( - 'This video is only available after 20:00', expected=True) - elif media_info.get('_geoblocked'): - raise ExtractorError('This video is not available due to geo restriction', expected=True) - - self._sort_formats(formats) - - duration = int_or_none(media_info.get('_duration')) - thumbnail = media_info.get('_previewImage') - is_live = media_info.get('_isLive') is True - - subtitles = {} - subtitle_url = media_info.get('_subtitleUrl') - if subtitle_url: - subtitles['de'] = [{ - 'ext': 'ttml', - 'url': subtitle_url, - }] - - return { - 'id': video_id, - 'duration': duration, - 'thumbnail': thumbnail, - 'is_live': is_live, - 'formats': formats, - 'subtitles': subtitles, - } - - def _extract_formats(self, media_info, video_id): - type_ = media_info.get('_type') - media_array = media_info.get('_mediaArray', []) - formats = [] - for num, media in enumerate(media_array): - for stream in media.get('_mediaStreamArray', []): - stream_urls = stream.get('_stream') - if not stream_urls: - continue - if not isinstance(stream_urls, list): - stream_urls = [stream_urls] - quality = stream.get('_quality') - server = stream.get('_server') - for stream_url in stream_urls: - if not url_or_none(stream_url): - continue - ext = determine_ext(stream_url) - if quality != 'auto' and ext in ('f4m', 'm3u8'): - continue - if ext == 'f4m': - formats.extend(self._extract_f4m_formats( - update_url_query(stream_url, { - 'hdcore': '3.1.1', - 'plugin': 'aasp-3.1.1.69.124' - }), - video_id, f4m_id='hds', fatal=False)) - elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) - else: - if server and server.startswith('rtmp'): - f = { - 'url': server, - 'play_path': stream_url, - 'format_id': 'a%s-rtmp-%s' % (num, quality), - } - else: - f = { - 'url': stream_url, - 'format_id': 'a%s-%s-%s' % (num, ext, quality) - } - m = re.search(r'_(?P\d+)x(?P\d+)\.mp4$', stream_url) - if m: - f.update({ - 'width': int(m.group('width')), - 'height': int(m.group('height')), - }) - if type_ == 'audio': - f['vcodec'] = 'none' - formats.append(f) - return formats - def _real_extract(self, url): # determine video id from url m = re.match(self._VALID_URL, url) @@ -302,19 +309,20 @@ class ARDIE(InfoExtractor): } -class ARDBetaMediathekIE(InfoExtractor): - _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P[a-zA-Z0-9]+)(?:/(?P[^/?#]+))?' +class ARDBetaMediathekIE(ARDMediathekBaseIE): + _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P[^/]+)/(?:player|live)/(?P[a-zA-Z0-9]+)(?:/(?P[^/?#]+))?' _TESTS = [{ 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', - 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', + 'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f', 'info_dict': { 'display_id': 'die-robuste-roswita', - 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', - 'title': 'Tatort: Die robuste Roswita', + 'id': '70153354', + 'title': 'Die robuste Roswita', 'description': r're:^Der Mord.*trüber ist als die Ilm.', 'duration': 5316, - 'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard', - 'upload_date': '20180826', + 'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard', + 'timestamp': 1577047500, + 'upload_date': '20191222', 'ext': 'mp4', }, }, { @@ -330,71 +338,69 @@ class ARDBetaMediathekIE(InfoExtractor): video_id = mobj.group('video_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') - data = self._parse_json(data_json, display_id) - - res = { - 'id': video_id, - 'display_id': display_id, + player_page = self._download_json( + 'https://api.ardmediathek.de/public-gateway', + display_id, data=json.dumps({ + 'query': '''{ + playerPage(client:"%s", clipId: "%s") { + blockedByFsk + broadcastedOn + maturityContentRating + mediaCollection { + _duration + _geoblocked + _isLive + _mediaArray { + _mediaStreamArray { + _quality + _server + _stream } - formats = [] - subtitles = {} - geoblocked = False - for widget in data.values(): - if widget.get('_geoblocked') is True: - geoblocked = True - if '_duration' in widget: - 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['timestamp'] = unified_timestamp(widget['broadcastedOn']) - if 'synopsis' in widget: - res['description'] = widget['synopsis'] - subtitle_url = url_or_none(widget.get('_subtitleUrl')) - if subtitle_url: - subtitles.setdefault('de', []).append({ - 'ext': 'ttml', - 'url': subtitle_url, - }) - if '_quality' in widget: - 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 ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - 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-' + 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.update({ - 'subtitles': subtitles, - 'formats': formats, + } + _previewImage + _subtitleUrl + _type + } + show { + title + } + synopsis + title + tracking { + atiCustomVars { + contentId + } + } + } +}''' % (mobj.group('client'), video_id), + }).encode(), headers={ + 'Content-Type': 'application/json' + })['data']['playerPage'] + title = player_page['title'] + content_id = str_or_none(try_get( + player_page, lambda x: x['tracking']['atiCustomVars']['contentId'])) + media_collection = player_page.get('mediaCollection') or {} + if not media_collection and content_id: + media_collection = self._download_json( + 'https://www.ardmediathek.de/play/media/' + content_id, + content_id, fatal=False) or {} + info = self._parse_media_info( + media_collection, content_id or video_id, + player_page.get('blockedByFsk')) + age_limit = None + description = player_page.get('synopsis') + maturity_content_rating = player_page.get('maturityContentRating') + if maturity_content_rating: + age_limit = int_or_none(maturity_content_rating.lstrip('FSK')) + if not age_limit and description: + age_limit = int_or_none(self._search_regex( + r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None)) + info.update({ + 'age_limit': age_limit, + 'display_id': display_id, + 'title': title, + 'description': description, + 'timestamp': unified_timestamp(player_page.get('broadcastedOn')), + 'series': try_get(player_page, lambda x: x['show']['title']), }) - - return res + return info diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index fcbdc71b9..b1e20def5 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -47,39 +47,19 @@ class AZMedienIE(InfoExtractor): 'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1', 'only_matching': True }] - + _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d' _PARTNER_ID = '1719221' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - host = mobj.group('host') - video_id = mobj.group('id') - entry_id = mobj.group('kaltura_id') + host, display_id, article_id, entry_id = re.match(self._VALID_URL, url).groups() if not entry_id: - api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0]) - payload = { - 'query': '''query VideoContext($articleId: ID!) { - article: node(id: $articleId) { - ... on Article { - mainAssetRelation { - asset { - ... on VideoAsset { - kalturaId - } - } - } - } - } - }''', - 'variables': {'articleId': 'Article:%s' % mobj.group('article_id')}, - } - json_data = self._download_json( - api_url, video_id, headers={ - 'Content-Type': 'application/json', - }, - data=json.dumps(payload).encode()) - entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId'] + entry_id = self._download_json( + self._API_TEMPL % (host, host.split('.')[0]), display_id, query={ + 'variables': json.dumps({ + 'contextId': 'NewsArticle:' + article_id, + }), + })['data']['context']['mainAsset']['video']['kaltura']['kalturaId'] return self.url_result( 'kaltura:%s:%s' % (self._PARTNER_ID, entry_id), diff --git a/youtube_dl/extractor/businessinsider.py b/youtube_dl/extractor/businessinsider.py index dfcf9bc6b..73a57b1e4 100644 --- a/youtube_dl/extractor/businessinsider.py +++ b/youtube_dl/extractor/businessinsider.py @@ -9,21 +9,26 @@ class BusinessInsiderIE(InfoExtractor): _VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6', - 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e', + 'md5': 'ffed3e1e12a6f950aa2f7d83851b497a', 'info_dict': { - 'id': 'hZRllCfw', + 'id': 'cjGDb0X9', 'ext': 'mp4', - 'title': "Here's how much radiation you're exposed to in everyday life", - 'description': 'md5:9a0d6e2c279948aadaa5e84d6d9b99bd', - 'upload_date': '20170709', - 'timestamp': 1499606400, - }, - 'params': { - 'skip_download': True, + 'title': "Bananas give you more radiation exposure than living next to a nuclear power plant", + 'description': 'md5:0175a3baf200dd8fa658f94cade841b3', + 'upload_date': '20160611', + 'timestamp': 1465675620, }, }, { 'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/', - 'only_matching': True, + 'md5': '43f438dbc6da0b89f5ac42f68529d84a', + 'info_dict': { + 'id': '5zJwd4FK', + 'ext': 'mp4', + 'title': 'Deze dingen zorgen ervoor dat je minder snel een date scoort', + 'description': 'md5:2af8975825d38a4fed24717bbe51db49', + 'upload_date': '20170705', + 'timestamp': 1499270528, + }, }, { 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T', 'only_matching': True, @@ -35,7 +40,8 @@ class BusinessInsiderIE(InfoExtractor): jwplatform_id = self._search_regex( (r'data-media-id=["\']([a-zA-Z0-9]{8})', r'id=["\']jwplayer_([a-zA-Z0-9]{8})', - r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})'), + r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})', + r'(?:jwplatform\.com/players/|jwplayer_)([a-zA-Z0-9]{8})'), webpage, 'jwplatform id') return self.url_result( 'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(), diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py index c506bc5dd..8667a0d04 100644 --- a/youtube_dl/extractor/canvas.py +++ b/youtube_dl/extractor/canvas.py @@ -13,6 +13,8 @@ from ..utils import ( int_or_none, merge_dicts, parse_iso8601, + str_or_none, + url_or_none, ) @@ -20,15 +22,15 @@ class CanvasIE(InfoExtractor): _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?Pcanvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', - 'md5': '90139b746a0a9bd7bb631283f6e2a64e', + 'md5': '68993eda72ef62386a15ea2cf3c93107', 'info_dict': { 'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', 'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Nachtwacht: De Greystook', - 'description': 'md5:1db3f5dc4c7109c821261e7512975be7', + 'description': 'Nachtwacht: De Greystook', 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 1468.03, + 'duration': 1468.04, }, 'expected_warnings': ['is not a supported codec', 'Unknown MIME type'], }, { @@ -39,23 +41,45 @@ class CanvasIE(InfoExtractor): 'HLS': 'm3u8_native', 'HLS_AES': 'm3u8', } + _REST_API_BASE = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v1' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) site_id, video_id = mobj.group('site_id'), mobj.group('id') + # Old API endpoint, serves more formats but may fail for some videos data = self._download_json( 'https://mediazone.vrt.be/api/v1/%s/assets/%s' - % (site_id, video_id), video_id) + % (site_id, video_id), video_id, 'Downloading asset JSON', + 'Unable to download asset JSON', fatal=False) + + # New API endpoint + if not data: + token = self._download_json( + '%s/tokens' % self._REST_API_BASE, video_id, + 'Downloading token', data=b'', + headers={'Content-Type': 'application/json'})['vrtPlayerToken'] + data = self._download_json( + '%s/videos/%s' % (self._REST_API_BASE, video_id), + video_id, 'Downloading video JSON', fatal=False, query={ + 'vrtPlayerToken': token, + 'client': '%s@PROD' % site_id, + }, expected_status=400) + message = data.get('message') + if message and not data.get('title'): + if data.get('code') == 'AUTHENTICATION_REQUIRED': + self.raise_login_required(message) + raise ExtractorError(message, expected=True) title = data['title'] description = data.get('description') formats = [] for target in data['targetUrls']: - format_url, format_type = target.get('url'), target.get('type') + format_url, format_type = url_or_none(target.get('url')), str_or_none(target.get('type')) if not format_url or not format_type: continue + format_type = format_type.upper() if format_type in self._HLS_ENTRY_PROTOCOLS_MAP: formats.extend(self._extract_m3u8_formats( format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type], @@ -134,20 +158,20 @@ class CanvasEenIE(InfoExtractor): }, 'skip': 'Pagina niet gevonden', }, { - 'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles', + 'url': 'https://www.een.be/thuis/emma-pakt-thilly-aan', 'info_dict': { - 'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f', - 'display_id': 'herbekijk-sorry-voor-alles', + 'id': 'md-ast-3a24ced2-64d7-44fb-b4ed-ed1aafbf90b8', + 'display_id': 'emma-pakt-thilly-aan', 'ext': 'mp4', - 'title': 'Herbekijk Sorry voor alles', - 'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3', + 'title': 'Emma pakt Thilly aan', + 'description': 'md5:c5c9b572388a99b2690030afa3f3bad7', 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 3788.06, + 'duration': 118.24, }, 'params': { 'skip_download': True, }, - 'skip': 'Episode no longer available', + 'expected_warnings': ['is not a supported codec'], }, { 'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend', 'only_matching': True, @@ -183,19 +207,44 @@ class VrtNUIE(GigyaBaseIE): IE_DESC = 'VrtNU.be' _VALID_URL = r'https?://(?:www\.)?vrt\.be/(?Pvrtnu)/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ + # Available via old API endpoint 'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/', 'info_dict': { 'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'De zwarte weduwe', - 'description': 'md5:d90c21dced7db869a85db89a623998d4', + 'description': 'md5:db1227b0f318c849ba5eab1fef895ee4', 'duration': 1457.04, 'thumbnail': r're:^https?://.*\.jpg$', - 'season': '1', + 'season': 'Season 1', 'season_number': 1, 'episode_number': 1, }, - 'skip': 'This video is only available for registered users' + 'skip': 'This video is only available for registered users', + 'params': { + 'username': '', + 'password': '', + }, + 'expected_warnings': ['is not a supported codec'], + }, { + # Only available via new API endpoint + 'url': 'https://www.vrt.be/vrtnu/a-z/kamp-waes/1/kamp-waes-s1a5/', + 'info_dict': { + 'id': 'pbs-pub-0763b56c-64fb-4d38-b95b-af60bf433c71$vid-ad36a73c-4735-4f1f-b2c0-a38e6e6aa7e1', + 'ext': 'mp4', + 'title': 'Aflevering 5', + 'description': 'Wie valt door de mand tijdens een missie?', + 'duration': 2967.06, + 'season': 'Season 1', + 'season_number': 1, + 'episode_number': 5, + }, + 'skip': 'This video is only available for registered users', + 'params': { + 'username': '', + 'password': '', + }, + 'expected_warnings': ['Unable to download asset JSON', 'is not a supported codec', 'Unknown MIME type'], }] _NETRC_MACHINE = 'vrtnu' _APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy' diff --git a/youtube_dl/extractor/cloudflarestream.py b/youtube_dl/extractor/cloudflarestream.py index 8ff2c6531..2fdcfbb3a 100644 --- a/youtube_dl/extractor/cloudflarestream.py +++ b/youtube_dl/extractor/cloudflarestream.py @@ -1,20 +1,24 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import re from .common import InfoExtractor class CloudflareStreamIE(InfoExtractor): + _DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)' + _EMBED_RE = r'embed\.%s/embed/[^/]+\.js\?.*?\bvideo=' % _DOMAIN_RE + _ID_RE = r'[\da-f]{32}|[\w-]+\.[\w-]+\.[\w-]+' _VALID_URL = r'''(?x) https?:// (?: - (?:watch\.)?(?:cloudflarestream\.com|videodelivery\.net)/| - embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo= + (?:watch\.)?%s/| + %s ) - (?P[\da-f]+) - ''' + (?P%s) + ''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE) _TESTS = [{ 'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717', 'info_dict': { @@ -41,23 +45,28 @@ class CloudflareStreamIE(InfoExtractor): return [ mobj.group('url') for mobj in re.finditer( - r']+\bsrc=(["\'])(?P(?:https?:)?//embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1', + r']+\bsrc=(["\'])(?P(?:https?:)?//%s(?:%s).*?)\1' % (CloudflareStreamIE._EMBED_RE, CloudflareStreamIE._ID_RE), webpage)] def _real_extract(self, url): video_id = self._match_id(url) + domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net' + base_url = 'https://%s/%s/' % (domain, video_id) + if '.' in video_id: + video_id = self._parse_json(base64.urlsafe_b64decode( + video_id.split('.')[1]), video_id)['sub'] + manifest_base_url = base_url + 'manifest/video.' formats = self._extract_m3u8_formats( - 'https://cloudflarestream.com/%s/manifest/video.m3u8' % video_id, - video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', - fatal=False) + manifest_base_url + 'm3u8', video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) formats.extend(self._extract_mpd_formats( - 'https://cloudflarestream.com/%s/manifest/video.mpd' % video_id, - video_id, mpd_id='dash', fatal=False)) + manifest_base_url + 'mpd', video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) return { 'id': video_id, 'title': video_id, + 'thumbnail': base_url + 'thumbnails/thumbnail.jpg', 'formats': formats, } diff --git a/youtube_dl/extractor/dctp.py b/youtube_dl/extractor/dctp.py index 04ff214f7..e700f8d86 100644 --- a/youtube_dl/extractor/dctp.py +++ b/youtube_dl/extractor/dctp.py @@ -16,10 +16,11 @@ class DctpTvIE(InfoExtractor): _TESTS = [{ # 4x3 'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/', + 'md5': '3ffbd1556c3fe210724d7088fad723e3', 'info_dict': { 'id': '95eaa4f33dad413aa17b4ee613cccc6c', 'display_id': 'videoinstallation-fuer-eine-kaufhausfassade', - 'ext': 'flv', + 'ext': 'm4v', 'title': 'Videoinstallation für eine Kaufhausfassade', 'description': 'Kurzfilm', 'thumbnail': r're:^https?://.*\.jpg$', @@ -27,10 +28,6 @@ class DctpTvIE(InfoExtractor): 'timestamp': 1302172322, 'upload_date': '20110407', }, - 'params': { - # rtmp download - 'skip_download': True, - }, }, { # 16x9 'url': 'http://www.dctp.tv/filme/sind-youtuber-die-besseren-lehrer/', @@ -59,33 +56,26 @@ class DctpTvIE(InfoExtractor): uuid = media['uuid'] title = media['title'] - ratio = '16x9' if media.get('is_wide') else '4x3' - play_path = 'mp4:%s_dctp_0500_%s.m4v' % (uuid, ratio) + is_wide = media.get('is_wide') + formats = [] - servers = self._download_json( - 'http://www.dctp.tv/streaming_servers/', display_id, - note='Downloading server list JSON', fatal=False) + def add_formats(suffix): + templ = 'https://%%s/%s_dctp_%s.m4v' % (uuid, suffix) + formats.extend([{ + 'format_id': 'hls-' + suffix, + 'url': templ % 'cdn-segments.dctp.tv' + '/playlist.m3u8', + 'protocol': 'm3u8_native', + }, { + 'format_id': 's3-' + suffix, + 'url': templ % 'completed-media.s3.amazonaws.com', + }, { + 'format_id': 'http-' + suffix, + 'url': templ % 'cdn-media.dctp.tv', + }]) - if servers: - endpoint = next( - server['endpoint'] - for server in servers - if url_or_none(server.get('endpoint')) - and 'cloudfront' in server['endpoint']) - else: - endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/' - - app = self._search_regex( - r'^rtmpe?://[^/]+/(?P.*)$', endpoint, 'app') - - formats = [{ - 'url': endpoint, - 'app': app, - 'play_path': play_path, - 'page_url': url, - 'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-110.swf', - 'ext': 'flv', - }] + add_formats('0500_' + ('16x9' if is_wide else '4x3')) + if is_wide: + add_formats('720p') thumbnails = [] images = media.get('images') diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 6a2712cc5..e0139cc86 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -13,8 +13,8 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): _VALID_URL = r'''(?x)https?:// (?P - (?:(?:www|go)\.)?discovery| - (?:www\.)? + go\.discovery| + www\. (?: investigationdiscovery| discoverylife| @@ -22,8 +22,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): ahctv| destinationamerica| sciencechannel| - tlc| - velocity + tlc )| watch\. (?: @@ -83,7 +82,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): 'authRel': 'authorization', 'client_id': '3020a40c2356a645b4b4', 'nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), - 'redirectUri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html?https://www.%s.com' % site, + 'redirectUri': 'https://www.discovery.com/', })['access_token'] headers = self.geo_verification_headers() diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index c050bf9df..fe42821c7 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( encode_base_n, ExtractorError, @@ -55,7 +54,7 @@ class EpornerIE(InfoExtractor): webpage, urlh = self._download_webpage_handle(url, display_id) - video_id = self._match_id(compat_str(urlh.geturl())) + video_id = self._match_id(urlh.geturl()) hash = self._search_regex( r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7b05f5410..64d1fa251 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -497,7 +497,6 @@ from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .joj import JojIE from .jwplatform import JWPlatformIE -from .jpopsukitv import JpopsukiIE from .kakao import KakaoIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE @@ -808,7 +807,6 @@ from .packtpub import ( PacktPubIE, PacktPubCourseIE, ) -from .pandatv import PandaTVIE from .pandoratv import PandoraTVIE from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE @@ -851,6 +849,7 @@ from .polskieradio import ( PolskieRadioIE, PolskieRadioCategoryIE, ) +from .popcorntimes import PopcorntimesIE from .popcorntv import PopcornTVIE from .porn91 import Porn91IE from .porncom import PornComIE diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index b8fa17588..306b45fc9 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -31,7 +31,13 @@ class FranceCultureIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_data = extract_attributes(self._search_regex( - r'(?s)]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(]+data-asset-source="[^"]+"[^>]+>)', + r'''(?sx) + (?: + | + ]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*> + ).*? + (]+data-asset-source="[^"]+"[^>]+>) + ''', webpage, 'video data')) video_url = video_data['data-asset-source'] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 743ef47db..d1ec56be9 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2098,6 +2098,9 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'Smoky Barbecue Favorites', 'thumbnail': r're:^https?://.*\.jpe?g', + 'description': 'md5:5ff01e76316bd8d46508af26dc86023b', + 'upload_date': '20170909', + 'timestamp': 1504915200, }, 'add_ie': [ZypeIE.ie_key()], 'params': { @@ -2284,7 +2287,7 @@ class GenericIE(InfoExtractor): if head_response is not False: # Check for redirect - new_url = compat_str(head_response.geturl()) + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) if force_videoid: @@ -2384,12 +2387,12 @@ class GenericIE(InfoExtractor): return self.playlist_result( self._parse_xspf( doc, video_id, xspf_url=url, - xspf_base_url=compat_str(full_response.geturl())), + xspf_base_url=full_response.geturl()), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( doc, - mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0], + mpd_base_url=full_response.geturl().rpartition('/')[0], mpd_url=url) self._sort_formats(info_dict['formats']) return info_dict @@ -2534,14 +2537,15 @@ class GenericIE(InfoExtractor): dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) # Look for embedded Wistia player - wistia_url = WistiaIE._extract_url(webpage) - if wistia_url: - return { - '_type': 'url_transparent', - 'url': self._proto_relative_url(wistia_url), - 'ie_key': WistiaIE.ie_key(), - 'uploader': video_uploader, - } + wistia_urls = WistiaIE._extract_urls(webpage) + if wistia_urls: + playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key()) + for entry in playlist['entries']: + entry.update({ + '_type': 'url_transparent', + 'uploader': video_uploader, + }) + return playlist # Look for SVT player svt_url = SVTIE._extract_url(webpage) @@ -2960,7 +2964,7 @@ class GenericIE(InfoExtractor): # Look for VODPlatform embeds mobj = re.search( - r']+src=(["\'])(?P(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1', + r']+src=(["\'])(?P(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1', webpage) if mobj is not None: return self.url_result( diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 436759da5..a31301985 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import base64 +import json import re from .common import InfoExtractor @@ -8,6 +10,7 @@ from ..utils import ( mimetype2ext, parse_duration, qualities, + try_get, url_or_none, ) @@ -15,15 +18,16 @@ from ..utils import ( class ImdbIE(InfoExtractor): IE_NAME = 'imdb' IE_DESC = 'Internet Movie Database trailers' - _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P\d+)' + _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P\d+)' _TESTS = [{ 'url': 'http://www.imdb.com/video/imdb/vi2524815897', 'info_dict': { 'id': '2524815897', 'ext': 'mp4', - 'title': 'No. 2 from Ice Age: Continental Drift (2012)', + 'title': 'No. 2', 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7', + 'duration': 152, } }, { 'url': 'http://www.imdb.com/video/_/vi2524815897', @@ -47,21 +51,23 @@ class ImdbIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'https://www.imdb.com/videoplayer/vi' + video_id, video_id) - video_metadata = self._parse_json(self._search_regex( - r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage, - 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id] - title = self._html_search_meta( - ['og:title', 'twitter:title'], webpage) or self._html_search_regex( - r'(.+?)', webpage, 'title', fatal=False) or video_metadata['title'] + + data = self._download_json( + 'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id, + query={ + 'key': base64.b64encode(json.dumps({ + 'type': 'VIDEO_PLAYER', + 'subType': 'FORCE_LEGACY', + 'id': 'vi%s' % video_id, + }).encode()).decode(), + })[0] quality = qualities(('SD', '480p', '720p', '1080p')) formats = [] - for encoding in video_metadata.get('encodings', []): + for encoding in data['videoLegacyEncodings']: if not encoding or not isinstance(encoding, dict): continue - video_url = url_or_none(encoding.get('videoUrl')) + video_url = url_or_none(encoding.get('url')) if not video_url: continue ext = mimetype2ext(encoding.get( @@ -69,7 +75,7 @@ class ImdbIE(InfoExtractor): if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( video_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + preference=1, m3u8_id='hls', fatal=False)) continue format_id = encoding.get('definition') formats.append({ @@ -80,13 +86,33 @@ class ImdbIE(InfoExtractor): }) self._sort_formats(formats) + webpage = self._download_webpage( + 'https://www.imdb.com/video/vi' + video_id, video_id) + video_metadata = self._parse_json(self._search_regex( + r'args\.push\(\s*({.+?})\s*\)\s*;', webpage, + 'video metadata'), video_id) + + video_info = video_metadata.get('VIDEO_INFO') + if video_info and isinstance(video_info, dict): + info = try_get( + video_info, lambda x: x[list(video_info.keys())[0]][0], dict) + else: + info = {} + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage) or self._html_search_regex( + r'(.+?)', webpage, 'title', + default=None) or info['videoTitle'] + return { 'id': video_id, 'title': title, + 'alt_title': info.get('videoSubTitle'), 'formats': formats, - 'description': video_metadata.get('description'), - 'thumbnail': video_metadata.get('slate', {}).get('url'), - 'duration': parse_duration(video_metadata.get('duration')), + 'description': info.get('videoDescription'), + 'thumbnail': url_or_none(try_get( + video_metadata, lambda x: x['videoSlate']['source'])), + 'duration': parse_duration(info.get('videoRuntime')), } diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index a502e8806..b5a740a01 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -239,7 +239,7 @@ class IviCompilationIE(InfoExtractor): self.url_result( 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key()) for serie in re.findall( - r']+data-id="\1"' % compilation_id, html)] + r']+\bhref=["\']/watch/%s/(\d+)["\']' % compilation_id, html)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py deleted file mode 100644 index 4b5f346d1..000000000 --- a/youtube_dl/extractor/jpopsukitv.py +++ /dev/null @@ -1,68 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - unified_strdate, -) - - -class JpopsukiIE(InfoExtractor): - IE_NAME = 'jpopsuki.tv' - _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P\S+)' - - _TEST = { - 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', - 'md5': '88018c0c1a9b1387940e90ec9e7e198e', - 'info_dict': { - 'id': '00be659d23b0b40508169cdee4545771', - 'ext': 'mp4', - 'title': 'ayumi hamasaki - evolution', - 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', - 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', - 'uploader': 'plama_chan', - 'uploader_id': '404', - 'upload_date': '20121101' - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_url = 'http://www.jpopsuki.tv' + self._html_search_regex( - r'from: uploaded: (.*?)', webpage, 'video upload_date', - fatal=False)) - view_count_str = self._html_search_regex( - r'
  • Hits: ([0-9]+?)
    • ', webpage, 'video view_count', - fatal=False) - comment_count_str = self._html_search_regex( - r'

    ([0-9]+?) comments

    ', webpage, 'video comment_count', - fatal=False) - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - 'view_count': int_or_none(view_count_str), - 'comment_count': int_or_none(comment_count_str), - } diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 6ed7da4ab..1b2dcef46 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( clean_html, determine_ext, @@ -36,7 +35,7 @@ class LecturioBaseIE(InfoExtractor): self._LOGIN_URL, None, 'Downloading login popup') def is_logged(url_handle): - return self._LOGIN_URL not in compat_str(url_handle.geturl()) + return self._LOGIN_URL not in url_handle.geturl() # Already logged in if is_logged(urlh): diff --git a/youtube_dl/extractor/lego.py b/youtube_dl/extractor/lego.py index b312e77f1..1e3c19dfd 100644 --- a/youtube_dl/extractor/lego.py +++ b/youtube_dl/extractor/lego.py @@ -2,23 +2,24 @@ from __future__ import unicode_literals import re +import uuid from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( - unescapeHTML, - parse_duration, - get_element_by_class, + ExtractorError, + int_or_none, + qualities, ) class LEGOIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P[0-9a-f]+)' + _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P[a-z]{2}-[a-z]{2})/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P[0-9a-f]{32})' _TESTS = [{ 'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1', 'md5': 'f34468f176cfd76488767fc162c405fa', 'info_dict': { - 'id': '55492d823b1b4d5e985787fa8c2973b1', + 'id': '55492d82-3b1b-4d5e-9857-87fa8c2973b1_en-US', 'ext': 'mp4', 'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi', 'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi', @@ -26,103 +27,123 @@ class LEGOIE(InfoExtractor): }, { # geo-restricted but the contentUrl contain a valid url 'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399', - 'md5': '4c3fec48a12e40c6e5995abc3d36cc2e', + 'md5': 'c7420221f7ffd03ff056f9db7f8d807c', 'info_dict': { - 'id': '13bdc2299ab24d9685701a915b3d71e7', + 'id': '13bdc229-9ab2-4d96-8570-1a915b3d71e7_nl-NL', 'ext': 'mp4', - 'title': 'Aflevering 20 - Helden van het koninkrijk', + 'title': 'Aflevering 20: Helden van het koninkrijk', 'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941', + 'age_limit': 5, }, }, { - # special characters in title - 'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d', + # with subtitle + 'url': 'https://www.lego.com/nl-nl/kids/videos/classic/creative-storytelling-the-little-puppy-aa24f27c7d5242bc86102ebdc0f24cba', 'info_dict': { - 'id': '9685ee9d12e84ff38e84b4e3d0db533d', + 'id': 'aa24f27c-7d52-42bc-8610-2ebdc0f24cba_nl-NL', 'ext': 'mp4', - 'title': 'Force Surprise – LEGO® Star Wars™ Microfighters', - 'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3', + 'title': 'De kleine puppy', + 'description': 'md5:5b725471f849348ac73f2e12cfb4be06', + 'age_limit': 1, + 'subtitles': { + 'nl': [{ + 'ext': 'srt', + 'url': r're:^https://.+\.srt$', + }], + }, }, 'params': { 'skip_download': True, }, }] - _BITRATES = [256, 512, 1024, 1536, 2560] + _QUALITIES = { + 'Lowest': (64, 180, 320), + 'Low': (64, 270, 480), + 'Medium': (96, 360, 640), + 'High': (128, 540, 960), + 'Highest': (128, 720, 1280), + } def _real_extract(self, url): locale, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) - title = get_element_by_class('video-header', webpage).strip() - progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/' - streaming_base = 'http://legoprod-f.akamaihd.net/' - content_url = self._html_search_meta('contentUrl', webpage) - path = self._search_regex( - r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)', - content_url, 'video path', default=None) - if not path: - player_url = self._proto_relative_url(self._search_regex( - r']+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)', - webpage, 'player url', default=None)) - if not player_url: - base_url = self._proto_relative_url(self._search_regex( - r'data-baseurl="([^"]+)"', webpage, 'base url', - default='http://www.lego.com/%s/mediaplayer/video/' % locale)) - player_url = base_url + video_id - player_webpage = self._download_webpage(player_url, video_id) - video_data = self._parse_json(unescapeHTML(self._search_regex( - r"video='([^']+)'", player_webpage, 'video data')), video_id) - progressive_base = self._search_regex( - r'data-video-progressive-url="([^"]+)"', - player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/') - streaming_base = self._search_regex( - r'data-video-streaming-url="([^"]+)"', - player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/') - item_id = video_data['ItemId'] + countries = [locale.split('-')[1].upper()] + self._initialize_geo_bypass({ + 'countries': countries, + }) - net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]]) - base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])]) - path = '/'.join([net_storage_path, base_path]) - streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES)) + try: + item = self._download_json( + # https://contentfeed.services.lego.com/api/v2/item/[VIDEO_ID]?culture=[LOCALE]&contentType=Video + 'https://services.slingshot.lego.com/mediaplayer/v2', + video_id, query={ + 'videoId': '%s_%s' % (uuid.UUID(video_id), locale), + }, headers=self.geo_verification_headers()) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 451: + self.raise_geo_restricted(countries=countries) + raise - formats = self._extract_akamai_formats( - '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id) - m3u8_formats = list(filter( - lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none', - formats)) - if len(m3u8_formats) == len(self._BITRATES): - self._sort_formats(m3u8_formats) - for bitrate, m3u8_format in zip(self._BITRATES, m3u8_formats): - progressive_base_url = '%spublic/%s_%d.' % (progressive_base, path, bitrate) - mp4_f = m3u8_format.copy() - mp4_f.update({ - 'url': progressive_base_url + 'mp4', - 'format_id': m3u8_format['format_id'].replace('hls', 'mp4'), - 'protocol': 'http', - }) - web_f = { - 'url': progressive_base_url + 'webm', - 'format_id': m3u8_format['format_id'].replace('hls', 'webm'), - 'width': m3u8_format['width'], - 'height': m3u8_format['height'], - 'tbr': m3u8_format.get('tbr'), - 'ext': 'webm', + video = item['Video'] + video_id = video['Id'] + title = video['Title'] + + q = qualities(['Lowest', 'Low', 'Medium', 'High', 'Highest']) + formats = [] + for video_source in item.get('VideoFormats', []): + video_source_url = video_source.get('Url') + if not video_source_url: + continue + video_source_format = video_source.get('Format') + if video_source_format == 'F4M': + formats.extend(self._extract_f4m_formats( + video_source_url, video_id, + f4m_id=video_source_format, fatal=False)) + elif video_source_format == 'M3U8': + formats.extend(self._extract_m3u8_formats( + video_source_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=video_source_format, fatal=False)) + else: + video_source_quality = video_source.get('Quality') + format_id = [] + for v in (video_source_format, video_source_quality): + if v: + format_id.append(v) + f = { + 'format_id': '-'.join(format_id), + 'quality': q(video_source_quality), + 'url': video_source_url, } - formats.extend([web_f, mp4_f]) - else: - for bitrate in self._BITRATES: - for ext in ('web', 'mp4'): - formats.append({ - 'format_id': '%s-%s' % (ext, bitrate), - 'url': '%spublic/%s_%d.%s' % (progressive_base, path, bitrate, ext), - 'tbr': bitrate, - 'ext': ext, - }) + quality = self._QUALITIES.get(video_source_quality) + if quality: + f.update({ + 'abr': quality[0], + 'height': quality[1], + 'width': quality[2], + }), + formats.append(f) self._sort_formats(formats) + subtitles = {} + sub_file_id = video.get('SubFileId') + if sub_file_id and sub_file_id != '00000000-0000-0000-0000-000000000000': + net_storage_path = video.get('NetstoragePath') + invariant_id = video.get('InvariantId') + video_file_id = video.get('VideoFileId') + video_version = video.get('VideoVersion') + if net_storage_path and invariant_id and video_file_id and video_version: + subtitles.setdefault(locale[:2], []).append({ + 'url': 'https://lc-mediaplayerns-live-s.legocdn.com/public/%s/%s_%s_%s_%s_sub.srt' % (net_storage_path, invariant_id, video_file_id, locale, video_version), + }) + return { 'id': video_id, 'title': title, - 'description': self._html_search_meta('description', webpage), - 'thumbnail': self._html_search_meta('thumbnail', webpage), - 'duration': parse_duration(self._html_search_meta('duration', webpage)), + 'description': video.get('Description'), + 'thumbnail': video.get('GeneratedCoverImage') or video.get('GeneratedThumbnail'), + 'duration': int_or_none(video.get('Length')), 'formats': formats, + 'subtitles': subtitles, + 'age_limit': int_or_none(video.get('AgeFrom')), + 'season': video.get('SeasonTitle'), + 'season_number': int_or_none(video.get('Season')) or None, + 'episode_number': int_or_none(video.get('Episode')) or None, } diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py index a78c6556e..23ca965d9 100644 --- a/youtube_dl/extractor/linuxacademy.py +++ b/youtube_dl/extractor/linuxacademy.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_b64decode, compat_HTTPError, - compat_str, ) from ..utils import ( ExtractorError, @@ -99,7 +98,7 @@ class LinuxAcademyIE(InfoExtractor): 'sso': 'true', }) - login_state_url = compat_str(urlh.geturl()) + login_state_url = urlh.geturl() try: login_page = self._download_webpage( @@ -129,7 +128,7 @@ class LinuxAcademyIE(InfoExtractor): }) access_token = self._search_regex( - r'access_token=([^=&]+)', compat_str(urlh.geturl()), + r'access_token=([^=&]+)', urlh.geturl(), 'access token') self._download_webpage( diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 027a790b8..933df1495 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -6,7 +6,6 @@ import re from .theplatform import ThePlatformBaseIE from ..compat import ( compat_parse_qs, - compat_str, compat_urllib_parse_urlparse, ) from ..utils import ( @@ -114,7 +113,7 @@ class MediasetIE(ThePlatformBaseIE): continue urlh = ie._request_webpage( embed_url, video_id, note='Following embed URL redirect') - embed_url = compat_str(urlh.geturl()) + embed_url = urlh.geturl() program_guid = _program_guid(_qs(embed_url)) if program_guid: entries.append(embed_url) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 694a264d6..d6eb15740 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -129,7 +129,7 @@ class MediasiteIE(InfoExtractor): query = mobj.group('query') webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() # XXX: might have also extracted UrlReferrer and QueryString from the html service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index bb3d94413..61fc59126 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -1,68 +1,33 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( + clean_html, + dict_get, ExtractorError, int_or_none, + parse_duration, + try_get, update_url_query, ) -class NaverIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P\d+)' +class NaverBaseIE(InfoExtractor): + _CAPTION_EXT_RE = r'\.(?:ttml|vtt)' - _TESTS = [{ - 'url': 'http://tv.naver.com/v/81652', - 'info_dict': { - 'id': '81652', - 'ext': 'mp4', - 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', - 'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', - 'upload_date': '20130903', - }, - }, { - 'url': 'http://tv.naver.com/v/395837', - 'md5': '638ed4c12012c458fefcddfd01f173cd', - 'info_dict': { - 'id': '395837', - 'ext': 'mp4', - 'title': '9년이 지나도 아픈 기억, 전효성의 아버지', - 'description': 'md5:5bf200dcbf4b66eb1b350d1eb9c753f7', - 'upload_date': '20150519', - }, - 'skip': 'Georestricted', - }, { - 'url': 'http://tvcast.naver.com/v/81652', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - vid = self._search_regex( - r'videoId["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, - 'video id', fatal=None, group='value') - in_key = self._search_regex( - r'inKey["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, - 'key', default=None, group='value') - - if not vid or not in_key: - error = self._html_search_regex( - r'(?s)
    \s*(?:)?\s*

    (?P.+?)

    \s*
    ', - webpage, 'error', default=None) - if error: - raise ExtractorError(error, expected=True) - raise ExtractorError('couldn\'t extract vid and key') + def _extract_video_info(self, video_id, vid, key): video_data = self._download_json( 'http://play.rmcnmv.naver.com/vod/play/v2.0/' + vid, video_id, query={ - 'key': in_key, + 'key': key, }) meta = video_data['meta'] title = meta['subject'] formats = [] + get_list = lambda x: try_get(video_data, lambda y: y[x + 's']['list'], list) or [] def extract_formats(streams, stream_type, query={}): for stream in streams: @@ -73,7 +38,7 @@ class NaverIE(InfoExtractor): encoding_option = stream.get('encodingOption', {}) bitrate = stream.get('bitrate', {}) formats.append({ - 'format_id': '%s_%s' % (stream.get('type') or stream_type, encoding_option.get('id') or encoding_option.get('name')), + 'format_id': '%s_%s' % (stream.get('type') or stream_type, dict_get(encoding_option, ('name', 'id'))), 'url': stream_url, 'width': int_or_none(encoding_option.get('width')), 'height': int_or_none(encoding_option.get('height')), @@ -83,7 +48,7 @@ class NaverIE(InfoExtractor): 'protocol': 'm3u8_native' if stream_type == 'HLS' else None, }) - extract_formats(video_data.get('videos', {}).get('list', []), 'H264') + extract_formats(get_list('video'), 'H264') for stream_set in video_data.get('streams', []): query = {} for param in stream_set.get('keys', []): @@ -101,28 +66,101 @@ class NaverIE(InfoExtractor): 'mp4', 'm3u8_native', m3u8_id=stream_type, fatal=False)) self._sort_formats(formats) + replace_ext = lambda x, y: re.sub(self._CAPTION_EXT_RE, '.' + y, x) + + def get_subs(caption_url): + if re.search(self._CAPTION_EXT_RE, caption_url): + return [{ + 'url': replace_ext(caption_url, 'ttml'), + }, { + 'url': replace_ext(caption_url, 'vtt'), + }] + else: + return [{'url': caption_url}] + + automatic_captions = {} subtitles = {} - for caption in video_data.get('captions', {}).get('list', []): + for caption in get_list('caption'): caption_url = caption.get('source') if not caption_url: continue - subtitles.setdefault(caption.get('language') or caption.get('locale'), []).append({ - 'url': caption_url, - }) + sub_dict = automatic_captions if caption.get('type') == 'auto' else subtitles + sub_dict.setdefault(dict_get(caption, ('locale', 'language')), []).extend(get_subs(caption_url)) - upload_date = self._search_regex( - r']+class="date".*?(\d{4}\.\d{2}\.\d{2})', - webpage, 'upload date', fatal=False) - if upload_date: - upload_date = upload_date.replace('.', '') + user = meta.get('user', {}) return { 'id': video_id, 'title': title, 'formats': formats, 'subtitles': subtitles, - 'description': self._og_search_description(webpage), - 'thumbnail': meta.get('cover', {}).get('source') or self._og_search_thumbnail(webpage), + 'automatic_captions': automatic_captions, + 'thumbnail': try_get(meta, lambda x: x['cover']['source']), 'view_count': int_or_none(meta.get('count')), - 'upload_date': upload_date, + 'uploader_id': user.get('id'), + 'uploader': user.get('name'), + 'uploader_url': user.get('url'), } + + +class NaverIE(NaverBaseIE): + _VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/(?:v|embed)/(?P\d+)' + _GEO_BYPASS = False + _TESTS = [{ + 'url': 'http://tv.naver.com/v/81652', + 'info_dict': { + 'id': '81652', + 'ext': 'mp4', + 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', + 'description': '메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', + 'timestamp': 1378200754, + 'upload_date': '20130903', + 'uploader': '메가스터디, 합격불변의 법칙', + 'uploader_id': 'megastudy', + }, + }, { + 'url': 'http://tv.naver.com/v/395837', + 'md5': '8a38e35354d26a17f73f4e90094febd3', + 'info_dict': { + 'id': '395837', + 'ext': 'mp4', + 'title': '9년이 지나도 아픈 기억, 전효성의 아버지', + 'description': 'md5:eb6aca9d457b922e43860a2a2b1984d3', + 'timestamp': 1432030253, + 'upload_date': '20150519', + 'uploader': '4가지쇼 시즌2', + 'uploader_id': 'wrappinguser29', + }, + 'skip': 'Georestricted', + }, { + 'url': 'http://tvcast.naver.com/v/81652', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + content = self._download_json( + 'https://tv.naver.com/api/json/v/' + video_id, + video_id, headers=self.geo_verification_headers()) + player_info_json = content.get('playerInfoJson') or {} + current_clip = player_info_json.get('currentClip') or {} + + vid = current_clip.get('videoId') + in_key = current_clip.get('inKey') + + if not vid or not in_key: + player_auth = try_get(player_info_json, lambda x: x['playerOption']['auth']) + if player_auth == 'notCountry': + self.raise_geo_restricted(countries=['KR']) + elif player_auth == 'notLogin': + self.raise_login_required() + raise ExtractorError('couldn\'t extract vid and key') + info = self._extract_video_info(video_id, vid, in_key) + info.update({ + 'description': clean_html(current_clip.get('description')), + 'timestamp': int_or_none(current_clip.get('firstExposureTime'), 1000), + 'duration': parse_duration(current_clip.get('displayPlayTime')), + 'like_count': int_or_none(current_clip.get('recommendPoint')), + 'age_limit': 19 if current_clip.get('adult') else None, + }) + return info diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 5bc39d002..6f3cb3003 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -87,11 +87,25 @@ class NBCIE(AdobePassIE): def _real_extract(self, url): permalink, video_id = re.match(self._VALID_URL, url).groups() permalink = 'http' + compat_urllib_parse_unquote(permalink) - response = self._download_json( + video_data = self._download_json( 'https://friendship.nbc.co/v2/graphql', video_id, query={ - 'query': '''{ - page(name: "%s", platform: web, type: VIDEO, userId: "0") { - data { + 'query': '''query bonanzaPage( + $app: NBCUBrands! = nbc + $name: String! + $oneApp: Boolean + $platform: SupportedPlatforms! = web + $type: EntityPageType! = VIDEO + $userId: String! +) { + bonanzaPage( + app: $app + name: $name + oneApp: $oneApp + platform: $platform + type: $type + userId: $userId + ) { + metadata { ... on VideoPageData { description episodeNumber @@ -100,15 +114,20 @@ class NBCIE(AdobePassIE): mpxAccountId mpxGuid rating + resourceId seasonNumber secondaryTitle seriesShortTitle } } } -}''' % permalink, - }) - video_data = response['data']['page']['data'] +}''', + 'variables': json.dumps({ + 'name': permalink, + 'oneApp': True, + 'userId': '0', + }), + })['data']['bonanzaPage']['metadata'] query = { 'mbr': 'true', 'manifest': 'm3u', @@ -117,8 +136,8 @@ class NBCIE(AdobePassIE): title = video_data['secondaryTitle'] if video_data.get('locked'): resource = self._get_mvpd_resource( - 'nbcentertainment', title, video_id, - video_data.get('rating')) + video_data.get('resourceId') or 'nbcentertainment', + title, video_id, video_data.get('rating')) query['auth'] = self._extract_mvpd_auth( url, video_id, 'nbcentertainment', resource) theplatform_url = smuggle_url(update_url_query( diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index aec2ea133..9c8bf05af 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -9,6 +9,8 @@ from ..utils import ( int_or_none, parse_iso8601, qualities, + try_get, + urljoin, ) @@ -220,11 +222,17 @@ class NDREmbedBaseIE(InfoExtractor): upload_date = ppjson.get('config', {}).get('publicationDate') duration = int_or_none(config.get('duration')) - thumbnails = [{ - 'id': thumbnail.get('quality') or thumbnail_id, - 'url': thumbnail['src'], - 'preference': quality_key(thumbnail.get('quality')), - } for thumbnail_id, thumbnail in config.get('poster', {}).items() if thumbnail.get('src')] + thumbnails = [] + poster = try_get(config, lambda x: x['poster'], dict) or {} + for thumbnail_id, thumbnail in poster.items(): + thumbnail_url = urljoin(url, thumbnail.get('src')) + if not thumbnail_url: + continue + thumbnails.append({ + 'id': thumbnail.get('quality') or thumbnail_id, + 'url': thumbnail_url, + 'preference': quality_key(thumbnail.get('quality')), + }) return { 'id': video_id, diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 901f44b54..2850af5db 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -18,7 +18,7 @@ class NovaEmbedIE(InfoExtractor): _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P[^/?#&]+)' _TEST = { 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', - 'md5': 'b3834f6de5401baabf31ed57456463f7', + 'md5': 'ee009bafcc794541570edd44b71cbea3', 'info_dict': { 'id': '8o0n0r', 'ext': 'mp4', @@ -44,11 +44,17 @@ class NovaEmbedIE(InfoExtractor): formats = [] for format_id, format_list in bitrates.items(): if not isinstance(format_list, list): - continue + format_list = [format_list] for format_url in format_list: format_url = url_or_none(format_url) if not format_url: continue + if format_id == 'hls': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + continue f = { 'url': format_url, } @@ -91,7 +97,7 @@ class NovaIE(InfoExtractor): _VALID_URL = r'https?://(?:[^.]+\.)?(?Ptv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P[^/]+?)(?:\.html|/|$)' _TESTS = [{ 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', - 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', + 'md5': '249baab7d0104e186e78b0899c7d5f28', 'info_dict': { 'id': '1757139', 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', @@ -113,7 +119,8 @@ class NovaIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'gone', }, { # media.cms.nova.cz embed 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', @@ -128,6 +135,7 @@ class NovaIE(InfoExtractor): 'skip_download': True, }, 'add_ie': [NovaEmbedIE.ie_key()], + 'skip': 'CHYBA 404: STRÁNKA NENALEZENA', }, { 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'only_matching': True, @@ -152,14 +160,29 @@ class NovaIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + description = clean_html(self._og_search_description(webpage, default=None)) + if site == 'novaplus': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) + elif site == 'fanda': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) + else: + upload_date = None + # novaplus embed_id = self._search_regex( r']+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', webpage, 'embed url', default=None) if embed_id: - return self.url_result( - 'https://media.cms.nova.cz/embed/%s' % embed_id, - ie=NovaEmbedIE.ie_key(), video_id=embed_id) + return { + '_type': 'url_transparent', + 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id, + 'ie_key': NovaEmbedIE.ie_key(), + 'id': embed_id, + 'description': description, + 'upload_date': upload_date + } video_id = self._search_regex( [r"(?:media|video_id)\s*:\s*'(\d+)'", @@ -233,18 +256,8 @@ class NovaIE(InfoExtractor): self._sort_formats(formats) title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) - description = clean_html(self._og_search_description(webpage, default=None)) thumbnail = config.get('poster') - if site == 'novaplus': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) - elif site == 'fanda': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) - else: - upload_date = None - return { 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/npr.py b/youtube_dl/extractor/npr.py index a5e8baa7e..53acc6e57 100644 --- a/youtube_dl/extractor/npr.py +++ b/youtube_dl/extractor/npr.py @@ -4,6 +4,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, qualities, + url_or_none, ) @@ -48,6 +49,10 @@ class NprIE(InfoExtractor): }, }], 'expected_warnings': ['Failed to download m3u8 information'], + }, { + # multimedia, no formats, stream + 'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert', + 'only_matching': True, }] def _real_extract(self, url): @@ -95,6 +100,17 @@ class NprIE(InfoExtractor): 'format_id': format_id, 'quality': quality(format_id), }) + for stream_id, stream_entry in media.get('stream', {}).items(): + if not isinstance(stream_entry, dict): + continue + if stream_id != 'hlsUrl': + continue + stream_url = url_or_none(stream_entry.get('$text')) + if not stream_url: + continue + formats.extend(self._extract_m3u8_formats( + stream_url, stream_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) self._sort_formats(formats) entries.append({ diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 60933f069..94115534b 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -12,6 +12,7 @@ from ..utils import ( ExtractorError, int_or_none, JSON_LD_RE, + js_to_json, NO_DEFAULT, parse_age_limit, parse_duration, @@ -105,6 +106,7 @@ class NRKBaseIE(InfoExtractor): MESSAGES = { 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', 'ProgramRightsHasExpired': 'Programmet har gått ut', + 'NoProgramRights': 'Ikke tilgjengelig', 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', } message_type = data.get('messageType', '') @@ -255,6 +257,17 @@ class NRKTVIE(NRKBaseIE): ''' % _EPISODE_RE _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') _TESTS = [{ + 'url': 'https://tv.nrk.no/program/MDDP12000117', + 'md5': '8270824df46ec629b66aeaa5796b36fb', + 'info_dict': { + 'id': 'MDDP12000117AA', + 'ext': 'mp4', + 'title': 'Alarm Trolltunga', + 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce', + 'duration': 2223, + 'age_limit': 6, + }, + }, { 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', 'md5': '9a167e54d04671eb6317a37b7bc8a280', 'info_dict': { @@ -266,6 +279,7 @@ class NRKTVIE(NRKBaseIE): 'series': '20 spørsmål', 'episode': '23.05.2014', }, + 'skip': 'NoProgramRights', }, { 'url': 'https://tv.nrk.no/program/mdfp15000514', 'info_dict': { @@ -370,7 +384,24 @@ class NRKTVIE(NRKBaseIE): class NRKTVEpisodeIE(InfoExtractor): _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P[^/]+/sesong/\d+/episode/\d+)' - _TEST = { + _TESTS = [{ + 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2', + 'info_dict': { + 'id': 'MUHH36005220BA', + 'ext': 'mp4', + 'title': 'Kro, krig og kjærlighet 2:6', + 'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350', + 'duration': 1563, + 'series': 'Hellums kro', + 'season_number': 1, + 'episode_number': 2, + 'episode': '2:6', + 'age_limit': 6, + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', 'info_dict': { 'id': 'MSUI14000816AA', @@ -386,7 +417,8 @@ class NRKTVEpisodeIE(InfoExtractor): 'params': { 'skip_download': True, }, - } + 'skip': 'ProgramRightsHasExpired', + }] def _real_extract(self, url): display_id = self._match_id(url) @@ -409,7 +441,7 @@ class NRKTVSerieBaseIE(InfoExtractor): (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;', r'({.+?})\s*,\s*"[^"]+"\s*\)\s*'), webpage, 'config', default='{}' if not fatal else NO_DEFAULT), - display_id, fatal=False) + display_id, fatal=False, transform_source=js_to_json) if not config: return return try_get( @@ -479,6 +511,14 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P[^/]+)' _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P\d+)' _TESTS = [{ + 'url': 'https://tv.nrk.no/serie/blank', + 'info_dict': { + 'id': 'blank', + 'title': 'Blank', + 'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e', + }, + 'playlist_mincount': 30, + }, { # new layout, seasons 'url': 'https://tv.nrk.no/serie/backstage', 'info_dict': { @@ -648,7 +688,7 @@ class NRKSkoleIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099', - 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6', + 'md5': '18c12c3d071953c3bf8d54ef6b2587b7', 'info_dict': { 'id': '6021', 'ext': 'mp4', diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 2bb77ab24..fc78ca56c 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor): 'width': int_or_none(video.get('width')), 'height': int_or_none(video.get('height')), 'filesize': get_file_size(video.get('file_size') or video.get('fileSize')), - 'tbr': int_or_none(video.get('bitrate'), 1000), + 'tbr': int_or_none(video.get('bitrate'), 1000) or None, 'ext': ext, }) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id')) thumbnails = [] for image in video_data.get('images', []): diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 3425f7602..d54b8ace6 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -6,12 +6,14 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + clean_html, determine_ext, float_or_none, HEADRequest, int_or_none, orderedSet, remove_end, + str_or_none, strip_jsonp, unescapeHTML, unified_strdate, @@ -88,8 +90,11 @@ class ORFTVthekIE(InfoExtractor): format_id = '-'.join(format_id_list) ext = determine_ext(src) if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id=format_id, fatal=False)) + m3u8_formats = self._extract_m3u8_formats( + src, video_id, 'mp4', m3u8_id=format_id, fatal=False) + if any('/geoprotection' in f['url'] for f in m3u8_formats): + self.raise_geo_restricted() + formats.extend(m3u8_formats) elif ext == 'f4m': formats.extend(self._extract_f4m_formats( src, video_id, f4m_id=format_id, fatal=False)) @@ -161,44 +166,48 @@ class ORFRadioIE(InfoExtractor): show_date = mobj.group('date') show_id = mobj.group('show') - if station == 'fm4': - show_id = '4%s' % show_id - data = self._download_json( - 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date), - show_id - ) + 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' + % (station, show_id, show_date), show_id) - def extract_entry_dict(info, title, subtitle): - return { - 'id': info['loopStreamId'].replace('.mp3', ''), - 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']), + entries = [] + for info in data['streams']: + loop_stream_id = str_or_none(info.get('loopStreamId')) + if not loop_stream_id: + continue + title = str_or_none(data.get('title')) + if not title: + continue + start = int_or_none(info.get('start'), scale=1000) + end = int_or_none(info.get('end'), scale=1000) + duration = end - start if end and start else None + entries.append({ + 'id': loop_stream_id.replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id), 'title': title, - 'description': subtitle, - 'duration': (info['end'] - info['start']) / 1000, - 'timestamp': info['start'] / 1000, + 'description': clean_html(data.get('subtitle')), + 'duration': duration, + 'timestamp': start, 'ext': 'mp3', - 'series': data.get('programTitle') - } - - entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + 'series': data.get('programTitle'), + }) return { '_type': 'playlist', 'id': show_id, - 'title': data['title'], - 'description': data['subtitle'], - 'entries': entries + 'title': data.get('title'), + 'description': clean_html(data.get('subtitle')), + 'entries': entries, } class ORFFM4IE(ORFRadioIE): IE_NAME = 'orf:fm4' IE_DESC = 'radio FM4' - _VALID_URL = r'https?://(?Pfm4)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _VALID_URL = r'https?://(?Pfm4)\.orf\.at/player/(?P[0-9]+)/(?P4\w+)' _TEST = { - 'url': 'http://fm4.orf.at/player/20170107/CC', + 'url': 'http://fm4.orf.at/player/20170107/4CC', 'md5': '2b0be47375432a7ef104453432a19212', 'info_dict': { 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295', @@ -209,7 +218,8 @@ class ORFFM4IE(ORFRadioIE): 'timestamp': 1483819257, 'upload_date': '20170107', }, - 'skip': 'Shows from ORF radios are only available for 7 days.' + 'skip': 'Shows from ORF radios are only available for 7 days.', + 'only_matching': True, } diff --git a/youtube_dl/extractor/pandatv.py b/youtube_dl/extractor/pandatv.py deleted file mode 100644 index 4219802d5..000000000 --- a/youtube_dl/extractor/pandatv.py +++ /dev/null @@ -1,99 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - qualities, -) - - -class PandaTVIE(InfoExtractor): - IE_DESC = '熊猫TV' - _VALID_URL = r'https?://(?:www\.)?panda\.tv/(?P[0-9]+)' - _TESTS = [{ - 'url': 'http://www.panda.tv/66666', - 'info_dict': { - 'id': '66666', - 'title': 're:.+', - 'uploader': '刘杀鸡', - 'ext': 'flv', - 'is_live': True, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Live stream is offline', - }, { - 'url': 'https://www.panda.tv/66666', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - config = self._download_json( - 'https://www.panda.tv/api_room_v2?roomid=%s' % video_id, video_id) - - error_code = config.get('errno', 0) - if error_code != 0: - raise ExtractorError( - '%s returned error %s: %s' - % (self.IE_NAME, error_code, config['errmsg']), - expected=True) - - data = config['data'] - video_info = data['videoinfo'] - - # 2 = live, 3 = offline - if video_info.get('status') != '2': - raise ExtractorError( - 'Live stream is offline', expected=True) - - title = data['roominfo']['name'] - uploader = data.get('hostinfo', {}).get('name') - room_key = video_info['room_key'] - stream_addr = video_info.get( - 'stream_addr', {'OD': '1', 'HD': '1', 'SD': '1'}) - - # Reverse engineered from web player swf - # (http://s6.pdim.gs/static/07153e425f581151.swf at the moment of - # writing). - plflag0, plflag1 = video_info['plflag'].split('_') - plflag0 = int(plflag0) - 1 - if plflag1 == '21': - plflag0 = 10 - plflag1 = '4' - live_panda = 'live_panda' if plflag0 < 1 else '' - - plflag_auth = self._parse_json(video_info['plflag_list'], video_id) - sign = plflag_auth['auth']['sign'] - ts = plflag_auth['auth']['time'] - rid = plflag_auth['auth']['rid'] - - quality_key = qualities(['OD', 'HD', 'SD']) - suffix = ['_small', '_mid', ''] - formats = [] - for k, v in stream_addr.items(): - if v != '1': - continue - quality = quality_key(k) - if quality <= 0: - continue - for pref, (ext, pl) in enumerate((('m3u8', '-hls'), ('flv', ''))): - formats.append({ - 'url': 'https://pl%s%s.live.panda.tv/live_panda/%s%s%s.%s?sign=%s&ts=%s&rid=%s' - % (pl, plflag1, room_key, live_panda, suffix[quality], ext, sign, ts, rid), - 'format_id': '%s-%s' % (k, ext), - 'quality': quality, - 'source_preference': pref, - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': self._live_title(title), - 'uploader': uploader, - 'formats': formats, - 'is_live': True, - } diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py index 602207beb..23c8256b5 100644 --- a/youtube_dl/extractor/platzi.py +++ b/youtube_dl/extractor/platzi.py @@ -46,7 +46,7 @@ class PlatziBaseIE(InfoExtractor): headers={'Referer': self._LOGIN_URL}) # login succeeded - if 'platzi.com/login' not in compat_str(urlh.geturl()): + if 'platzi.com/login' not in urlh.geturl(): return login_error = self._webpage_read_content( diff --git a/youtube_dl/extractor/popcorntimes.py b/youtube_dl/extractor/popcorntimes.py new file mode 100644 index 000000000..7bf7f9858 --- /dev/null +++ b/youtube_dl/extractor/popcorntimes.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_chr, +) +from ..utils import int_or_none + + +class PopcorntimesIE(InfoExtractor): + _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P[^/]+)/(?P[^/?#&]+)' + _TEST = { + 'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy', + 'md5': '93f210991ad94ba8c3485950a2453257', + 'info_dict': { + 'id': 'A1XCFvz', + 'display_id': 'haensel-und-gretel-opera-fantasy', + 'ext': 'mp4', + 'title': 'Hänsel und Gretel', + 'description': 'md5:1b8146791726342e7b22ce8125cf6945', + 'thumbnail': r're:^https?://.*\.jpg$', + 'creator': 'John Paul', + 'release_date': '19541009', + 'duration': 4260, + 'tbr': 5380, + 'width': 720, + 'height': 540, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._search_regex( + r'

    ([^<]+)', webpage, 'title', + default=None) or self._html_search_meta( + 'ya:ovs:original_name', webpage, 'title', fatal=True) + + loc = self._search_regex( + r'PCTMLOC\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'loc', + group='value') + + loc_b64 = '' + for c in loc: + c_ord = ord(c) + if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'): + upper = ord('Z') if c_ord <= ord('Z') else ord('z') + c_ord += 13 + if upper < c_ord: + c_ord -= 26 + loc_b64 += compat_chr(c_ord) + + video_url = compat_b64decode(loc_b64).decode('utf-8') + + description = self._html_search_regex( + r'(?s)]+class=["\']pt-movie-desc[^>]+>(.+?)', webpage, + 'description', fatal=False) + + thumbnail = self._search_regex( + r']+class=["\']video-preview[^>]+\bsrc=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'thumbnail', default=None, + group='value') or self._og_search_thumbnail(webpage) + + creator = self._html_search_meta( + 'video:director', webpage, 'creator', default=None) + + release_date = self._html_search_meta( + 'video:release_date', webpage, default=None) + if release_date: + release_date = release_date.replace('-', '') + + def int_meta(name): + return int_or_none(self._html_search_meta( + name, webpage, default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'creator': creator, + 'release_date': release_date, + 'duration': int_meta('video:duration'), + 'tbr': int_meta('ya:ovs:bitrate'), + 'width': int_meta('og:video:width'), + 'height': int_meta('og:video:height'), + 'http_headers': { + 'Referer': url, + }, + } diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 27d65d4b9..c6052ac9f 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -8,6 +8,7 @@ from ..utils import ( ExtractorError, int_or_none, js_to_json, + merge_dicts, urljoin, ) @@ -27,23 +28,22 @@ class PornHdIE(InfoExtractor): 'view_count': int, 'like_count': int, 'age_limit': 18, - } + }, + 'skip': 'HTTP Error 404: Not Found', }, { - # removed video 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'md5': '956b8ca569f7f4d8ec563e2c41598441', + 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de', 'info_dict': { 'id': '1962', 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', - 'title': 'Sierra loves doing laundry', + 'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, 'like_count': int, 'age_limit': 18, }, - 'skip': 'Not available anymore', }] def _real_extract(self, url): @@ -61,7 +61,13 @@ class PornHdIE(InfoExtractor): r"(?s)sources'?\s*[:=]\s*(\{.+?\})", webpage, 'sources', default='{}')), video_id) + info = {} if not sources: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info = entries[0] + + if not sources and not info: message = self._html_search_regex( r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P.+?)]+class="description"[^>]*>(?P[^<]+)]+class=["\']video-description[^>]+>(?P.+?)', + r'<(div|p)[^>]+class="description"[^>]*>(?P[^<]+)(?:(?!\1).)+)\1", webpage, - 'thumbnail', fatal=False, group='url') + 'thumbnail', default=None, group='url') like_count = int_or_none(self._search_regex( - (r'(\d+)\s*]+>(?: |\s)*\blikes', + (r'(\d+)\s*likes', + r'(\d+)\s*]+>(?: |\s)*\blikes', r'class=["\']save-count["\'][^>]*>\s*(\d+)'), webpage, 'like count', fatal=False)) - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -106,4 +118,4 @@ class PornHdIE(InfoExtractor): 'like_count': like_count, 'formats': formats, 'age_limit': 18, - } + }) diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 5c84028ef..b1bde1e81 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -43,8 +43,15 @@ class RedTubeIE(InfoExtractor): webpage = self._download_webpage( 'http://www.redtube.com/%s' % video_id, video_id) - if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']): - raise ExtractorError('Video %s has been removed' % video_id, expected=True) + ERRORS = ( + (('video-deleted-info', '>This video has been removed'), 'has been removed'), + (('private_video_text', '>This video is private', '>Send a friend request to its owner to be able to view it'), 'is private'), + ) + + for patterns, message in ERRORS: + if any(p in webpage for p in patterns): + raise ExtractorError( + 'Video %s %s' % (video_id, message), expected=True) info = self._search_json_ld(webpage, video_id, default={}) diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index bd9ee1647..2cc665122 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_parse_qs, - compat_str, compat_urlparse, ) from ..utils import ( @@ -39,13 +38,13 @@ class SafariBaseIE(InfoExtractor): 'Downloading login page') def is_logged(urlh): - return 'learning.oreilly.com/home/' in compat_str(urlh.geturl()) + return 'learning.oreilly.com/home/' in urlh.geturl() if is_logged(urlh): self.LOGGED_IN = True return - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() parsed_url = compat_urlparse.urlparse(redirect_url) qs = compat_parse_qs(parsed_url.query) next_uri = compat_urlparse.urljoin( @@ -165,7 +164,8 @@ class SafariIE(SafariBaseIE): kaltura_session = self._download_json( '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id), video_id, 'Downloading kaltura session JSON', - 'Unable to download kaltura session JSON', fatal=False) + 'Unable to download kaltura session JSON', fatal=False, + headers={'Accept': 'application/json'}) if kaltura_session: session = kaltura_session.get('session') if session: diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index afab9591d..b40b4c4af 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -106,7 +106,7 @@ class ScrippsNetworksWatchIE(AWSIE): class ScrippsNetworksIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?Pcookingchanneltv|(?:diy|food)network|hgtv|travelchannel)\.com/videos/[0-9a-z-]+-(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?(?Pcookingchanneltv|discovery|(?:diy|food)network|hgtv|travelchannel)\.com/videos/[0-9a-z-]+-(?P\d+)' _TESTS = [{ 'url': 'https://www.cookingchanneltv.com/videos/the-best-of-the-best-0260338', 'info_dict': { @@ -131,9 +131,13 @@ class ScrippsNetworksIE(InfoExtractor): }, { 'url': 'https://www.travelchannel.com/videos/two-climates-one-bag-5302184', 'only_matching': True, + }, { + 'url': 'https://www.discovery.com/videos/guardians-of-the-glades-cooking-with-tom-cobb-5578368', + 'only_matching': True, }] _ACCOUNT_MAP = { 'cookingchanneltv': 2433005105, + 'discovery': 2706091867, 'diynetwork': 2433004575, 'foodnetwork': 2433005105, 'hgtv': 2433004575, diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 62e9d8643..a1372d389 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -96,7 +96,7 @@ class SoundcloudIE(InfoExtractor): 'repost_count': int, } }, - # not streamable song + # not streamable song, preview { 'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', 'info_dict': { @@ -119,7 +119,6 @@ class SoundcloudIE(InfoExtractor): # rtmp 'skip_download': True, }, - 'skip': 'Preview', }, # private link { @@ -239,7 +238,7 @@ class SoundcloudIE(InfoExtractor): 'ext': 'mp3', 'title': 'Mezzo Valzer', 'description': 'md5:4138d582f81866a530317bae316e8b61', - 'uploader': 'Giovanni Sarani', + 'uploader': 'Micronie', 'uploader_id': '3352531', 'timestamp': 1551394171, 'upload_date': '20190228', @@ -346,9 +345,9 @@ class SoundcloudIE(InfoExtractor): }) def invalid_url(url): - return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url) + return not url or url in format_urls - def add_format(f, protocol): + def add_format(f, protocol, is_preview=False): mobj = re.search(r'\.(?P\d+)\.(?P[0-9a-z]{3,4})(?=[/?])', stream_url) if mobj: for k, v in mobj.groupdict().items(): @@ -361,12 +360,16 @@ class SoundcloudIE(InfoExtractor): v = f.get(k) if v: format_id_list.append(v) + preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url']) + if preview: + format_id_list.append('preview') abr = f.get('abr') if abr: f['abr'] = int(abr) f.update({ 'format_id': '_'.join(format_id_list), 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', + 'preference': -10 if preview else None, }) formats.append(f) @@ -377,7 +380,7 @@ class SoundcloudIE(InfoExtractor): if not isinstance(t, dict): continue format_url = url_or_none(t.get('url')) - if not format_url or t.get('snipped') or '/preview/' in format_url: + if not format_url: continue stream = self._download_json( format_url, track_id, query=query, fatal=False) @@ -400,7 +403,8 @@ class SoundcloudIE(InfoExtractor): add_format({ 'url': stream_url, 'ext': ext, - }, 'http' if protocol == 'progressive' else protocol) + }, 'http' if protocol == 'progressive' else protocol, + t.get('snipped') or '/preview/' in format_url) if not formats: # Old API, does not work for some tracks (e.g. @@ -520,7 +524,17 @@ class SoundcloudIE(InfoExtractor): class SoundcloudPlaylistBaseIE(SoundcloudIE): - def _extract_track_entries(self, tracks, token=None): + def _extract_set(self, playlist, token=None): + playlist_id = compat_str(playlist['id']) + tracks = playlist.get('tracks') or [] + if not all([t.get('permalink_url') for t in tracks]) and token: + tracks = self._download_json( + self._API_V2_BASE + 'tracks', playlist_id, + 'Downloading tracks', query={ + 'ids': ','.join([compat_str(t['id']) for t in tracks]), + 'playlistId': playlist_id, + 'playlistSecretToken': token, + }) entries = [] for track in tracks: track_id = str_or_none(track.get('id')) @@ -533,7 +547,10 @@ class SoundcloudPlaylistBaseIE(SoundcloudIE): url += '?secret_token=' + token entries.append(self.url_result( url, SoundcloudIE.ie_key(), track_id)) - return entries + return self.playlist_result( + entries, playlist_id, + playlist.get('title'), + playlist.get('description')) class SoundcloudSetIE(SoundcloudPlaylistBaseIE): @@ -544,6 +561,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): 'info_dict': { 'id': '2284613', 'title': 'The Royal Concept EP', + 'description': 'md5:71d07087c7a449e8941a70a29e34671e', }, 'playlist_mincount': 5, }, { @@ -566,13 +584,10 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): msgs = (compat_str(err['error_message']) for err in info['errors']) raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) - entries = self._extract_track_entries(info['tracks'], token) - - return self.playlist_result( - entries, str_or_none(info.get('id')), info.get('title')) + return self._extract_set(info, token) -class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): +class SoundcloudPagedPlaylistBaseIE(SoundcloudIE): def _extract_playlist(self, base_url, playlist_id, playlist_title): COMMON_QUERY = { 'limit': 2000000000, @@ -770,10 +785,7 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): self._API_V2_BASE + 'playlists/' + playlist_id, playlist_id, 'Downloading playlist', query=query) - entries = self._extract_track_entries(data['tracks'], token) - - return self.playlist_result( - entries, playlist_id, data.get('title'), data.get('description')) + return self._extract_set(data, token) class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py index a3c35a899..378fc7568 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -13,36 +13,18 @@ from ..utils import ( class SportDeutschlandIE(InfoExtractor): _VALID_URL = r'https?://sportdeutschland\.tv/(?P[^/?#]+)/(?P[^?#/]+)(?:$|[?#])' _TESTS = [{ - 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0', 'info_dict': { - 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'id': 're-live-deutsche-meisterschaften-2020-halbfinals', 'ext': 'mp4', - 'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', - 'categories': ['Badminton'], + 'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals', + 'categories': ['Badminton-Deutschland'], 'view_count': int, - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': r're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV', + 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', 'timestamp': int, - 'upload_date': 're:^201408[23][0-9]$', + 'upload_date': '20200201', + 'description': 're:.*', # meaningless description for THIS video }, - 'params': { - 'skip_download': 'Live stream', - }, - }, { - 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', - 'info_dict': { - 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', - 'ext': 'mp4', - 'upload_date': '20140825', - 'description': 'md5:60a20536b57cee7d9a4ec005e8687504', - 'timestamp': 1408976060, - 'duration': 2732, - 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee', - 'thumbnail': r're:^https?://.*\.jpg$', - 'view_count': int, - 'categories': ['Li-Ning Badminton WM 2014'], - - } }] def _real_extract(self, url): @@ -50,7 +32,7 @@ class SportDeutschlandIE(InfoExtractor): video_id = mobj.group('id') sport_id = mobj.group('sport') - api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( + api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( sport_id, video_id) req = sanitized_Request(api_url, headers={ 'Accept': 'application/vnd.vidibus.v2.html+json', diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py index 28baf901c..359dadaa3 100644 --- a/youtube_dl/extractor/srmediathek.py +++ b/youtube_dl/extractor/srmediathek.py @@ -1,14 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -from .ard import ARDMediathekIE +from .ard import ARDMediathekBaseIE from ..utils import ( ExtractorError, get_element_by_attribute, ) -class SRMediathekIE(ARDMediathekIE): +class SRMediathekIE(ARDMediathekBaseIE): IE_NAME = 'sr:mediathek' IE_DESC = 'Saarländischer Rundfunk' _VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P[0-9]+)' diff --git a/youtube_dl/extractor/stretchinternet.py b/youtube_dl/extractor/stretchinternet.py index ae2ac1b42..4dbead2ba 100644 --- a/youtube_dl/extractor/stretchinternet.py +++ b/youtube_dl/extractor/stretchinternet.py @@ -5,44 +5,28 @@ from ..utils import int_or_none class StretchInternetIE(InfoExtractor): - _VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/portal\.htm\?.*?\beventId=(?P\d+)' + _VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/(?:portal|full)\.htm\?.*?\beventId=(?P\d+)' _TEST = { - 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video', + 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=573272&streamType=video', 'info_dict': { - 'id': '313900', + 'id': '573272', 'ext': 'mp4', - 'title': 'Augustana (S.D.) Baseball vs University of Mary', - 'description': 'md5:7578478614aae3bdd4a90f578f787438', - 'timestamp': 1490468400, - 'upload_date': '20170325', + 'title': 'University of Mary Wrestling vs. Upper Iowa', + 'timestamp': 1575668361, + 'upload_date': '20191206', } } def _real_extract(self, url): video_id = self._match_id(url) - stream = self._download_json( - 'https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s' - % video_id, video_id) - - video_url = 'https://%s' % stream['source'] - event = self._download_json( - 'https://neo-client.stretchinternet.com/portal-ws/getEvent.json', - video_id, query={ - 'clientID': 99997, - 'eventID': video_id, - 'token': 'asdf', - })['event'] - - title = event.get('title') or event['mobileTitle'] - description = event.get('customText') - timestamp = int_or_none(event.get('longtime')) + 'https://api.stretchinternet.com/trinity/event/tcg/' + video_id, + video_id)[0] return { 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'url': video_url, + 'title': event['title'], + 'timestamp': int_or_none(event.get('dateCreated'), 1000), + 'url': 'https://' + event['media'][0]['url'], } diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index 0901c3163..e12389cad 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -4,19 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_parse_qs, - compat_urllib_parse_urlparse, -) +from ..compat import compat_str from ..utils import ( determine_ext, dict_get, int_or_none, - orderedSet, + str_or_none, strip_or_none, try_get, - urljoin, - compat_str, ) @@ -237,23 +232,23 @@ class SVTPlayIE(SVTPlayBaseIE): class SVTSeriesIE(SVTPlayBaseIE): - _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P[^/?&#]+)' + _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P[^/?&#]+)(?:.+?\btab=(?P[^&#]+))?' _TESTS = [{ 'url': 'https://www.svtplay.se/rederiet', 'info_dict': { - 'id': 'rederiet', + 'id': '14445680', 'title': 'Rederiet', - 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e', + 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039', }, 'playlist_mincount': 318, }, { - 'url': 'https://www.svtplay.se/rederiet?tab=sasong2', + 'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680', 'info_dict': { - 'id': 'rederiet-sasong2', + 'id': 'season-2-14445680', 'title': 'Rederiet - Säsong 2', - 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e', + 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039', }, - 'playlist_count': 12, + 'playlist_mincount': 12, }] @classmethod @@ -261,83 +256,87 @@ class SVTSeriesIE(SVTPlayBaseIE): return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url) def _real_extract(self, url): - series_id = self._match_id(url) + series_slug, season_id = re.match(self._VALID_URL, url).groups() - qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) - season_slug = qs.get('tab', [None])[0] - - if season_slug: - series_id += '-%s' % season_slug - - webpage = self._download_webpage( - url, series_id, 'Downloading series page') - - root = self._parse_json( - self._search_regex( - self._SVTPLAY_RE, webpage, 'content', group='json'), - series_id) + series = self._download_json( + 'https://api.svt.se/contento/graphql', series_slug, + 'Downloading series page', query={ + 'query': '''{ + listablesBySlug(slugs: ["%s"]) { + associatedContent(include: [productionPeriod, season]) { + items { + item { + ... on Episode { + videoSvtId + } + } + } + id + name + } + id + longDescription + name + shortDescription + } +}''' % series_slug, + })['data']['listablesBySlug'][0] season_name = None entries = [] - for season in root['relatedVideoContent']['relatedVideosAccordion']: + for season in series['associatedContent']: if not isinstance(season, dict): continue - if season_slug: - if season.get('slug') != season_slug: + if season_id: + if season.get('id') != season_id: continue season_name = season.get('name') - videos = season.get('videos') - if not isinstance(videos, list): + items = season.get('items') + if not isinstance(items, list): continue - for video in videos: - content_url = video.get('contentUrl') - if not content_url or not isinstance(content_url, compat_str): + for item in items: + video = item.get('item') or {} + content_id = video.get('videoSvtId') + if not content_id or not isinstance(content_id, compat_str): continue - entries.append( - self.url_result( - urljoin(url, content_url), - ie=SVTPlayIE.ie_key(), - video_title=video.get('title') - )) + entries.append(self.url_result( + 'svt:' + content_id, SVTPlayIE.ie_key(), content_id)) - metadata = root.get('metaData') - if not isinstance(metadata, dict): - metadata = {} - - title = metadata.get('title') - season_name = season_name or season_slug + title = series.get('name') + season_name = season_name or season_id if title and season_name: title = '%s - %s' % (title, season_name) - elif season_slug: - title = season_slug + elif season_id: + title = season_id return self.playlist_result( - entries, series_id, title, metadata.get('description')) + entries, season_id or series.get('id'), title, + dict_get(series, ('longDescription', 'shortDescription'))) class SVTPageIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P[^/?&#]+)' + _VALID_URL = r'https?://(?:www\.)?svt\.se/(?P(?:[^/]+/)*(?P[^/?&#]+))' _TESTS = [{ - 'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', + 'url': 'https://www.svt.se/sport/ishockey/bakom-masken-lehners-kamp-mot-mental-ohalsa', 'info_dict': { - 'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', - 'title': 'GUIDE: Sommarträning du kan göra var och när du vill', + 'id': '25298267', + 'title': 'Bakom masken – Lehners kamp mot mental ohälsa', }, - 'playlist_count': 7, + 'playlist_count': 4, }, { - 'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', + 'url': 'https://www.svt.se/nyheter/utrikes/svenska-andrea-ar-en-mil-fran-branderna-i-kalifornien', 'info_dict': { - 'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', - 'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”', + 'id': '24243746', + 'title': 'Svenska Andrea redo att fly sitt hem i Kalifornien', }, - 'playlist_count': 1, + 'playlist_count': 2, }, { # only programTitle 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', 'info_dict': { - 'id': '2900353', + 'id': '8439V2K', 'ext': 'mp4', 'title': 'Stjärnorna skojar till det - under SVT-intervjun', 'duration': 27, @@ -356,16 +355,26 @@ class SVTPageIE(InfoExtractor): return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url) def _real_extract(self, url): - playlist_id = self._match_id(url) + path, display_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, playlist_id) + article = self._download_json( + 'https://api.svt.se/nss-api/page/' + path, display_id, + query={'q': 'articles'})['articles']['content'][0] - entries = [ - self.url_result( - 'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id) - for video_id in orderedSet(re.findall( - r'data-video-id=["\'](\d+)', webpage))] + entries = [] - title = strip_or_none(self._og_search_title(webpage, default=None)) + def _process_content(content): + if content.get('_type') in ('VIDEOCLIP', 'VIDEOEPISODE'): + video_id = compat_str(content['image']['svtId']) + entries.append(self.url_result( + 'svt:' + video_id, SVTPlayIE.ie_key(), video_id)) - return self.playlist_result(entries, playlist_id, title) + for media in article.get('media', []): + _process_content(media) + + for obj in article.get('structuredBody', []): + _process_content(obj.get('content') or {}) + + return self.playlist_result( + entries, str_or_none(article.get('id')), + strip_or_none(article.get('title'))) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 6b7f13b43..4316a6962 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -4,7 +4,6 @@ import re from .common import InfoExtractor from .wistia import WistiaIE -from ..compat import compat_str from ..utils import ( clean_html, ExtractorError, @@ -58,7 +57,7 @@ class TeachableBaseIE(InfoExtractor): self._logged_in = True return - login_url = compat_str(urlh.geturl()) + login_url = urlh.geturl() login_form = self._hidden_inputs(login_page) @@ -160,8 +159,8 @@ class TeachableIE(TeachableBaseIE): webpage = self._download_webpage(url, video_id) - wistia_url = WistiaIE._extract_url(webpage) - if not wistia_url: + wistia_urls = WistiaIE._extract_urls(webpage) + if not wistia_urls: if any(re.search(p, webpage) for p in ( r'class=["\']lecture-contents-locked', r'>\s*Lecture contents locked', @@ -174,12 +173,14 @@ class TeachableIE(TeachableBaseIE): title = self._og_search_title(webpage, default=None) - return { + entries = [{ '_type': 'url_transparent', 'url': wistia_url, 'ie_key': WistiaIE.ie_key(), 'title': title, - } + } for wistia_url in wistia_urls] + + return self.playlist_result(entries, video_id, title) class TeachableCourseIE(TeachableBaseIE): diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index d37e1b055..9ba3da341 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -11,6 +11,7 @@ from ..utils import ( determine_ext, int_or_none, str_or_none, + try_get, urljoin, ) @@ -24,7 +25,7 @@ class TelecincoIE(InfoExtractor): 'info_dict': { 'id': '1876350223', 'title': 'Bacalao con kokotxas al pil-pil', - 'description': 'md5:1382dacd32dd4592d478cbdca458e5bb', + 'description': 'md5:716caf5601e25c3c5ab6605b1ae71529', }, 'playlist': [{ 'md5': 'adb28c37238b675dad0f042292f209a7', @@ -55,6 +56,26 @@ class TelecincoIE(InfoExtractor): 'description': 'md5:2771356ff7bfad9179c5f5cd954f1477', 'duration': 50, }, + }, { + # video in opening's content + 'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html', + 'info_dict': { + 'id': '2907195140', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'description': 'md5:73f340a7320143d37ab895375b2bf13a', + }, + 'playlist': [{ + 'md5': 'adb28c37238b675dad0f042292f209a7', + 'info_dict': { + 'id': 'TpI2EttSDAReWpJ1o0NVh2', + 'ext': 'mp4', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'duration': 1015, + }, + }], + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', 'only_matching': True, @@ -135,17 +156,28 @@ class TelecincoIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) article = self._parse_json(self._search_regex( - r'window\.\$REACTBASE_STATE\.article\s*=\s*({.+})', + r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})', webpage, 'article'), display_id)['article'] title = article.get('title') - description = clean_html(article.get('leadParagraph')) + description = clean_html(article.get('leadParagraph')) or '' if article.get('editorialType') != 'VID': entries = [] - for p in article.get('body', []): - content = p.get('content') - if p.get('type') != 'video' or not content: + body = [article.get('opening')] + body.extend(try_get(article, lambda x: x['body'], list) or []) + for p in body: + if not isinstance(p, dict): continue - entries.append(self._parse_content(content, url)) + content = p.get('content') + if not content: + continue + type_ = p.get('type') + if type_ == 'paragraph': + content_str = str_or_none(content) + if content_str: + description += content_str + continue + if type_ == 'video' and isinstance(content, dict): + entries.append(self._parse_content(content, url)) return self.playlist_result( entries, str_or_none(article.get('id')), title, description) content = article['opening']['content'] diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 6ab147ad7..387f955ee 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -2,43 +2,42 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str -from ..utils import try_get class ThisOldHouseIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P[^/?#]+)' _TESTS = [{ 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', - 'md5': '568acf9ca25a639f0c4ff905826b662f', 'info_dict': { - 'id': '2REGtUDQ', + 'id': '5dcdddf673c3f956ef5db202', 'ext': 'mp4', 'title': 'How to Build a Storage Bench', 'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.', 'timestamp': 1442548800, 'upload_date': '20150918', - } + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', 'only_matching': True, }, { 'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric', 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench', + 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost', + 'only_matching': True, }] + _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - (r'data-mid=(["\'])(?P(?:(?!\1).)+)\1', - r'id=(["\'])inline-video-player-(?P(?:(?!\1).)+)\1'), - webpage, 'video id', default=None, group='id') - if not video_id: - drupal_settings = self._parse_json(self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings'), display_id) - video_id = try_get( - drupal_settings, lambda x: x['jwplatform']['video_id'], - compat_str) or list(drupal_settings['comScore'])[0] - return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id) + r']+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})', + webpage, 'video id') + return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id) diff --git a/youtube_dl/extractor/toggle.py b/youtube_dl/extractor/toggle.py index 5e5efda0f..ca2e36efe 100644 --- a/youtube_dl/extractor/toggle.py +++ b/youtube_dl/extractor/toggle.py @@ -17,9 +17,9 @@ from ..utils import ( class ToggleIE(InfoExtractor): IE_NAME = 'toggle' - _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P[0-9]+)' + _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P[0-9]+)' _TESTS = [{ - 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', + 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', 'info_dict': { 'id': '343115', 'ext': 'mp4', @@ -33,7 +33,7 @@ class ToggleIE(InfoExtractor): } }, { 'note': 'DRM-protected video', - 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', + 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413', 'info_dict': { 'id': '341413', 'ext': 'wvm', @@ -48,7 +48,7 @@ class ToggleIE(InfoExtractor): }, { # this also tests correct video id extraction 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', - 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', + 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', 'info_dict': { 'id': '332861', 'ext': 'mp4', @@ -65,19 +65,22 @@ class ToggleIE(InfoExtractor): 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', + 'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', + 'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/movies/seven-days/321936', + 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', 'only_matching': True, }, { - 'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'url': 'http://www.mewatch.sg/en/movies/seven-days/321936', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585', + 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'only_matching': True, + }, { + 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585', 'only_matching': True, }] diff --git a/youtube_dl/extractor/trunews.py b/youtube_dl/extractor/trunews.py index b0c7caabf..cca5b5ceb 100644 --- a/youtube_dl/extractor/trunews.py +++ b/youtube_dl/extractor/trunews.py @@ -1,21 +1,12 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - dict_get, - float_or_none, - int_or_none, - unified_timestamp, - update_url_query, - url_or_none, -) class TruNewsIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P[^/?#&]+)' _TEST = { 'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', - 'md5': 'a19c024c3906ff954fac9b96ce66bb08', 'info_dict': { 'id': '5c5a21e65d3c196e1c0020cc', 'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', @@ -28,48 +19,16 @@ class TruNewsIE(InfoExtractor): }, 'add_ie': ['Zype'], } + _ZYPE_TEMPL = 'https://player.zype.com/embed/%s.js?api_key=X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt' def _real_extract(self, url): display_id = self._match_id(url) - video = self._download_json( + zype_id = self._download_json( 'https://api.zype.com/videos', display_id, query={ 'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H', 'per_page': 1, 'active': 'true', 'friendly_title': display_id, - })['response'][0] - - zype_id = video['_id'] - - thumbnails = [] - thumbnails_list = video.get('thumbnails') - if isinstance(thumbnails_list, list): - for thumbnail in thumbnails_list: - if not isinstance(thumbnail, dict): - continue - thumbnail_url = url_or_none(thumbnail.get('url')) - if not thumbnail_url: - continue - thumbnails.append({ - 'url': thumbnail_url, - 'width': int_or_none(thumbnail.get('width')), - 'height': int_or_none(thumbnail.get('height')), - }) - - return { - '_type': 'url_transparent', - 'url': update_url_query( - 'https://player.zype.com/embed/%s.js' % zype_id, - {'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}), - 'ie_key': 'Zype', - 'id': zype_id, - 'display_id': display_id, - 'title': video.get('title'), - 'description': dict_get(video, ('description', 'ott_description', 'short_description')), - 'duration': int_or_none(video.get('duration')), - 'timestamp': unified_timestamp(video.get('published_at')), - 'average_rating': float_or_none(video.get('rating')), - 'view_count': int_or_none(video.get('request_count')), - 'thumbnails': thumbnails, - } + })['response'][0]['_id'] + return self.url_result(self._ZYPE_TEMPL % zype_id, 'Zype', zype_id) diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index edbb0aa69..ae584ad69 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, @@ -151,7 +150,7 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage, urlh = self._download_webpage_handle(url, video_id) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() if 'tumblr.com/safe-mode' in redirect_url or redirect_url.startswith('/safe-mode'): raise ExtractorError( 'This Tumblr may contain sensitive media. ' diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py index 611fdc0c6..8bda9348d 100644 --- a/youtube_dl/extractor/tv2dk.py +++ b/youtube_dl/extractor/tv2dk.py @@ -106,7 +106,7 @@ class TV2DKBornholmPlayIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, + 'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, data=json.dumps({ 'playlist_id': video_id, 'serienavn': '', diff --git a/youtube_dl/extractor/tv5mondeplus.py b/youtube_dl/extractor/tv5mondeplus.py index 88b6baa31..b7fe082b9 100644 --- a/youtube_dl/extractor/tv5mondeplus.py +++ b/youtube_dl/extractor/tv5mondeplus.py @@ -3,31 +3,51 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - clean_html, determine_ext, extract_attributes, - get_element_by_class, int_or_none, parse_duration, - parse_iso8601, ) class TV5MondePlusIE(InfoExtractor): IE_DESC = 'TV5MONDE+' - _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P[^/?#]+)' - _TEST = { - 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', - 'md5': '12130fc199f020673138a83466542ec6', + _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P[^/?#]+)' + _TESTS = [{ + # movie + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit', + 'md5': '8cbde5ea7b296cf635073e27895e227f', 'info_dict': { - 'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', + 'id': '822a4756-0712-7329-1859-a13ac7fd1407', + 'display_id': 'rendez-vous-a-atlit', 'ext': 'mp4', - 'title': 'Tdah, mon amour - Enfants', - 'description': 'md5:230e3aca23115afcf8006d1bece6df74', - 'upload_date': '20170401', - 'timestamp': 1491022860, - } - } + 'title': 'Rendez-vous à Atlit', + 'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb', + 'upload_date': '20200130', + }, + }, { + # series episode + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree', + 'info_dict': { + 'id': '0df7007c-4900-3936-c601-87a13a93a068', + 'display_id': 'c-est-la-vie-ennemie-juree', + 'ext': 'mp4', + 'title': "C'est la vie - Ennemie jurée", + 'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e', + 'upload_date': '20200130', + 'series': "C'est la vie", + 'episode': 'Ennemie jurée', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver', + 'only_matching': True, + }, { + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30', + 'only_matching': True, + }] _GEO_BYPASS = False def _real_extract(self, url): @@ -37,11 +57,7 @@ class TV5MondePlusIE(InfoExtractor): if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage: self.raise_geo_restricted(countries=['FR']) - series = get_element_by_class('video-detail__title', webpage) - title = episode = get_element_by_class( - 'video-detail__subtitle', webpage) or series - if series and series != title: - title = '%s - %s' % (series, title) + title = episode = self._html_search_regex(r'

    ([^<]+)', webpage, 'title') vpl_data = extract_attributes(self._search_regex( r'(<[^>]+class="video_player_loader"[^>]+>)', webpage, 'video player loader')) @@ -65,15 +81,37 @@ class TV5MondePlusIE(InfoExtractor): }) self._sort_formats(formats) + description = self._html_search_regex( + r'(?s)]+class=["\']episode-texte[^>]+>(.+?)', webpage, + 'description', fatal=False) + + series = self._html_search_regex( + r']+class=["\']episode-emission[^>]+>([^<]+)', webpage, + 'series', default=None) + + if series and series != title: + title = '%s - %s' % (series, title) + + upload_date = self._search_regex( + r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})', + webpage, 'upload date', default=None) + if upload_date: + upload_date = upload_date.replace('_', '') + + video_id = self._search_regex( + (r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', + r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id', + default=display_id) + return { - 'id': display_id, + 'id': video_id, 'display_id': display_id, 'title': title, - 'description': clean_html(get_element_by_class('video-detail__description', webpage)), + 'description': description, 'thumbnail': vpl_data.get('data-image'), 'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)), - 'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)), + 'upload_date': upload_date, 'formats': formats, - 'episode': episode, 'series': series, + 'episode': episode, } diff --git a/youtube_dl/extractor/tva.py b/youtube_dl/extractor/tva.py index 0b863df2f..443f46e8a 100644 --- a/youtube_dl/extractor/tva.py +++ b/youtube_dl/extractor/tva.py @@ -9,8 +9,8 @@ from ..utils import ( class TVAIE(InfoExtractor): - _VALID_URL = r'https?://videos\.tva\.ca/details/_(?P\d+)' - _TEST = { + _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P\d+)' + _TESTS = [{ 'url': 'https://videos.tva.ca/details/_5596811470001', 'info_dict': { 'id': '5596811470001', @@ -24,7 +24,10 @@ class TVAIE(InfoExtractor): # m3u8 download 'skip_download': True, } - } + }, { + 'url': 'https://video.tva.ca/details/_5596811470001', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s' def _real_extract(self, url): diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 1d66eeaff..74d14049b 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -17,8 +17,8 @@ class TwentyFourVideoIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?P - (?:(?:www|porno)\.)?24video\. - (?:net|me|xxx|sexy?|tube|adult|site) + (?:(?:www|porno?)\.)?24video\. + (?:net|me|xxx|sexy?|tube|adult|site|vip) )/ (?: video/(?:(?:view|xml)/)?| @@ -59,6 +59,12 @@ class TwentyFourVideoIE(InfoExtractor): }, { 'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle', 'only_matching': True, + }, { + 'url': 'https://www.24video.vip/video/view/1044982', + 'only_matching': True, + }, { + 'url': 'https://porn.24video.net/video/2640421-vsya-takay', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index a8c2502af..0db2dca41 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -575,8 +575,8 @@ class TwitchStreamIE(TwitchBaseIE): channel_id = self._match_id(url) stream = self._call_api( - 'kraken/streams/%s?stream_type=all' % channel_id, channel_id, - 'Downloading stream JSON').get('stream') + 'kraken/streams/%s?stream_type=all' % channel_id.lower(), + channel_id, 'Downloading stream JSON').get('stream') if not stream: raise ExtractorError('%s is offline' % channel_id, expected=True) diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 5f8d90fb4..01468981c 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -251,10 +251,10 @@ class TwitterIE(TwitterBaseIE): 'info_dict': { 'id': '700207533655363584', 'ext': 'mp4', - 'title': 'Simon Vertugo - BEAT PROD: @suhmeduh #Damndaniel', + 'title': 'simon vetugo - BEAT PROD: @suhmeduh #Damndaniel', 'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ', 'thumbnail': r're:^https?://.*\.jpg', - 'uploader': 'Simon Vertugo', + 'uploader': 'simon vetugo', 'uploader_id': 'simonvertugo', 'duration': 30.0, 'timestamp': 1455777459, @@ -376,6 +376,10 @@ class TwitterIE(TwitterBaseIE): # Twitch Clip Embed 'url': 'https://twitter.com/GunB1g/status/1163218564784017422', 'only_matching': True, + }, { + # promo_video_website card + 'url': 'https://twitter.com/GunB1g/status/1163218564784017422', + 'only_matching': True, }] def _real_extract(self, url): @@ -458,10 +462,11 @@ class TwitterIE(TwitterBaseIE): return try_get(o, lambda x: x[x['type'].lower() + '_value']) card_name = card['name'].split(':')[-1] - if card_name == 'amplify': - formats = self._extract_formats_from_vmap_url( - get_binding_value('amplify_url_vmap'), - get_binding_value('amplify_content_id') or twid) + if card_name in ('amplify', 'promo_video_website'): + is_amplify = card_name == 'amplify' + vmap_url = get_binding_value('amplify_url_vmap') if is_amplify else get_binding_value('player_stream_url') + content_id = get_binding_value('%s_content_id' % (card_name if is_amplify else 'player')) + formats = self._extract_formats_from_vmap_url(vmap_url, content_id or twid) self._sort_formats(formats) thumbnails = [] diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 8fdfd743d..e37499512 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,35 +1,50 @@ # coding: utf-8 from __future__ import unicode_literals -import re -import time +import functools import hashlib import json import random +import re +import time from .adobepass import AdobePassIE -from .youtube import YoutubeIE from .common import InfoExtractor +from .youtube import YoutubeIE from ..compat import ( compat_HTTPError, compat_str, ) from ..utils import ( + clean_html, ExtractorError, int_or_none, + OnDemandPagedList, parse_age_limit, str_or_none, try_get, ) -class ViceIE(AdobePassIE): +class ViceBaseIE(InfoExtractor): + def _call_api(self, resource, resource_key, resource_id, locale, fields, args=''): + return self._download_json( + 'https://video.vice.com/api/v1/graphql', resource_id, query={ + 'query': '''{ + %s(locale: "%s", %s: "%s"%s) { + %s + } +}''' % (resource, locale, resource_key, resource_id, args, fields), + })['data'][resource] + + +class ViceIE(ViceBaseIE, AdobePassIE): IE_NAME = 'vice' - _VALID_URL = r'https?://(?:(?:video|vms)\.vice|(?:www\.)?viceland)\.com/(?P[^/]+)/(?:video/[^/]+|embed)/(?P[\da-f]+)' + _VALID_URL = r'https?://(?:(?:video|vms)\.vice|(?:www\.)?vice(?:land|tv))\.com/(?P[^/]+)/(?:video/[^/]+|embed)/(?P[\da-f]{24})' _TESTS = [{ 'url': 'https://video.vice.com/en_us/video/pet-cremator/58c69e38a55424f1227dc3f7', 'info_dict': { - 'id': '5e647f0125e145c9aef2069412c0cbde', + 'id': '58c69e38a55424f1227dc3f7', 'ext': 'mp4', 'title': '10 Questions You Always Wanted To Ask: Pet Cremator', 'description': 'md5:fe856caacf61fe0e74fab15ce2b07ca5', @@ -43,17 +58,16 @@ class ViceIE(AdobePassIE): # m3u8 download 'skip_download': True, }, - 'add_ie': ['UplynkPreplay'], }, { # geo restricted to US 'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56', 'info_dict': { - 'id': '930c0ad1f47141cc955087eecaddb0e2', + 'id': '5816510690b70e6c5fd39a56', 'ext': 'mp4', - 'uploader': 'waypoint', + 'uploader': 'vice', 'title': 'The Signal From Tölva', 'description': 'md5:3927e3c79f9e8094606a2b3c5b5e55d5', - 'uploader_id': '57f7d621e05ca860fa9ccaf9', + 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1477941983, 'upload_date': '20161031', }, @@ -61,15 +75,14 @@ class ViceIE(AdobePassIE): # m3u8 download 'skip_download': True, }, - 'add_ie': ['UplynkPreplay'], }, { 'url': 'https://video.vice.com/alps/video/ulfs-wien-beruchtigste-grafitti-crew-part-1/581b12b60a0e1f4c0fb6ea2f', 'info_dict': { 'id': '581b12b60a0e1f4c0fb6ea2f', 'ext': 'mp4', 'title': 'ULFs - Wien berüchtigste Grafitti Crew - Part 1', - 'description': '

    Zwischen Hinterzimmer-Tattoos und U-Bahnschächten erzählen uns die Ulfs, wie es ist, "süchtig nach Sachbeschädigung" zu sein.

    ', - 'uploader': 'VICE', + 'description': 'Zwischen Hinterzimmer-Tattoos und U-Bahnschächten erzählen uns die Ulfs, wie es ist, "süchtig nach Sachbeschädigung" zu sein.', + 'uploader': 'vice', 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1485368119, 'upload_date': '20170125', @@ -78,9 +91,7 @@ class ViceIE(AdobePassIE): 'params': { # AES-encrypted m3u8 'skip_download': True, - 'proxy': '127.0.0.1:8118', }, - 'add_ie': ['UplynkPreplay'], }, { 'url': 'https://video.vice.com/en_us/video/pizza-show-trailer/56d8c9a54d286ed92f7f30e4', 'only_matching': True, @@ -98,7 +109,7 @@ class ViceIE(AdobePassIE): @staticmethod def _extract_urls(webpage): return re.findall( - r']+\bsrc=["\']((?:https?:)?//video\.vice\.com/[^/]+/embed/[\da-f]+)', + r']+\bsrc=["\']((?:https?:)?//video\.vice\.com/[^/]+/embed/[\da-f]{24})', webpage) @staticmethod @@ -109,31 +120,16 @@ class ViceIE(AdobePassIE): def _real_extract(self, url): locale, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage( - 'https://video.vice.com/%s/embed/%s' % (locale, video_id), - video_id) - - video = self._parse_json( - self._search_regex( - r'PREFETCH_DATA\s*=\s*({.+?})\s*;\s*\n', webpage, - 'app state'), video_id)['video'] - video_id = video.get('vms_id') or video.get('id') or video_id - title = video['title'] - is_locked = video.get('locked') + video = self._call_api('videos', 'id', video_id, locale, '''body + locked + rating + thumbnail_url + title''')[0] + title = video['title'].strip() rating = video.get('rating') - thumbnail = video.get('thumbnail_url') - duration = int_or_none(video.get('duration')) - series = try_get( - video, lambda x: x['episode']['season']['show']['title'], - compat_str) - episode_number = try_get( - video, lambda x: x['episode']['episode_number']) - season_number = try_get( - video, lambda x: x['episode']['season']['season_number']) - uploader = None query = {} - if is_locked: + if video.get('locked'): resource = self._get_mvpd_resource( 'VICELAND', title, video_id, rating) query['tvetoken'] = self._extract_mvpd_auth( @@ -148,12 +144,9 @@ class ViceIE(AdobePassIE): query.update({ 'exp': exp, 'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(), - '_ad_blocked': None, - '_ad_unit': '', - '_debug': '', + 'skipadstitching': 1, 'platform': 'desktop', 'rn': random.randint(10000, 100000), - 'fbprebidtoken': '', }) try: @@ -169,85 +162,94 @@ class ViceIE(AdobePassIE): raise video_data = preplay['video'] - base = video_data['base'] - uplynk_preplay_url = preplay['preplayURL'] - episode = video_data.get('episode', {}) - channel = video_data.get('channel', {}) + formats = self._extract_m3u8_formats( + preplay['playURL'], video_id, 'mp4', 'm3u8_native') + self._sort_formats(formats) + episode = video_data.get('episode') or {} + channel = video_data.get('channel') or {} + season = video_data.get('season') or {} subtitles = {} - cc_url = preplay.get('ccURL') - if cc_url: - subtitles['en'] = [{ + for subtitle in preplay.get('subtitleURLs', []): + cc_url = subtitle.get('url') + if not cc_url: + continue + language_code = try_get(subtitle, lambda x: x['languages'][0]['language_code'], compat_str) or 'en' + subtitles.setdefault(language_code, []).append({ 'url': cc_url, - }] + }) return { - '_type': 'url_transparent', - 'url': uplynk_preplay_url, + 'formats': formats, 'id': video_id, 'title': title, - 'description': base.get('body') or base.get('display_body'), - 'thumbnail': thumbnail, - 'duration': int_or_none(video_data.get('video_duration')) or duration, + 'description': clean_html(video.get('body')), + 'thumbnail': video.get('thumbnail_url'), + 'duration': int_or_none(video_data.get('video_duration')), 'timestamp': int_or_none(video_data.get('created_at'), 1000), - 'age_limit': parse_age_limit(video_data.get('video_rating')), - 'series': video_data.get('show_title') or series, - 'episode_number': int_or_none(episode.get('episode_number') or episode_number), + 'age_limit': parse_age_limit(video_data.get('video_rating') or rating), + 'series': try_get(video_data, lambda x: x['show']['base']['display_title'], compat_str), + 'episode_number': int_or_none(episode.get('episode_number')), 'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')), - 'season_number': int_or_none(season_number), - 'season_id': str_or_none(episode.get('season_id')), - 'uploader': channel.get('base', {}).get('title') or channel.get('name') or uploader, + 'season_number': int_or_none(season.get('season_number')), + 'season_id': str_or_none(season.get('id') or video_data.get('season_id')), + 'uploader': channel.get('name'), 'uploader_id': str_or_none(channel.get('id')), 'subtitles': subtitles, - 'ie_key': 'UplynkPreplay', } -class ViceShowIE(InfoExtractor): +class ViceShowIE(ViceBaseIE): IE_NAME = 'vice:show' - _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P[^/?#&]+)' - - _TEST = { - 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2', + _VALID_URL = r'https?://(?:video\.vice|(?:www\.)?vice(?:land|tv))\.com/(?P[^/]+)/show/(?P[^/?#&]+)' + _PAGE_SIZE = 25 + _TESTS = [{ + 'url': 'https://video.vice.com/en_us/show/fck-thats-delicious', 'info_dict': { - 'id': 'fuck-thats-delicious-2', - 'title': "Fuck, That's Delicious", - 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.', + 'id': '57a2040c8cb727dec794c901', + 'title': 'F*ck, That’s Delicious', + 'description': 'The life and eating habits of rap’s greatest bon vivant, Action Bronson.', }, - 'playlist_count': 17, - } + 'playlist_mincount': 64, + }, { + 'url': 'https://www.vicetv.com/en_us/show/fck-thats-delicious', + 'only_matching': True, + }] + + def _fetch_page(self, locale, show_id, page): + videos = self._call_api('videos', 'show_id', show_id, locale, '''body + id + url''', ', page: %d, per_page: %d' % (page + 1, self._PAGE_SIZE)) + for video in videos: + yield self.url_result( + video['url'], ViceIE.ie_key(), video.get('id')) def _real_extract(self, url): - show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) + locale, display_id = re.match(self._VALID_URL, url).groups() + show = self._call_api('shows', 'slug', display_id, locale, '''dek + id + title''')[0] + show_id = show['id'] - entries = [ - self.url_result(video_url, ViceIE.ie_key()) - for video_url, _ in re.findall( - r']+class="article-title"[^>]+data-id="\d+"[^>]*>\s*]+href="(%s.*?)"' - % ViceIE._VALID_URL, webpage)] + entries = OnDemandPagedList( + functools.partial(self._fetch_page, locale, show_id), + self._PAGE_SIZE) - title = self._search_regex( - r'(.+?)', webpage, 'title', default=None) - if title: - title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip() - description = self._html_search_meta( - 'description', webpage, 'description') - - return self.playlist_result(entries, show_id, title, description) + return self.playlist_result( + entries, show_id, show.get('title'), show.get('dek')) -class ViceArticleIE(InfoExtractor): +class ViceArticleIE(ViceBaseIE): IE_NAME = 'vice:article' - _VALID_URL = r'https://www\.vice\.com/[^/]+/article/(?P[^?#]+)' + _VALID_URL = r'https://(?:www\.)?vice\.com/(?P[^/]+)/article/(?:[0-9a-z]{6}/)?(?P[^?#]+)' _TESTS = [{ 'url': 'https://www.vice.com/en_us/article/on-set-with-the-woman-making-mormon-porn-in-utah', 'info_dict': { - 'id': '41eae2a47b174a1398357cec55f1f6fc', + 'id': '58dc0a3dee202d2a0ccfcbd8', 'ext': 'mp4', - 'title': 'Mormon War on Porn ', - 'description': 'md5:6394a8398506581d0346b9ab89093fef', + 'title': 'Mormon War on Porn', + 'description': 'md5:1c5d91fe25fa8aa304f9def118b92dbf', 'uploader': 'vice', 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1491883129, @@ -258,10 +260,10 @@ class ViceArticleIE(InfoExtractor): # AES-encrypted m3u8 'skip_download': True, }, - 'add_ie': ['UplynkPreplay'], + 'add_ie': [ViceIE.ie_key()], }, { 'url': 'https://www.vice.com/en_us/article/how-to-hack-a-car', - 'md5': '7fe8ebc4fa3323efafc127b82bd821d9', + 'md5': '13010ee0bc694ea87ec40724397c2349', 'info_dict': { 'id': '3jstaBeXgAs', 'ext': 'mp4', @@ -271,15 +273,15 @@ class ViceArticleIE(InfoExtractor): 'uploader_id': 'MotherboardTV', 'upload_date': '20140529', }, - 'add_ie': ['Youtube'], + 'add_ie': [YoutubeIE.ie_key()], }, { 'url': 'https://www.vice.com/en_us/article/znm9dx/karley-sciortino-slutever-reloaded', 'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2', 'info_dict': { - 'id': 'e2ed435eb67e43efb66e6ef9a6930a88', + 'id': '57f41d3556a0a80f54726060', 'ext': 'mp4', 'title': "Making The World's First Male Sex Doll", - 'description': 'md5:916078ef0e032d76343116208b6cc2c4', + 'description': 'md5:19b00b215b99961cf869c40fbe9df755', 'uploader': 'vice', 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1476919911, @@ -288,6 +290,7 @@ class ViceArticleIE(InfoExtractor): }, 'params': { 'skip_download': True, + 'format': 'bestvideo', }, 'add_ie': [ViceIE.ie_key()], }, { @@ -299,14 +302,11 @@ class ViceArticleIE(InfoExtractor): }] def _real_extract(self, url): - display_id = self._match_id(url) + locale, display_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, display_id) - - prefetch_data = self._parse_json(self._search_regex( - r'__APP_STATE\s*=\s*({.+?})(?:\s*\|\|\s*{}\s*)?;\s*\n', - webpage, 'app state'), display_id)['pageData'] - body = prefetch_data['body'] + article = self._call_api('articles', 'slug', display_id, locale, '''body + embed_code''')[0] + body = article['body'] def _url_res(video_url, ie_key): return { @@ -316,7 +316,7 @@ class ViceArticleIE(InfoExtractor): 'ie_key': ie_key, } - vice_url = ViceIE._extract_url(webpage) + vice_url = ViceIE._extract_url(body) if vice_url: return _url_res(vice_url, ViceIE.ie_key()) @@ -332,6 +332,6 @@ class ViceArticleIE(InfoExtractor): video_url = self._html_search_regex( r'data-video-url="([^"]+)"', - prefetch_data['embed_code'], 'video URL') + article['embed_code'], 'video URL') return _url_res(video_url, ViceIE.ie_key()) diff --git a/youtube_dl/extractor/viewlift.py b/youtube_dl/extractor/viewlift.py index 851ad936c..d6b92b1c8 100644 --- a/youtube_dl/extractor/viewlift.py +++ b/youtube_dl/extractor/viewlift.py @@ -1,28 +1,62 @@ from __future__ import unicode_literals -import base64 +import json import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, - clean_html, - determine_ext, int_or_none, - js_to_json, parse_age_limit, - parse_duration, - try_get, ) class ViewLiftBaseIE(InfoExtractor): - _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv' + _API_BASE = 'https://prod-api.viewlift.com/' + _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv' + _SITE_MAP = { + 'ftfnext': 'lax', + 'funnyforfree': 'snagfilms', + 'hoichoi': 'hoichoitv', + 'kiddovid': 'snagfilms', + 'laxsportsnetwork': 'lax', + 'legapallacanestro': 'lnp', + 'marquee': 'marquee-tv', + 'monumentalsportsnetwork': 'monumental-network', + 'moviespree': 'bingeflix', + 'pflmma': 'pfl', + 'snagxtreme': 'snagfilms', + 'theidentitytb': 'tampabay', + 'vayafilm': 'snagfilms', + } + _TOKENS = {} + + def _call_api(self, site, path, video_id, query): + token = self._TOKENS.get(site) + if not token: + token_query = {'site': site} + email, password = self._get_login_info(netrc_machine=site) + if email: + resp = self._download_json( + self._API_BASE + 'identity/signin', video_id, + 'Logging in', query=token_query, data=json.dumps({ + 'email': email, + 'password': password, + }).encode()) + else: + resp = self._download_json( + self._API_BASE + 'identity/anonymous-token', video_id, + 'Downloading authorization token', query=token_query) + self._TOKENS[site] = token = resp['authorizationToken'] + return self._download_json( + self._API_BASE + path, video_id, + headers={'Authorization': token}, query=query) class ViewLiftEmbedIE(ViewLiftBaseIE): - _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX + IE_NAME = 'viewlift:embed' + _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P%s)/embed/player\?.*\bfilmId=(?P[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX _TESTS = [{ 'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500', 'md5': '2924e9215c6eff7a55ed35b72276bd93', @@ -30,6 +64,9 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): 'id': '74849a00-85a9-11e1-9660-123139220831', 'ext': 'mp4', 'title': '#whilewewatch', + 'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8', + 'timestamp': 1334350096, + 'upload_date': '20120413', } }, { # invalid labels, 360p is better that 480p @@ -39,7 +76,8 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): 'id': '17ca0950-a74a-11e0-a92a-0026bb61d036', 'ext': 'mp4', 'title': 'Life in Limbo', - } + }, + 'skip': 'The video does not exist', }, { 'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017', 'only_matching': True, @@ -54,67 +92,68 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): return mobj.group('url') def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - if '>This film is not playable in your area.<' in webpage: - raise ExtractorError( - 'Film %s is not playable in your area.' % video_id, expected=True) + domain, film_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[-2] + if site in self._SITE_MAP: + site = self._SITE_MAP[site] + try: + content_data = self._call_api( + site, 'entitlement/video/status', film_id, { + 'id': film_id + })['video'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + error_message = self._parse_json(e.cause.read().decode(), film_id).get('errorMessage') + if error_message == 'User does not have a valid subscription or has not purchased this content.': + self.raise_login_required() + raise ExtractorError(error_message, expected=True) + raise + gist = content_data['gist'] + title = gist['title'] + video_assets = content_data['streamingInfo']['videoAssets'] formats = [] - has_bitrate = False - sources = self._parse_json(self._search_regex( - r'(?s)sources:\s*(\[.+?\]),', webpage, - 'sources', default='[]'), video_id, js_to_json) - for source in sources: - file_ = source.get('file') - if not file_: + mpeg_video_assets = video_assets.get('mpeg') or [] + for video_asset in mpeg_video_assets: + video_asset_url = video_asset.get('url') + if not video_asset: continue - type_ = source.get('type') - ext = determine_ext(file_) - format_id = source.get('label') or ext - if all(v in ('m3u8', 'hls') for v in (type_, ext)): - formats.extend(self._extract_m3u8_formats( - file_, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - else: - bitrate = int_or_none(self._search_regex( - [r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext], - file_, 'bitrate', default=None)) - if not has_bitrate and bitrate: - has_bitrate = True - height = int_or_none(self._search_regex( - r'^(\d+)[pP]$', format_id, 'height', default=None)) - formats.append({ - 'url': file_, - 'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')), - 'tbr': bitrate, - 'height': height, - }) - if not formats: - hls_url = self._parse_json(self._search_regex( - r'filmInfo\.src\s*=\s*({.+?});', - webpage, 'src'), video_id, js_to_json)['src'] - formats = self._extract_m3u8_formats( - hls_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False) - field_preference = None if has_bitrate else ('height', 'tbr', 'format_id') - self._sort_formats(formats, field_preference) + bitrate = int_or_none(video_asset.get('bitrate')) + height = int_or_none(self._search_regex( + r'^_?(\d+)[pP]$', video_asset.get('renditionValue'), + 'height', default=None)) + formats.append({ + 'url': video_asset_url, + 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''), + 'tbr': bitrate, + 'height': height, + 'vcodec': video_asset.get('codec'), + }) - title = self._search_regex( - [r"title\s*:\s*'([^']+)'", r'([^<]+)'], - webpage, 'title') + hls_url = video_assets.get('hls') + if hls_url: + formats.extend(self._extract_m3u8_formats( + hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + self._sort_formats(formats, ('height', 'tbr', 'format_id')) - return { - 'id': video_id, + info = { + 'id': film_id, 'title': title, + 'description': gist.get('description'), + 'thumbnail': gist.get('videoImageUrl'), + 'duration': int_or_none(gist.get('runtime')), + 'age_limit': parse_age_limit(content_data.get('parentalRating')), + 'timestamp': int_or_none(gist.get('publishDate'), 1000), 'formats': formats, } + for k in ('categories', 'tags'): + info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')] + return info class ViewLiftIE(ViewLiftBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?P%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX + IE_NAME = 'viewlift' + _VALID_URL = r'https?://(?:www\.)?(?P%s)(?P(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX _TESTS = [{ 'url': 'http://www.snagfilms.com/films/title/lost_for_life', 'md5': '19844f897b35af219773fd63bdec2942', @@ -151,10 +190,13 @@ class ViewLiftIE(ViewLiftBaseIE): 'id': '00000148-7b53-de26-a9fb-fbf306f70020', 'display_id': 'augie_alone/s_2_ep_12_love', 'ext': 'mp4', - 'title': 'Augie, Alone:S. 2 Ep. 12 - Love', - 'description': 'md5:db2a5c72d994f16a780c1eb353a8f403', + 'title': 'S. 2 Ep. 12 - Love', + 'description': 'Augie finds love.', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 107, + 'upload_date': '20141012', + 'timestamp': 1413129540, + 'age_limit': 17, }, 'params': { 'skip_download': True, @@ -177,6 +219,9 @@ class ViewLiftIE(ViewLiftBaseIE): # Was once Kaltura embed 'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15', 'only_matching': True, + }, { + 'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters', + 'only_matching': True, }] @classmethod @@ -184,119 +229,22 @@ class ViewLiftIE(ViewLiftBaseIE): return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url) def _real_extract(self, url): - domain, display_id = re.match(self._VALID_URL, url).groups() - - webpage = self._download_webpage(url, display_id) - - if ">Sorry, the Film you're looking for is not available.<" in webpage: - raise ExtractorError( - 'Film %s is not available.' % display_id, expected=True) - - initial_store_state = self._search_regex( - r"window\.initialStoreState\s*=.*?JSON\.parse\(unescape\(atob\('([^']+)'\)\)\)", - webpage, 'Initial Store State', default=None) - if initial_store_state: - modules = self._parse_json(compat_urllib_parse_unquote(base64.b64decode( - initial_store_state).decode()), display_id)['page']['data']['modules'] - content_data = next(m['contentData'][0] for m in modules if m.get('moduleType') == 'VideoDetailModule') - gist = content_data['gist'] - film_id = gist['id'] - title = gist['title'] - video_assets = try_get( - content_data, lambda x: x['streamingInfo']['videoAssets'], dict) - if not video_assets: - token = self._download_json( - 'https://prod-api.viewlift.com/identity/anonymous-token', - film_id, 'Downloading authorization token', - query={'site': 'snagfilms'})['authorizationToken'] - video_assets = self._download_json( - 'https://prod-api.viewlift.com/entitlement/video/status', - film_id, headers={ - 'Authorization': token, - 'Referer': url, - }, query={ - 'id': film_id - })['video']['streamingInfo']['videoAssets'] - - formats = [] - mpeg_video_assets = video_assets.get('mpeg') or [] - for video_asset in mpeg_video_assets: - video_asset_url = video_asset.get('url') - if not video_asset: - continue - bitrate = int_or_none(video_asset.get('bitrate')) - height = int_or_none(self._search_regex( - r'^_?(\d+)[pP]$', video_asset.get('renditionValue'), - 'height', default=None)) - formats.append({ - 'url': video_asset_url, - 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''), - 'tbr': bitrate, - 'height': height, - 'vcodec': video_asset.get('codec'), - }) - - hls_url = video_assets.get('hls') - if hls_url: - formats.extend(self._extract_m3u8_formats( - hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - self._sort_formats(formats, ('height', 'tbr', 'format_id')) - - info = { - 'id': film_id, - 'display_id': display_id, - 'title': title, - 'description': gist.get('description'), - 'thumbnail': gist.get('videoImageUrl'), - 'duration': int_or_none(gist.get('runtime')), - 'age_limit': parse_age_limit(content_data.get('parentalRating')), - 'timestamp': int_or_none(gist.get('publishDate'), 1000), - 'formats': formats, - } - for k in ('categories', 'tags'): - info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')] - return info - else: - film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id') - - snag = self._parse_json( - self._search_regex( - r'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag', default='[]'), - display_id) - - for item in snag: - if item.get('data', {}).get('film', {}).get('id') == film_id: - data = item['data']['film'] - title = data['title'] - description = clean_html(data.get('synopsis')) - thumbnail = data.get('image') - duration = int_or_none(data.get('duration') or data.get('runtime')) - categories = [ - category['title'] for category in data.get('categories', []) - if category.get('title')] - break - else: - title = self._html_search_regex( - (r'itemprop="title">([^<]+)<', - r'(?s)itemprop="title">(.+?)(.+?)', - webpage, 'description', default=None) or self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - duration = parse_duration(self._search_regex( - r'([^<]+)<', - webpage, 'duration', fatal=False)) - categories = re.findall(r'    ([^<]+)', webpage) - - return { - '_type': 'url_transparent', - 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), - 'id': film_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'categories': categories, - 'ie_key': 'ViewLiftEmbed', - } + domain, path, display_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[-2] + if site in self._SITE_MAP: + site = self._SITE_MAP[site] + modules = self._call_api( + site, 'content/pages', display_id, { + 'includeContent': 'true', + 'moduleOffset': 1, + 'path': path, + 'site': site, + })['modules'] + film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule') + return { + '_type': 'url_transparent', + 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), + 'id': film_id, + 'display_id': display_id, + 'ie_key': 'ViewLiftEmbed', + } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index baa46d5f3..1da4ced96 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -591,7 +591,7 @@ class VimeoIE(VimeoBaseInfoExtractor): # Retrieve video webpage to extract further information webpage, urlh = self._download_webpage_handle( url, video_id, headers=headers) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() @@ -841,33 +841,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): return self._TITLE or self._html_search_regex( self._TITLE_RE, webpage, 'list title', fatal=False) - def _login_list_password(self, page_url, list_id, webpage): - login_form = self._search_regex( - r'(?s)]+?id="pw_form"(.*?)', - webpage, 'login form', default=None) - if not login_form: - return webpage - - password = self._downloader.params.get('videopassword') - if password is None: - raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) - fields = self._hidden_inputs(login_form) - token, vuid = self._extract_xsrft_and_vuid(webpage) - fields['token'] = token - fields['password'] = password - post = urlencode_postdata(fields) - password_path = self._search_regex( - r'action="([^"]+)"', login_form, 'password URL') - password_url = compat_urlparse.urljoin(page_url, password_path) - password_request = sanitized_Request(password_url, post) - password_request.add_header('Content-type', 'application/x-www-form-urlencoded') - self._set_vimeo_cookie('vuid', vuid) - self._set_vimeo_cookie('xsrft', token) - - return self._download_webpage( - password_request, list_id, - 'Verifying the password', 'Wrong password') - def _title_and_entries(self, list_id, base_url): for pagenum in itertools.count(1): page_url = self._page_url(base_url, pagenum) @@ -876,7 +849,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): 'Downloading page %s' % pagenum) if pagenum == 1: - webpage = self._login_list_password(page_url, list_id, webpage) yield self._extract_list_title(webpage) # Try extracting href first since not all videos are available via @@ -923,7 +895,7 @@ class VimeoUserIE(VimeoChannelIE): _BASE_URL_TEMPL = 'https://vimeo.com/%s' -class VimeoAlbumIE(VimeoChannelIE): +class VimeoAlbumIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:album' _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P\d+)(?:$|[?#]|/(?!video))' _TITLE_RE = r'
    \n\s*

    (.*?)

    ' @@ -973,13 +945,39 @@ class VimeoAlbumIE(VimeoChannelIE): def _real_extract(self, url): album_id = self._match_id(url) webpage = self._download_webpage(url, album_id) - webpage = self._login_list_password(url, album_id, webpage) - api_config = self._extract_vimeo_config(webpage, album_id)['api'] + viewer = self._parse_json(self._search_regex( + r'bootstrap_data\s*=\s*({.+?})', + webpage, 'bootstrap data'), album_id)['viewer'] + jwt = viewer['jwt'] + album = self._download_json( + 'https://api.vimeo.com/albums/' + album_id, + album_id, headers={'Authorization': 'jwt ' + jwt}, + query={'fields': 'description,name,privacy'}) + hashed_pass = None + if try_get(album, lambda x: x['privacy']['view']) == 'password': + password = self._downloader.params.get('videopassword') + if not password: + raise ExtractorError( + 'This album is protected by a password, use the --video-password option', + expected=True) + self._set_vimeo_cookie('vuid', viewer['vuid']) + try: + hashed_pass = self._download_json( + 'https://vimeo.com/showcase/%s/auth' % album_id, + album_id, 'Verifying the password', data=urlencode_postdata({ + 'password': password, + 'token': viewer['xsrft'], + }), headers={ + 'X-Requested-With': 'XMLHttpRequest', + })['hashed_pass'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError('Wrong password', expected=True) + raise entries = OnDemandPagedList(functools.partial( - self._fetch_page, album_id, api_config['jwt'], - api_config.get('hashed_pass')), self._PAGE_SIZE) - return self.playlist_result(entries, album_id, self._html_search_regex( - r'\s*(.+?)(?:\s+on Vimeo)?', webpage, 'title', fatal=False)) + self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE) + return self.playlist_result( + entries, album_id, album.get('name'), album.get('description')) class VimeoGroupsIE(VimeoChannelIE): diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index c3429f723..f79531e6f 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -6,22 +6,18 @@ import time import itertools from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlencode, - compat_str, -) +from .naver import NaverBaseIE +from ..compat import compat_str from ..utils import ( - dict_get, ExtractorError, - float_or_none, - int_or_none, + merge_dicts, remove_start, try_get, urlencode_postdata, ) -class VLiveIE(InfoExtractor): +class VLiveIE(NaverBaseIE): IE_NAME = 'vlive' _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P[0-9]+)' _NETRC_MACHINE = 'vlive' @@ -34,6 +30,7 @@ class VLiveIE(InfoExtractor): 'title': "[V LIVE] Girl's Day's Broadcast", 'creator': "Girl's Day", 'view_count': int, + 'uploader_id': 'muploader_a', }, }, { 'url': 'http://www.vlive.tv/video/16937', @@ -44,6 +41,7 @@ class VLiveIE(InfoExtractor): 'creator': 'EXO', 'view_count': int, 'subtitles': 'mincount:12', + 'uploader_id': 'muploader_j', }, 'params': { 'skip_download': True, @@ -187,45 +185,9 @@ class VLiveIE(InfoExtractor): 'This video is only available for CH+ subscribers') long_video_id, key = video_info['vid'], video_info['inkey'] - playinfo = self._download_json( - 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s' - % compat_urllib_parse_urlencode({ - 'videoId': long_video_id, - 'key': key, - 'ptc': 'http', - 'doct': 'json', # document type (xml or json) - 'cpt': 'vtt', # captions type (vtt or ttml) - }), video_id) - - formats = [{ - 'url': vid['source'], - 'format_id': vid.get('encodingOption', {}).get('name'), - 'abr': float_or_none(vid.get('bitrate', {}).get('audio')), - 'vbr': float_or_none(vid.get('bitrate', {}).get('video')), - 'width': int_or_none(vid.get('encodingOption', {}).get('width')), - 'height': int_or_none(vid.get('encodingOption', {}).get('height')), - 'filesize': int_or_none(vid.get('size')), - } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')] - self._sort_formats(formats) - - view_count = int_or_none(playinfo.get('meta', {}).get('count')) - - subtitles = {} - for caption in playinfo.get('captions', {}).get('list', []): - lang = dict_get(caption, ('locale', 'language', 'country', 'label')) - if lang and caption.get('source'): - subtitles[lang] = [{ - 'ext': 'vtt', - 'url': caption['source']}] - - info = self._get_common_fields(webpage) - info.update({ - 'id': video_id, - 'formats': formats, - 'view_count': view_count, - 'subtitles': subtitles, - }) - return info + return merge_dicts( + self._get_common_fields(webpage), + self._extract_video_info(video_id, long_video_id, key)) def _download_init_page(self, video_id): return self._download_webpage( diff --git a/youtube_dl/extractor/vodplatform.py b/youtube_dl/extractor/vodplatform.py index 239644340..74d2257e7 100644 --- a/youtube_dl/extractor/vodplatform.py +++ b/youtube_dl/extractor/vodplatform.py @@ -6,8 +6,8 @@ from ..utils import unescapeHTML class VODPlatformIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vod-platform\.net/[eE]mbed/(?P[^/?#]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/(?P[^/?#]+)' + _TESTS = [{ # from http://www.lbcgroup.tv/watch/chapter/29143/52844/%D8%A7%D9%84%D9%86%D8%B5%D8%B1%D8%A9-%D9%81%D9%8A-%D8%B6%D9%8A%D8%A7%D9%81%D8%A9-%D8%A7%D9%84%D9%80-cnn/ar 'url': 'http://vod-platform.net/embed/RufMcytHDolTH1MuKHY9Fw', 'md5': '1db2b7249ce383d6be96499006e951fc', @@ -16,7 +16,10 @@ class VODPlatformIE(InfoExtractor): 'ext': 'mp4', 'title': 'LBCi News_ النصرة في ضيافة الـ "سي.أن.أن"', } - } + }, { + 'url': 'http://embed.kwikmotion.com/embed/RufMcytHDolTH1MuKHY9Fw', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/voicerepublic.py b/youtube_dl/extractor/voicerepublic.py index 59e1359c4..a52e40afa 100644 --- a/youtube_dl/extractor/voicerepublic.py +++ b/youtube_dl/extractor/voicerepublic.py @@ -1,17 +1,12 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_urlparse, -) +from ..compat import compat_str from ..utils import ( ExtractorError, determine_ext, int_or_none, - sanitized_Request, + urljoin, ) @@ -26,8 +21,7 @@ class VoiceRepublicIE(InfoExtractor): 'ext': 'm4a', 'title': 'Watching the Watchers: Building a Sousveillance State', 'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.', - 'thumbnail': r're:^https?://.*\.(?:png|jpg)$', - 'duration': 1800, + 'duration': 1556, 'view_count': int, } }, { @@ -38,63 +32,31 @@ class VoiceRepublicIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - req = sanitized_Request( - compat_urlparse.urljoin(url, '/talks/%s' % display_id)) - # Older versions of Firefox get redirected to an "upgrade browser" page - req.add_header('User-Agent', 'youtube-dl') - webpage = self._download_webpage(req, display_id) + webpage = self._download_webpage(url, display_id) if '>Queued for processing, please stand by...<' in webpage: raise ExtractorError( 'Audio is still queued for processing', expected=True) - config = self._search_regex( - r'(?s)return ({.+?});\s*\n', webpage, - 'data', default=None) - data = self._parse_json(config, display_id, fatal=False) if config else None - if data: - title = data['title'] - description = data.get('teaser') - talk_id = compat_str(data.get('talk_id') or display_id) - talk = data['talk'] - duration = int_or_none(talk.get('duration')) - formats = [{ - 'url': compat_urlparse.urljoin(url, talk_url), - 'format_id': format_id, - 'ext': determine_ext(talk_url) or format_id, - 'vcodec': 'none', - } for format_id, talk_url in talk['links'].items()] - else: - title = self._og_search_title(webpage) - description = self._html_search_regex( - r"(?s)
    ]*>(.+?)
    ", - webpage, 'description', fatal=False) - talk_id = self._search_regex( - [r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"], - webpage, 'talk id', default=None) or display_id - duration = None - player = self._search_regex( - r"class='vr-player jp-jplayer'([^>]+)>", webpage, 'player') - formats = [{ - 'url': compat_urlparse.urljoin(url, talk_url), - 'format_id': format_id, - 'ext': determine_ext(talk_url) or format_id, - 'vcodec': 'none', - } for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", player)] + talk = self._parse_json(self._search_regex( + r'initialSnapshot\s*=\s*({.+?});', + webpage, 'talk'), display_id)['talk'] + title = talk['title'] + formats = [{ + 'url': urljoin(url, talk_url), + 'format_id': format_id, + 'ext': determine_ext(talk_url) or format_id, + 'vcodec': 'none', + } for format_id, talk_url in talk['media_links'].items()] self._sort_formats(formats) - thumbnail = self._og_search_thumbnail(webpage) - view_count = int_or_none(self._search_regex( - r"class='play-count[^']*'>\s*(\d+) plays", - webpage, 'play count', fatal=False)) - return { - 'id': talk_id, + 'id': compat_str(talk.get('id') or display_id), 'display_id': display_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'view_count': view_count, + 'description': talk.get('teaser'), + 'thumbnail': talk.get('image_url'), + 'duration': int_or_none(talk.get('archived_duration')), + 'view_count': int_or_none(talk.get('play_count')), 'formats': formats, } diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 0fbc888ec..168e5e901 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -13,8 +13,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P[a-z0-9]{10})' - _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' - _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' + _EMBED_BASE_URL = 'http://fast.wistia.com/embed/' _TESTS = [{ 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt', @@ -46,31 +45,32 @@ class WistiaIE(InfoExtractor): # https://wistia.com/support/embed-and-share/video-on-your-website @staticmethod def _extract_url(webpage): - match = re.search( - r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage) - if match: - return unescapeHTML(match.group('url')) + urls = WistiaIE._extract_urls(webpage) + return urls[0] if urls else None - match = re.search( - r'''(?sx) - ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]{10})\b.*?\2 - ''', webpage) - if match: - return 'wistia:%s' % match.group('id') - - match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P[a-z0-9]{10})', webpage) - if match: - return 'wistia:%s' % match.group('id') + @staticmethod + def _extract_urls(webpage): + urls = [] + for match in re.finditer( + r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage): + urls.append(unescapeHTML(match.group('url'))) + for match in re.finditer( + r'''(?sx) + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]{10})\b.*?\2 + ''', webpage): + urls.append('wistia:%s' % match.group('id')) + for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P[a-z0-9]{10})', webpage): + urls.append('wistia:%s' % match.group('id')) + return urls def _real_extract(self, url): video_id = self._match_id(url) data_json = self._download_json( - self._API_URL % video_id, video_id, + self._EMBED_BASE_URL + 'medias/%s.json' % video_id, video_id, # Some videos require this. headers={ - 'Referer': url if url.startswith('http') else self._IFRAME_URL % video_id, + 'Referer': url if url.startswith('http') else self._EMBED_BASE_URL + 'iframe/' + video_id, }) if data_json.get('error'): @@ -95,27 +95,61 @@ class WistiaIE(InfoExtractor): 'url': aurl, 'width': int_or_none(a.get('width')), 'height': int_or_none(a.get('height')), + 'filesize': int_or_none(a.get('size')), }) else: aext = a.get('ext') - is_m3u8 = a.get('container') == 'm3u8' or aext == 'm3u8' - formats.append({ - 'format_id': atype, + display_name = a.get('display_name') + format_id = atype + if atype and atype.endswith('_video') and display_name: + format_id = '%s-%s' % (atype[:-6], display_name) + f = { + 'format_id': format_id, 'url': aurl, - 'tbr': int_or_none(a.get('bitrate')), - 'vbr': int_or_none(a.get('opt_vbitrate')), - 'width': int_or_none(a.get('width')), - 'height': int_or_none(a.get('height')), - 'filesize': int_or_none(a.get('size')), - 'vcodec': a.get('codec'), - 'container': a.get('container'), - 'ext': 'mp4' if is_m3u8 else aext, - 'protocol': 'm3u8' if is_m3u8 else None, + 'tbr': int_or_none(a.get('bitrate')) or None, 'preference': 1 if atype == 'original' else None, - }) + } + if display_name == 'Audio': + f.update({ + 'vcodec': 'none', + }) + else: + f.update({ + 'width': int_or_none(a.get('width')), + 'height': int_or_none(a.get('height')), + 'vcodec': a.get('codec'), + }) + if a.get('container') == 'm3u8' or aext == 'm3u8': + ts_f = f.copy() + ts_f.update({ + 'ext': 'ts', + 'format_id': f['format_id'].replace('hls-', 'ts-'), + 'url': f['url'].replace('.bin', '.ts'), + }) + formats.append(ts_f) + f.update({ + 'ext': 'mp4', + 'protocol': 'm3u8_native', + }) + else: + f.update({ + 'container': a.get('container'), + 'ext': aext, + 'filesize': int_or_none(a.get('size')), + }) + formats.append(f) self._sort_formats(formats) + subtitles = {} + for caption in data.get('captions', []): + language = caption.get('language') + if not language: + continue + subtitles[language] = [{ + 'url': self._EMBED_BASE_URL + 'captions/' + video_id + '.vtt?language=' + language, + }] + return { 'id': video_id, 'title': title, @@ -124,4 +158,5 @@ class WistiaIE(InfoExtractor): 'thumbnails': thumbnails, 'duration': float_or_none(data.get('duration')), 'timestamp': int_or_none(data.get('createdAt')), + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index a5b94d279..0f7be6a7d 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -113,7 +113,7 @@ class XHamsterIE(InfoExtractor): display_id = mobj.group('display_id') or mobj.group('display_id_2') desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) - webpage = self._download_webpage(desktop_url, video_id) + webpage, urlh = self._download_webpage_handle(desktop_url, video_id) error = self._html_search_regex( r']+id=["\']videoClosed["\'][^>]*>(.+?)', @@ -161,6 +161,9 @@ class XHamsterIE(InfoExtractor): 'ext': determine_ext(format_url, 'mp4'), 'height': get_height(quality), 'filesize': filesize, + 'http_headers': { + 'Referer': urlh.geturl(), + }, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index c6c0b3291..47caec1de 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -47,7 +47,7 @@ class XTubeIE(InfoExtractor): 'display_id': 'A-Super-Run-Part-1-YT', 'ext': 'flv', 'title': 'A Super Run - Part 1 (YT)', - 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93', + 'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616', 'uploader': 'tshirtguy59', 'duration': 579, 'view_count': int, @@ -87,10 +87,24 @@ class XTubeIE(InfoExtractor): 'Cookie': 'age_verified=1; cookiesAccepted=1', }) - sources = self._parse_json(self._search_regex( - r'(["\'])?sources\1?\s*:\s*(?P{.+?}),', - webpage, 'sources', group='sources'), video_id, - transform_source=js_to_json) + title, thumbnail, duration = [None] * 3 + + config = self._parse_json(self._search_regex( + r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', + default='{}'), video_id, transform_source=js_to_json, fatal=False) + if config: + config = config.get('mainRoll') + if isinstance(config, dict): + title = config.get('title') + thumbnail = config.get('poster') + duration = int_or_none(config.get('duration')) + sources = config.get('sources') + + if isinstance(sources, dict): + sources = self._parse_json(self._search_regex( + r'(["\'])?sources\1?\s*:\s*(?P{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) formats = [] for format_id, format_url in sources.items(): @@ -102,20 +116,25 @@ class XTubeIE(InfoExtractor): self._remove_duplicate_formats(formats) self._sort_formats(formats) - title = self._search_regex( - (r'

    \s*(?P[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), - webpage, 'title', group='title') - description = self._search_regex( + if not title: + title = self._search_regex( + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + webpage, 'title', group='title') + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage, default=None) or self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) uploader = self._search_regex( (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"', r'<span[^>]+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) - duration = parse_duration(self._search_regex( - r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', - webpage, 'duration', fatal=False)) + if not duration: + duration = parse_duration(self._search_regex( + r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', + webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( - r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>', + (r'["\']viewsCount["\'][^>]*>(\d+)\s+views', + r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'), webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( r'>Comments? \(([\d,\.]+)\)<', @@ -126,6 +145,7 @@ class XTubeIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'thumbnail': thumbnail, 'uploader': uploader, 'duration': duration, 'view_count': view_count, @@ -144,7 +164,7 @@ class XTubeUserIE(InfoExtractor): 'id': 'greenshowers-4056496', 'age_limit': 18, }, - 'playlist_mincount': 155, + 'playlist_mincount': 154, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index dff69fcb7..88aabd272 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -44,7 +44,7 @@ class YouJizzIE(InfoExtractor): encodings = self._parse_json( self._search_regex( - r'encodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', + r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', default='[]'), video_id, fatal=False) for encoding in encodings: diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 8a2d5f63b..98347491e 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( parse_duration, urljoin, @@ -8,9 +9,9 @@ from ..utils import ( class YourPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)' + _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)' _TESTS = [{ - 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', + 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html', 'md5': '6f8682b6464033d87acaa7a8ff0c092e', 'info_dict': { 'id': '57ffcb2e1179b', @@ -33,11 +34,19 @@ class YourPornIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_url = urljoin(url, self._parse_json( + parts = self._parse_json( self._search_regex( r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]).replace('/cdn/', '/cdn5/') + video_id)[video_id].split('/') + + num = 0 + for c in parts[6] + parts[7]: + if c.isnumeric(): + num += int(c) + parts[5] = compat_str(int(parts[5]) - num) + parts[1] += '8' + video_url = urljoin(url, '/'.join(parts)) title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', @@ -54,4 +63,5 @@ class YourPornIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'age_limit': 18, + 'ext': 'mp4', } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index b913d07a6..eacaa5ecd 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1343,6 +1343,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): funcname = self._search_regex( (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', # Obsolete patterns r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', diff --git a/youtube_dl/extractor/zapiks.py b/youtube_dl/extractor/zapiks.py index bacb82eee..f6496f516 100644 --- a/youtube_dl/extractor/zapiks.py +++ b/youtube_dl/extractor/zapiks.py @@ -29,7 +29,6 @@ class ZapiksIE(InfoExtractor): 'timestamp': 1359044972, 'upload_date': '20130124', 'view_count': int, - 'comment_count': int, }, }, { diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 145c123a4..656864b2e 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -244,14 +244,14 @@ class ZDFChannelIE(ZDFBaseIE): 'id': 'das-aktuelle-sportstudio', 'title': 'das aktuelle sportstudio | ZDF', }, - 'playlist_count': 21, + 'playlist_mincount': 23, }, { 'url': 'https://www.zdf.de/dokumentation/planet-e', 'info_dict': { 'id': 'planet-e', 'title': 'planet e.', }, - 'playlist_count': 4, + 'playlist_mincount': 50, }, { 'url': 'https://www.zdf.de/filme/taunuskrimi/', 'only_matching': True, diff --git a/youtube_dl/extractor/zype.py b/youtube_dl/extractor/zype.py index 3b16e703b..2e2e97a0c 100644 --- a/youtube_dl/extractor/zype.py +++ b/youtube_dl/extractor/zype.py @@ -4,10 +4,20 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + dict_get, + ExtractorError, + int_or_none, + js_to_json, + parse_iso8601, +) class ZypeIE(InfoExtractor): - _VALID_URL = r'https?://player\.zype\.com/embed/(?P<id>[\da-fA-F]+)\.js\?.*?api_key=[^&]+' + _ID_RE = r'[\da-fA-F]+' + _COMMON_RE = r'//player\.zype\.com/embed/%s\.(?:js|json|html)\?.*?(?:access_token|(?:ap[ip]|player)_key)=' + _VALID_URL = r'https?:%s[^&]+' % (_COMMON_RE % ('(?P<id>%s)' % _ID_RE)) _TEST = { 'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false', 'md5': 'eaee31d474c76a955bdaba02a505c595', @@ -16,6 +26,9 @@ class ZypeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Smoky Barbecue Favorites', 'thumbnail': r're:^https?://.*\.jpe?g', + 'description': 'md5:5ff01e76316bd8d46508af26dc86023b', + 'timestamp': 1504915200, + 'upload_date': '20170909', }, } @@ -24,34 +37,98 @@ class ZypeIE(InfoExtractor): return [ mobj.group('url') for mobj in re.finditer( - r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//player\.zype\.com/embed/[\da-fA-F]+\.js\?.*?api_key=.+?)\1', + r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?%s.+?)\1' % (ZypeIE._COMMON_RE % ZypeIE._ID_RE), webpage)] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + try: + response = self._download_json(re.sub( + r'\.(?:js|html)\?', '.json?', url), video_id)['response'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 403): + raise ExtractorError(self._parse_json( + e.cause.read().decode(), video_id)['message'], expected=True) + raise - title = self._search_regex( - r'video_title\s*[:=]\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, - 'title', group='value') + body = response['body'] + video = response['video'] + title = video['title'] - m3u8_url = self._search_regex( - r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', webpage, - 'm3u8 url', group='url') - - formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls') + if isinstance(body, dict): + formats = [] + for output in body.get('outputs', []): + output_url = output.get('url') + if not output_url: + continue + name = output.get('name') + if name == 'm3u8': + formats = self._extract_m3u8_formats( + output_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + else: + f = { + 'format_id': name, + 'tbr': int_or_none(output.get('bitrate')), + 'url': output_url, + } + if name in ('m4a', 'mp3'): + f['vcodec'] = 'none' + else: + f.update({ + 'height': int_or_none(output.get('height')), + 'width': int_or_none(output.get('width')), + }) + formats.append(f) + text_tracks = body.get('subtitles') or [] + else: + m3u8_url = self._search_regex( + r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', + body, 'm3u8 url', group='url') + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls') + text_tracks = self._search_regex( + r'textTracks\s*:\s*(\[[^]]+\])', + body, 'text tracks', default=None) + if text_tracks: + text_tracks = self._parse_json( + text_tracks, video_id, js_to_json, False) self._sort_formats(formats) - thumbnail = self._search_regex( - r'poster\s*[:=]\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'thumbnail', - default=False, group='url') + subtitles = {} + if text_tracks: + for text_track in text_tracks: + tt_url = dict_get(text_track, ('file', 'src')) + if not tt_url: + continue + subtitles.setdefault(text_track.get('label') or 'English', []).append({ + 'url': tt_url, + }) + + thumbnails = [] + for thumbnail in video.get('thumbnails', []): + thumbnail_url = thumbnail.get('url') + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int_or_none(thumbnail.get('width')), + 'height': int_or_none(thumbnail.get('height')), + }) return { 'id': video_id, + 'display_id': video.get('friendly_title'), 'title': title, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, + 'description': dict_get(video, ('description', 'ott_description', 'short_description')), + 'timestamp': parse_iso8601(video.get('published_at')), + 'duration': int_or_none(video.get('duration')), + 'view_count': int_or_none(video.get('request_count')), + 'average_rating': int_or_none(video.get('rating')), + 'season_number': int_or_none(video.get('season')), + 'episode_number': int_or_none(video.get('episode')), 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 1ffabc62b..8826b382c 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -134,7 +134,7 @@ def parseOpts(overrideArguments=None): action='help', help='Print this help text and exit') general.add_option( - '-v', '--version', + '--version', action='version', help='Print program version and exit') general.add_option( diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 002ea7f33..84c964617 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -9,6 +9,7 @@ import subprocess import sys from zipimport import zipimporter +from .compat import compat_realpath from .utils import encode_compat_str from .version import __version__ @@ -84,7 +85,9 @@ def update_self(to_screen, verbose, opener): print_notes(to_screen, versions_info['versions']) # sys.executable is set to the full pathname of the exe-file for py2exe - filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0] + # though symlinks are not followed so that we need to do this manually + # with help of realpath + filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0]) if not os.access(filename, os.W_OK): to_screen('ERROR: no write permissions on %s' % filename) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index f6204692a..8ccf25489 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2795,6 +2795,15 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): https_response = http_response +class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler): + if sys.version_info[0] < 3: + def redirect_request(self, req, fp, code, msg, headers, newurl): + # On python 2 urlh.geturl() may sometimes return redirect URL + # as byte string instead of unicode. This workaround allows + # to force it always return unicode. + return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl)) + + def extract_timezone(date_str): m = re.search( r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)', diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 8ad2df674..fabc1e543 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.01.01' +__version__ = '2020.03.01'