diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index ce0319fe2..e2cbaee1c 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 **2020.09.20** +- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1** - [ ] 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 2020.09.20 + [debug] youtube-dl version 2020.11.21.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index a4002603c..e531e89c0 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 **2020.09.20** +- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1** - [ ] 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 3f8b6ce2e..686878c56 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 **2020.09.20** +- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1** - [ ] 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 d880c225a..17b853716 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 **2020.09.20** +- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1** - [ ] 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 2020.09.20 + [debug] youtube-dl version 2020.11.21.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index dd5fb5144..109c47925 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 **2020.09.20** +- [ ] I've verified that I'm running youtube-dl version **2020.11.21.1** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 9b52b7bd2..5a08b3a66 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,118 @@ +version 2020.11.21.1 + +Core +* [downloader/http] Fix crash during urlopen caused by missing reason + of URLError +* [YoutubeDL] Fix --ignore-errors for playlists with generator-based entries + of url_transparent (#27064) + +Extractors ++ [svtplay] Add support for svt.se/barnkanalen (#24817) ++ [svt] Extract timestamp (#27130) +* [svtplay] Improve thumbnail extraction (#27130) +* [youtube] Fix error reason extraction (#27081) +* [youtube] Fix like and dislike count extraction (#25977) ++ [youtube:tab] Add support for current video and fix lives extraction (#27126) +* [infoq] Fix format extraction (#25984) +* [francetv] Update to fix thumbnail URL issue (#27120) +* [youtube] Improve yt initial data extraction (#27093) ++ [discoverynetworks] Add support new TLC/DMAX URLs (#27100) +* [rai] Fix protocol relative relinker URLs (#22766) +* [rai] Fix unavailable video format detection +* [rai] Improve extraction +* [rai] Fix extraction (#27077) +* [viki] Improve format extraction +* [viki] Fix stream extraction from MPD (#27092) +* [googledrive] Fix format extraction (#26979) ++ [amara] Add support for amara.org (#20618) +* [vimeo:album] Fix extraction (#27079) +* [mtv] Fix mgid extraction (#26841) + + +version 2020.11.19 + +Core +* [extractor/common] Output error for invalid URLs in _is_valid_url (#21400, + #24151, #25617, #25618, #25586, #26068, #27072) + +Extractors +* [youporn] Fix upload date extraction +* [youporn] Make comment count optional (#26986) +* [arte] Rework extractors + * Reimplement embed and playlist extractors to delegate to the single + entrypoint artetv extractor + * Improve embeds detection (#27057) ++ [arte] Extract m3u8 formats (#27061) +* [mgtv] Fix format extraction (#26415) ++ [lbry] Add support for odysee.com (#26806) +* [francetv] Improve info extraction ++ [francetv] Add fallback video URL extraction (#27047) + + +version 2020.11.18 + +Extractors +* [spiegel] Fix extraction (#24206, #24767) +* [youtube] Improve extraction + + Add support for --no-playlist (#27009) + * Improve playlist and mix extraction (#26390, #26509, #26534, #27011) + + Extract playlist uploader data +* [youtube:tab] Fix view count extraction (#27051) +* [malltv] Fix extraction (#27035) ++ [bandcamp] Extract playlist description (#22684) +* [urplay] Fix extraction (#26828) +* [youtube:tab] Fix playlist title extraction (#27015) +* [youtube] Fix chapters extraction (#26005) + + +version 2020.11.17 + +Core +* [utils] Skip ! prefixed code in js_to_json + +Extractors +* [youtube:tab] Fix extraction with cookies provided (#27005) +* [lrt] Fix extraction with empty tags (#20264) ++ [ndr:embed:base] Extract subtitles (#25447, #26106) ++ [servus] Add support for pm-wissen.com (#25869) +* [servus] Fix extraction (#26872, #26967, #26983, #27000) +* [xtube] Fix extraction (#26996) +* [lrt] Fix extraction ++ [lbry] Add support for lbry.tv ++ [condenast] Extract subtitles +* [condenast] Fix extraction +* [bandcamp] Fix extraction (#26681, #26684) +* [rai] Fix RaiPlay extraction (#26064, #26096) +* [vlive] Fix extraction +* [usanetwork] Fix extraction +* [nbc] Fix NBCNews/Today/MSNBC extraction +* [cnbc] Fix extraction + + +version 2020.11.12 + +Extractors +* [youtube] Rework extractors + + +version 2020.11.01 + +Core +* [utils] Don't attempt to coerce JS strings to numbers in js_to_json (#26851) +* [downloader/http] Properly handle missing message in SSLError (#26646) +* [downloader/http] Fix access to not yet opened stream in retry + +Extractors +* [youtube] Fix JS player URL extraction +* [ytsearch] Fix extraction (#26920) +* [afreecatv] Fix typo (#26970) +* [23video] Relax URL regular expression (#26870) ++ [ustream] Add support for video.ibm.com (#26894) +* [iqiyi] Fix typo (#26884) ++ [expressen] Add support for di.se (#26670) +* [iprima] Improve video id extraction (#26507, #26494) + + version 2020.09.20 Core @@ -283,7 +398,7 @@ Extractors + Add support for more domains * [svt] Fix series extraction (#22297) * [svt] Fix article extraction (#22897, #22919) -* [soundcloud] Imporve private playlist/set tracks extraction (#3707) +* [soundcloud] Improve private playlist/set tracks extraction (#3707) version 2020.01.24 @@ -409,7 +524,7 @@ Extractors * [abcotvs] Relax URL regular expression and improve metadata extraction (#18014) * [channel9] Reduce response size -* [adobetv] Improve extaction +* [adobetv] Improve extraction * Use OnDemandPagedList for list extractors * Reduce show extraction requests * Extract original video format and subtitles @@ -434,7 +549,7 @@ Extractors * [dailymotion] Improve extraction * Extract http formats included in m3u8 manifest * Fix user extraction (#3553, #21415) - + Add suport for User Authentication (#11491) + + Add support for User Authentication (#11491) * Fix password protected videos extraction (#23176) * Respect age limit option and family filter cookie value (#18437) * Handle video url playlist query param @@ -519,7 +634,7 @@ Extractors - [go90] Remove extractor * [kakao] Remove raw request + [kakao] Extract format total bitrate -* [daum] Fix VOD and Clip extracton (#15015) +* [daum] Fix VOD and Clip extraction (#15015) * [kakao] Improve extraction + Add support for embed URLs + Add support for Kakao Legacy vid based embed URLs @@ -563,7 +678,7 @@ Extractors * Improve format extraction (#22123) + Extract uploader_id and uploader_url (#21916) + Extract all known thumbnails (#19071, #20659) - * Fix extration for private playlists (#20976) + * Fix extraction for private playlists (#20976) + Add support for playlist embeds (#20976) * Skip preview formats (#22806) * [dplay] Improve extraction @@ -1038,7 +1153,7 @@ Extractors * [hbo] Fix extraction and extract subtitles (#14629, #13709) * [youtube] Extract srv[1-3] subtitle formats (#20566) * [adultswim] Fix extraction (#18025) -* [teamcoco] Fix extraction and add suport for subdomains (#17099, #20339) +* [teamcoco] Fix extraction and add support for subdomains (#17099, #20339) * [adn] Fix subtitle compatibility with ffmpeg * [adn] Fix extraction and add support for positioning styles (#20549) * [vk] Use unique video id (#17848) @@ -1450,7 +1565,7 @@ version 2018.11.18 Extractors + [wwe] Extract subtitles -+ [wwe] Add support for playlistst (#14781) ++ [wwe] Add support for playlists (#14781) + [wwe] Add support for wwe.com (#14781, #17450) * [vk] Detect geo restriction (#17767) * [openload] Use original host during extraction (#18211) @@ -2483,7 +2598,7 @@ Extractors * [youku] Update ccode (#14872) * [mnet] Fix format extraction (#14883) + [xiami] Add Referer header to API request -* [mtv] Correct scc extention in extracted subtitles (#13730) +* [mtv] Correct scc extension in extracted subtitles (#13730) * [vvvvid] Fix extraction for kenc videos (#13406) + [br] Add support for BR Mediathek videos (#14560, #14788) + [daisuki] Add support for motto.daisuki.com (#14681) @@ -2504,7 +2619,7 @@ Extractors * [nexx] Extract more formats + [openload] Add support for openload.link (#14763) * [empflix] Relax URL regular expression -* [empflix] Fix extractrion +* [empflix] Fix extraction * [tnaflix] Don't modify download URLs (#14811) - [gamersyde] Remove extractor * [francetv:generationwhat] Fix extraction @@ -2699,7 +2814,7 @@ Extractors * [yahoo] Bypass geo restriction for brightcove (#14210) * [yahoo] Use extracted brightcove account id (#14210) * [rtve:alacarta] Fix extraction (#14290) -+ [yahoo] Add support for custom brigthcove embeds (#14210) ++ [yahoo] Add support for custom brightcove embeds (#14210) + [generic] Add support for Video.js embeds + [gfycat] Add support for /gifs/detail URLs (#14322) * [generic] Fix infinite recursion for twitter:player URLs (#14339) @@ -2944,7 +3059,7 @@ Extractors * [amcnetworks] Make rating optional (#12453) * [cloudy] Fix extraction (#13737) + [nickru] Add support for nickelodeon.ru -* [mtv] Improve thumbnal extraction +* [mtv] Improve thumbnail extraction * [nick] Automate geo-restriction bypass (#13711) * [niconico] Improve error reporting (#13696) @@ -3308,7 +3423,7 @@ Extractors + [cda] Support birthday verification (#12789) * [leeco] Fix extraction (#12974) + [pbs] Extract chapters -* [amp] Imporove thumbnail and subtitles extraction +* [amp] Improve thumbnail and subtitles extraction * [foxsports] Fix extraction (#12945) - [coub] Remove comment count extraction (#12941) @@ -3478,7 +3593,7 @@ Extractors + [rbmaradio] Add support for redbullradio.com URLs (#12687) + [npo:live] Add support for default URL (#12555) * [mixcloud:playlist] Fix title, description and view count extraction (#12582) -+ [thesun] Add suport for thesun.co.uk (#11298, #12674) ++ [thesun] Add support for thesun.co.uk (#11298, #12674) + [ceskateleveize:porady] Add support for porady (#7411, #12645) * [ceskateleveize] Improve extraction and remove URL replacement hacks + [kaltura] Add support for iframe embeds (#12679) @@ -3517,7 +3632,7 @@ Extractors * [funimation] Fix extraction (#10696, #11773) + [xfileshare] Add support for vidabc.com (#12589) + [xfileshare] Improve extraction and extract hls formats -+ [crunchyroll] Pass geo verifcation proxy ++ [crunchyroll] Pass geo verification proxy + [cwtv] Extract ISM formats + [tvplay] Bypass geo restriction + [vrv] Add support for vrv.co @@ -3581,7 +3696,7 @@ Extractors + [bostonglobe] Add extractor for bostonglobe.com (#12099) + [toongoggles] Add support for toongoggles.com (#12171) + [medialaan] Add support for Medialaan sites (#9974, #11912) -+ [discoverynetworks] Add support for more domains and bypass geo restiction ++ [discoverynetworks] Add support for more domains and bypass geo restriction * [openload] Fix extraction (#10408) @@ -5171,7 +5286,7 @@ version 2016.07.09.1 Fixed/improved extractors - youtube - ard -- srmediatek (#9373) +- srmediathek (#9373) version 2016.07.09 @@ -5235,7 +5350,7 @@ Fixed/improved extractors - kaltura (#5557) - la7 - Changed features -- Rename --cn-verfication-proxy to --geo-verification-proxy +- Rename --cn-verification-proxy to --geo-verification-proxy Miscellaneous - Add script for displaying downloads statistics diff --git a/devscripts/make_lazy_extractors.py b/devscripts/make_lazy_extractors.py index 0a1762dbc..878ae72b1 100644 --- a/devscripts/make_lazy_extractors.py +++ b/devscripts/make_lazy_extractors.py @@ -61,7 +61,7 @@ def build_lazy_ie(ie, name): return s -# find the correct sorting and add the required base classes so that sublcasses +# find the correct sorting and add the required base classes so that subclasses # can be correctly created classes = _ALL_CLASSES[:-1] ordered_cls = [] diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 367545a96..53dbc28e5 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -41,6 +41,7 @@ - **AlJazeera** - **Allocine** - **AlphaPorno** + - **Amara** - **AMCNetworks** - **AmericasTestKitchen** - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl @@ -58,9 +59,9 @@ - **ARD:mediathek** - **ARDBetaMediathek** - **Arkena** - - **arte.tv:+7** - - **arte.tv:embed** - - **arte.tv:playlist** + - **ArteTV** + - **ArteTVEmbed** + - **ArteTVPlaylist** - **AsianCrush** - **AsianCrushPlaylist** - **AtresPlayer** @@ -417,6 +418,7 @@ - **la7.it** - **laola1tv** - **laola1tv:embed** + - **lbry.tv** - **LCI** - **Lcp** - **LcpPlay** @@ -823,8 +825,6 @@ - **SpankBangPlaylist** - **Spankwire** - **Spiegel** - - **Spiegel:Article**: Articles on spiegel.de - - **Spiegeltv** - **sport.francetvinfo.fr** - **Sport5** - **SportBox** @@ -1042,7 +1042,6 @@ - **vk:wallpost** - **vlive** - **vlive:channel** - - **vlive:playlist** - **Vodlocker** - **VODPl** - **VODPlatform** @@ -1131,20 +1130,15 @@ - **YourPorn** - **YourUpload** - **youtube**: YouTube.com - - **youtube:channel**: YouTube.com channels - - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication) - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication) - - **youtube:live**: YouTube.com live streams - **youtube:playlist**: YouTube.com playlists - - **youtube:playlists**: YouTube.com user/channel playlists - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication) - **youtube:search**: YouTube.com searches - **youtube:search:date**: YouTube.com searches, newest videos first - - **youtube:search_url**: YouTube.com search URLs - - **youtube:show**: YouTube.com (multi-season) shows - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication) - - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword) + - **youtube:tab**: YouTube.com tab - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication) + - **YoutubeYtUser** - **Zapiks** - **Zaq1** - **Zattoo** diff --git a/test/parameters.json b/test/parameters.json index 7bf59c25f..65fd54428 100644 --- a/test/parameters.json +++ b/test/parameters.json @@ -37,7 +37,7 @@ "writeinfojson": true, "writesubtitles": false, "allsubtitles": false, - "listssubtitles": false, + "listsubtitles": false, "socket_timeout": 20, "fixup": "never" } diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 1e204e551..62f916d11 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -919,6 +919,76 @@ class TestYoutubeDL(unittest.TestCase): self.assertEqual(downloaded['extractor'], 'testex') self.assertEqual(downloaded['extractor_key'], 'TestEx') + # Test case for https://github.com/ytdl-org/youtube-dl/issues/27064 + def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self): + + class _YDL(YDL): + def __init__(self, *args, **kwargs): + super(_YDL, self).__init__(*args, **kwargs) + + def trouble(self, s, tb=None): + pass + + ydl = _YDL({ + 'format': 'extra', + 'ignoreerrors': True, + }) + + class VideoIE(InfoExtractor): + _VALID_URL = r'video:(?P\d+)' + + def _real_extract(self, url): + video_id = self._match_id(url) + formats = [{ + 'format_id': 'default', + 'url': 'url:', + }] + if video_id == '0': + raise ExtractorError('foo') + if video_id == '2': + formats.append({ + 'format_id': 'extra', + 'url': TEST_URL, + }) + return { + 'id': video_id, + 'title': 'Video %s' % video_id, + 'formats': formats, + } + + class PlaylistIE(InfoExtractor): + _VALID_URL = r'playlist:' + + def _entries(self): + for n in range(3): + video_id = compat_str(n) + yield { + '_type': 'url_transparent', + 'ie_key': VideoIE.ie_key(), + 'id': video_id, + 'url': 'video:%s' % video_id, + 'title': 'Video Transparent %s' % video_id, + } + + def _real_extract(self, url): + return self.playlist_result(self._entries()) + + ydl.add_info_extractor(VideoIE(ydl)) + ydl.add_info_extractor(PlaylistIE(ydl)) + info = ydl.extract_info('playlist:') + entries = info['entries'] + self.assertEqual(len(entries), 3) + self.assertTrue(entries[0] is None) + self.assertTrue(entries[1] is None) + self.assertEqual(len(ydl.downloaded_info_dicts), 1) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(entries[2], downloaded) + self.assertEqual(downloaded['url'], TEST_URL) + self.assertEqual(downloaded['title'], 'Video Transparent 2') + self.assertEqual(downloaded['id'], '2') + self.assertEqual(downloaded['extractor'], 'Video') + self.assertEqual(downloaded['extractor_key'], 'Video') + if __name__ == '__main__': unittest.main() diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 81056a999..56a08bed8 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -31,16 +31,17 @@ class TestAllURLsMatching(unittest.TestCase): def test_youtube_playlist_matching(self): assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist']) + assertTab = lambda url: self.assertMatch(url, ['youtube:tab']) assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585 assertPlaylist('PL63F0C78739B09958') - assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') + assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') - assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') - assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668 + assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') + assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668 self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M')) # Top tracks - assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101') + assertTab('https://www.youtube.com/playlist?list=MCUS.20142101') def test_youtube_matching(self): self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M')) @@ -51,26 +52,22 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube']) def test_youtube_channel_matching(self): - assertChannel = lambda url: self.assertMatch(url, ['youtube:channel']) + assertChannel = lambda url: self.assertMatch(url, ['youtube:tab']) assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM') assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec') assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos') - def test_youtube_user_matching(self): - self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user']) + # def test_youtube_user_matching(self): + # self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab']) def test_youtube_feeds(self): self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater']) self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions']) self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended']) - self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites']) - def test_youtube_show_matching(self): - self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show']) - - def test_youtube_search_matching(self): - self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url']) - self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url']) + # def test_youtube_search_matching(self): + # self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url']) + # self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url']) def test_youtube_extract(self): assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id) diff --git a/test/test_utils.py b/test/test_utils.py index c2d1e4fb1..925a21d34 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -937,6 +937,28 @@ class TestUtil(unittest.TestCase): self.assertEqual(d['x'], 1) self.assertEqual(d['y'], 'a') + # Just drop ! prefix for now though this results in a wrong value + on = js_to_json('''{ + a: !0, + b: !1, + c: !!0, + d: !!42.42, + e: !!![], + f: !"abc", + g: !"", + !42: 42 + }''') + self.assertEqual(json.loads(on), { + 'a': 0, + 'b': 1, + 'c': 0, + 'd': 42.42, + 'e': [], + 'f': "abc", + 'g': "", + '42': 42 + }) + on = js_to_json('["abc", "def",]') self.assertEqual(json.loads(on), ['abc', 'def']) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 19370f62b..855a73157 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -793,21 +793,14 @@ class YoutubeDL(object): self.report_warning('The program functionality for this site has been marked as broken, ' 'and will probably not work.') + return self.__extract_info(url, ie, download, extra_info, process) + else: + self.report_error('no suitable InfoExtractor for URL %s' % url) + + def __handle_extraction_exceptions(func): + def wrapper(self, *args, **kwargs): try: - ie_result = ie.extract(url) - if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) - break - if isinstance(ie_result, list): - # Backwards compatibility: old IE result format - ie_result = { - '_type': 'compat_list', - 'entries': ie_result, - } - self.add_default_extra_info(ie_result, ie, url) - if process: - return self.process_ie_result(ie_result, download, extra_info) - else: - return ie_result + return func(self, *args, **kwargs) except GeoRestrictedError as e: msg = e.msg if e.countries: @@ -815,20 +808,33 @@ class YoutubeDL(object): map(ISO3166Utils.short2full, e.countries)) msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.' self.report_error(msg) - break except ExtractorError as e: # An error we somewhat expected self.report_error(compat_str(e), e.format_traceback()) - break except MaxDownloadsReached: raise except Exception as e: if self.params.get('ignoreerrors', False): self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc())) - break else: raise + return wrapper + + @__handle_extraction_exceptions + def __extract_info(self, url, ie, download, extra_info, process): + ie_result = ie.extract(url) + if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) + return + if isinstance(ie_result, list): + # Backwards compatibility: old IE result format + ie_result = { + '_type': 'compat_list', + 'entries': ie_result, + } + self.add_default_extra_info(ie_result, ie, url) + if process: + return self.process_ie_result(ie_result, download, extra_info) else: - self.report_error('no suitable InfoExtractor for URL %s' % url) + return ie_result def add_default_extra_info(self, ie_result, ie, url): self.add_extra_info(ie_result, { @@ -1003,9 +1009,8 @@ class YoutubeDL(object): self.to_screen('[download] ' + reason) continue - entry_result = self.process_ie_result(entry, - download=download, - extra_info=extra) + entry_result = self.__process_iterable_entry(entry, download, extra) + # TODO: skip failed (empty) entries? playlist_results.append(entry_result) ie_result['entries'] = playlist_results self.to_screen('[download] Finished downloading playlist: %s' % playlist) @@ -1034,6 +1039,11 @@ class YoutubeDL(object): else: raise Exception('Invalid result type: %s' % result_type) + @__handle_extraction_exceptions + def __process_iterable_entry(self, entry, download, extra_info): + return self.process_ie_result( + entry, download=download, extra_info=extra_info) + def _build_format_filter(self, filter_spec): " Returns a function to filter the formats according to the filter_spec " diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 0ee9bc760..6c3d49d45 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2345,7 +2345,7 @@ except ImportError: # Python <3.4 # HTMLParseError has been deprecated in Python 3.3 and removed in # Python 3.5. Introducing dummy exception for Python >3.5 for compatible - # and uniform cross-version exceptiong handling + # and uniform cross-version exception handling class compat_HTMLParseError(Exception): pass diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 96379caf1..d8ac41dcc 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -109,7 +109,9 @@ class HttpFD(FileDownloader): try: ctx.data = self.ydl.urlopen(request) except (compat_urllib_error.URLError, ) as err: - if isinstance(err.reason, socket.timeout): + # reason may not be available, e.g. for urllib2.HTTPError on python 2.6 + reason = getattr(err, 'reason', None) + if isinstance(reason, socket.timeout): raise RetryDownload(err) raise err # When trying to resume, Content-Range HTTP header of response has to be checked diff --git a/youtube_dl/extractor/amara.py b/youtube_dl/extractor/amara.py new file mode 100644 index 000000000..61d469574 --- /dev/null +++ b/youtube_dl/extractor/amara.py @@ -0,0 +1,103 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .youtube import YoutubeIE +from .vimeo import VimeoIE +from ..utils import ( + int_or_none, + parse_iso8601, + update_url_query, +) + + +class AmaraIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?amara\.org/(?:\w+/)?videos/(?P\w+)' + _TESTS = [{ + # Youtube + 'url': 'https://amara.org/en/videos/jVx79ZKGK1ky/info/why-jury-trials-are-becoming-less-common/?tab=video', + 'md5': 'ea10daf2b6154b8c1ecf9922aca5e8ae', + 'info_dict': { + 'id': 'h6ZuVdvYnfE', + 'ext': 'mp4', + 'title': 'Why jury trials are becoming less common', + 'description': 'md5:a61811c319943960b6ab1c23e0cbc2c1', + 'thumbnail': r're:^https?://.*\.jpg$', + 'subtitles': dict, + 'upload_date': '20160813', + 'uploader': 'PBS NewsHour', + 'uploader_id': 'PBSNewsHour', + 'timestamp': 1549639570, + } + }, { + # Vimeo + 'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011', + 'md5': '99392c75fa05d432a8f11df03612195e', + 'info_dict': { + 'id': '18622084', + 'ext': 'mov', + 'title': 'Vimeo at CES 2011!', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'subtitles': dict, + 'timestamp': 1294763658, + 'upload_date': '20110111', + 'uploader': 'Sam Morrill', + 'uploader_id': 'sammorrill' + } + }, { + # Direct Link + 'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/', + 'md5': 'd3970f08512738ee60c5807311ff5d3f', + 'info_dict': { + 'id': 's8KL7I3jLmh6', + 'ext': 'mp4', + 'title': 'The danger of a single story', + 'description': 'md5:d769b31139c3b8bb5be9177f62ea3f23', + 'thumbnail': r're:^https?://.*\.jpg$', + 'subtitles': dict, + 'upload_date': '20091007', + 'timestamp': 1254942511, + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + meta = self._download_json( + 'https://amara.org/api/videos/%s/' % video_id, + video_id, query={'format': 'json'}) + title = meta['title'] + video_url = meta['all_urls'][0] + + subtitles = {} + for language in (meta.get('languages') or []): + subtitles_uri = language.get('subtitles_uri') + if not (subtitles_uri and language.get('published')): + continue + subtitle = subtitles.setdefault(language.get('code') or 'en', []) + for f in ('json', 'srt', 'vtt'): + subtitle.append({ + 'ext': f, + 'url': update_url_query(subtitles_uri, {'format': f}), + }) + + info = { + 'url': video_url, + 'id': video_id, + 'subtitles': subtitles, + 'title': title, + 'description': meta.get('description'), + 'thumbnail': meta.get('thumbnail'), + 'duration': int_or_none(meta.get('duration')), + 'timestamp': parse_iso8601(meta.get('created')), + } + + for ie in (YoutubeIE, VimeoIE): + if ie.suitable(video_url): + info.update({ + '_type': 'url_transparent', + 'ie_key': ie.ie_key(), + }) + break + + return info diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 2bd3bfe8a..03abdbfaf 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -4,23 +4,57 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_str, + compat_urlparse, +) from ..utils import ( ExtractorError, int_or_none, qualities, try_get, unified_strdate, + url_or_none, ) -# There are different sources of video in arte.tv, the extraction process -# is different for each one. The videos usually expire in 7 days, so we can't -# add tests. - class ArteTVBaseIE(InfoExtractor): - def _extract_from_json_url(self, json_url, video_id, lang, title=None): - info = self._download_json(json_url, video_id) + _ARTE_LANGUAGES = 'fr|de|en|es|it|pl' + _API_BASE = 'https://api.arte.tv/api/player/v1' + + +class ArteTVIE(ArteTVBaseIE): + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?arte\.tv/(?P%(langs)s)/videos| + api\.arte\.tv/api/player/v\d+/config/(?P%(langs)s) + ) + /(?P\d{6}-\d{3}-[AF]) + ''' % {'langs': ArteTVBaseIE._ARTE_LANGUAGES} + _TESTS = [{ + 'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/', + 'info_dict': { + 'id': '088501-000-A', + 'ext': 'mp4', + 'title': 'Mexico: Stealing Petrol to Survive', + 'upload_date': '20190628', + }, + }, { + 'url': 'https://www.arte.tv/pl/videos/100103-000-A/usa-dyskryminacja-na-porodowce/', + 'only_matching': True, + }, { + 'url': 'https://api.arte.tv/api/player/v2/config/de/100605-013-A', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + lang = mobj.group('lang') or mobj.group('lang_2') + + info = self._download_json( + '%s/config/%s/%s' % (self._API_BASE, lang, video_id), video_id) player_info = info['videoJsonPlayer'] vsr = try_get(player_info, lambda x: x['VSR'], dict) @@ -37,18 +71,11 @@ class ArteTVBaseIE(InfoExtractor): if not upload_date_str: upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0] - title = (player_info.get('VTI') or title or player_info['VID']).strip() + title = (player_info.get('VTI') or player_info['VID']).strip() subtitle = player_info.get('VSU', '').strip() if subtitle: title += ' - %s' % subtitle - info_dict = { - 'id': player_info['VID'], - 'title': title, - 'description': player_info.get('VDE'), - 'upload_date': unified_strdate(upload_date_str), - 'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'), - } qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ']) LANGS = { @@ -65,6 +92,10 @@ class ArteTVBaseIE(InfoExtractor): formats = [] for format_id, format_dict in vsr.items(): f = dict(format_dict) + format_url = url_or_none(f.get('url')) + streamer = f.get('streamer') + if not format_url and not streamer: + continue versionCode = f.get('versionCode') l = re.escape(langcode) @@ -107,6 +138,16 @@ class ArteTVBaseIE(InfoExtractor): else: lang_pref = -1 + media_type = f.get('mediaType') + if media_type == 'hls': + m3u8_formats = self._extract_m3u8_formats( + format_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id=format_id, fatal=False) + for m3u8_format in m3u8_formats: + m3u8_format['language_preference'] = lang_pref + formats.extend(m3u8_formats) + continue + format = { 'format_id': format_id, 'preference': -10 if f.get('videoFormat') == 'M3U8' else None, @@ -118,7 +159,7 @@ class ArteTVBaseIE(InfoExtractor): 'quality': qfunc(f.get('quality')), } - if f.get('mediaType') == 'rtmp': + if media_type == 'rtmp': format['url'] = f['streamer'] format['play_path'] = 'mp4:' + f['url'] format['ext'] = 'flv' @@ -127,56 +168,50 @@ class ArteTVBaseIE(InfoExtractor): formats.append(format) - self._check_formats(formats, video_id) self._sort_formats(formats) - info_dict['formats'] = formats - return info_dict + return { + 'id': player_info.get('VID') or video_id, + 'title': title, + 'description': player_info.get('VDE'), + 'upload_date': unified_strdate(upload_date_str), + 'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'), + 'formats': formats, + } -class ArteTVPlus7IE(ArteTVBaseIE): - IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?Pfr|de|en|es|it|pl)/videos/(?P\d{6}-\d{3}-[AF])' - +class ArteTVEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+' _TESTS = [{ - 'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/', + 'url': 'https://www.arte.tv/player/v5/index.php?json_url=https%3A%2F%2Fapi.arte.tv%2Fapi%2Fplayer%2Fv2%2Fconfig%2Fde%2F100605-013-A&lang=de&autoplay=true&mute=0100605-013-A', 'info_dict': { - 'id': '088501-000-A', + 'id': '100605-013-A', 'ext': 'mp4', - 'title': 'Mexico: Stealing Petrol to Survive', - 'upload_date': '20190628', + 'title': 'United we Stream November Lockdown Edition #13', + 'description': 'md5:be40b667f45189632b78c1425c7c2ce1', + 'upload_date': '20201116', }, + }, { + 'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A', + 'only_matching': True, }] - def _real_extract(self, url): - lang, video_id = re.match(self._VALID_URL, url).groups() - return self._extract_from_json_url( - 'https://api.arte.tv/api/player/v1/config/%s/%s' % (lang, video_id), - video_id, lang) - - -class ArteTVEmbedIE(ArteTVPlus7IE): - IE_NAME = 'arte.tv:embed' - _VALID_URL = r'''(?x) - https://www\.arte\.tv - /player/v3/index\.php\?json_url= - (?P - https?://api\.arte\.tv/api/player/v1/config/ - (?P[^/]+)/(?P\d{6}-\d{3}-[AF]) - ) - ''' - - _TESTS = [] + @staticmethod + def _extract_urls(webpage): + return [url for _, url in re.findall( + r'<(?:iframe|script)[^>]+src=(["\'])(?P(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1', + webpage)] def _real_extract(self, url): - json_url, lang, video_id = re.match(self._VALID_URL, url).groups() - return self._extract_from_json_url(json_url, video_id, lang) + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + json_url = qs['json_url'][0] + video_id = ArteTVIE._match_id(json_url) + return self.url_result( + json_url, ie=ArteTVIE.ie_key(), video_id=video_id) class ArteTVPlaylistIE(ArteTVBaseIE): - IE_NAME = 'arte.tv:playlist' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?Pfr|de|en|es|it|pl)/videos/(?PRC-\d{6})' - + _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P%s)/videos/(?PRC-\d{6})' % ArteTVBaseIE._ARTE_LANGUAGES _TESTS = [{ 'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/', 'info_dict': { @@ -185,17 +220,35 @@ class ArteTVPlaylistIE(ArteTVBaseIE): 'description': 'md5:d322c55011514b3a7241f7fb80d494c2', }, 'playlist_mincount': 6, + }, { + 'url': 'https://www.arte.tv/pl/videos/RC-014123/arte-reportage/', + 'only_matching': True, }] def _real_extract(self, url): lang, playlist_id = re.match(self._VALID_URL, url).groups() collection = self._download_json( - 'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos' - % (lang, playlist_id), playlist_id) + '%s/collectionData/%s/%s?source=videos' + % (self._API_BASE, lang, playlist_id), playlist_id) + entries = [] + for video in collection['videos']: + if not isinstance(video, dict): + continue + video_url = url_or_none(video.get('url')) or url_or_none(video.get('jsonUrl')) + if not video_url: + continue + video_id = video.get('programId') + entries.append({ + '_type': 'url_transparent', + 'url': video_url, + 'id': video_id, + 'title': video.get('title'), + 'alt_title': video.get('subtitle'), + 'thumbnail': url_or_none(try_get(video, lambda x: x['mainImage']['url'], compat_str)), + 'duration': int_or_none(video.get('durationSeconds')), + 'view_count': int_or_none(video.get('views')), + 'ie_key': ArteTVIE.ie_key(), + }) title = collection.get('title') description = collection.get('shortDescription') or collection.get('teaserText') - entries = [ - self._extract_from_json_url( - video['jsonUrl'], video.get('programId') or playlist_id, lang) - for video in collection['videos'] if video.get('jsonUrl')] return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index f14b407dc..69e673a26 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import random @@ -5,10 +6,7 @@ import re import time from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_urlparse, -) +from ..compat import compat_str from ..utils import ( ExtractorError, float_or_none, @@ -17,30 +15,32 @@ from ..utils import ( parse_filesize, str_or_none, try_get, - unescapeHTML, update_url_query, unified_strdate, unified_timestamp, url_or_none, + urljoin, ) class BandcampIE(InfoExtractor): - _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P[^/?#&]+)' + _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', 'md5': 'c557841d5e50261777a6585648adf439', 'info_dict': { 'id': '1812978515', 'ext': 'mp3', - 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", + 'title': "youtube-dl \"'/\\ä↭ - youtube-dl \"'/\\ä↭ - youtube-dl test song \"'/\\ä↭", 'duration': 9.8485, + 'uploader': 'youtube-dl "\'/\\ä↭', + 'upload_date': '20121129', + 'timestamp': 1354224127, }, '_skip': 'There is a limit of 200 free downloads / month for the test song' }, { # free download 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', - 'md5': '853e35bf34aa1d6fe2615ae612564b36', 'info_dict': { 'id': '2650410135', 'ext': 'aiff', @@ -79,11 +79,16 @@ class BandcampIE(InfoExtractor): }, }] + def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True): + return self._parse_json(self._html_search_regex( + r'data-%s=(["\'])({.+?})\1' % attr, webpage, + attr + ' data', group=2), video_id, fatal=fatal) + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - title = mobj.group('title') + title = self._match_id(url) webpage = self._download_webpage(url, title) - thumbnail = self._html_search_meta('og:image', webpage, default=None) + tralbum = self._extract_data_attr(webpage, title) + thumbnail = self._og_search_thumbnail(webpage) track_id = None track = None @@ -91,10 +96,7 @@ class BandcampIE(InfoExtractor): duration = None formats = [] - track_info = self._parse_json( - self._search_regex( - r'trackinfo\s*:\s*\[\s*({.+?})\s*\]\s*,\s*?\n', - webpage, 'track info', default='{}'), title) + track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict) if track_info: file_ = track_info.get('file') if isinstance(file_, dict): @@ -111,37 +113,25 @@ class BandcampIE(InfoExtractor): 'abr': int_or_none(abr_str), }) track = track_info.get('title') - track_id = str_or_none(track_info.get('track_id') or track_info.get('id')) + track_id = str_or_none( + track_info.get('track_id') or track_info.get('id')) track_number = int_or_none(track_info.get('track_num')) duration = float_or_none(track_info.get('duration')) - def extract(key): - return self._search_regex( - r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key, - webpage, key, default=None, group='value') - - artist = extract('artist') - album = extract('album_title') + embed = self._extract_data_attr(webpage, title, 'embed', False) + current = tralbum.get('current') or {} + artist = embed.get('artist') or current.get('artist') or tralbum.get('artist') timestamp = unified_timestamp( - extract('publish_date') or extract('album_publish_date')) - release_date = unified_strdate(extract('album_release_date')) + current.get('publish_date') or tralbum.get('album_publish_date')) - download_link = self._search_regex( - r'freeDownloadPage\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, - 'download link', default=None, group='url') + download_link = tralbum.get('freeDownloadPage') if download_link: - track_id = self._search_regex( - r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$', - webpage, 'track id') + track_id = compat_str(tralbum['id']) download_webpage = self._download_webpage( download_link, track_id, 'Downloading free downloads page') - blob = self._parse_json( - self._search_regex( - r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage, - 'blob', group='blob'), - track_id, transform_source=unescapeHTML) + blob = self._extract_data_attr(download_webpage, track_id, 'blob') info = try_get( blob, (lambda x: x['digital_items'][0], @@ -207,20 +197,20 @@ class BandcampIE(InfoExtractor): 'thumbnail': thumbnail, 'uploader': artist, 'timestamp': timestamp, - 'release_date': release_date, + 'release_date': unified_strdate(tralbum.get('album_release_date')), 'duration': duration, 'track': track, 'track_number': track_number, 'track_id': track_id, 'artist': artist, - 'album': album, + 'album': embed.get('album_title'), 'formats': formats, } -class BandcampAlbumIE(InfoExtractor): +class BandcampAlbumIE(BandcampIE): IE_NAME = 'Bandcamp:album' - _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^/?#&]+))?' + _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<id>[^/?#&]+))?' _TESTS = [{ 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', @@ -230,7 +220,10 @@ class BandcampAlbumIE(InfoExtractor): 'info_dict': { 'id': '1353101989', 'ext': 'mp3', - 'title': 'Intro', + 'title': 'Blazo - Intro', + 'timestamp': 1311756226, + 'upload_date': '20110727', + 'uploader': 'Blazo', } }, { @@ -238,7 +231,10 @@ class BandcampAlbumIE(InfoExtractor): 'info_dict': { 'id': '38097443', 'ext': 'mp3', - 'title': 'Kero One - Keep It Alive (Blazo remix)', + 'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)', + 'timestamp': 1311757238, + 'upload_date': '20110727', + 'uploader': 'Blazo', } }, ], @@ -274,6 +270,7 @@ class BandcampAlbumIE(InfoExtractor): 'title': '"Entropy" EP', 'uploader_id': 'jstrecords', 'id': 'entropy-ep', + 'description': 'md5:0ff22959c943622972596062f2f366a5', }, 'playlist_mincount': 3, }, { @@ -283,6 +280,7 @@ class BandcampAlbumIE(InfoExtractor): 'id': 'we-are-the-plague', 'title': 'WE ARE THE PLAGUE', 'uploader_id': 'insulters', + 'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f', }, 'playlist_count': 2, }] @@ -294,41 +292,34 @@ class BandcampAlbumIE(InfoExtractor): else super(BandcampAlbumIE, cls).suitable(url)) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - uploader_id = mobj.group('subdomain') - album_id = mobj.group('album_id') + uploader_id, album_id = re.match(self._VALID_URL, url).groups() playlist_id = album_id or uploader_id webpage = self._download_webpage(url, playlist_id) - track_elements = re.findall( - r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage) - if not track_elements: + tralbum = self._extract_data_attr(webpage, playlist_id) + track_info = tralbum.get('trackinfo') + if not track_info: raise ExtractorError('The page doesn\'t contain any tracks') # Only tracks with duration info have songs entries = [ self.url_result( - compat_urlparse.urljoin(url, t_path), - ie=BandcampIE.ie_key(), - video_title=self._search_regex( - r'<span\b[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', - elem_content, 'track title', fatal=False)) - for elem_content, t_path in track_elements - if self._html_search_meta('duration', elem_content, default=None)] + urljoin(url, t['title_link']), BandcampIE.ie_key(), + str_or_none(t.get('track_id') or t.get('id')), t.get('title')) + for t in track_info + if t.get('duration')] + + current = tralbum.get('current') or {} - title = self._html_search_regex( - r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"', - webpage, 'title', fatal=False) - if title: - title = title.replace(r'\"', '"') return { '_type': 'playlist', 'uploader_id': uploader_id, 'id': playlist_id, - 'title': title, + 'title': current.get('title'), + 'description': current.get('about'), 'entries': entries, } -class BandcampWeeklyIE(InfoExtractor): +class BandcampWeeklyIE(BandcampIE): IE_NAME = 'Bandcamp:weekly' _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)' _TESTS = [{ @@ -343,29 +334,23 @@ class BandcampWeeklyIE(InfoExtractor): 'release_date': '20170404', 'series': 'Bandcamp Weekly', 'episode': 'Magic Moments', - 'episode_number': 208, 'episode_id': '224', - } + }, + 'params': { + 'format': 'opus-lo', + }, }, { 'url': 'https://bandcamp.com/?blah/blah@&show=228', 'only_matching': True }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + show_id = self._match_id(url) + webpage = self._download_webpage(url, show_id) - blob = self._parse_json( - self._search_regex( - r'data-blob=(["\'])(?P<blob>{.+?})\1', webpage, - 'blob', group='blob'), - video_id, transform_source=unescapeHTML) + blob = self._extract_data_attr(webpage, show_id, 'blob') - show = blob['bcw_show'] - - # This is desired because any invalid show id redirects to `bandcamp.com` - # which happens to expose the latest Bandcamp Weekly episode. - show_id = int_or_none(show.get('show_id')) or int_or_none(video_id) + show = blob['bcw_data'][show_id] formats = [] for format_id, format_url in show['audio_stream'].items(): @@ -390,20 +375,8 @@ class BandcampWeeklyIE(InfoExtractor): if subtitle: title += ' - %s' % subtitle - episode_number = None - seq = blob.get('bcw_seq') - - if seq and isinstance(seq, list): - try: - episode_number = next( - int_or_none(e.get('episode_number')) - for e in seq - if isinstance(e, dict) and int_or_none(e.get('id')) == show_id) - except StopIteration: - pass - return { - 'id': video_id, + 'id': show_id, 'title': title, 'description': show.get('desc') or show.get('short_desc'), 'duration': float_or_none(show.get('audio_duration')), @@ -411,7 +384,6 @@ class BandcampWeeklyIE(InfoExtractor): 'release_date': unified_strdate(show.get('published_date')), 'series': 'Bandcamp Weekly', 'episode': show.get('subtitle'), - 'episode_number': episode_number, - 'episode_id': compat_str(video_id), + 'episode_id': show_id, 'formats': formats } diff --git a/youtube_dl/extractor/box.py b/youtube_dl/extractor/box.py new file mode 100644 index 000000000..aae82d1af --- /dev/null +++ b/youtube_dl/extractor/box.py @@ -0,0 +1,98 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + parse_iso8601, + # try_get, + update_url_query, +) + + +class BoxIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/]+)/file/(?P<id>\d+)' + _TEST = { + 'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538', + 'md5': '1f81b2fd3960f38a40a3b8823e5fcd43', + 'info_dict': { + 'id': '510727257538', + 'ext': 'mp4', + 'title': 'Garber St. Louis will be 28th MLS team +scarving.mp4', + 'uploader': 'MLS Video', + 'timestamp': 1566320259, + 'upload_date': '20190820', + 'uploader_id': '235196876', + } + } + + def _real_extract(self, url): + shared_name, file_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, file_id) + request_token = self._parse_json(self._search_regex( + r'Box\.config\s*=\s*({.+?});', webpage, + 'Box config'), file_id)['requestToken'] + access_token = self._download_json( + 'https://app.box.com/app-api/enduserapp/elements/tokens', file_id, + 'Downloading token JSON metadata', + data=json.dumps({'fileIDs': [file_id]}).encode(), headers={ + 'Content-Type': 'application/json', + 'X-Request-Token': request_token, + 'X-Box-EndUser-API': 'sharedName=' + shared_name, + })[file_id]['read'] + shared_link = 'https://app.box.com/s/' + shared_name + f = self._download_json( + 'https://api.box.com/2.0/files/' + file_id, file_id, + 'Downloading file JSON metadata', headers={ + 'Authorization': 'Bearer ' + access_token, + 'BoxApi': 'shared_link=' + shared_link, + 'X-Rep-Hints': '[dash]', # TODO: extract `hls` formats + }, query={ + 'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size' + }) + title = f['name'] + + query = { + 'access_token': access_token, + 'shared_link': shared_link + } + + formats = [] + + # for entry in (try_get(f, lambda x: x['representations']['entries'], list) or []): + # entry_url_template = try_get( + # entry, lambda x: x['content']['url_template']) + # if not entry_url_template: + # continue + # representation = entry.get('representation') + # if representation == 'dash': + # TODO: append query to every fragment URL + # formats.extend(self._extract_mpd_formats( + # entry_url_template.replace('{+asset_path}', 'manifest.mpd'), + # file_id, query=query)) + + authenticated_download_url = f.get('authenticated_download_url') + if authenticated_download_url and f.get('is_download_available'): + formats.append({ + 'ext': f.get('extension') or determine_ext(title), + 'filesize': f.get('size'), + 'format_id': 'download', + 'url': update_url_query(authenticated_download_url, query), + }) + + self._sort_formats(formats) + + creator = f.get('created_by') or {} + + return { + 'id': file_id, + 'title': title, + 'formats': formats, + 'description': f.get('description') or None, + 'uploader': creator.get('name'), + 'timestamp': parse_iso8601(f.get('created_at')), + 'uploader_id': creator.get('id'), + } diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 2aa9f4782..000eac71c 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -147,7 +147,7 @@ class BrightcoveLegacyIE(InfoExtractor): ] @classmethod - def _build_brighcove_url(cls, object_str): + def _build_brightcove_url(cls, object_str): """ Build a Brightcove url from a xml string containing <object class="BrightcoveExperience">{params}</object> @@ -217,7 +217,7 @@ class BrightcoveLegacyIE(InfoExtractor): return cls._make_brightcove_url(params) @classmethod - def _build_brighcove_url_from_js(cls, object_js): + def _build_brightcove_url_from_js(cls, object_js): # The layout of JS is as follows: # customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) { # // build Brightcove <object /> XML @@ -272,12 +272,12 @@ class BrightcoveLegacyIE(InfoExtractor): ).+?>\s*</object>''', webpage) if matches: - return list(filter(None, [cls._build_brighcove_url(m) for m in matches])) + return list(filter(None, [cls._build_brightcove_url(m) for m in matches])) matches = re.findall(r'(customBC\.createVideo\(.+?\);)', webpage) if matches: return list(filter(None, [ - cls._build_brighcove_url_from_js(custom_bc) + cls._build_brightcove_url_from_js(custom_bc) for custom_bc in matches])) return [src for _, src in re.findall( r'<iframe[^>]+src=([\'"])((?:https?:)?//link\.brightcove\.com/services/player/(?!\1).+)\1', webpage)] diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py index 6889b0f40..7b9f4536a 100644 --- a/youtube_dl/extractor/cnbc.py +++ b/youtube_dl/extractor/cnbc.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import re from .common import InfoExtractor from ..utils import smuggle_url @@ -38,7 +39,7 @@ class CNBCIE(InfoExtractor): class CNBCVideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cnbc\.com/video/(?:[^/]+/)+(?P<id>[^./?#&]+)' + _VALID_URL = r'https?://(?:www\.)?cnbc\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\.html)' _TEST = { 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'info_dict': { @@ -56,11 +57,15 @@ class CNBCVideoIE(InfoExtractor): } def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'content_id["\']\s*:\s*["\'](\d+)', webpage, display_id, - 'video id') + path, display_id = re.match(self._VALID_URL, url).groups() + video_id = self._download_json( + 'https://webql-redesign.cnbcfm.com/graphql', display_id, query={ + 'query': '''{ + page(path: "%s") { + vcpsId + } +}''' % path, + })['data']['page']['vcpsId'] return self.url_result( - 'http://video.cnbc.com/gallery/?video=%s' % video_id, + 'http://video.cnbc.com/gallery/?video=%d' % video_id, CNBCIE.ie_key()) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 021945a89..16aff885c 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1456,9 +1456,10 @@ class InfoExtractor(object): try: self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers) return True - except ExtractorError: + except ExtractorError as e: self.to_screen( - '%s: %s URL is invalid, skipping' % (video_id, item)) + '%s: %s URL is invalid, skipping: %s' + % (video_id, item, error_to_compat_str(e.cause))) return False def http_scheme(self): @@ -1663,7 +1664,7 @@ class InfoExtractor(object): # just the media without qualities renditions. # Fortunately, master playlist can be easily distinguished from media # playlist based on particular tags availability. As of [1, 4.3.3, 4.3.4] - # master playlist tags MUST NOT appear in a media playist and vice versa. + # master playlist tags MUST NOT appear in a media playlist and vice versa. # As of [1, 4.3.3.1] #EXT-X-TARGETDURATION tag is REQUIRED for every # media playlist and MUST NOT appear in master playlist thus we can # clearly detect media playlist with this criterion. @@ -2595,6 +2596,7 @@ class InfoExtractor(object): def _extract_akamai_formats(self, manifest_url, video_id, hosts={}): formats = [] + hdcore_sign = 'hdcore=3.7.0' f4m_url = re.sub(r'(https?://[^/]+)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m') hds_host = hosts.get('hds') @@ -2607,6 +2609,7 @@ class InfoExtractor(object): for entry in f4m_formats: entry.update({'extra_param_to_segment_url': hdcore_sign}) formats.extend(f4m_formats) + m3u8_url = re.sub(r'(https?://[^/]+)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8') hls_host = hosts.get('hls') if hls_host: @@ -2614,6 +2617,31 @@ class InfoExtractor(object): formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + + http_host = hosts.get('http') + if http_host and 'hdnea=' not in manifest_url: + REPL_REGEX = r'https://[^/]+/i/([^,]+),([^/]+),([^/]+).csmil/.+' + qualities = re.match(REPL_REGEX, m3u8_url).group(2).split(',') + qualities_length = len(qualities) + if len(formats) in (qualities_length + 1, qualities_length * 2 + 1): + i = 0 + http_formats = [] + for f in formats: + if f['protocol'] == 'm3u8_native' and f['vcodec'] != 'none': + for protocol in ('http', 'https'): + http_f = f.copy() + del http_f['manifest_url'] + http_url = re.sub( + REPL_REGEX, protocol + r'://%s/\1%s\3' % (http_host, qualities[i]), f['url']) + http_f.update({ + 'format_id': http_f['format_id'].replace('hls-', protocol + '-'), + 'url': http_url, + 'protocol': protocol, + }) + http_formats.append(http_f) + i += 1 + formats.extend(http_formats) + return formats def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]): diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index ed278fefc..d5e77af32 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -16,6 +16,8 @@ from ..utils import ( mimetype2ext, orderedSet, parse_iso8601, + strip_or_none, + try_get, ) @@ -82,6 +84,7 @@ class CondeNastIE(InfoExtractor): 'uploader': 'gq', 'upload_date': '20170321', 'timestamp': 1490126427, + 'description': 'How much grimmer would things be if these people were competent?', }, }, { # JS embed @@ -93,7 +96,7 @@ class CondeNastIE(InfoExtractor): 'title': '3D printed TSA Travel Sentry keys really do open TSA locks', 'uploader': 'arstechnica', 'upload_date': '20150916', - 'timestamp': 1442434955, + 'timestamp': 1442434920, } }, { 'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player', @@ -196,6 +199,13 @@ class CondeNastIE(InfoExtractor): }) self._sort_formats(formats) + subtitles = {} + for t, caption in video_info.get('captions', {}).items(): + caption_url = caption.get('src') + if not (t in ('vtt', 'srt', 'tml') and caption_url): + continue + subtitles.setdefault('en', []).append({'url': caption_url}) + return { 'id': video_id, 'formats': formats, @@ -208,6 +218,7 @@ class CondeNastIE(InfoExtractor): 'season': video_info.get('season_title'), 'timestamp': parse_iso8601(video_info.get('premiere_date')), 'categories': video_info.get('categories'), + 'subtitles': subtitles, } def _real_extract(self, url): @@ -225,8 +236,16 @@ class CondeNastIE(InfoExtractor): if url_type == 'series': return self._extract_series(url, webpage) else: - params = self._extract_video_params(webpage, display_id) - info = self._search_json_ld( - webpage, display_id, fatal=False) + video = try_get(self._parse_json(self._search_regex( + r'__PRELOADED_STATE__\s*=\s*({.+?});', webpage, + 'preload state', '{}'), display_id), + lambda x: x['transformed']['video']) + if video: + params = {'videoId': video['id']} + info = {'description': strip_or_none(video.get('description'))} + else: + params = self._extract_video_params(webpage, display_id) + info = self._search_json_ld( + webpage, display_id, fatal=False) info.update(self._extract_video(params)) return info diff --git a/youtube_dl/extractor/discoverynetworks.py b/youtube_dl/extractor/discoverynetworks.py index 607a54948..c512b95d0 100644 --- a/youtube_dl/extractor/discoverynetworks.py +++ b/youtube_dl/extractor/discoverynetworks.py @@ -7,7 +7,7 @@ from .dplay import DPlayIE class DiscoveryNetworksDeIE(DPlayIE): - _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show|sendungen)/(?P<programme>[^/]+)/(?:video/)?(?P<alternate_id>[^/]+)' _TESTS = [{ 'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100', @@ -29,6 +29,9 @@ class DiscoveryNetworksDeIE(DPlayIE): }, { 'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B', 'only_matching': True, + }, { + 'url': 'https://tlc.de/sendungen/breaking-amish/die-welt-da-drauen/', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/europa.py b/youtube_dl/extractor/europa.py index 1efc0b2ec..2c1c747a1 100644 --- a/youtube_dl/extractor/europa.py +++ b/youtube_dl/extractor/europa.py @@ -60,7 +60,7 @@ class EuropaIE(InfoExtractor): title = get_item('title', preferred_langs) or video_id description = get_item('description', preferred_langs) - thumbnmail = xpath_text(playlist, './info/thumburl', 'thumbnail') + thumbnail = xpath_text(playlist, './info/thumburl', 'thumbnail') upload_date = unified_strdate(xpath_text(playlist, './info/date', 'upload date')) duration = parse_duration(xpath_text(playlist, './info/duration', 'duration')) view_count = int_or_none(xpath_text(playlist, './info/views', 'views')) @@ -85,7 +85,7 @@ class EuropaIE(InfoExtractor): 'id': video_id, 'title': title, 'description': description, - 'thumbnail': thumbnmail, + 'thumbnail': thumbnail, 'upload_date': upload_date, 'duration': duration, 'view_count': view_count, diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ae7079a6a..7ba4087fd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -36,6 +36,7 @@ from .afreecatv import AfreecaTVIE from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE from .alphaporno import AlphaPornoIE +from .amara import AmaraIE from .amcnetworks import AMCNetworksIE from .americastestkitchen import AmericasTestKitchenIE from .animeondemand import AnimeOnDemandIE @@ -58,7 +59,7 @@ from .ard import ( ARDMediathekIE, ) from .arte import ( - ArteTVPlus7IE, + ArteTVIE, ArteTVEmbedIE, ArteTVPlaylistIE, ) @@ -121,6 +122,7 @@ from .blinkx import BlinkxIE from .bloomberg import BloombergIE from .bokecc import BokeCCIE from .bostonglobe import BostonGlobeIE +from .box import BoxIE from .bpb import BpbIE from .br import ( BRIE, @@ -529,6 +531,7 @@ from .laola1tv import ( EHFTVIE, ITTFIE, ) +from .lbry import LBRYIE from .lci import LCIIE from .lcp import ( LcpPlayIE, @@ -780,6 +783,7 @@ from .ntvru import NTVRuIE from .nytimes import ( NYTimesIE, NYTimesArticleIE, + NYTimesCookingIE, ) from .nuvid import NuvidIE from .nzz import NZZIE @@ -842,6 +846,10 @@ from .picarto import ( ) from .piksel import PikselIE from .pinkbike import PinkbikeIE +from .pinterest import ( + PinterestIE, + PinterestCollectionIE, +) from .pladform import PladformIE from .platzi import ( PlatziIE, @@ -957,6 +965,7 @@ from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETe from .rtvnh import RTVNHIE from .rtvs import RTVSIE from .ruhd import RUHDIE +from .rumble import RumbleEmbedIE from .rutube import ( RutubeIE, RutubeChannelIE, @@ -1007,6 +1016,16 @@ from .shared import ( from .showroomlive import ShowRoomLiveIE from .sina import SinaIE from .sixplay import SixPlayIE +from .skyit import ( + SkyItPlayerIE, + SkyItVideoIE, + SkyItVideoLiveIE, + SkyItIE, + SkyItAcademyIE, + SkyItArteIE, + CieloTVItIE, + TV8ItIE, +) from .skylinewebcams import SkylineWebcamsIE from .skynewsarabia import ( SkyNewsArabiaIE, @@ -1053,8 +1072,7 @@ from .spankbang import ( SpankBangPlaylistIE, ) from .spankwire import SpankwireIE -from .spiegel import SpiegelIE, SpiegelArticleIE -from .spiegeltv import SpiegeltvIE +from .spiegel import SpiegelIE from .spike import ( BellatorIE, ParamountNetworkIE, @@ -1357,7 +1375,6 @@ from .vk import ( from .vlive import ( VLiveIE, VLiveChannelIE, - VLivePlaylistIE ) from .vodlocker import VodlockerIE from .vodpl import VODPlIE @@ -1474,21 +1491,17 @@ from .yourporn import YourPornIE from .yourupload import YourUploadIE from .youtube import ( YoutubeIE, - YoutubeChannelIE, - YoutubeFavouritesIE, YoutubeHistoryIE, - YoutubeLiveIE, + YoutubeTabIE, YoutubePlaylistIE, - YoutubePlaylistsIE, YoutubeRecommendedIE, YoutubeSearchDateIE, YoutubeSearchIE, - YoutubeSearchURLIE, - YoutubeShowIE, + #YoutubeSearchURLIE, YoutubeSubscriptionsIE, YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, - YoutubeUserIE, + YoutubeYtUserIE, YoutubeWatchLaterIE, ) from .zapiks import ZapiksIE diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 05806895c..ae822a50e 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -16,6 +16,7 @@ class FranceInterIE(InfoExtractor): 'ext': 'mp3', 'title': 'Affaire Cahuzac : le contentieux du compte en Suisse', 'description': 'md5:401969c5d318c061f86bda1fa359292b', + 'thumbnail': r're:^https?://.*\.jpg', 'upload_date': '20160907', }, } @@ -31,6 +32,7 @@ class FranceInterIE(InfoExtractor): title = self._og_search_title(webpage) description = self._og_search_description(webpage) + thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage) upload_date_str = self._search_regex( r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<', @@ -48,6 +50,7 @@ class FranceInterIE(InfoExtractor): 'id': video_id, 'title': title, 'description': description, + 'thumbnail': thumbnail, 'upload_date': upload_date, 'formats': [{ 'url': video_url, diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 81b468c7d..3ca415077 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -17,6 +17,7 @@ from ..utils import ( parse_duration, try_get, url_or_none, + urljoin, ) from .dailymotion import DailymotionIE @@ -128,18 +129,38 @@ class FranceTVIE(InfoExtractor): is_live = None - formats = [] - for video in info['videos']: - if video['statut'] != 'ONLINE': + videos = [] + + for video in (info.get('videos') or []): + if video.get('statut') != 'ONLINE': continue - video_url = video['url'] + if not video.get('url'): + continue + videos.append(video) + + if not videos: + for device_type in ['desktop', 'mobile']: + fallback_info = self._download_json( + 'https://player.webservices.francetelevisions.fr/v1/videos/%s' % video_id, + video_id, 'Downloading fallback %s video JSON' % device_type, query={ + 'device_type': device_type, + 'browser': 'chrome', + }, fatal=False) + + if fallback_info and fallback_info.get('video'): + videos.append(fallback_info['video']) + + formats = [] + for video in videos: + video_url = video.get('url') if not video_url: continue if is_live is None: is_live = (try_get( - video, lambda x: x['plages_ouverture'][0]['direct'], - bool) is True) or '/live.francetv.fr/' in video_url - format_id = video['format'] + video, lambda x: x['plages_ouverture'][0]['direct'], bool) is True + or video.get('is_live') is True + or '/live.francetv.fr/' in video_url) + format_id = video.get('format') ext = determine_ext(video_url) if ext == 'f4m': if georestricted: @@ -154,6 +175,9 @@ class FranceTVIE(InfoExtractor): sign(video_url, format_id), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)) + elif ext == 'mpd': + formats.extend(self._extract_mpd_formats( + sign(video_url, format_id), video_id, mpd_id=format_id, fatal=False)) elif video_url.startswith('rtmp'): formats.append({ 'url': video_url, @@ -166,6 +190,7 @@ class FranceTVIE(InfoExtractor): 'url': video_url, 'format_id': format_id, }) + self._sort_formats(formats) title = info['titre'] @@ -185,10 +210,10 @@ class FranceTVIE(InfoExtractor): return { 'id': video_id, 'title': self._live_title(title) if is_live else title, - 'description': clean_html(info['synopsis']), - 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']), - 'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']), - 'timestamp': int_or_none(info['diffusion']['timestamp']), + 'description': clean_html(info.get('synopsis')), + 'thumbnail': urljoin('https://sivideo.webservices.francetelevisions.fr', info.get('image')), + 'duration': int_or_none(info.get('real_duration')) or parse_duration(info.get('duree')), + 'timestamp': int_or_none(try_get(info, lambda x: x['diffusion']['timestamp'])), 'is_live': is_live, 'formats': formats, 'subtitles': subtitles, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 355067a50..f10f11244 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -91,6 +91,7 @@ from .piksel import PikselIE from .videa import VideaIE from .twentymin import TwentyMinutenIE from .ustream import UstreamIE +from .arte import ArteTVEmbedIE from .videopress import VideoPressIE from .rutube import RutubeIE from .limelight import LimelightBaseIE @@ -841,7 +842,7 @@ class GenericIE(InfoExtractor): 'skip_download': True, } }, - # MTVSercices embed + # MTVServices embed { 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html', 'md5': 'ca1aef97695ef2c1d6973256a57e5252', @@ -2760,11 +2761,9 @@ class GenericIE(InfoExtractor): return self.url_result(ustream_url, UstreamIE.ie_key()) # Look for embedded arte.tv player - mobj = re.search( - r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"', - webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'ArteTVEmbed') + arte_urls = ArteTVEmbedIE._extract_urls(webpage) + if arte_urls: + return self.playlist_from_matches(arte_urls, video_id, video_title) # Look for embedded francetv player mobj = re.search( diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py index f2cc57e44..de8c80e36 100644 --- a/youtube_dl/extractor/googledrive.py +++ b/youtube_dl/extractor/googledrive.py @@ -3,11 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_parse_qs from ..utils import ( determine_ext, ExtractorError, int_or_none, lowercase_escape, + try_get, update_url_query, ) @@ -38,21 +40,10 @@ class GoogleDriveIE(InfoExtractor): # video can't be watched anonymously due to view count limit reached, # but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046) 'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view', - 'md5': 'bfbd670d03a470bb1e6d4a257adec12e', - 'info_dict': { - 'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ', - 'ext': 'mp4', - 'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4', - } + 'only_matching': True, }, { # video id is longer than 28 characters 'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit', - 'info_dict': { - 'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ', - 'ext': 'mp4', - 'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4', - 'duration': 189, - }, 'only_matching': True, }, { 'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28', @@ -171,23 +162,21 @@ class GoogleDriveIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'http://docs.google.com/file/d/%s' % video_id, video_id) + video_info = compat_parse_qs(self._download_webpage( + 'https://drive.google.com/get_video_info', + video_id, query={'docid': video_id})) - title = self._search_regex( - r'"title"\s*,\s*"([^"]+)', webpage, 'title', - default=None) or self._og_search_title(webpage) - duration = int_or_none(self._search_regex( - r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', - default=None)) + def get_value(key): + return try_get(video_info, lambda x: x[key][0]) + + reason = get_value('reason') + title = get_value('title') + if not title and reason: + raise ExtractorError(reason, expected=True) formats = [] - fmt_stream_map = self._search_regex( - r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, - 'fmt stream map', default='').split(',') - fmt_list = self._search_regex( - r'"fmt_list"\s*,\s*"([^"]+)', webpage, - 'fmt_list', default='').split(',') + fmt_stream_map = (get_value('fmt_stream_map') or '').split(',') + fmt_list = (get_value('fmt_list') or '').split(',') if fmt_stream_map and fmt_list: resolutions = {} for fmt in fmt_list: @@ -257,19 +246,14 @@ class GoogleDriveIE(InfoExtractor): if urlh and urlh.headers.get('Content-Disposition'): add_source_format(urlh) - if not formats: - reason = self._search_regex( - r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None) - if reason: - raise ExtractorError(reason, expected=True) + if not formats and reason: + raise ExtractorError(reason, expected=True) self._sort_formats(formats) - hl = self._search_regex( - r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None) + hl = get_value('hl') subtitles_id = None - ttsurl = self._search_regex( - r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None) + ttsurl = get_value('ttsurl') if ttsurl: # the video Id for subtitles will be the last value in the ttsurl # query string @@ -279,8 +263,8 @@ class GoogleDriveIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage, default=None), - 'duration': duration, + 'thumbnail': 'https://drive.google.com/thumbnail?id=' + video_id, + 'duration': int_or_none(get_value('length_seconds')), 'formats': formats, 'subtitles': self.extract_subtitles(video_id, subtitles_id, hl), 'automatic_captions': self.extract_automatic_captions( diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 18249cf9b..0a70a1fb4 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -54,7 +54,7 @@ class InfoQIE(BokeCCBaseIE): def _extract_rtmp_video(self, webpage): # The server URL is hardcoded - video_url = 'rtmpe://video.infoq.com/cfx/st/' + video_url = 'rtmpe://videof.infoq.com/cfx/st/' # Extract video URL encoded_id = self._search_regex( @@ -86,17 +86,18 @@ class InfoQIE(BokeCCBaseIE): return [{ 'format_id': 'http_video', 'url': http_video_url, + 'http_headers': {'Referer': 'https://www.infoq.com/'}, }] def _extract_http_audio(self, webpage, video_id): - fields = self._hidden_inputs(webpage) + fields = self._form_hidden_inputs('mp3Form', webpage) http_audio_url = fields.get('filename') if not http_audio_url: return [] # base URL is found in the Location header in the response returned by # GET https://www.infoq.com/mp3download.action?filename=... when logged in. - http_audio_url = compat_urlparse.urljoin('http://res.infoq.com/downloads/mp3downloads/', http_audio_url) + http_audio_url = compat_urlparse.urljoin('http://ress.infoq.com/downloads/mp3downloads/', http_audio_url) http_audio_url = update_url_query(http_audio_url, self._extract_cf_auth(webpage)) # audio file seem to be missing some times even if there is a download link diff --git a/youtube_dl/extractor/kusi.py b/youtube_dl/extractor/kusi.py index 6a7e3baa7..9833d35eb 100644 --- a/youtube_dl/extractor/kusi.py +++ b/youtube_dl/extractor/kusi.py @@ -64,7 +64,7 @@ class KUSIIE(InfoExtractor): duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000) description = xpath_text(doc, 'ABSTRACT') thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME') - createtion_time = timeconvert(xpath_text(doc, 'rfc822creationdate')) + creation_time = timeconvert(xpath_text(doc, 'rfc822creationdate')) quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content') formats = [] @@ -84,5 +84,5 @@ class KUSIIE(InfoExtractor): 'duration': duration, 'formats': formats, 'thumbnail': thumbnail, - 'timestamp': createtion_time, + 'timestamp': creation_time, } diff --git a/youtube_dl/extractor/lbry.py b/youtube_dl/extractor/lbry.py new file mode 100644 index 000000000..6177297ab --- /dev/null +++ b/youtube_dl/extractor/lbry.py @@ -0,0 +1,91 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + ExtractorError, + int_or_none, + mimetype2ext, + try_get, +) + + +class LBRYIE(InfoExtractor): + IE_NAME = 'lbry.tv' + _VALID_URL = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/(?P<id>@[^:]+:[0-9a-z]+/[^:]+:[0-9a-z])' + _TESTS = [{ + # Video + 'url': 'https://lbry.tv/@Mantega:1/First-day-LBRY:1', + 'md5': '65bd7ec1f6744ada55da8e4c48a2edf9', + 'info_dict': { + 'id': '17f983b61f53091fb8ea58a9c56804e4ff8cff4d', + 'ext': 'mp4', + 'title': 'First day in LBRY? Start HERE!', + 'description': 'md5:f6cb5c704b332d37f5119313c2c98f51', + 'timestamp': 1595694354, + 'upload_date': '20200725', + } + }, { + # Audio + 'url': 'https://lbry.tv/@LBRYFoundation:0/Episode-1:e', + 'md5': 'c94017d3eba9b49ce085a8fad6b98d00', + 'info_dict': { + 'id': 'e7d93d772bd87e2b62d5ab993c1c3ced86ebb396', + 'ext': 'mp3', + 'title': 'The LBRY Foundation Community Podcast Episode 1 - Introduction, Streaming on LBRY, Transcoding', + 'description': 'md5:661ac4f1db09f31728931d7b88807a61', + 'timestamp': 1591312601, + 'upload_date': '20200604', + } + }, { + 'url': 'https://odysee.com/@BrodieRobertson:5/apple-is-tracking-everything-you-do-on:e', + 'only_matching': True, + }, { + 'url': "https://odysee.com/@ScammerRevolts:b0/I-SYSKEY'D-THE-SAME-SCAMMERS-3-TIMES!:b", + 'only_matching': True, + }] + + def _call_api_proxy(self, method, display_id, params): + return self._download_json( + 'https://api.lbry.tv/api/v1/proxy', display_id, + headers={'Content-Type': 'application/json-rpc'}, + data=json.dumps({ + 'method': method, + 'params': params, + }).encode())['result'] + + def _real_extract(self, url): + display_id = self._match_id(url).replace(':', '#') + uri = 'lbry://' + display_id + result = self._call_api_proxy( + 'resolve', display_id, {'urls': [uri]})[uri] + result_value = result['value'] + if result_value.get('stream_type') not in ('video', 'audio'): + raise ExtractorError('Unsupported URL', expected=True) + streaming_url = self._call_api_proxy( + 'get', display_id, {'uri': uri})['streaming_url'] + source = result_value.get('source') or {} + media = result_value.get('video') or result_value.get('audio') or {} + signing_channel = result_value.get('signing_channel') or {} + + return { + 'id': result['claim_id'], + 'title': result_value['title'], + 'thumbnail': try_get(result_value, lambda x: x['thumbnail']['url'], compat_str), + 'description': result_value.get('description'), + 'license': result_value.get('license'), + 'timestamp': int_or_none(result.get('timestamp')), + 'tags': result_value.get('tags'), + 'width': int_or_none(media.get('width')), + 'height': int_or_none(media.get('height')), + 'duration': int_or_none(media.get('duration')), + 'channel': signing_channel.get('name'), + 'channel_id': signing_channel.get('claim_id'), + 'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')), + 'filesize': int_or_none(source.get('size')), + 'url': streaming_url, + } diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py index f5c997ef4..89d549858 100644 --- a/youtube_dl/extractor/lrt.py +++ b/youtube_dl/extractor/lrt.py @@ -5,28 +5,26 @@ import re from .common import InfoExtractor from ..utils import ( - determine_ext, - int_or_none, - parse_duration, - remove_end, + clean_html, + merge_dicts, ) class LRTIE(InfoExtractor): IE_NAME = 'lrt.lt' - _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?lrt\.lt(?P<path>/mediateka/irasas/(?P<id>[0-9]+))' _TESTS = [{ # m3u8 download - 'url': 'http://www.lrt.lt/mediateka/irasas/54391/', - 'md5': 'fe44cf7e4ab3198055f2c598fc175cb0', + 'url': 'https://www.lrt.lt/mediateka/irasas/2000127261/greita-ir-gardu-sicilijos-ikvepta-klasikiniu-makaronu-su-baklazanais-vakariene', + 'md5': '85cb2bb530f31d91a9c65b479516ade4', 'info_dict': { - 'id': '54391', + 'id': '2000127261', 'ext': 'mp4', - 'title': 'Septynios Kauno dienos', - 'description': 'md5:24d84534c7dc76581e59f5689462411a', - 'duration': 1783, - 'view_count': int, - 'like_count': int, + 'title': 'Greita ir gardu: Sicilijos įkvėpta klasikinių makaronų su baklažanais vakarienė', + 'description': 'md5:ad7d985f51b0dc1489ba2d76d7ed47fa', + 'duration': 3035, + 'timestamp': 1604079000, + 'upload_date': '20201030', }, }, { # direct mp3 download @@ -43,52 +41,35 @@ class LRTIE(InfoExtractor): }, }] + def _extract_js_var(self, webpage, var_name, default): + return self._search_regex( + r'%s\s*=\s*(["\'])((?:(?!\1).)+)\1' % var_name, + webpage, var_name.replace('_', ' '), default, group=2) + def _real_extract(self, url): - video_id = self._match_id(url) + path, video_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, video_id) - title = remove_end(self._og_search_title(webpage), ' - LRT') + media_url = self._extract_js_var(webpage, 'main_url', path) + media = self._download_json(self._extract_js_var( + webpage, 'media_info_url', + 'https://www.lrt.lt/servisai/stream_url/vod/media_info/'), + video_id, query={'url': media_url}) + jw_data = self._parse_jwplayer_data( + media['playlist_item'], video_id, base_url=url) - formats = [] - for _, file_url in re.findall( - r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage): - ext = determine_ext(file_url) - if ext not in ('m3u8', 'mp3'): + json_ld_data = self._search_json_ld(webpage, video_id) + + tags = [] + for tag in (media.get('tags') or []): + tag_name = tag.get('name') + if not tag_name: continue - # mp3 served as m3u8 produces stuttered media file - if ext == 'm3u8' and '.mp3' in file_url: - continue - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - file_url, video_id, 'mp4', entry_protocol='m3u8_native', - fatal=False)) - elif ext == 'mp3': - formats.append({ - 'url': file_url, - 'vcodec': 'none', - }) - self._sort_formats(formats) + tags.append(tag_name) - thumbnail = self._og_search_thumbnail(webpage) - description = self._og_search_description(webpage) - duration = parse_duration(self._search_regex( - r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1', - webpage, 'duration', default=None, group='duration')) - - view_count = int_or_none(self._html_search_regex( - r'<div[^>]+class=(["\']).*?record-desc-seen.*?\1[^>]*>(?P<count>.+?)</div>', - webpage, 'view count', fatal=False, group='count')) - like_count = int_or_none(self._search_regex( - r'<span[^>]+id=(["\'])flikesCount.*?\1>(?P<count>\d+)<', - webpage, 'like count', fatal=False, group='count')) - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, - 'duration': duration, - 'view_count': view_count, - 'like_count': like_count, + clean_info = { + 'description': clean_html(media.get('content')), + 'tags': tags, } + + return merge_dicts(clean_info, jw_data, json_ld_data) diff --git a/youtube_dl/extractor/malltv.py b/youtube_dl/extractor/malltv.py index 6f4fd927f..fadfd9338 100644 --- a/youtube_dl/extractor/malltv.py +++ b/youtube_dl/extractor/malltv.py @@ -1,10 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import merge_dicts +from ..utils import ( + clean_html, + dict_get, + float_or_none, + int_or_none, + merge_dicts, + parse_duration, + try_get, +) class MallTVIE(InfoExtractor): @@ -17,7 +23,7 @@ class MallTVIE(InfoExtractor): 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', 'ext': 'mp4', 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', - 'description': 'md5:25fc0ec42a72ba602b602c683fa29deb', + 'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35', 'duration': 216, 'timestamp': 1538870400, 'upload_date': '20181007', @@ -37,20 +43,46 @@ class MallTVIE(InfoExtractor): webpage = self._download_webpage( url, display_id, headers=self.geo_verification_headers()) - SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b' + video = self._parse_json(self._search_regex( + r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);', + webpage, 'video object'), display_id) + video_source = video['VideoSource'] video_id = self._search_regex( - SOURCE_RE, webpage, 'video id', group='id') + r'/([\da-z]+)/index\b', video_source, 'video id') - media = self._parse_html5_media_entries( - url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id, - m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0] + formats = self._extract_m3u8_formats( + video_source + '.m3u8', video_id, 'mp4', 'm3u8_native') + self._sort_formats(formats) + + subtitles = {} + for s in (video.get('Subtitles') or {}): + s_url = s.get('Url') + if not s_url: + continue + subtitles.setdefault(s.get('Language') or 'cz', []).append({ + 'url': s_url, + }) + + entity_counts = video.get('EntityCounts') or {} + + def get_count(k): + v = entity_counts.get(k + 's') or {} + return int_or_none(dict_get(v, ('Count', 'StrCount'))) info = self._search_json_ld(webpage, video_id, default={}) - return merge_dicts(media, info, { + return merge_dicts({ 'id': video_id, 'display_id': display_id, - 'title': self._og_search_title(webpage, default=None) or display_id, - 'description': self._og_search_description(webpage, default=None), - 'thumbnail': self._og_search_thumbnail(webpage, default=None), - }) + 'title': video.get('Title'), + 'description': clean_html(video.get('Description')), + 'thumbnail': video.get('ThumbnailUrl'), + 'formats': formats, + 'subtitles': subtitles, + 'duration': int_or_none(video.get('DurationSeconds')) or parse_duration(video.get('Duration')), + 'view_count': get_count('View'), + 'like_count': get_count('Like'), + 'dislike_count': get_count('Dislike'), + 'average_rating': float_or_none(try_get(video, lambda x: x['EntityRating']['AvarageRate'])), + 'comment_count': get_count('Comment'), + }, info) diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py index 71fc3ec56..cab3aa045 100644 --- a/youtube_dl/extractor/mgtv.py +++ b/youtube_dl/extractor/mgtv.py @@ -17,9 +17,8 @@ from ..utils import ( class MGTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html' + _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html' IE_DESC = '芒果TV' - _GEO_COUNTRIES = ['CN'] _TESTS = [{ 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html', @@ -34,14 +33,18 @@ class MGTVIE(InfoExtractor): }, { 'url': 'http://www.mgtv.com/b/301817/3826653.html', 'only_matching': True, + }, { + 'url': 'https://w.mgtv.com/b/301817/3826653.html', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) + tk2 = base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1] try: api_data = self._download_json( 'https://pcweb.api.mgtv.com/player/video', video_id, query={ - 'tk2': base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1], + 'tk2': tk2, 'video_id': video_id, }, headers=self.geo_verification_headers())['data'] except ExtractorError as e: @@ -56,6 +59,7 @@ class MGTVIE(InfoExtractor): stream_data = self._download_json( 'https://pcweb.api.mgtv.com/player/getSource', video_id, query={ 'pm2': api_data['atc']['pm2'], + 'tk2': tk2, 'video_id': video_id, }, headers=self.geo_verification_headers())['data'] stream_domain = stream_data['stream_domain'][0] diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index fedd5f46b..df1034fc5 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -349,6 +349,18 @@ class MTVIE(MTVServicesInfoExtractor): 'only_matching': True, }] + @staticmethod + def extract_child_with_type(parent, t): + children = parent['children'] + return next(c for c in children if c.get('type') == t) + + def _extract_mgid(self, webpage): + data = self._parse_json(self._search_regex( + r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None) + main_container = self.extract_child_with_type(data, 'MainContainer') + video_player = self.extract_child_with_type(main_container, 'VideoPlayer') + return video_player['props']['media']['video']['config']['uri'] + class MTVJapanIE(MTVServicesInfoExtractor): IE_NAME = 'mtvjapan' diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 6f3cb3003..ea5f5a315 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -10,7 +10,6 @@ from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( int_or_none, - js_to_json, parse_duration, smuggle_url, try_get, @@ -394,8 +393,8 @@ class NBCNewsIE(ThePlatformIE): webpage = self._download_webpage(url, video_id) data = self._parse_json(self._search_regex( - r'window\.__data\s*=\s*({.+});', webpage, - 'bootstrap json'), video_id, js_to_json) + r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>', + webpage, 'bootstrap json'), video_id)['props']['initialState'] video_data = try_get(data, lambda x: x['video']['current'], dict) if not video_data: video_data = data['article']['content'][0]['primaryMedia']['video'] diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 2447c812e..ddd828d92 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -81,6 +81,29 @@ class NDRIE(NDRBaseIE): 'params': { 'skip_download': True, }, + }, { + # with subtitles + 'url': 'https://www.ndr.de/fernsehen/sendungen/extra_3/extra-3-Satiremagazin-mit-Christian-Ehring,sendung1091858.html', + 'info_dict': { + 'id': 'extra18674', + 'display_id': 'extra-3-Satiremagazin-mit-Christian-Ehring', + 'ext': 'mp4', + 'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring', + 'description': 'md5:42ee53990a715eaaf4dc7f13a3bd56c6', + 'uploader': 'ndrtv', + 'upload_date': '20201113', + 'duration': 1749, + 'subtitles': { + 'de': [{ + 'ext': 'ttml', + 'url': r're:^https://www\.ndr\.de.+', + }], + }, + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { 'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html', 'only_matching': True, @@ -239,6 +262,20 @@ class NDREmbedBaseIE(InfoExtractor): 'preference': quality_key(thumbnail.get('quality')), }) + subtitles = {} + tracks = config.get('tracks') + if tracks and isinstance(tracks, list): + for track in tracks: + if not isinstance(track, dict): + continue + track_url = urljoin(url, track.get('src')) + if not track_url: + continue + subtitles.setdefault(track.get('srclang') or 'de', []).append({ + 'url': track_url, + 'ext': 'ttml', + }) + return { 'id': video_id, 'title': title, @@ -248,6 +285,7 @@ class NDREmbedBaseIE(InfoExtractor): 'duration': duration, 'thumbnails': thumbnails, 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/npr.py b/youtube_dl/extractor/npr.py index 53acc6e57..9d1122f0c 100644 --- a/youtube_dl/extractor/npr.py +++ b/youtube_dl/extractor/npr.py @@ -33,7 +33,7 @@ class NprIE(InfoExtractor): }, }], }, { - # mutlimedia, not media title + # multimedia, not media title 'url': 'https://www.npr.org/2017/06/19/533198237/tigers-jaw-tiny-desk-concert', 'info_dict': { 'id': '533198237', diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index fc78ca56c..976b1c694 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -221,3 +221,41 @@ class NYTimesArticleIE(NYTimesBaseIE): r'NYTD\.FlexTypes\.push\s*\(\s*({.+})\s*\)\s*;'), webpage, 'podcast data') return self._extract_podcast_from_json(podcast_data, page_id, webpage) + + +class NYTimesCookingIE(NYTimesBaseIE): + _VALID_URL = r'https?://cooking\.nytimes\.com/(?:guid|recip)es/(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://cooking.nytimes.com/recipes/1017817-cranberry-curd-tart', + 'md5': 'dab81fa2eaeb3f9ed47498bdcfcdc1d3', + 'info_dict': { + 'id': '100000004756089', + 'ext': 'mov', + 'timestamp': 1479383008, + 'uploader': 'By SHAW LASH, ADAM SAEWITZ and JAMES HERRON', + 'title': 'Cranberry Tart', + 'upload_date': '20161117', + 'description': 'If you are a fan of lemon curd or the classic French tarte au citron, you will love this cranberry version.', + }, + }, { + 'url': 'https://cooking.nytimes.com/guides/13-how-to-cook-a-turkey', + 'md5': '4b2e8c70530a89b8d905a2b572316eb8', + 'info_dict': { + 'id': '100000003951728', + 'ext': 'mov', + 'timestamp': 1445509539, + 'description': 'Turkey guide', + 'upload_date': '20151022', + 'title': 'Turkey', + } + }] + + def _real_extract(self, url): + page_id = self._match_id(url) + + webpage = self._download_webpage(url, page_id) + + video_id = self._search_regex( + r'data-video-id=["\'](\d+)', webpage, 'video id') + + return self._extract_video_from_id(video_id) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 4dbe661be..d4baa16ee 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -477,7 +477,7 @@ class PBSIE(InfoExtractor): if media_id: return media_id, presumptive_id, upload_date, description - # Fronline video embedded via flp + # Frontline video embedded via flp video_id = self._search_regex( r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None) if video_id: diff --git a/youtube_dl/extractor/pinterest.py b/youtube_dl/extractor/pinterest.py new file mode 100644 index 000000000..2bb4ca660 --- /dev/null +++ b/youtube_dl/extractor/pinterest.py @@ -0,0 +1,176 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + float_or_none, + int_or_none, + try_get, + unified_timestamp, + url_or_none, +) + + +class PinterestBaseIE(InfoExtractor): + _VALID_URL_BASE = r'https?://(?:[^/]+\.)?pinterest\.(?:com|fr|de|ch|jp|cl|ca|it|co\.uk|nz|ru|com\.au|at|pt|co\.kr|es|com\.mx|dk|ph|th|com\.uy|co|nl|info|kr|ie|vn|com\.vn|ec|mx|in|pe|co\.at|hu|co\.in|co\.nz|id|com\.ec|com\.py|tw|be|uk|com\.bo|com\.pe)' + + def _extract_resource(self, webpage, video_id): + return self._parse_json( + self._search_regex( + r'<script[^>]+\bid=["\']initial-state["\'][^>]*>({.+?})</script>', + webpage, 'application json'), + video_id)['resourceResponses'] + + def _extract_video(self, data, extract_formats=True): + video_id = data['id'] + + title = (data.get('title') or data.get('grid_title') or video_id).strip() + + formats = [] + duration = None + if extract_formats: + for format_id, format_dict in data['videos']['video_list'].items(): + if not isinstance(format_dict, dict): + continue + format_url = url_or_none(format_dict.get('url')) + if not format_url: + continue + duration = float_or_none(format_dict.get('duration'), scale=1000) + ext = determine_ext(format_url) + if 'hls' in format_id.lower() or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id=format_id, fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'width': int_or_none(format_dict.get('width')), + 'height': int_or_none(format_dict.get('height')), + 'duration': duration, + }) + self._sort_formats( + formats, field_preference=('height', 'width', 'tbr', 'format_id')) + + description = data.get('description') or data.get('description_html') or data.get('seo_description') + timestamp = unified_timestamp(data.get('created_at')) + + def _u(field): + return try_get(data, lambda x: x['closeup_attribution'][field], compat_str) + + uploader = _u('full_name') + uploader_id = _u('id') + + repost_count = int_or_none(data.get('repin_count')) + comment_count = int_or_none(data.get('comment_count')) + categories = try_get(data, lambda x: x['pin_join']['visual_annotation'], list) + tags = data.get('hashtags') + + thumbnails = [] + images = data.get('images') + if isinstance(images, dict): + for thumbnail_id, thumbnail in images.items(): + 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 { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'thumbnails': thumbnails, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'repost_count': repost_count, + 'comment_count': comment_count, + 'categories': categories, + 'tags': tags, + 'formats': formats, + 'extractor_key': PinterestIE.ie_key(), + } + + +class PinterestIE(PinterestBaseIE): + _VALID_URL = r'%s/pin/(?P<id>\d+)' % PinterestBaseIE._VALID_URL_BASE + _TESTS = [{ + 'url': 'https://www.pinterest.com/pin/664281013778109217/', + 'md5': '6550c2af85d6d9f3fe3b88954d1577fc', + 'info_dict': { + 'id': '664281013778109217', + 'ext': 'mp4', + 'title': 'Origami', + 'description': 'md5:b9d90ddf7848e897882de9e73344f7dd', + 'duration': 57.7, + 'timestamp': 1593073622, + 'upload_date': '20200625', + 'uploader': 'Love origami -I am Dafei', + 'uploader_id': '586523688879454212', + 'repost_count': 50, + 'comment_count': 0, + 'categories': list, + 'tags': list, + }, + }, { + 'url': 'https://co.pinterest.com/pin/824721750502199491/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + data = self._extract_resource(webpage, video_id)[0]['response']['data'] + return self._extract_video(data) + + +class PinterestCollectionIE(PinterestBaseIE): + _VALID_URL = r'%s/[^/]+/(?P<id>[^/?#&]+)' % PinterestBaseIE._VALID_URL_BASE + _TESTS = [{ + 'url': 'https://www.pinterest.ca/mashal0407/cool-diys/', + 'info_dict': { + 'id': '585890301462791043', + 'title': 'cool diys', + }, + 'playlist_count': 8, + }] + + @classmethod + def suitable(cls, url): + return False if PinterestIE.suitable(url) else super( + PinterestCollectionIE, cls).suitable(url) + + def _real_extract(self, url): + collection_name = self._match_id(url) + webpage = self._download_webpage(url, collection_name) + resource = self._extract_resource(webpage, collection_name)[1] + entries = [] + for item in resource['response']['data']: + if not isinstance(item, dict) or item.get('type') != 'pin': + continue + video_id = item.get('id') + if video_id: + # Some pins may not be available anonymously via pin URL + # video = self._extract_video(item, extract_formats=False) + # video.update({ + # '_type': 'url_transparent', + # 'url': 'https://www.pinterest.com/pin/%s/' % video_id, + # }) + # entries.append(video) + entries.append(self._extract_video(item)) + title = try_get( + resource, lambda x: x['options']['board_title'], compat_str) + collection_id = try_get( + resource, lambda x: x['options']['board_id'], + compat_str) or collection_name + return self.playlist_result( + entries, playlist_id=collection_id, playlist_title=title) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 207a6c247..ecb628f14 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -15,9 +16,9 @@ from ..utils import ( GeoRestrictedError, int_or_none, parse_duration, + remove_start, strip_or_none, try_get, - unescapeHTML, unified_strdate, unified_timestamp, update_url_query, @@ -67,7 +68,7 @@ class RaiBaseIE(InfoExtractor): # This does not imply geo restriction (e.g. # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html) - if media_url == 'http://download.rai.it/video_no_available.mp4': + if '/video_no_available.mp4' in media_url: continue ext = determine_ext(media_url) @@ -122,40 +123,20 @@ class RaiBaseIE(InfoExtractor): class RaiPlayIE(RaiBaseIE): - _VALID_URL = r'(?P<url>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s)\.html)' % RaiBaseIE._UUID_RE + _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE _TESTS = [{ - 'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter', - 'md5': '340aa3b7afb54bfd14a8c11786450d76', - 'info_dict': { - 'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66', - 'ext': 'mp4', - 'title': 'La Casa Bianca', - 'alt_title': 'S2016 - Puntata del 23/10/2016', - 'description': 'md5:a09d45890850458077d1f68bb036e0a5', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Rai 3', - 'creator': 'Rai 3', - 'duration': 3278, - 'timestamp': 1477764300, - 'upload_date': '20161029', - 'series': 'La Casa Bianca', - 'season': '2016', - }, - }, { 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html', 'md5': '8970abf8caf8aef4696e7b1f2adfc696', 'info_dict': { 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391', 'ext': 'mp4', 'title': 'Report del 07/04/2014', - 'alt_title': 'S2013/14 - Puntata del 07/04/2014', - 'description': 'md5:f27c544694cacb46a078db84ec35d2d9', + 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014', + 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e', 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Rai 5', - 'creator': 'Rai 5', + 'uploader': 'Rai Gulp', 'duration': 6160, 'series': 'Report', - 'season_number': 5, 'season': '2013/14', }, 'params': { @@ -167,48 +148,52 @@ class RaiPlayIE(RaiBaseIE): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - url, video_id = mobj.group('url', 'id') + base, video_id = re.match(self._VALID_URL, url).groups() media = self._download_json( - '%s?json' % url, video_id, 'Downloading video JSON') + base + '.json', video_id, 'Downloading video JSON') title = media['name'] video = media['video'] - relinker_info = self._extract_relinker_info(video['contentUrl'], video_id) + relinker_info = self._extract_relinker_info(video['content_url'], video_id) self._sort_formats(relinker_info['formats']) thumbnails = [] - if 'images' in media: - for _, value in media.get('images').items(): - if value: - thumbnails.append({ - 'url': value.replace('[RESOLUTION]', '600x400') - }) + for _, value in media.get('images', {}).items(): + if value: + thumbnails.append({ + 'url': urljoin(url, value), + }) - timestamp = unified_timestamp(try_get( - media, lambda x: x['availabilities'][0]['start'], compat_str)) + date_published = media.get('date_published') + time_published = media.get('time_published') + if date_published and time_published: + date_published += ' ' + time_published subtitles = self._extract_subtitles(url, video.get('subtitles')) + program_info = media.get('program_info') or {} + season = media.get('season') + info = { - 'id': video_id, + 'id': remove_start(media.get('id'), 'ContentItem-') or video_id, + 'display_id': video_id, 'title': self._live_title(title) if relinker_info.get( 'is_live') else title, - 'alt_title': media.get('subtitle'), + 'alt_title': strip_or_none(media.get('subtitle')), 'description': media.get('description'), 'uploader': strip_or_none(media.get('channel')), - 'creator': strip_or_none(media.get('editor')), + 'creator': strip_or_none(media.get('editor') or None), 'duration': parse_duration(video.get('duration')), - 'timestamp': timestamp, + 'timestamp': unified_timestamp(date_published), 'thumbnails': thumbnails, - 'series': try_get( - media, lambda x: x['isPartOf']['name'], compat_str), - 'season_number': int_or_none(try_get( - media, lambda x: x['isPartOf']['numeroStagioni'])), - 'season': media.get('stagione') or None, + 'series': program_info.get('name'), + 'season_number': int_or_none(season), + 'season': season if (season and not season.isdigit()) else None, + 'episode': media.get('episode_title'), + 'episode_number': int_or_none(media.get('episode')), 'subtitles': subtitles, } @@ -216,16 +201,16 @@ class RaiPlayIE(RaiBaseIE): return info -class RaiPlayLiveIE(RaiBaseIE): - _VALID_URL = r'https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+)' - _TEST = { +class RaiPlayLiveIE(RaiPlayIE): + _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))' + _TESTS = [{ 'url': 'http://www.raiplay.it/dirette/rainews24', 'info_dict': { 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', 'display_id': 'rainews24', 'ext': 'mp4', 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:6eca31500550f9376819f174e5644754', + 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', 'uploader': 'Rai News 24', 'creator': 'Rai News 24', 'is_live': True, @@ -233,58 +218,50 @@ class RaiPlayLiveIE(RaiBaseIE): 'params': { 'skip_download': True, }, - } - - 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-uniquename=["\']ContentItem-(%s)' % RaiBaseIE._UUID_RE, - webpage, 'content id') - - return { - '_type': 'url_transparent', - 'ie_key': RaiPlayIE.ie_key(), - 'url': 'http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id, - 'id': video_id, - 'display_id': display_id, - } + }] class RaiPlayPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)' + _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))' _TESTS = [{ 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', 'info_dict': { 'id': 'nondirloalmiocapo', 'title': 'Non dirlo al mio capo', - 'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86', + 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b', }, 'playlist_mincount': 12, }] def _real_extract(self, url): - playlist_id = self._match_id(url) + base, playlist_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, playlist_id) - - title = self._html_search_meta( - ('programma', 'nomeProgramma'), webpage, 'title') - description = unescapeHTML(self._html_search_meta( - ('description', 'og:description'), webpage, 'description')) + program = self._download_json( + base + '.json', playlist_id, 'Downloading program JSON') entries = [] - for mobj in re.finditer( - r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1', - webpage): - video_url = urljoin(url, mobj.group('path')) - entries.append(self.url_result( - video_url, ie=RaiPlayIE.ie_key(), - video_id=RaiPlayIE._match_id(video_url))) + for b in (program.get('blocks') or []): + for s in (b.get('sets') or []): + s_id = s.get('id') + if not s_id: + continue + medias = self._download_json( + '%s/%s.json' % (base, s_id), s_id, + 'Downloading content set JSON', fatal=False) + if not medias: + continue + for m in (medias.get('items') or []): + path_id = m.get('path_id') + if not path_id: + continue + video_url = urljoin(url, path_id) + entries.append(self.url_result( + video_url, ie=RaiPlayIE.ie_key(), + video_id=RaiPlayIE._match_id(video_url))) - return self.playlist_result(entries, playlist_id, title, description) + return self.playlist_result( + entries, playlist_id, program.get('name'), + try_get(program, lambda x: x['program_info']['description'])) class RaiIE(RaiBaseIE): @@ -300,7 +277,8 @@ class RaiIE(RaiBaseIE): 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 1758, 'upload_date': '20140612', - } + }, + 'skip': 'This content is available only in Italy', }, { # with ContentItem in many metas 'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html', @@ -316,7 +294,7 @@ class RaiIE(RaiBaseIE): }, { # with ContentItem in og:url 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html', - 'md5': '11959b4e44fa74de47011b5799490adf', + 'md5': '6865dd00cf0bbf5772fdd89d59bd768a', 'info_dict': { 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c', 'ext': 'mp4', @@ -326,18 +304,6 @@ class RaiIE(RaiBaseIE): 'duration': 2214, 'upload_date': '20161103', } - }, { - # drawMediaRaiTV(...) - 'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html', - 'md5': '2dd727e61114e1ee9c47f0da6914e178', - 'info_dict': { - 'id': '59d69d28-6bb6-409d-a4b5-ed44096560af', - 'ext': 'mp4', - 'title': 'Il pacco', - 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a', - 'thumbnail': r're:^https?://.*\.jpg$', - 'upload_date': '20141221', - }, }, { # initEdizione('ContentItem-...' 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined', @@ -349,17 +315,6 @@ class RaiIE(RaiBaseIE): 'upload_date': '20170401', }, 'skip': 'Changes daily', - }, { - # HDS live stream with only relinker URL - 'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews', - 'info_dict': { - 'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc', - 'ext': 'flv', - 'title': 'EuroNews', - }, - 'params': { - 'skip_download': True, - }, }, { # HLS live stream with ContentItem in og:url 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html', @@ -469,7 +424,7 @@ class RaiIE(RaiBaseIE): except ExtractorError: pass - relinker_url = self._search_regex( + relinker_url = self._proto_relative_url(self._search_regex( r'''(?x) (?: var\s+videoURL| @@ -481,7 +436,7 @@ class RaiIE(RaiBaseIE): //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\? (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1 ''', - webpage, 'relinker URL', group='url') + webpage, 'relinker URL', group='url')) relinker_info = self._extract_relinker_info( urljoin(url, relinker_url), video_id) diff --git a/youtube_dl/extractor/rumble.py b/youtube_dl/extractor/rumble.py new file mode 100644 index 000000000..4a0225109 --- /dev/null +++ b/youtube_dl/extractor/rumble.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + int_or_none, + parse_iso8601, + try_get, +) + + +class RumbleEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)' + _TESTS = [{ + 'url': 'https://rumble.com/embed/v5pv5f', + 'md5': '36a18a049856720189f30977ccbb2c34', + 'info_dict': { + 'id': 'v5pv5f', + 'ext': 'mp4', + 'title': 'WMAR 2 News Latest Headlines | October 20, 6pm', + 'timestamp': 1571611968, + 'upload_date': '20191020', + } + }, { + 'url': 'https://rumble.com/embed/ufe9n.v5pv5f', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + video = self._download_json( + 'https://rumble.com/embedJS/', video_id, + query={'request': 'video', 'v': video_id}) + title = video['title'] + + formats = [] + for height, ua in (video.get('ua') or {}).items(): + for i in range(2): + f_url = try_get(ua, lambda x: x[i], compat_str) + if f_url: + ext = determine_ext(f_url) + f = { + 'ext': ext, + 'format_id': '%s-%sp' % (ext, height), + 'height': int_or_none(height), + 'url': f_url, + } + bitrate = try_get(ua, lambda x: x[i + 2]['bitrate']) + if bitrate: + f['tbr'] = int_or_none(bitrate) + formats.append(f) + self._sort_formats(formats) + + author = video.get('author') or {} + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': video.get('i'), + 'timestamp': parse_iso8601(video.get('pubDate')), + 'channel': author.get('name'), + 'channel_url': author.get('url'), + 'duration': int_or_none(video.get('duration')), + } diff --git a/youtube_dl/extractor/servus.py b/youtube_dl/extractor/servus.py index 9401bf2cf..1610ddc2c 100644 --- a/youtube_dl/extractor/servus.py +++ b/youtube_dl/extractor/servus.py @@ -1,9 +1,15 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import ( + determine_ext, + float_or_none, + int_or_none, + unified_timestamp, + urlencode_postdata, + url_or_none, +) class ServusIE(InfoExtractor): @@ -12,20 +18,29 @@ class ServusIE(InfoExtractor): (?:www\.)? (?: servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)| - servustv\.com/videos + (?:servustv|pm-wissen)\.com/videos ) /(?P<id>[aA]{2}-\w+|\d+-\d+) ''' _TESTS = [{ # new URL schema 'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/', - 'md5': '3e1dd16775aa8d5cbef23628cfffc1f4', + 'md5': '60474d4c21f3eb148838f215c37f02b9', 'info_dict': { 'id': 'AA-1T6VBU5PW1W12', 'ext': 'mp4', 'title': 'Die Grünen aus Sicht des Volkes', + 'alt_title': 'Talk im Hangar-7 Voxpops Gruene', 'description': 'md5:1247204d85783afe3682644398ff2ec4', 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 62.442, + 'timestamp': 1605193976, + 'upload_date': '20201112', + 'series': 'Talk im Hangar-7', + 'season': 'Season 9', + 'season_number': 9, + 'episode': 'Episode 31 - September 14', + 'episode_number': 31, } }, { # old URL schema @@ -40,30 +55,94 @@ class ServusIE(InfoExtractor): }, { 'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/', 'only_matching': True, + }, { + 'url': 'https://www.pm-wissen.com/videos/aa-24mus4g2w2112/', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url).upper() - webpage = self._download_webpage(url, video_id) - title = self._search_regex( - (r'videoLabel\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', - r'<h\d+[^>]+\bclass=["\']heading--(?:one|two)["\'][^>]*>(?P<title>[^<]+)'), - webpage, 'title', default=None, - group='title') or self._og_search_title(webpage) - title = re.sub(r'\s*-\s*Servus TV\s*$', '', title) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) + token = self._download_json( + 'https://auth.redbullmediahouse.com/token', video_id, + 'Downloading token', data=urlencode_postdata({ + 'grant_type': 'client_credentials', + }), headers={ + 'Authorization': 'Basic SVgtMjJYNEhBNFdEM1cxMTpEdDRVSkFLd2ZOMG5IMjB1NGFBWTBmUFpDNlpoQ1EzNA==', + }) + access_token = token['access_token'] + token_type = token.get('token_type', 'Bearer') - formats = self._extract_m3u8_formats( - 'https://stv.rbmbtnx.net/api/v1/manifests/%s.m3u8' % video_id, - video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + video = self._download_json( + 'https://sparkle-api.liiift.io/api/v1/stv/channels/international/assets/%s' % video_id, + video_id, 'Downloading video JSON', headers={ + 'Authorization': '%s %s' % (token_type, access_token), + }) + + formats = [] + thumbnail = None + for resource in video['resources']: + if not isinstance(resource, dict): + continue + format_url = url_or_none(resource.get('url')) + if not format_url: + continue + extension = resource.get('extension') + type_ = resource.get('type') + if extension == 'jpg' or type_ == 'reference_keyframe': + thumbnail = format_url + continue + ext = determine_ext(format_url) + if type_ == 'dash' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + format_url, video_id, mpd_id='dash', fatal=False)) + elif type_ == 'hls' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif extension == 'mp4' or ext == 'mp4': + formats.append({ + 'url': format_url, + 'format_id': type_, + 'width': int_or_none(resource.get('width')), + 'height': int_or_none(resource.get('height')), + }) self._sort_formats(formats) + attrs = {} + for attribute in video['attributes']: + if not isinstance(attribute, dict): + continue + key = attribute.get('fieldKey') + value = attribute.get('fieldValue') + if not key or not value: + continue + attrs[key] = value + + title = attrs.get('title_stv') or video_id + alt_title = attrs.get('title') + description = attrs.get('long_description') or attrs.get('short_description') + series = attrs.get('label') + season = attrs.get('season') + episode = attrs.get('chapter') + duration = float_or_none(attrs.get('duration'), scale=1000) + season_number = int_or_none(self._search_regex( + r'Season (\d+)', season or '', 'season number', default=None)) + episode_number = int_or_none(self._search_regex( + r'Episode (\d+)', episode or '', 'episode number', default=None)) + return { 'id': video_id, 'title': title, + 'alt_title': alt_title, 'description': description, 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': unified_timestamp(video.get('lastPublished')), + 'series': series, + 'season': season, + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, 'formats': formats, } diff --git a/youtube_dl/extractor/skyit.py b/youtube_dl/extractor/skyit.py new file mode 100644 index 000000000..14a4d8d4c --- /dev/null +++ b/youtube_dl/extractor/skyit.py @@ -0,0 +1,239 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_parse_qs, + compat_urllib_parse_urlparse, +) +from ..utils import ( + dict_get, + int_or_none, + parse_duration, + unified_timestamp, +) + + +class SkyItPlayerIE(InfoExtractor): + IE_NAME = 'player.sky.it' + _VALID_URL = r'https?://player\.sky\.it/player/(?:external|social)\.html\?.*?\bid=(?P<id>\d+)' + _GEO_BYPASS = False + _DOMAIN = 'sky' + _PLAYER_TMPL = 'https://player.sky.it/player/external.html?id=%s&domain=%s' + # http://static.sky.it/static/skyplayer/conf.json + _TOKEN_MAP = { + 'cielo': 'Hh9O7M8ks5yi6nSROL7bKYz933rdf3GhwZlTLMgvy4Q', + 'hotclub': 'kW020K2jq2lk2eKRJD2vWEg832ncx2EivZlTLQput2C', + 'mtv8': 'A5Nn9GGb326CI7vP5e27d7E4PIaQjota', + 'salesforce': 'C6D585FD1615272C98DE38235F38BD86', + 'sitocommerciale': 'VJwfFuSGnLKnd9Phe9y96WkXgYDCguPMJ2dLhGMb2RE', + 'sky': 'F96WlOd8yoFmLQgiqv6fNQRvHZcsWk5jDaYnDvhbiJk', + 'skyacademy': 'A6LAn7EkO2Q26FRy0IAMBekX6jzDXYL3', + 'skyarte': 'LWk29hfiU39NNdq87ePeRach3nzTSV20o0lTv2001Cd', + 'theupfront': 'PRSGmDMsg6QMGc04Obpoy7Vsbn7i2Whp', + } + + def _player_url_result(self, video_id): + return self.url_result( + self._PLAYER_TMPL % (video_id, self._DOMAIN), + SkyItPlayerIE.ie_key(), video_id) + + def _parse_video(self, video, video_id): + title = video['title'] + is_live = video.get('type') == 'live' + hls_url = video.get(('streaming' if is_live else 'hls') + '_url') + if not hls_url and video.get('geoblock' if is_live else 'geob'): + self.raise_geo_restricted(countries=['IT']) + + if is_live: + formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4') + else: + formats = self._extract_akamai_formats( + hls_url, video_id, {'http': 'videoplatform.sky.it'}) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._live_title(title) if is_live else title, + 'formats': formats, + 'thumbnail': dict_get(video, ('video_still', 'video_still_medium', 'thumb')), + 'description': video.get('short_desc') or None, + 'timestamp': unified_timestamp(video.get('create_date')), + 'duration': int_or_none(video.get('duration_sec')) or parse_duration(video.get('duration')), + 'is_live': is_live, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + domain = compat_parse_qs(compat_urllib_parse_urlparse( + url).query).get('domain', [None])[0] + token = dict_get(self._TOKEN_MAP, (domain, 'sky')) + video = self._download_json( + 'https://apid.sky.it/vdp/v1/getVideoData', + video_id, query={ + 'caller': 'sky', + 'id': video_id, + 'token': token + }, headers=self.geo_verification_headers()) + return self._parse_video(video, video_id) + + +class SkyItVideoIE(SkyItPlayerIE): + IE_NAME = 'video.sky.it' + _VALID_URL = r'https?://(?:masterchef|video|xfactor)\.sky\.it(?:/[^/]+)*/video/[0-9a-z-]+-(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://video.sky.it/news/mondo/video/uomo-ucciso-da-uno-squalo-in-australia-631227', + 'md5': 'fe5c91e59a84a3437eaa0bca6e134ccd', + 'info_dict': { + 'id': '631227', + 'ext': 'mp4', + 'title': 'Uomo ucciso da uno squalo in Australia', + 'timestamp': 1606036192, + 'upload_date': '20201122', + } + }, { + 'url': 'https://xfactor.sky.it/video/x-factor-2020-replay-audizioni-1-615820', + 'only_matching': True, + }, { + 'url': 'https://masterchef.sky.it/video/masterchef-9-cosa-e-successo-nella-prima-puntata-562831', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + return self._player_url_result(video_id) + + +class SkyItVideoLiveIE(SkyItPlayerIE): + IE_NAME = 'video.sky.it:live' + _VALID_URL = r'https?://video\.sky\.it/diretta/(?P<id>[^/?&#]+)' + _TEST = { + 'url': 'https://video.sky.it/diretta/tg24', + 'info_dict': { + 'id': '1', + 'ext': 'mp4', + 'title': r're:Diretta TG24 \d{4}-\d{2}-\d{2} \d{2}:\d{2}', + 'description': 'Guarda la diretta streaming di SkyTg24, segui con Sky tutti gli appuntamenti e gli speciali di Tg24.', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + asset_id = compat_str(self._parse_json(self._search_regex( + r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>', + webpage, 'next data'), display_id)['props']['initialState']['livePage']['content']['asset_id']) + livestream = self._download_json( + 'https://apid.sky.it/vdp/v1/getLivestream', + asset_id, query={'id': asset_id}) + return self._parse_video(livestream, asset_id) + + +class SkyItIE(SkyItPlayerIE): + IE_NAME = 'sky.it' + _VALID_URL = r'https?://(?:sport|tg24)\.sky\.it(?:/[^/]+)*/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)' + _TESTS = [{ + 'url': 'https://sport.sky.it/calcio/serie-a/2020/11/21/juventus-cagliari-risultato-gol', + 'info_dict': { + 'id': '631201', + 'ext': 'mp4', + 'title': 'Un rosso alla violenza: in campo per i diritti delle donne', + 'upload_date': '20201121', + 'timestamp': 1605995753, + }, + 'expected_warnings': ['Unable to download f4m manifest'], + }, { + 'url': 'https://tg24.sky.it/mondo/2020/11/22/australia-squalo-uccide-uomo', + 'md5': 'fe5c91e59a84a3437eaa0bca6e134ccd', + 'info_dict': { + 'id': '631227', + 'ext': 'mp4', + 'title': 'Uomo ucciso da uno squalo in Australia', + 'timestamp': 1606036192, + 'upload_date': '20201122', + }, + }] + _VIDEO_ID_REGEX = r'data-videoid="(\d+)"' + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + self._VIDEO_ID_REGEX, webpage, 'video id') + return self._player_url_result(video_id) + + +class SkyItAcademyIE(SkyItIE): + IE_NAME = 'skyacademy.it' + _VALID_URL = r'https?://(?:www\.)?skyacademy\.it(?:/[^/]+)*/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)' + _TESTS = [{ + 'url': 'https://www.skyacademy.it/eventi-speciali/2019/07/05/a-lezione-di-cinema-con-sky-academy-/', + 'md5': 'ced5c26638b7863190cbc44dd6f6ba08', + 'info_dict': { + 'id': '523458', + 'ext': 'mp4', + 'title': 'Sky Academy "The Best CineCamp 2019"', + 'timestamp': 1562843784, + 'upload_date': '20190711', + } + }] + _DOMAIN = 'skyacademy' + _VIDEO_ID_REGEX = r'id="news-videoId_(\d+)"' + + +class SkyItArteIE(SkyItIE): + IE_NAME = 'arte.sky.it' + _VALID_URL = r'https?://arte\.sky\.it/video/(?P<id>[^/?&#]+)' + _TESTS = [{ + 'url': 'https://arte.sky.it/video/serie-musei-venezia-collezionismo-12-novembre/', + 'md5': '515aee97b87d7a018b6c80727d3e7e17', + 'info_dict': { + 'id': '627926', + 'ext': 'mp4', + 'title': "Musei Galleria Franchetti alla Ca' d'Oro Palazzo Grimani", + 'upload_date': '20201106', + 'timestamp': 1604664493, + } + }] + _DOMAIN = 'skyarte' + _VIDEO_ID_REGEX = r'(?s)<iframe[^>]+src="(?:https:)?//player\.sky\.it/player/external\.html\?[^"]*\bid=(\d+)' + + +class CieloTVItIE(SkyItIE): + IE_NAME = 'cielotv.it' + _VALID_URL = r'https?://(?:www\.)?cielotv\.it/video/(?P<id>[^.]+)\.html' + _TESTS = [{ + 'url': 'https://www.cielotv.it/video/Il-lunedi-e-sempre-un-dramma.html', + 'md5': 'c4deed77552ba901c2a0d9258320304b', + 'info_dict': { + 'id': '499240', + 'ext': 'mp4', + 'title': 'Il lunedì è sempre un dramma', + 'upload_date': '20190329', + 'timestamp': 1553862178, + } + }] + _DOMAIN = 'cielo' + _VIDEO_ID_REGEX = r'videoId\s*=\s*"(\d+)"' + + +class TV8ItIE(SkyItVideoIE): + IE_NAME = 'tv8.it' + _VALID_URL = r'https?://tv8\.it/showvideo/(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://tv8.it/showvideo/630529/ogni-mattina-ucciso-asino-di-andrea-lo-cicero/18-11-2020/', + 'md5': '9ab906a3f75ea342ed928442f9dabd21', + 'info_dict': { + 'id': '630529', + 'ext': 'mp4', + 'title': 'Ogni mattina - Ucciso asino di Andrea Lo Cicero', + 'timestamp': 1605721374, + 'upload_date': '20201118', + } + }] + _DOMAIN = 'mtv8' diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index a2fddf6d9..abb85e1e5 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -558,7 +558,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): class SoundcloudPagedPlaylistBaseIE(SoundcloudIE): def _extract_playlist(self, base_url, playlist_id, playlist_title): - # Per the SoundCloud documentation, the maximum limit for a linked partioning query is 200. + # Per the SoundCloud documentation, the maximum limit for a linked partitioning query is 200. # https://developers.soundcloud.com/blog/offset-pagination-deprecated COMMON_QUERY = { 'limit': 200, diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 4df7f4ddc..2da32b9b2 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -1,159 +1,54 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .nexx import ( - NexxIE, - NexxEmbedIE, -) -from .spiegeltv import SpiegeltvIE -from ..compat import compat_urlparse -from ..utils import ( - parse_duration, - strip_or_none, - unified_timestamp, -) +from .jwplatform import JWPlatformIE class SpiegelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' + _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}' + _VALID_URL = r'https?://(?:www\.)?(?:spiegel|manager-magazin)\.de(?:/[^/]+)+/[^/]*-(?P<id>[0-9]+|%s)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' % _UUID_RE _TESTS = [{ 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', - 'md5': 'b57399839d055fccfeb9a0455c439868', + 'md5': '50c7948883ec85a3e431a0a44b7ad1d6', 'info_dict': { - 'id': '563747', + 'id': 'II0BUyxY', + 'display_id': '1259285', 'ext': 'mp4', - 'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv', + 'title': 'Vulkan Tungurahua in Ecuador ist wieder aktiv - DER SPIEGEL - Wissenschaft', 'description': 'md5:8029d8310232196eb235d27575a8b9f4', - 'duration': 49, + 'duration': 48.0, 'upload_date': '20130311', - 'timestamp': 1362994320, + 'timestamp': 1362997920, }, }, { 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', - 'md5': '5b6c2f4add9d62912ed5fc78a1faed80', - 'info_dict': { - 'id': '580988', - 'ext': 'mp4', - 'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers', - 'description': 'md5:c2322b65e58f385a820c10fa03b2d088', - 'duration': 983, - 'upload_date': '20131115', - 'timestamp': 1384546642, - }, - }, { - 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html', - 'md5': '97b91083a672d72976faa8433430afb9', - 'info_dict': { - 'id': '601883', - 'ext': 'mp4', - 'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.', - 'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"', - 'upload_date': '20140904', - 'timestamp': 1409834160, - } - }, { - 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html', 'only_matching': True, }, { - # nexx video + 'url': 'https://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html', + 'only_matching': True, + }, { + 'url': 'https://www.spiegel.de/panorama/urteile-im-goldmuenzenprozess-haftstrafen-fuer-clanmitglieder-a-aae8df48-43c1-4c61-867d-23f0a2d254b7', + 'only_matching': True, + }, { 'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html', 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - metadata_url = 'http://www.spiegel.de/video/metadata/video-%s.json' % video_id - handle = self._request_webpage(metadata_url, video_id) - - # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html - if SpiegeltvIE.suitable(handle.geturl()): - return self.url_result(handle.geturl(), 'Spiegeltv') - - video_data = self._parse_json(self._webpage_read_content( - handle, metadata_url, video_id), video_id) - title = video_data['title'] - nexx_id = video_data['nexxOmniaId'] - domain_id = video_data.get('nexxOmniaDomain') or '748' - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'nexx:%s:%s' % (domain_id, nexx_id), - 'title': title, - 'description': strip_or_none(video_data.get('teaser')), - 'duration': parse_duration(video_data.get('duration')), - 'timestamp': unified_timestamp(video_data.get('datum')), - 'ie_key': NexxIE.ie_key(), - } - - -class SpiegelArticleIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html' - IE_NAME = 'Spiegel:Article' - IE_DESC = 'Articles on spiegel.de' - _TESTS = [{ + }, { 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', - 'info_dict': { - 'id': '1516455', - 'ext': 'mp4', - 'title': 'Faszination Badminton: Nennt es bloß nicht Federball', - 'description': 're:^Patrick Kämnitz gehört.{100,}', - 'upload_date': '20140825', - }, - }, { - 'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html', - 'info_dict': { - - }, - 'playlist_count': 6, - }, { - # Nexx iFrame embed - 'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html', - 'info_dict': { - 'id': '161464', - 'ext': 'mp4', - 'title': 'Nervenkitzel Achterbahn', - 'alt_title': 'Karussellbauer in Deutschland', - 'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc', - 'release_year': 2005, - 'creator': 'SPIEGEL TV', - 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 2761, - 'timestamp': 1394021479, - 'upload_date': '20140305', - }, - 'params': { - 'format': 'bestvideo', - 'skip_download': True, - }, + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - - # Single video on top of the page - video_link = self._search_regex( - r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage, - 'video page URL', default=None) - if video_link: - video_url = compat_urlparse.urljoin( - self.http_scheme() + '//spiegel.de/', video_link) - return self.url_result(video_url) - - # Multiple embedded videos - embeds = re.findall( - r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"', - webpage) - entries = [ - self.url_result(compat_urlparse.urljoin( - self.http_scheme() + '//spiegel.de/', embed_path)) - for embed_path in embeds] - if embeds: - return self.playlist_result(entries) - - return self.playlist_from_matches( - NexxEmbedIE._extract_urls(webpage), ie=NexxEmbedIE.ie_key()) + media_id = self._html_search_regex( + r'("|["\'])mediaId\1\s*:\s*("|["\'])(?P<id>(?:(?!\2).)+)\2', + webpage, 'media id', group='id') + return { + '_type': 'url_transparent', + 'id': video_id, + 'display_id': video_id, + 'url': 'jwplatform:%s' % media_id, + 'title': self._og_search_title(webpage, default=None), + 'ie_key': JWPlatformIE.ie_key(), + } diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py deleted file mode 100644 index 6ccf4c342..000000000 --- a/youtube_dl/extractor/spiegeltv.py +++ /dev/null @@ -1,17 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from .nexx import NexxIE - - -class SpiegeltvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/videos/(?P<id>\d+)' - _TEST = { - 'url': 'http://www.spiegel.tv/videos/161681-flug-mh370/', - 'only_matching': True, - } - - def _real_extract(self, url): - return self.url_result( - 'https://api.nexx.cloud/v3/748/videos/byid/%s' - % self._match_id(url), ie=NexxIE.ie_key()) diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index 2f6887d86..a0b6ef4db 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -9,6 +9,7 @@ from ..utils import ( determine_ext, dict_get, int_or_none, + unified_timestamp, str_or_none, strip_or_none, try_get, @@ -44,7 +45,8 @@ class SVTBaseIE(InfoExtractor): 'format_id': player_type, 'url': vurl, }) - if not formats and video_info.get('rights', {}).get('geoBlockedSweden'): + rights = try_get(video_info, lambda x: x['rights'], dict) or {} + if not formats and rights.get('geoBlockedSweden'): self.raise_geo_restricted( 'This video is only available in Sweden', countries=self._GEO_COUNTRIES) @@ -70,6 +72,7 @@ class SVTBaseIE(InfoExtractor): episode = video_info.get('episodeTitle') episode_number = int_or_none(video_info.get('episodeNumber')) + timestamp = unified_timestamp(rights.get('validFrom')) duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration'))) age_limit = None adult = dict_get( @@ -84,6 +87,7 @@ class SVTBaseIE(InfoExtractor): 'formats': formats, 'subtitles': subtitles, 'duration': duration, + 'timestamp': timestamp, 'age_limit': age_limit, 'series': series, 'season_number': season_number, @@ -136,26 +140,39 @@ class SVTPlayIE(SVTPlayBaseIE): IE_DESC = 'SVT Play and Öppet arkiv' _VALID_URL = r'''(?x) (?: - svt:(?P<svt_id>[^/?#&]+)| + (?: + svt:| + https?://(?:www\.)?svt\.se/barnkanalen/barnplay/[^/]+/ + ) + (?P<svt_id>[^/?#&]+)| https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+) ) ''' _TESTS = [{ - 'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2', - 'md5': '2b6704fe4a28801e1a098bbf3c5ac611', + 'url': 'https://www.svtplay.se/video/26194546/det-har-ar-himlen', + 'md5': '2382036fd6f8c994856c323fe51c426e', 'info_dict': { - 'id': '5996901', + 'id': 'jNwpV9P', 'ext': 'mp4', - 'title': 'Flygplan till Haile Selassie', - 'duration': 3527, - 'thumbnail': r're:^https?://.*[\.-]jpg$', + 'title': 'Det här är himlen', + 'timestamp': 1586044800, + 'upload_date': '20200405', + 'duration': 3515, + 'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$', 'age_limit': 0, 'subtitles': { 'sv': [{ - 'ext': 'wsrt', + 'ext': 'vtt', }] }, }, + 'params': { + 'format': 'bestvideo', + # skip for now due to download test asserts that segment is > 10000 bytes and svt uses + # init segments that are smaller + # AssertionError: Expected test_SVTPlay_jNwpV9P.mp4 to be at least 9.77KiB, but it's only 864.00B + 'skip_download': True, + }, }, { # geo restricted to Sweden 'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten', @@ -172,6 +189,12 @@ class SVTPlayIE(SVTPlayBaseIE): }, { 'url': 'svt:14278044', 'only_matching': True, + }, { + 'url': 'https://www.svt.se/barnkanalen/barnplay/kar/eWv5MLX/', + 'only_matching': True, + }, { + 'url': 'svt:eWv5MLX', + 'only_matching': True, }] def _adjust_title(self, info): @@ -236,7 +259,10 @@ class SVTPlayIE(SVTPlayBaseIE): r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)'), webpage, 'video id') - return self._extract_by_video_id(svt_id, webpage) + info_dict = self._extract_by_video_id(svt_id, webpage) + info_dict['thumbnail'] = thumbnail + + return info_dict class SVTSeriesIE(SVTPlayBaseIE): @@ -360,7 +386,7 @@ class SVTPageIE(InfoExtractor): @classmethod def suitable(cls, url): - return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url) + return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTPageIE, cls).suitable(url) def _real_extract(self, url): path, display_id = re.match(self._VALID_URL, url).groups() diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py index c351b7545..8ceab7e35 100644 --- a/youtube_dl/extractor/tagesschau.py +++ b/youtube_dl/extractor/tagesschau.py @@ -86,7 +86,7 @@ class TagesschauPlayerIE(InfoExtractor): # return self._extract_via_api(kind, video_id) # JSON api does not provide some audio formats (e.g. ogg) thus - # extractiong audio via webpage + # extracting audio via webpage webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 07055513a..41bfbe80f 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -208,7 +208,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): if m: return [m.group('url')] - # Are whitesapces ignored in URLs? + # Are whitespaces ignored in URLs? # https://github.com/ytdl-org/youtube-dl/issues/12044 matches = re.findall( r'(?s)<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage) diff --git a/youtube_dl/extractor/turner.py b/youtube_dl/extractor/turner.py index 4a6cbfbb8..2964504a2 100644 --- a/youtube_dl/extractor/turner.py +++ b/youtube_dl/extractor/turner.py @@ -56,9 +56,9 @@ class TurnerBaseIE(AdobePassIE): content_id = xpath_text(video_data, 'contentId') or video_id # rtmp_src = xpath_text(video_data, 'akamai/src') # if rtmp_src: - # splited_rtmp_src = rtmp_src.split(',') - # if len(splited_rtmp_src) == 2: - # rtmp_src = splited_rtmp_src[1] + # split_rtmp_src = rtmp_src.split(',') + # if len(split_rtmp_src) == 2: + # rtmp_src = split_rtmp_src[1] # aifp = xpath_text(video_data, 'akamai/aifp', default='') urls = [] diff --git a/youtube_dl/extractor/urplay.py b/youtube_dl/extractor/urplay.py index 6030b7cb5..10b817760 100644 --- a/youtube_dl/extractor/urplay.py +++ b/youtube_dl/extractor/urplay.py @@ -2,7 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import unified_timestamp +from ..utils import ( + dict_get, + int_or_none, + unified_timestamp, +) class URPlayIE(InfoExtractor): @@ -15,8 +19,8 @@ class URPlayIE(InfoExtractor): 'ext': 'mp4', 'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd', 'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a', - 'timestamp': 1513512768, - 'upload_date': '20171217', + 'timestamp': 1513292400, + 'upload_date': '20171214', }, }, { 'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde', @@ -25,7 +29,7 @@ class URPlayIE(InfoExtractor): 'ext': 'mp4', 'title': 'Tripp, Trapp, Träd : Sovkudde', 'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1', - 'timestamp': 1440093600, + 'timestamp': 1440086400, 'upload_date': '20150820', }, }, { @@ -35,37 +39,58 @@ class URPlayIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - + url = url.replace('skola.se/Produkter', 'play.se/program') webpage = self._download_webpage(url, video_id) - urplayer_data = self._parse_json(self._search_regex( - r'urPlayer\.init\(({.+?})\);', webpage, 'urplayer data'), video_id) - host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect'] + urplayer_data = self._parse_json(self._html_search_regex( + r'data-react-class="components/Player/Player"[^>]+data-react-props="({.+?})"', + webpage, 'urplayer data'), video_id)['currentProduct'] + episode = urplayer_data['title'] + raw_streaming_info = urplayer_data['streamingInfo']['raw'] + host = self._download_json( + 'http://streaming-loadbalancer.ur.se/loadbalancer.json', + video_id)['redirect'] formats = [] - for quality_attr, quality, preference in (('', 'sd', 0), ('_hd', 'hd', 1)): - file_http = urplayer_data.get('file_http' + quality_attr) or urplayer_data.get('file_http_sub' + quality_attr) + for k, v in raw_streaming_info.items(): + if not (k in ('sd', 'hd') and isinstance(v, dict)): + continue + file_http = v.get('location') if file_http: formats.extend(self._extract_wowza_formats( - 'http://%s/%splaylist.m3u8' % (host, file_http), video_id, skip_protocols=['rtmp', 'rtsp'])) + 'http://%s/%splaylist.m3u8' % (host, file_http), + video_id, skip_protocols=['f4m', 'rtmp', 'rtsp'])) self._sort_formats(formats) - subtitles = {} - for subtitle in urplayer_data.get('subtitles', []): - subtitle_url = subtitle.get('file') - kind = subtitle.get('kind') - if not subtitle_url or (kind and kind != 'captions'): - continue - subtitles.setdefault(subtitle.get('label', 'Svenska'), []).append({ - 'url': subtitle_url, - }) + image = urplayer_data.get('image') or {} + thumbnails = [] + for k, v in image.items(): + t = { + 'id': k, + 'url': v, + } + wh = k.split('x') + if len(wh) == 2: + t.update({ + 'width': int_or_none(wh[0]), + 'height': int_or_none(wh[1]), + }) + thumbnails.append(t) + + series = urplayer_data.get('series') or {} + series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle')) return { 'id': video_id, - 'title': urplayer_data['title'], - 'description': self._og_search_description(webpage), - 'thumbnail': urplayer_data.get('image'), - 'timestamp': unified_timestamp(self._html_search_meta(('uploadDate', 'schema:uploadDate'), webpage, 'timestamp')), - 'series': urplayer_data.get('series_title'), - 'subtitles': subtitles, + 'title': '%s : %s' % (series_title, episode) if series_title else episode, + 'description': urplayer_data.get('description'), + 'thumbnails': thumbnails, + 'timestamp': unified_timestamp(urplayer_data.get('publishedAt')), + 'series': series_title, 'formats': formats, + 'duration': int_or_none(urplayer_data.get('duration')), + 'categories': urplayer_data.get('categories'), + 'tags': urplayer_data.get('keywords'), + 'season': series.get('label'), + 'episode': episode, + 'episode_number': int_or_none(urplayer_data.get('episodeNumber')), } diff --git a/youtube_dl/extractor/usanetwork.py b/youtube_dl/extractor/usanetwork.py index 54c7495cc..e3784e55f 100644 --- a/youtube_dl/extractor/usanetwork.py +++ b/youtube_dl/extractor/usanetwork.py @@ -1,74 +1,24 @@ # coding: utf-8 from __future__ import unicode_literals -from .adobepass import AdobePassIE -from ..utils import ( - NO_DEFAULT, - smuggle_url, - update_url_query, -) +from .nbc import NBCIE -class USANetworkIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?usanetwork\.com/(?:[^/]+/videos|movies)/(?P<id>[^/?#]+)' - _TEST = { - 'url': 'http://www.usanetwork.com/mrrobot/videos/hpe-cybersecurity', - 'md5': '33c0d2ba381571b414024440d08d57fd', +class USANetworkIE(NBCIE): + _VALID_URL = r'https?(?P<permalink>://(?:www\.)?usanetwork\.com/[^/]+/video/[^/]+/(?P<id>\d+))' + _TESTS = [{ + 'url': 'https://www.usanetwork.com/peacock-trailers/video/intelligence-trailer/4185302', 'info_dict': { - 'id': '3086229', + 'id': '4185302', 'ext': 'mp4', - 'title': 'HPE Cybersecurity', - 'description': 'The more we digitize our world, the more vulnerable we are.', - 'upload_date': '20160818', - 'timestamp': 1471535460, - 'uploader': 'NBCU-USA', + 'title': 'Intelligence (Trailer)', + 'description': 'A maverick NSA agent enlists the help of a junior systems analyst in a workplace power grab.', + 'upload_date': '20200715', + 'timestamp': 1594785600, + 'uploader': 'NBCU-MPAT', }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - def _x(name, default=NO_DEFAULT): - return self._search_regex( - r'data-%s\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % name, - webpage, name, default=default, group='value') - - video_id = _x('mpx-guid') - title = _x('episode-title') - mpx_account_id = _x('mpx-account-id', '2304992029') - - query = { - 'mbr': 'true', - } - if _x('is-full-episode', None) == '1': - query['manifest'] = 'm3u' - - if _x('is-entitlement', None) == '1': - adobe_pass = {} - drupal_settings = self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings', fatal=False) - if drupal_settings: - drupal_settings = self._parse_json(drupal_settings, video_id, fatal=False) - if drupal_settings: - adobe_pass = drupal_settings.get('adobePass', {}) - resource = self._get_mvpd_resource( - adobe_pass.get('adobePassResourceId', 'usa'), - title, video_id, _x('episode-rating', 'TV-14')) - query['auth'] = self._extract_mvpd_auth( - url, video_id, adobe_pass.get('adobePassRequestorId', 'usa'), resource) - - info = self._search_json_ld(webpage, video_id, default={}) - info.update({ - '_type': 'url_transparent', - 'url': smuggle_url(update_url_query( - 'http://link.theplatform.com/s/HNK2IC/media/guid/%s/%s' % (mpx_account_id, video_id), - query), {'force_smil_url': True}), - 'id': video_id, - 'title': title, - 'series': _x('show-title', None), - 'episode': title, - 'ie_key': 'ThePlatform', - }) - return info + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index b0dcdc0e6..a003b7af8 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import hashlib import hmac import itertools @@ -9,6 +10,10 @@ import re import time from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -165,19 +170,20 @@ class VikiIE(VikiBaseIE): }, { # episode 'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1', - 'md5': '5fa476a902e902783ac7a4d615cdbc7a', + 'md5': '94e0e34fd58f169f40c184f232356cfe', 'info_dict': { 'id': '44699v', 'ext': 'mp4', 'title': 'Boys Over Flowers - Episode 1', 'description': 'md5:b89cf50038b480b88b5b3c93589a9076', - 'duration': 4204, + 'duration': 4172, 'timestamp': 1270496524, 'upload_date': '20100405', 'uploader': 'group8', 'like_count': int, 'age_limit': 13, - } + }, + 'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'], }, { # youtube external 'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1', @@ -194,14 +200,15 @@ class VikiIE(VikiBaseIE): 'uploader_id': 'ad14065n', 'like_count': int, 'age_limit': 13, - } + }, + 'skip': 'Page not found!', }, { 'url': 'http://www.viki.com/player/44699v', 'only_matching': True, }, { # non-English description 'url': 'http://www.viki.com/videos/158036v-love-in-magic', - 'md5': '1713ae35df5a521b31f6dc40730e7c9c', + 'md5': 'adf9e321a0ae5d0aace349efaaff7691', 'info_dict': { 'id': '158036v', 'ext': 'mp4', @@ -217,8 +224,11 @@ class VikiIE(VikiBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - video = self._call_api( - 'videos/%s.json' % video_id, video_id, 'Downloading video JSON') + resp = self._download_json( + 'https://www.viki.com/api/videos/' + video_id, + video_id, 'Downloading video JSON', + headers={'x-viki-app-ver': '4.0.57'}) + video = resp['video'] self._check_errors(video) @@ -265,57 +275,74 @@ class VikiIE(VikiBaseIE): 'subtitles': subtitles, } - streams = self._call_api( - 'videos/%s/streams.json' % video_id, video_id, - 'Downloading video streams JSON') - - if 'external' in streams: - result.update({ - '_type': 'url_transparent', - 'url': streams['external']['url'], - }) - return result - formats = [] - for format_id, stream_dict in streams.items(): - height = int_or_none(self._search_regex( - r'^(\d+)[pP]$', format_id, 'height', default=None)) - for protocol, format_dict in stream_dict.items(): - # rtmps URLs does not seem to work - if protocol == 'rtmps': - continue - format_url = format_dict['url'] - if format_id == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - format_url, video_id, 'mp4', - entry_protocol='m3u8_native', - m3u8_id='m3u8-%s' % protocol, fatal=False) - # Despite CODECS metadata in m3u8 all video-only formats - # are actually video+audio - for f in m3u8_formats: - if f.get('acodec') == 'none' and f.get('vcodec') != 'none': - f['acodec'] = None - formats.extend(m3u8_formats) - elif format_url.startswith('rtmp'): - mobj = re.search( - r'^(?P<url>rtmp://[^/]+/(?P<app>.+?))/(?P<playpath>mp4:.+)$', - format_url) - if not mobj: + + def add_format(format_id, format_dict, protocol='http'): + # rtmps URLs does not seem to work + if protocol == 'rtmps': + return + format_url = format_dict.get('url') + if not format_url: + return + qs = compat_parse_qs(compat_urllib_parse_urlparse(format_url).query) + stream = qs.get('stream', [None])[0] + if stream: + format_url = base64.b64decode(stream).decode() + if format_id in ('m3u8', 'hls'): + m3u8_formats = self._extract_m3u8_formats( + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', + m3u8_id='m3u8-%s' % protocol, fatal=False) + # Despite CODECS metadata in m3u8 all video-only formats + # are actually video+audio + for f in m3u8_formats: + if '_drm/index_' in f['url']: continue - formats.append({ - 'format_id': 'rtmp-%s' % format_id, - 'ext': 'flv', - 'url': mobj.group('url'), - 'play_path': mobj.group('playpath'), - 'app': mobj.group('app'), - 'page_url': url, - }) - else: - formats.append({ - 'url': format_url, - 'format_id': '%s-%s' % (format_id, protocol), - 'height': height, - }) + if f.get('acodec') == 'none' and f.get('vcodec') != 'none': + f['acodec'] = None + formats.append(f) + elif format_id in ('mpd', 'dash'): + formats.extend(self._extract_mpd_formats( + format_url, video_id, 'mpd-%s' % protocol, fatal=False)) + elif format_url.startswith('rtmp'): + mobj = re.search( + r'^(?P<url>rtmp://[^/]+/(?P<app>.+?))/(?P<playpath>mp4:.+)$', + format_url) + if not mobj: + return + formats.append({ + 'format_id': 'rtmp-%s' % format_id, + 'ext': 'flv', + 'url': mobj.group('url'), + 'play_path': mobj.group('playpath'), + 'app': mobj.group('app'), + 'page_url': url, + }) + else: + formats.append({ + 'url': format_url, + 'format_id': '%s-%s' % (format_id, protocol), + 'height': int_or_none(self._search_regex( + r'^(\d+)[pP]$', format_id, 'height', default=None)), + }) + + for format_id, format_dict in (resp.get('streams') or {}).items(): + add_format(format_id, format_dict) + if not formats: + streams = self._call_api( + 'videos/%s/streams.json' % video_id, video_id, + 'Downloading video streams JSON') + + if 'external' in streams: + result.update({ + '_type': 'url_transparent', + 'url': streams['external']['url'], + }) + return result + + for format_id, stream_dict in streams.items(): + for protocol, format_dict in stream_dict.items(): + add_format(format_id, format_dict, protocol) self._sort_formats(formats) result['formats'] = formats diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 421795b94..4c55946f1 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -922,7 +922,7 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): }] _PAGE_SIZE = 100 - def _fetch_page(self, album_id, authorizaion, hashed_pass, page): + def _fetch_page(self, album_id, authorization, hashed_pass, page): api_page = page + 1 query = { 'fields': 'link,uri', @@ -934,7 +934,7 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): videos = self._download_json( 'https://api.vimeo.com/albums/%s/videos' % album_id, album_id, 'Downloading page %d' % api_page, query=query, headers={ - 'Authorization': 'jwt ' + authorizaion, + 'Authorization': 'jwt ' + authorization, })['data'] for video in videos: link = video.get('link') @@ -946,10 +946,13 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): def _real_extract(self, url): album_id = self._match_id(url) - webpage = self._download_webpage(url, album_id) - viewer = self._parse_json(self._search_regex( - r'bootstrap_data\s*=\s*({.+?})</script>', - webpage, 'bootstrap data'), album_id)['viewer'] + viewer = self._download_json( + 'https://vimeo.com/_rv/viewer', album_id, fatal=False) + if not viewer: + webpage = self._download_webpage(url, album_id) + viewer = self._parse_json(self._search_regex( + r'bootstrap_data\s*=\s*({.+?})</script>', + webpage, 'bootstrap data'), album_id)['viewer'] jwt = viewer['jwt'] album = self._download_json( 'https://api.vimeo.com/albums/' + album_id, diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index f79531e6f..df1dc78dd 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -1,25 +1,30 @@ # coding: utf-8 from __future__ import unicode_literals -import re -import time import itertools +import json -from .common import InfoExtractor from .naver import NaverBaseIE -from ..compat import compat_str +from ..compat import ( + compat_HTTPError, + compat_str, +) from ..utils import ( ExtractorError, + int_or_none, merge_dicts, - remove_start, try_get, urlencode_postdata, ) -class VLiveIE(NaverBaseIE): +class VLiveBaseIE(NaverBaseIE): + _APP_ID = '8c6cc7b45d2568fb668be6e05b6e5a3b' + + +class VLiveIE(VLiveBaseIE): IE_NAME = 'vlive' - _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/(?:video|embed)/(?P<id>[0-9]+)' _NETRC_MACHINE = 'vlive' _TESTS = [{ 'url': 'http://www.vlive.tv/video/1326', @@ -27,7 +32,7 @@ class VLiveIE(NaverBaseIE): 'info_dict': { 'id': '1326', 'ext': 'mp4', - 'title': "[V LIVE] Girl's Day's Broadcast", + 'title': "Girl's Day's Broadcast", 'creator': "Girl's Day", 'view_count': int, 'uploader_id': 'muploader_a', @@ -37,7 +42,7 @@ class VLiveIE(NaverBaseIE): 'info_dict': { 'id': '16937', 'ext': 'mp4', - 'title': '[V LIVE] 첸백시 걍방', + 'title': '첸백시 걍방', 'creator': 'EXO', 'view_count': int, 'subtitles': 'mincount:12', @@ -58,12 +63,11 @@ class VLiveIE(NaverBaseIE): 'subtitles': 'mincount:10', }, 'skip': 'This video is only available for CH+ subscribers', + }, { + 'url': 'https://www.vlive.tv/embed/1326', + 'only_matching': True, }] - @classmethod - def suitable(cls, url): - return False if VLivePlaylistIE.suitable(url) else super(VLiveIE, cls).suitable(url) - def _real_initialize(self): self._login() @@ -95,173 +99,122 @@ class VLiveIE(NaverBaseIE): if not is_logged_in(): raise ExtractorError('Unable to log in', expected=True) + def _call_api(self, path_template, video_id, fields=None): + query = {'appId': self._APP_ID} + if fields: + query['fields'] = fields + return self._download_json( + 'https://www.vlive.tv/globalv-web/vam-web/' + path_template % video_id, video_id, + 'Downloading %s JSON metadata' % path_template.split('/')[-1].split('-')[0], + headers={'Referer': 'https://www.vlive.tv/'}, query=query) + def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'https://www.vlive.tv/video/%s' % video_id, video_id) + try: + post = self._call_api( + 'post/v1.0/officialVideoPost-%s', video_id, + 'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId}') + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self.raise_login_required(json.loads(e.cause.read().decode())['message']) + raise - VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)' - VIDEO_PARAMS_FIELD = 'video params' + video = post['officialVideo'] - params = self._parse_json(self._search_regex( - VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD, default=''), video_id, - transform_source=lambda s: '[' + s + ']', fatal=False) + def get_common_fields(): + channel = post.get('channel') or {} + return { + 'title': video.get('title'), + 'creator': post.get('author', {}).get('nickname'), + 'channel': channel.get('channelName'), + 'channel_id': channel.get('channelCode'), + 'duration': int_or_none(video.get('playTime')), + 'view_count': int_or_none(video.get('playCount')), + 'like_count': int_or_none(video.get('likeCount')), + 'comment_count': int_or_none(video.get('commentCount')), + } - if not params or len(params) < 7: - params = self._search_regex( - VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD) - params = [p.strip(r'"') for p in re.split(r'\s*,\s*', params)] - - status, long_video_id, key = params[2], params[5], params[6] - status = remove_start(status, 'PRODUCT_') - - if status in ('LIVE_ON_AIR', 'BIG_EVENT_ON_AIR'): - return self._live(video_id, webpage) - elif status in ('VOD_ON_AIR', 'BIG_EVENT_INTRO'): - return self._replay(video_id, webpage, long_video_id, key) - - if status == 'LIVE_END': - raise ExtractorError('Uploading for replay. Please wait...', - expected=True) - elif status == 'COMING_SOON': - raise ExtractorError('Coming soon!', expected=True) - elif status == 'CANCELED': - raise ExtractorError('We are sorry, ' - 'but the live broadcast has been canceled.', - expected=True) - elif status == 'ONLY_APP': - raise ExtractorError('Unsupported video type', expected=True) - else: - raise ExtractorError('Unknown status %s' % status) - - def _get_common_fields(self, webpage): - title = self._og_search_title(webpage) - creator = self._html_search_regex( - r'<div[^>]+class="info_area"[^>]*>\s*(?:<em[^>]*>.*?</em\s*>\s*)?<a\s+[^>]*>([^<]+)', - webpage, 'creator', fatal=False) - thumbnail = self._og_search_thumbnail(webpage) - return { - 'title': title, - 'creator': creator, - 'thumbnail': thumbnail, - } - - def _live(self, video_id, webpage): - init_page = self._download_init_page(video_id) - - live_params = self._search_regex( - r'"liveStreamInfo"\s*:\s*(".*"),', - init_page, 'live stream info') - live_params = self._parse_json(live_params, video_id) - live_params = self._parse_json(live_params, video_id) - - formats = [] - for vid in live_params.get('resolutions', []): - formats.extend(self._extract_m3u8_formats( - vid['cdnUrl'], video_id, 'mp4', - m3u8_id=vid.get('name'), - fatal=False, live=True)) - self._sort_formats(formats) - - info = self._get_common_fields(webpage) - info.update({ - 'title': self._live_title(info['title']), - 'id': video_id, - 'formats': formats, - 'is_live': True, - }) - return info - - def _replay(self, video_id, webpage, long_video_id, key): - if '' in (long_video_id, key): - init_page = self._download_init_page(video_id) - video_info = self._parse_json(self._search_regex( - (r'(?s)oVideoStatus\s*=\s*({.+?})\s*</script', - r'(?s)oVideoStatus\s*=\s*({.+})'), init_page, 'video info'), - video_id) - if video_info.get('status') == 'NEED_CHANNEL_PLUS': - self.raise_login_required( - 'This video is only available for CH+ subscribers') - long_video_id, key = video_info['vid'], video_info['inkey'] - - 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( - 'https://www.vlive.tv/video/init/view', - video_id, note='Downloading live webpage', - data=urlencode_postdata({'videoSeq': video_id}), - headers={ - 'Referer': 'https://www.vlive.tv/video/%s' % video_id, - 'Content-Type': 'application/x-www-form-urlencoded' - }) + video_type = video.get('type') + if video_type == 'VOD': + inkey = self._call_api('video/v1.0/vod/%s/inkey', video_id)['inkey'] + vod_id = video['vodId'] + return merge_dicts( + get_common_fields(), + self._extract_video_info(video_id, vod_id, inkey)) + elif video_type == 'LIVE': + status = video.get('status') + if status == 'ON_AIR': + stream_url = self._call_api( + 'old/v3/live/%s/playInfo', + video_id)['result']['adaptiveStreamUrl'] + formats = self._extract_m3u8_formats(stream_url, video_id, 'mp4') + info = get_common_fields() + info.update({ + 'title': self._live_title(video['title']), + 'id': video_id, + 'formats': formats, + 'is_live': True, + }) + return info + elif status == 'ENDED': + raise ExtractorError( + 'Uploading for replay. Please wait...', expected=True) + elif status == 'RESERVED': + raise ExtractorError('Coming soon!', expected=True) + elif video.get('exposeStatus') == 'CANCEL': + raise ExtractorError( + 'We are sorry, but the live broadcast has been canceled.', + expected=True) + else: + raise ExtractorError('Unknown status ' + status) -class VLiveChannelIE(InfoExtractor): +class VLiveChannelIE(VLiveBaseIE): IE_NAME = 'vlive:channel' - _VALID_URL = r'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)' - _TEST = { + _VALID_URL = r'https?://(?:channels\.vlive\.tv|(?:(?:www|m)\.)?vlive\.tv/channel)/(?P<id>[0-9A-Z]+)' + _TESTS = [{ 'url': 'http://channels.vlive.tv/FCD4B', 'info_dict': { 'id': 'FCD4B', 'title': 'MAMAMOO', }, 'playlist_mincount': 110 - } - _APP_ID = '8c6cc7b45d2568fb668be6e05b6e5a3b' + }, { + 'url': 'https://www.vlive.tv/channel/FCD4B', + 'only_matching': True, + }] + + def _call_api(self, path, channel_key_suffix, channel_value, note, query): + q = { + 'app_id': self._APP_ID, + 'channel' + channel_key_suffix: channel_value, + } + q.update(query) + return self._download_json( + 'http://api.vfan.vlive.tv/vproxy/channelplus/' + path, + channel_value, note='Downloading ' + note, query=q)['result'] def _real_extract(self, url): channel_code = self._match_id(url) - webpage = self._download_webpage( - 'http://channels.vlive.tv/%s/video' % channel_code, channel_code) + channel_seq = self._call_api( + 'decodeChannelCode', 'Code', channel_code, + 'decode channel code', {})['channelSeq'] - app_id = None - - app_js_url = self._search_regex( - r'<script[^>]+src=(["\'])(?P<url>http.+?/app\.js.*?)\1', - webpage, 'app js', default=None, group='url') - - if app_js_url: - app_js = self._download_webpage( - app_js_url, channel_code, 'Downloading app JS', fatal=False) - if app_js: - app_id = self._search_regex( - r'Global\.VFAN_APP_ID\s*=\s*[\'"]([^\'"]+)[\'"]', - app_js, 'app id', default=None) - - app_id = app_id or self._APP_ID - - channel_info = self._download_json( - 'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode', - channel_code, note='Downloading decode channel code', - query={ - 'app_id': app_id, - 'channelCode': channel_code, - '_': int(time.time()) - }) - - channel_seq = channel_info['result']['channelSeq'] channel_name = None entries = [] for page_num in itertools.count(1): - video_list = self._download_json( - 'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList', - channel_code, note='Downloading channel list page #%d' % page_num, - query={ - 'app_id': app_id, - 'channelSeq': channel_seq, + video_list = self._call_api( + 'getChannelVideoList', 'Seq', channel_seq, + 'channel list page #%d' % page_num, { # Large values of maxNumOfRows (~300 or above) may cause # empty responses (see [1]), e.g. this happens for [2] that # has more than 300 videos. # 1. https://github.com/ytdl-org/youtube-dl/issues/13830 # 2. http://channels.vlive.tv/EDBF. 'maxNumOfRows': 100, - '_': int(time.time()), 'pageNo': page_num } ) @@ -269,11 +222,11 @@ class VLiveChannelIE(InfoExtractor): if not channel_name: channel_name = try_get( video_list, - lambda x: x['result']['channelInfo']['channelName'], + lambda x: x['channelInfo']['channelName'], compat_str) videos = try_get( - video_list, lambda x: x['result']['videoList'], list) + video_list, lambda x: x['videoList'], list) if not videos: break @@ -289,79 +242,3 @@ class VLiveChannelIE(InfoExtractor): return self.playlist_result( entries, channel_code, channel_name) - - -class VLivePlaylistIE(InfoExtractor): - IE_NAME = 'vlive:playlist' - _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)' - _VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s' - _TESTS = [{ - # regular working playlist - 'url': 'https://www.vlive.tv/video/117956/playlist/117963', - 'info_dict': { - 'id': '117963', - 'title': '아이돌룸(IDOL ROOM) 41회 - (여자)아이들' - }, - 'playlist_mincount': 10 - }, { - # playlist with no playlistVideoSeqs - 'url': 'http://www.vlive.tv/video/22867/playlist/22912', - 'info_dict': { - 'id': '22867', - 'ext': 'mp4', - 'title': '[V LIVE] Valentine Day Message from MINA', - 'creator': 'TWICE', - 'view_count': int - }, - 'params': { - 'skip_download': True, - } - }] - - def _build_video_result(self, video_id, message): - self.to_screen(message) - return self.url_result( - self._VIDEO_URL_TEMPLATE % video_id, - ie=VLiveIE.ie_key(), video_id=video_id) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id, playlist_id = mobj.group('video_id', 'id') - - if self._downloader.params.get('noplaylist'): - return self._build_video_result( - video_id, - 'Downloading just video %s because of --no-playlist' - % video_id) - - self.to_screen( - 'Downloading playlist %s - add --no-playlist to just download video' - % playlist_id) - - webpage = self._download_webpage( - 'http://www.vlive.tv/video/%s/playlist/%s' - % (video_id, playlist_id), playlist_id) - - raw_item_ids = self._search_regex( - r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage, - 'playlist video seqs', default=None, fatal=False) - - if not raw_item_ids: - return self._build_video_result( - video_id, - 'Downloading just video %s because no playlist was found' - % video_id) - - item_ids = self._parse_json(raw_item_ids, playlist_id) - - entries = [ - self.url_result( - self._VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(), - video_id=compat_str(item_id)) - for item_id in item_ids] - - playlist_name = self._html_search_regex( - r'<div[^>]+class="[^"]*multicam_playlist[^>]*>\s*<h3[^>]+>([^<]+)', - webpage, 'playlist title', fatal=False) - - return self.playlist_result(entries, playlist_id, playlist_name) diff --git a/youtube_dl/extractor/xiami.py b/youtube_dl/extractor/xiami.py index 618da8382..769aab331 100644 --- a/youtube_dl/extractor/xiami.py +++ b/youtube_dl/extractor/xiami.py @@ -54,17 +54,17 @@ class XiamiBaseIE(InfoExtractor): def _decrypt(origin): n = int(origin[0]) origin = origin[1:] - short_lenth = len(origin) // n - long_num = len(origin) - short_lenth * n + short_length = len(origin) // n + long_num = len(origin) - short_length * n l = tuple() for i in range(0, n): - length = short_lenth + length = short_length if i < long_num: length += 1 l += (origin[0:length], ) origin = origin[length:] ans = '' - for i in range(0, short_lenth + 1): + for i in range(0, short_length + 1): for j in range(0, n): if len(l[j]) > i: ans += l[j][i] diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 01b253dcb..18969058f 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -90,7 +90,7 @@ class XTubeIE(InfoExtractor): title, thumbnail, duration = [None] * 3 config = self._parse_json(self._search_regex( - r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', + r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf)', webpage, 'config', default='{}'), video_id, transform_source=js_to_json, fatal=False) if config: config = config.get('mainRoll') diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index e7fca22de..7b9feafeb 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -29,7 +29,6 @@ class YouPornIE(InfoExtractor): 'upload_date': '20101217', 'average_rating': int, 'view_count': int, - 'comment_count': int, 'categories': list, 'tags': list, 'age_limit': 18, @@ -48,7 +47,6 @@ class YouPornIE(InfoExtractor): 'upload_date': '20110418', 'average_rating': int, 'view_count': int, - 'comment_count': int, 'categories': list, 'tags': list, 'age_limit': 18, @@ -156,7 +154,8 @@ class YouPornIE(InfoExtractor): r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>', webpage, 'uploader', fatal=False) upload_date = unified_strdate(self._html_search_regex( - [r'Date\s+[Aa]dded:\s*<span>([^<]+)', + [r'UPLOADED:\s*<span>([^<]+)', + r'Date\s+[Aa]dded:\s*<span>([^<]+)', r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'], webpage, 'upload date', fatal=False)) @@ -171,7 +170,7 @@ class YouPornIE(InfoExtractor): webpage, 'view count', fatal=False, group='count')) comment_count = str_to_int(self._search_regex( r'>All [Cc]omments? \(([\d,.]+)\)', - webpage, 'comment count', fatal=False)) + webpage, 'comment count', default=None)) def extract_tag_box(regex, title): tag_box = self._search_regex(regex, webpage, title, default=None) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 02f3ab61a..2aad855c8 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -16,8 +16,6 @@ from ..jsinterp import JSInterpreter from ..swfinterp import SWFInterpreter from ..compat import ( compat_chr, - compat_HTTPError, - compat_kwargs, compat_parse_qs, compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, @@ -30,10 +28,8 @@ from ..utils import ( bool_or_none, clean_html, error_to_compat_str, - extract_attributes, ExtractorError, float_or_none, - get_element_by_attribute, get_element_by_id, int_or_none, mimetype2ext, @@ -49,9 +45,11 @@ from ..utils import ( unescapeHTML, unified_strdate, unsmuggle_url, + update_url_query, uppercase_escape, url_or_none, urlencode_postdata, + urljoin, ) @@ -68,7 +66,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # If True it will raise an error if no login info is provided _LOGIN_REQUIRED = False - _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}' + _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)' _YOUTUBE_CLIENT_HEADERS = { 'x-youtube-client-name': '1', @@ -269,13 +267,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return True - def _download_webpage_handle(self, *args, **kwargs): - query = kwargs.get('query', {}).copy() - query['disable_polymer'] = 'true' - kwargs['query'] = query - return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( - *args, **compat_kwargs(kwargs)) - def _real_initialize(self): if self._downloader is None: return @@ -283,93 +274,36 @@ class YoutubeBaseInfoExtractor(InfoExtractor): if not self._login(): return + _DEFAULT_API_DATA = { + 'context': { + 'client': { + 'clientName': 'WEB', + 'clientVersion': '2.20201021.03.00', + } + }, + } -class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): - # Extract entries from page with "Load more" button - def _entries(self, page, playlist_id): - more_widget_html = content_html = page - for page_num in itertools.count(1): - for entry in self._process_page(content_html): - yield entry + _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;' - mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) - if not mobj: - break + def _call_api(self, ep, query, video_id): + data = self._DEFAULT_API_DATA.copy() + data.update(query) - count = 0 - retries = 3 - while count <= retries: - try: - # Downloading page may result in intermittent 5xx HTTP error - # that is usually worked around with a retry - more = self._download_json( - 'https://www.youtube.com/%s' % mobj.group('more'), playlist_id, - 'Downloading page #%s%s' - % (page_num, ' (retry #%d)' % count if count else ''), - transform_source=uppercase_escape, - headers=self._YOUTUBE_CLIENT_HEADERS) - break - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): - count += 1 - if count <= retries: - continue - raise + response = self._download_json( + 'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id, + note='Downloading API JSON', errnote='Unable to download API page', + data=json.dumps(data).encode('utf8'), + headers={'content-type': 'application/json'}, + query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'}) - content_html = more['content_html'] - if not content_html.strip(): - # Some webpages show a "Load more" button but they don't - # have more videos - break - more_widget_html = more['load_more_widget_html'] + return response - -class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): - def _process_page(self, content): - for video_id, video_title in self.extract_videos_from_page(content): - yield self.url_result(video_id, 'Youtube', video_id, video_title) - - def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page): - for mobj in re.finditer(video_re, page): - # The link with index 0 is not the first video of the playlist (not sure if still actual) - if 'index' in mobj.groupdict() and mobj.group('id') == '0': - continue - video_id = mobj.group('id') - video_title = unescapeHTML( - mobj.group('title')) if 'title' in mobj.groupdict() else None - if video_title: - video_title = video_title.strip() - if video_title == '► Play all': - video_title = None - try: - idx = ids_in_page.index(video_id) - if video_title and not titles_in_page[idx]: - titles_in_page[idx] = video_title - except ValueError: - ids_in_page.append(video_id) - titles_in_page.append(video_title) - - def extract_videos_from_page(self, page): - ids_in_page = [] - titles_in_page = [] - self.extract_videos_from_page_impl( - self._VIDEO_RE, page, ids_in_page, titles_in_page) - return zip(ids_in_page, titles_in_page) - - -class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): - def _process_page(self, content): - for playlist_id in orderedSet(re.findall( - r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', - content)): - yield self.url_result( - 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') - - def _real_extract(self, url): - playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - title = self._og_search_title(webpage, fatal=False) - return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) + def _extract_yt_initial_data(self, video_id, webpage): + return self._parse_json( + self._search_regex( + (r'%s\s*\n' % self._YT_INITIAL_DATA_RE, + self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'), + video_id) class YoutubeIE(YoutubeBaseInfoExtractor): @@ -430,7 +364,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= ) )? # all until now is optional -> you can pass the naked ID - ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID + (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID (?!.*?\blist= (?: %(playlist_id)s| # combined list/video URLs are handled by the playlist IE @@ -578,48 +512,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'end_time': 9, } }, - { - 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY', - 'note': 'Test generic use_cipher_signature video (#897)', - 'info_dict': { - 'id': 'UxxajLWwzqY', - 'ext': 'mp4', - 'upload_date': '20120506', - 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', - 'alt_title': 'I Love It (feat. Charli XCX)', - 'description': 'md5:19a2f98d9032b9311e686ed039564f63', - 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', - 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', - 'iconic ep', 'iconic', 'love', 'it'], - 'duration': 180, - 'uploader': 'Icona Pop', - 'uploader_id': 'IconaPop', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', - 'creator': 'Icona Pop', - 'track': 'I Love It (feat. Charli XCX)', - 'artist': 'Icona Pop', - } - }, - { - 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', - 'note': 'Test VEVO video with age protection (#956)', - 'info_dict': { - 'id': '07FYdnEawAQ', - 'ext': 'mp4', - 'upload_date': '20130703', - 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)', - 'alt_title': 'Tunnel Vision', - 'description': 'md5:07dab3356cde4199048e4c7cd93471e1', - 'duration': 419, - 'uploader': 'justintimberlakeVEVO', - 'uploader_id': 'justintimberlakeVEVO', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', - 'creator': 'Justin Timberlake', - 'track': 'Tunnel Vision', - 'artist': 'Justin Timberlake', - 'age_limit': 18, - } - }, { 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', 'note': 'Embed-only video (#1746)', @@ -636,7 +528,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } }, { - 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY', + 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', 'note': 'Use the first video ID in the URL', 'info_dict': { 'id': 'BaW_jenozKc', @@ -695,24 +587,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'format': '141/bestaudio[ext=m4a]', }, }, - # JS player signature function name containing $ - { - 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', - 'info_dict': { - 'id': 'nfWlot6h_JM', - 'ext': 'm4a', - 'title': 'Taylor Swift - Shake It Off', - 'description': 'md5:307195cd21ff7fa352270fe884570ef0', - 'duration': 242, - 'uploader': 'TaylorSwiftVEVO', - 'uploader_id': 'TaylorSwiftVEVO', - 'upload_date': '20140818', - }, - 'params': { - 'youtube_include_dash_manifest': True, - 'format': '141/bestaudio[ext=m4a]', - }, - }, # Controversy video { 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', @@ -744,22 +618,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'age_limit': 18, }, }, - # Age-gate video with encrypted signature - { - 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', - 'info_dict': { - 'id': '6kLq3WMV1nU', - 'ext': 'mp4', - 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', - 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', - 'duration': 246, - 'uploader': 'LloydVEVO', - 'uploader_id': 'LloydVEVO', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', - 'upload_date': '20110629', - 'age_limit': 18, - }, - }, # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) # YouTube Red ad is not captured for creator { @@ -1119,10 +977,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'sJL6WA-aGkQ', 'only_matching': True, }, - { - 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', - 'only_matching': True, - }, { 'url': 'https://invidio.us/watch?v=BaW_jenozKc', 'only_matching': True, @@ -1174,73 +1028,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'skip_download': True, }, }, - { - # Youtube Music Auto-generated description - # Retrieve 'artist' field from 'Artist:' in video description - # when it is present on youtube music video - 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY', - 'info_dict': { - 'id': 'k0jLE7tTwjY', - 'ext': 'mp4', - 'title': 'Latch Feat. Sam Smith', - 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335', - 'upload_date': '20150110', - 'uploader': 'Various Artists - Topic', - 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w', - 'artist': 'Disclosure', - 'track': 'Latch Feat. Sam Smith', - 'album': 'Latch Featuring Sam Smith', - 'release_date': '20121008', - 'release_year': 2012, - }, - 'params': { - 'skip_download': True, - }, - }, - { - # Youtube Music Auto-generated description - # handle multiple artists on youtube music video - 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA', - 'info_dict': { - 'id': '74qn0eJSjpA', - 'ext': 'mp4', - 'title': 'Eastside', - 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2', - 'upload_date': '20180710', - 'uploader': 'Benny Blanco - Topic', - 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A', - 'artist': 'benny blanco, Halsey, Khalid', - 'track': 'Eastside', - 'album': 'Eastside', - 'release_date': '20180713', - 'release_year': 2018, - }, - 'params': { - 'skip_download': True, - }, - }, - { - # Youtube Music Auto-generated description - # handle youtube music video with release_year and no release_date - 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M', - 'info_dict': { - 'id': '-hcAI0g-f5M', - 'ext': 'mp4', - 'title': 'Put It On Me', - 'description': 'md5:f6422397c07c4c907c6638e1fee380a5', - 'upload_date': '20180426', - 'uploader': 'Matt Maeson - Topic', - 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ', - 'artist': 'Matt Maeson', - 'track': 'Put It On Me', - 'album': 'The Hearse', - 'release_date': None, - 'release_year': 2018, - }, - 'params': { - 'skip_download': True, - }, - }, { 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', 'only_matching': True, @@ -1281,6 +1068,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'skip_download': True, }, }, + { + # with '};' inside yt initial data (see https://github.com/ytdl-org/youtube-dl/issues/27093) + 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', + 'info_dict': { + 'id': 'CHqg6qOn4no', + 'ext': 'mp4', + 'title': 'Part 77 Sort a list of simple types in c#', + 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', + 'upload_date': '20130831', + 'uploader_id': 'kudvenkat', + 'uploader': 'kudvenkat', + }, + 'params': { + 'skip_download': True, + }, + }, ] def __init__(self, *args, **kwargs): @@ -1677,21 +1480,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_chapters_from_json(self, webpage, video_id, duration): if not webpage: return - player = self._parse_json( - self._search_regex( - r'RELATED_PLAYER_ARGS["\']\s*:\s*({.+})\s*,?\s*\n', webpage, - 'player args', default='{}'), - video_id, fatal=False) - if not player or not isinstance(player, dict): - return - watch_next_response = player.get('watch_next_response') - if not isinstance(watch_next_response, compat_str): - return - response = self._parse_json(watch_next_response, video_id, fatal=False) - if not response or not isinstance(response, dict): + data = self._extract_yt_initial_data(video_id, webpage) + if not data or not isinstance(data, dict): return chapters_list = try_get( - response, + data, lambda x: x['playerOverlays'] ['playerOverlayRenderer'] ['decoratedPlayerBarRenderer'] @@ -1891,6 +1684,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): add_dash_mpd_pr(player_response) + if not video_info and not player_response: + player_response = extract_player_response( + self._search_regex( + r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;', video_webpage, + 'initial player response', default='{}'), + video_id) + def extract_unavailable_message(): messages = [] for tag, kind in (('h1', 'message'), ('div', 'submessage')): @@ -2086,7 +1886,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if cipher: if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): - ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' + ASSETS_RE = ( + r'<script[^>]+\bsrc=("[^"]+")[^>]+\bname=["\']player_ias/base', + r'"jsUrl"\s*:\s*("[^"]+")', + r'"assets":.+?"js":\s*("[^"]+")') jsplayer_url_json = self._search_regex( ASSETS_RE, embed_webpage if age_gate else video_webpage, @@ -2220,6 +2023,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): formats.append(a_format) else: error_message = extract_unavailable_message() + if not error_message: + reason_list = try_get( + player_response, + lambda x: x['playabilityStatus']['errorScreen']['playerErrorMessageRenderer']['subreason']['runs'], + list) or [] + for reason in reason_list: + if not isinstance(reason, dict): + continue + reason_text = try_get(reason, lambda x: x['text'], compat_str) + if reason_text: + if not error_message: + error_message = '' + error_message += reason_text + if error_message: + error_message = clean_html(error_message) if not error_message: error_message = clean_html(try_get( player_response, lambda x: x['playabilityStatus']['reason'], @@ -2393,8 +2211,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_count(count_name): return str_to_int(self._search_regex( - r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' - % re.escape(count_name), + (r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' % re.escape(count_name), + r'["\']label["\']\s*:\s*["\']([\d,.]+)\s+%ss["\']' % re.escape(count_name)), video_webpage, count_name, default=None)) like_count = _extract_count('like') @@ -2561,38 +2379,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } -class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): - IE_DESC = 'YouTube.com playlists' - _VALID_URL = r"""(?x)(?: - (?:https?://)? - (?:\w+\.)? - (?: - (?: - youtube(?:kids)?\.com| - invidio\.us - ) - / - (?: - (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) - \? (?:.*?[&;])*? (?:p|a|list)= - | p/ - )| - youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= - ) - ( - (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,} - # Top tracks, they can also include dots - |(?:MC)[\w\.]* - ) - .* - | - (%(playlist_id)s) - )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} - _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' - _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?' - _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' - IE_NAME = 'youtube:playlist' +class YoutubeTabIE(YoutubeBaseInfoExtractor): + IE_DESC = 'YouTube.com tab' + _VALID_URL = r'https?://(?:\w+\.)?(?:youtube(?:kids)?\.com|invidio\.us)/(?:(?:channel|c|user)/|(?:playlist|watch)\?.*?\blist=)(?P<id>[^/?#&]+)' + IE_NAME = 'youtube:tab' + _TESTS = [{ + # playlists, multipage + 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', + 'playlist_mincount': 94, + 'info_dict': { + 'id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'title': 'Игорь Клейнер - Playlists', + 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', + }, + }, { + # playlists, multipage, different order + 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', + 'playlist_mincount': 94, + 'info_dict': { + 'id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'title': 'Игорь Клейнер - Playlists', + 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', + }, + }, { + # playlists, singlepage + 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', + 'playlist_mincount': 4, + 'info_dict': { + 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', + 'title': 'ThirstForScience - Playlists', + 'description': 'md5:609399d937ea957b0f53cbffb747a14c', + } + }, { + 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', + 'only_matching': True, + }, { + # basic, single video playlist 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', 'info_dict': { 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', @@ -2602,6 +2425,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): }, 'playlist_count': 1, }, { + # empty playlist 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', 'info_dict': { 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', @@ -2610,6 +2434,69 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'title': 'youtube-dl empty playlist', }, 'playlist_count': 0, + }, { + # Home tab + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Home', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + }, + 'playlist_mincount': 2, + }, { + # Videos tab + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Videos', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + }, + 'playlist_mincount': 975, + }, { + # Videos tab, sorted by popular + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Videos', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + }, + 'playlist_mincount': 199, + }, { + # Playlists tab + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Playlists', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + }, + 'playlist_mincount': 17, + }, { + # Community tab + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Community', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + }, + 'playlist_mincount': 18, + }, { + # Channels tab + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Channels', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + }, + 'playlist_mincount': 138, + }, { + 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, }, { 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', @@ -2617,19 +2504,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'title': '29C3: Not my department', 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', 'uploader': 'Christiaan008', - 'uploader_id': 'ChRiStIaAn008', + 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', }, 'playlist_count': 96, - }, { - 'note': 'issue #673', - 'url': 'PLBB231211A4F62143', - 'info_dict': { - 'title': '[OLD]Team Fortress 2 (Class-based LP)', - 'id': 'PLBB231211A4F62143', - 'uploader': 'Wickydoo', - 'uploader_id': 'Wickydoo', - }, - 'playlist_mincount': 26, }, { 'note': 'Large playlist', 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', @@ -2637,45 +2514,13 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'title': 'Uploads from Cauchemar', 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', 'uploader': 'Cauchemar', - 'uploader_id': 'Cauchemar89', + 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', }, - 'playlist_mincount': 799, + 'playlist_mincount': 1123, }, { - 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', - 'info_dict': { - 'title': 'YDL_safe_search', - 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', - }, - 'playlist_count': 2, - 'skip': 'This playlist is private', - }, { - 'note': 'embedded', - 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', - 'playlist_count': 4, - 'info_dict': { - 'title': 'JODA15', - 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', - 'uploader': 'milan', - 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', - } - }, { - 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', - 'playlist_mincount': 485, - 'info_dict': { - 'title': '2018 Chinese New Singles (11/6 updated)', - 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', - 'uploader': 'LBK', - 'uploader_id': 'sdragonfang', - } - }, { - 'note': 'Embedded SWF player', - 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', - 'playlist_count': 4, - 'info_dict': { - 'title': 'JODA7', - 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', - }, - 'skip': 'This playlist does not exist', + # even larger playlist, 8832 videos + 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', + 'only_matching': True, }, { 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', @@ -2683,9 +2528,22 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'title': 'Uploads from Interstellar Movie', 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', 'uploader': 'Interstellar Movie', - 'uploader_id': 'InterstellarMovie1', + 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', }, 'playlist_mincount': 21, + }, { + # https://github.com/ytdl-org/youtube-dl/issues/21844 + 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'info_dict': { + 'title': 'Data Analysis with Dr Mike Pound', + 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', + 'uploader': 'Computerphile', + }, + 'playlist_mincount': 11, + }, { + 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'only_matching': True, }, { # Playlist URL that does not actually serve a playlist 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', @@ -2710,6 +2568,526 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): }, 'skip': 'This video is not available.', 'add_ie': [YoutubeIE.ie_key()], + }, { + 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', + 'info_dict': { + 'id': '9Auq9mYxFEE', + 'ext': 'mp4', + 'title': 'Watch Sky News live', + 'uploader': 'Sky News', + 'uploader_id': 'skynews', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', + 'upload_date': '20191102', + 'description': 'md5:78de4e1c2359d0ea3ed829678e38b662', + 'categories': ['News & Politics'], + 'tags': list, + 'like_count': int, + 'dislike_count': int, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.youtube.com/user/TheYoungTurks/live', + 'info_dict': { + 'id': 'a48o2S1cPoo', + 'ext': 'mp4', + 'title': 'The Young Turks - Live Main Show', + 'uploader': 'The Young Turks', + 'uploader_id': 'TheYoungTurks', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', + 'upload_date': '20150715', + 'license': 'Standard YouTube License', + 'description': 'md5:438179573adcdff3c97ebb1ee632b891', + 'categories': ['News & Politics'], + 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], + 'like_count': int, + 'dislike_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', + 'only_matching': True, + }, + # TODO + # { + # 'url': 'https://www.youtube.com/TheYoungTurks/live', + # 'only_matching': True, + # } + ] + + def _extract_channel_id(self, webpage): + channel_id = self._html_search_meta( + 'channelId', webpage, 'channel id', default=None) + if channel_id: + return channel_id + channel_url = self._html_search_meta( + ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', + 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', + 'twitter:app:url:googleplay'), webpage, 'channel url') + return self._search_regex( + r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', + channel_url, 'channel id') + + @staticmethod + def _extract_grid_item_renderer(item): + for item_kind in ('Playlist', 'Video', 'Channel'): + renderer = item.get('grid%sRenderer' % item_kind) + if renderer: + return renderer + + def _extract_video(self, renderer): + video_id = renderer.get('videoId') + title = try_get( + renderer, + (lambda x: x['title']['runs'][0]['text'], + lambda x: x['title']['simpleText']), compat_str) + description = try_get( + renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'], + compat_str) + duration = parse_duration(try_get( + renderer, lambda x: x['lengthText']['simpleText'], compat_str)) + view_count_text = try_get( + renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or '' + view_count = str_to_int(self._search_regex( + r'^([\d,]+)', re.sub(r'\s', '', view_count_text), + 'view count', default=None)) + uploader = try_get( + renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str) + return { + '_type': 'url_transparent', + 'ie_key': YoutubeIE.ie_key(), + 'id': video_id, + 'url': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'view_count': view_count, + 'uploader': uploader, + } + + def _grid_entries(self, grid_renderer): + for item in grid_renderer['items']: + if not isinstance(item, dict): + continue + renderer = self._extract_grid_item_renderer(item) + if not isinstance(renderer, dict): + continue + title = try_get( + renderer, lambda x: x['title']['runs'][0]['text'], compat_str) + # playlist + playlist_id = renderer.get('playlistId') + if playlist_id: + yield self.url_result( + 'https://www.youtube.com/playlist?list=%s' % playlist_id, + ie=YoutubeTabIE.ie_key(), video_id=playlist_id, + video_title=title) + # video + video_id = renderer.get('videoId') + if video_id: + yield self._extract_video(renderer) + # channel + channel_id = renderer.get('channelId') + if channel_id: + title = try_get( + renderer, lambda x: x['title']['simpleText'], compat_str) + yield self.url_result( + 'https://www.youtube.com/channel/%s' % channel_id, + ie=YoutubeTabIE.ie_key(), video_title=title) + + def _shelf_entries_trimmed(self, shelf_renderer): + renderer = try_get( + shelf_renderer, lambda x: x['content']['horizontalListRenderer'], dict) + if not renderer: + return + # TODO: add support for nested playlists so each shelf is processed + # as separate playlist + # TODO: this includes only first N items + for entry in self._grid_entries(renderer): + yield entry + + def _shelf_entries(self, shelf_renderer): + ep = try_get( + shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], + compat_str) + shelf_url = urljoin('https://www.youtube.com', ep) + if not shelf_url: + return + title = try_get( + shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str) + yield self.url_result(shelf_url, video_title=title) + + def _playlist_entries(self, video_list_renderer): + for content in video_list_renderer['contents']: + if not isinstance(content, dict): + continue + renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') + if not isinstance(renderer, dict): + continue + video_id = renderer.get('videoId') + if not video_id: + continue + yield self._extract_video(renderer) + + def _video_entry(self, video_renderer): + video_id = video_renderer.get('videoId') + if video_id: + return self._extract_video(video_renderer) + + def _post_thread_entries(self, post_thread_renderer): + post_renderer = try_get( + post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) + if not post_renderer: + return + # video attachment + video_renderer = try_get( + post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) + video_id = None + if video_renderer: + entry = self._video_entry(video_renderer) + if entry: + yield entry + # inline video links + runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] + for run in runs: + if not isinstance(run, dict): + continue + ep_url = try_get( + run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) + if not ep_url: + continue + if not YoutubeIE.suitable(ep_url): + continue + ep_video_id = YoutubeIE._match_id(ep_url) + if video_id == ep_video_id: + continue + yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=video_id) + + def _post_thread_continuation_entries(self, post_thread_continuation): + contents = post_thread_continuation.get('contents') + if not isinstance(contents, list): + return + for content in contents: + renderer = content.get('backstagePostThreadRenderer') + if not isinstance(renderer, dict): + continue + for entry in self._post_thread_entries(renderer): + yield entry + + @staticmethod + def _extract_next_continuation_data(renderer): + next_continuation = try_get( + renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict) + if not next_continuation: + return + continuation = next_continuation.get('continuation') + if not continuation: + return + ctp = next_continuation.get('clickTrackingParams') + return { + 'ctoken': continuation, + 'continuation': continuation, + 'itct': ctp, + } + + @classmethod + def _extract_continuation(cls, renderer): + next_continuation = cls._extract_next_continuation_data(renderer) + if next_continuation: + return next_continuation + contents = renderer.get('contents') + if not isinstance(contents, list): + return + for content in contents: + if not isinstance(content, dict): + continue + continuation_ep = try_get( + content, lambda x: x['continuationItemRenderer']['continuationEndpoint'], + dict) + if not continuation_ep: + continue + continuation = try_get( + continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) + if not continuation: + continue + ctp = continuation_ep.get('clickTrackingParams') + if not ctp: + continue + return { + 'ctoken': continuation, + 'continuation': continuation, + 'itct': ctp, + } + + def _entries(self, tab, identity_token): + continuation = None + slr_contents = try_get(tab, lambda x: x['sectionListRenderer']['contents'], list) or [] + for slr_content in slr_contents: + if not isinstance(slr_content, dict): + continue + is_renderer = try_get(slr_content, lambda x: x['itemSectionRenderer'], dict) + if not is_renderer: + continue + isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] + for isr_content in isr_contents: + if not isinstance(isr_content, dict): + continue + renderer = isr_content.get('playlistVideoListRenderer') + if renderer: + for entry in self._playlist_entries(renderer): + yield entry + continuation = self._extract_continuation(renderer) + continue + renderer = isr_content.get('gridRenderer') + if renderer: + for entry in self._grid_entries(renderer): + yield entry + continuation = self._extract_continuation(renderer) + continue + renderer = isr_content.get('shelfRenderer') + if renderer: + for entry in self._shelf_entries(renderer): + yield entry + continue + renderer = isr_content.get('backstagePostThreadRenderer') + if renderer: + for entry in self._post_thread_entries(renderer): + yield entry + continuation = self._extract_continuation(renderer) + continue + renderer = isr_content.get('videoRenderer') + if renderer: + entry = self._video_entry(renderer) + if entry: + yield entry + + if not continuation: + continuation = self._extract_continuation(is_renderer) + + headers = { + 'x-youtube-client-name': '1', + 'x-youtube-client-version': '2.20201112.04.01', + } + if identity_token: + headers['x-youtube-identity-token'] = identity_token + + for page_num in itertools.count(1): + if not continuation: + break + browse = self._download_json( + 'https://www.youtube.com/browse_ajax', None, + 'Downloading page %d' % page_num, + headers=headers, query=continuation, fatal=False) + if not browse: + break + response = try_get(browse, lambda x: x[1]['response'], dict) + if not response: + break + + continuation_contents = try_get( + response, lambda x: x['continuationContents'], dict) + if continuation_contents: + continuation_renderer = continuation_contents.get('playlistVideoListContinuation') + if continuation_renderer: + for entry in self._playlist_entries(continuation_renderer): + yield entry + continuation = self._extract_continuation(continuation_renderer) + continue + continuation_renderer = continuation_contents.get('gridContinuation') + if continuation_renderer: + for entry in self._grid_entries(continuation_renderer): + yield entry + continuation = self._extract_continuation(continuation_renderer) + continue + continuation_renderer = continuation_contents.get('itemSectionContinuation') + if continuation_renderer: + for entry in self._post_thread_continuation_entries(continuation_renderer): + yield entry + continuation = self._extract_continuation(continuation_renderer) + continue + + continuation_items = try_get( + response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list) + if continuation_items: + continuation_item = continuation_items[0] + if not isinstance(continuation_item, dict): + continue + renderer = continuation_item.get('playlistVideoRenderer') + if renderer: + video_list_renderer = {'contents': continuation_items} + for entry in self._playlist_entries(video_list_renderer): + yield entry + continuation = self._extract_continuation(video_list_renderer) + continue + + break + + @staticmethod + def _extract_selected_tab(tabs): + for tab in tabs: + if try_get(tab, lambda x: x['tabRenderer']['selected'], bool): + return tab['tabRenderer'] + else: + raise ExtractorError('Unable to find selected tab') + + @staticmethod + def _extract_uploader(data): + uploader = {} + sidebar_renderer = try_get( + data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) + if sidebar_renderer: + for item in sidebar_renderer: + if not isinstance(item, dict): + continue + renderer = item.get('playlistSidebarSecondaryInfoRenderer') + if not isinstance(renderer, dict): + continue + owner = try_get( + renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) + if owner: + uploader['uploader'] = owner.get('text') + uploader['uploader_id'] = try_get( + owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) + uploader['uploader_url'] = urljoin( + 'https://www.youtube.com/', + try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) + return uploader + + def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token): + selected_tab = self._extract_selected_tab(tabs) + renderer = try_get( + data, lambda x: x['metadata']['channelMetadataRenderer'], dict) + if renderer: + channel_title = renderer.get('title') or item_id + tab_title = selected_tab.get('title') + title = channel_title or item_id + if tab_title: + title += ' - %s' % tab_title + description = renderer.get('description') + playlist_id = renderer.get('externalId') + renderer = try_get( + data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) + if renderer: + title = renderer.get('title') + description = None + playlist_id = item_id + playlist = self.playlist_result( + self._entries(selected_tab['content'], identity_token), + playlist_id=playlist_id, playlist_title=title, + playlist_description=description) + playlist.update(self._extract_uploader(data)) + return playlist + + def _extract_from_playlist(self, item_id, data, playlist): + title = playlist.get('title') or try_get( + data, lambda x: x['titleText']['simpleText'], compat_str) + playlist_id = playlist.get('playlistId') or item_id + return self.playlist_result( + self._playlist_entries(playlist), playlist_id=playlist_id, + playlist_title=title) + + def _real_extract(self, url): + item_id = self._match_id(url) + url = compat_urlparse.urlunparse( + compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) + # Handle both video/playlist URLs + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + video_id = qs.get('v', [None])[0] + playlist_id = qs.get('list', [None])[0] + if video_id and playlist_id: + if self._downloader.params.get('noplaylist'): + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) + return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) + self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) + webpage = self._download_webpage(url, item_id) + identity_token = self._search_regex( + r'\bID_TOKEN["\']\s*:\s/l*["\'](.+?)["\']', webpage, + 'identity token', default=None) + data = self._extract_yt_initial_data(item_id, webpage) + tabs = try_get( + data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) + if tabs: + return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token) + playlist = try_get( + data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) + if playlist: + return self._extract_from_playlist(item_id, data, playlist) + # Fallback to video extraction if no playlist alike page is recognized. + # First check for the current video then try the v attribute of URL query. + video_id = try_get( + data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'], + compat_str) or video_id + if video_id: + return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) + # Failed to recognize + raise ExtractorError('Unable to recognize tab page') + + +class YoutubePlaylistIE(InfoExtractor): + IE_DESC = 'YouTube.com playlists' + _VALID_URL = r'''(?x)(?: + (?:https?://)? + (?:\w+\.)? + (?: + (?: + youtube(?:kids)?\.com| + invidio\.us| + youtu\.be + ) + /.*?\?.*?\blist= + )? + (?P<id>%(playlist_id)s) + )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} + IE_NAME = 'youtube:playlist' + _TESTS = [{ + 'note': 'issue #673', + 'url': 'PLBB231211A4F62143', + 'info_dict': { + 'title': '[OLD]Team Fortress 2 (Class-based LP)', + 'id': 'PLBB231211A4F62143', + 'uploader': 'Wickydoo', + 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', + }, + 'playlist_mincount': 29, + }, { + 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', + 'info_dict': { + 'title': 'YDL_safe_search', + 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', + }, + 'playlist_count': 2, + 'skip': 'This playlist is private', + }, { + 'note': 'embedded', + 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'playlist_count': 4, + 'info_dict': { + 'title': 'JODA15', + 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'uploader': 'milan', + 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', + } + }, { + 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', + 'playlist_mincount': 982, + 'info_dict': { + 'title': '2018 Chinese New Singles (11/6 updated)', + 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', + 'uploader': 'LBK', + 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', + } }, { 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', 'info_dict': { @@ -2730,16 +3108,6 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'noplaylist': True, 'skip_download': True, }, - }, { - # https://github.com/ytdl-org/youtube-dl/issues/21844 - 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'info_dict': { - 'title': 'Data Analysis with Dr Mike Pound', - 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'uploader_id': 'Computerphile', - 'uploader': 'Computerphile', - }, - 'playlist_mincount': 11, }, { 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', 'only_matching': True, @@ -2750,488 +3118,136 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): # music album playlist 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', 'only_matching': True, - }, { - 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', - 'only_matching': True, - }, { - 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', - 'only_matching': True, - }] - - def _real_initialize(self): - self._login() - - def extract_videos_from_page(self, page): - ids_in_page = [] - titles_in_page = [] - - for item in re.findall( - r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page): - attrs = extract_attributes(item) - video_id = attrs['data-video-id'] - video_title = unescapeHTML(attrs.get('data-title')) - if video_title: - video_title = video_title.strip() - ids_in_page.append(video_id) - titles_in_page.append(video_title) - - # Fallback with old _VIDEO_RE - self.extract_videos_from_page_impl( - self._VIDEO_RE, page, ids_in_page, titles_in_page) - - # Relaxed fallbacks - self.extract_videos_from_page_impl( - r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page, - ids_in_page, titles_in_page) - self.extract_videos_from_page_impl( - r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page, - ids_in_page, titles_in_page) - - return zip(ids_in_page, titles_in_page) - - def _extract_mix(self, playlist_id): - # The mixes are generated from a single video - # the id of the playlist is just 'RD' + video_id - ids = [] - last_id = playlist_id[-11:] - for n in itertools.count(1): - url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id) - webpage = self._download_webpage( - url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n)) - new_ids = orderedSet(re.findall( - r'''(?xs)data-video-username=".*?".*? - href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), - webpage)) - # Fetch new pages until all the videos are repeated, it seems that - # there are always 51 unique videos. - new_ids = [_id for _id in new_ids if _id not in ids] - if not new_ids: - break - ids.extend(new_ids) - last_id = ids[-1] - - url_results = self._ids_to_results(ids) - - search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) - title_span = ( - search_title('playlist-title') - or search_title('title long-title') - or search_title('title')) - title = clean_html(title_span) - - return self.playlist_result(url_results, playlist_id, title) - - def _extract_playlist(self, playlist_id): - url = self._TEMPLATE_URL % playlist_id - page = self._download_webpage(url, playlist_id) - - # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604) - for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page): - match = match.strip() - # Check if the playlist exists or is private - mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match) - if mobj: - reason = mobj.group('reason') - message = 'This playlist %s' % reason - if 'private' in reason: - message += ', use --username or --netrc to access it' - message += '.' - raise ExtractorError(message, expected=True) - elif re.match(r'[^<]*Invalid parameters[^<]*', match): - raise ExtractorError( - 'Invalid parameters. Maybe URL is incorrect.', - expected=True) - elif re.match(r'[^<]*Choose your language[^<]*', match): - continue - else: - self.report_warning('Youtube gives an alert message: ' + match) - - playlist_title = self._html_search_regex( - r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', - page, 'title', default=None) - - _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref=' - uploader = self._html_search_regex( - r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE, - page, 'uploader', default=None) - mobj = re.search( - r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE, - page) - if mobj: - uploader_id = mobj.group('uploader_id') - uploader_url = compat_urlparse.urljoin(url, mobj.group('path')) - else: - uploader_id = uploader_url = None - - has_videos = True - - if not playlist_title: - try: - # Some playlist URLs don't actually serve a playlist (e.g. - # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4) - next(self._entries(page, playlist_id)) - except StopIteration: - has_videos = False - - playlist = self.playlist_result( - self._entries(page, playlist_id), playlist_id, playlist_title) - playlist.update({ - 'uploader': uploader, - 'uploader_id': uploader_id, - 'uploader_url': uploader_url, - }) - - return has_videos, playlist - - def _check_download_just_video(self, url, playlist_id): - # Check if it's a video-specific URL - query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - video_id = query_dict.get('v', [None])[0] or self._search_regex( - r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url, - 'video id', default=None) - if video_id: - if self._downloader.params.get('noplaylist'): - self.to_screen('Downloading just video %s because of --no-playlist' % video_id) - return video_id, self.url_result(video_id, 'Youtube', video_id=video_id) - else: - self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) - return video_id, None - return None, None - - def _real_extract(self, url): - # Extract playlist id - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) - playlist_id = mobj.group(1) or mobj.group(2) - - video_id, video = self._check_download_just_video(url, playlist_id) - if video: - return video - - if playlist_id.startswith(('RD', 'UL', 'PU')): - # Mixes require a custom extraction process - return self._extract_mix(playlist_id) - - has_videos, playlist = self._extract_playlist(playlist_id) - if has_videos or not video_id: - return playlist - - # Some playlist URLs don't actually serve a playlist (see - # https://github.com/ytdl-org/youtube-dl/issues/10537). - # Fallback to plain video extraction if there is a video id - # along with playlist id. - return self.url_result(video_id, 'Youtube', video_id=video_id) - - -class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): - IE_DESC = 'YouTube.com channels' - _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' - _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' - _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' - IE_NAME = 'youtube:channel' - _TESTS = [{ - 'note': 'paginated channel', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'playlist_mincount': 91, - 'info_dict': { - 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'Uploads from lex will', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - } - }, { - 'note': 'Age restricted channel', - # from https://www.youtube.com/user/DeusExOfficial - 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', - 'playlist_mincount': 64, - 'info_dict': { - 'id': 'UUs0ifCMCm1icqRbqhUINa0w', - 'title': 'Uploads from Deus Ex', - 'uploader': 'Deus Ex', - 'uploader_id': 'DeusExOfficial', - }, - }, { - 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', - 'only_matching': True, - }, { - 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA', - 'only_matching': True, }] @classmethod def suitable(cls, url): - return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url) - else super(YoutubeChannelIE, cls).suitable(url)) - - def _build_template_url(self, url, channel_id): - return self._TEMPLATE_URL % channel_id + return False if YoutubeTabIE.suitable(url) else super( + YoutubePlaylistIE, cls).suitable(url) def _real_extract(self, url): - channel_id = self._match_id(url) - - url = self._build_template_url(url, channel_id) - - # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) - # Workaround by extracting as a playlist if managed to obtain channel playlist URL - # otherwise fallback on channel by page extraction - channel_page = self._download_webpage( - url + '?view=57', channel_id, - 'Downloading channel page', fatal=False) - if channel_page is False: - channel_playlist_id = False - else: - channel_playlist_id = self._html_search_meta( - 'channelId', channel_page, 'channel id', default=None) - if not channel_playlist_id: - channel_url = self._html_search_meta( - ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'), - channel_page, 'channel url', default=None) - if channel_url: - channel_playlist_id = self._search_regex( - r'vnd\.youtube://user/([0-9A-Za-z_-]+)', - channel_url, 'channel id', default=None) - if channel_playlist_id and channel_playlist_id.startswith('UC'): - playlist_id = 'UU' + channel_playlist_id[2:] - return self.url_result( - compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') - - channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') - autogenerated = re.search(r'''(?x) - class="[^"]*?(?: - channel-header-autogenerated-label| - yt-channel-title-autogenerated - )[^"]*"''', channel_page) is not None - - if autogenerated: - # The videos are contained in a single page - # the ajax pages can't be used, they are empty - entries = [ - self.url_result( - video_id, 'Youtube', video_id=video_id, - video_title=video_title) - for video_id, video_title in self.extract_videos_from_page(channel_page)] - return self.playlist_result(entries, channel_id) - - try: - next(self._entries(channel_page, channel_id)) - except StopIteration: - alert_message = self._html_search_regex( - r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>', - channel_page, 'alert', default=None, group='alert') - if alert_message: - raise ExtractorError('Youtube said: %s' % alert_message, expected=True) - - return self.playlist_result(self._entries(channel_page, channel_id), channel_id) + playlist_id = self._match_id(url) + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + if not qs: + qs = {'list': playlist_id} + return self.url_result( + update_url_query('https://www.youtube.com/playlist', qs), + ie=YoutubeTabIE.ie_key(), video_id=playlist_id) -class YoutubeUserIE(YoutubeChannelIE): - IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' - _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9%-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_%-]+)' - _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos' - IE_NAME = 'youtube:user' - +class YoutubeYtUserIE(InfoExtractor): + _VALID_URL = r'ytuser:(?P<id>.+)' _TESTS = [{ - 'url': 'https://www.youtube.com/user/TheLinuxFoundation', - 'playlist_mincount': 320, - 'info_dict': { - 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', - 'title': 'Uploads from The Linux Foundation', - 'uploader': 'The Linux Foundation', - 'uploader_id': 'TheLinuxFoundation', - } - }, { - # Only available via https://www.youtube.com/c/12minuteathlete/videos - # but not https://www.youtube.com/user/12minuteathlete/videos - 'url': 'https://www.youtube.com/c/12minuteathlete/videos', - 'playlist_mincount': 249, - 'info_dict': { - 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', - 'title': 'Uploads from 12 Minute Athlete', - 'uploader': '12 Minute Athlete', - 'uploader_id': 'the12minuteathlete', - } - }, { 'url': 'ytuser:phihag', 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/c/gametrailers', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/c/Pawe%C5%82Zadro%C5%BCniak', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/gametrailers', - 'only_matching': True, - }, { - # This channel is not available, geo restricted to JP - 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos', - 'only_matching': True, - }] - - @classmethod - def suitable(cls, url): - # Don't return True if the url can be extracted with other youtube - # extractor, the regex would is too permissive and it would match. - other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls) - if any(ie.suitable(url) for ie in other_yt_ies): - return False - else: - return super(YoutubeUserIE, cls).suitable(url) - - def _build_template_url(self, url, channel_id): - mobj = re.match(self._VALID_URL, url) - return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id')) - - -class YoutubeLiveIE(YoutubeBaseInfoExtractor): - IE_DESC = 'YouTube.com live streams' - _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live' - IE_NAME = 'youtube:live' - - _TESTS = [{ - 'url': 'https://www.youtube.com/user/TheYoungTurks/live', - 'info_dict': { - 'id': 'a48o2S1cPoo', - 'ext': 'mp4', - 'title': 'The Young Turks - Live Main Show', - 'uploader': 'The Young Turks', - 'uploader_id': 'TheYoungTurks', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', - 'upload_date': '20150715', - 'license': 'Standard YouTube License', - 'description': 'md5:438179573adcdff3c97ebb1ee632b891', - 'categories': ['News & Politics'], - 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], - 'like_count': int, - 'dislike_count': int, - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/TheYoungTurks/live', - 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - base_url = mobj.group('base_url') - webpage = self._download_webpage(url, channel_id, fatal=False) - if webpage: - page_type = self._og_search_property( - 'type', webpage, 'page type', default='') - video_id = self._html_search_meta( - 'videoId', webpage, 'video id', default=None) - if page_type.startswith('video') and video_id and re.match( - r'^[0-9A-Za-z_-]{11}$', video_id): - return self.url_result(video_id, YoutubeIE.ie_key()) - return self.url_result(base_url) + user_id = self._match_id(url) + return self.url_result( + 'https://www.youtube.com/user/%s' % user_id, + ie=YoutubeTabIE.ie_key(), video_id=user_id) -class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): - IE_DESC = 'YouTube.com user/channel playlists' - _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists' - IE_NAME = 'youtube:playlists' - - _TESTS = [{ - 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', - 'playlist_mincount': 4, - 'info_dict': { - 'id': 'ThirstForScience', - 'title': 'ThirstForScience', - }, - }, { - # with "Load more" button - 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', - 'playlist_mincount': 70, - 'info_dict': { - 'id': 'igorkle1', - 'title': 'Игорь Клейнер', - }, - }, { - 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', - 'playlist_mincount': 17, - 'info_dict': { - 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', - 'title': 'Chem Player', - }, - 'skip': 'Blocked', - }, { - 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', - 'only_matching': True, - }] - - -class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor): - _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?' - - -class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor): +class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com searches' # there doesn't appear to be a real limit, for example if you search for # 'python' you get more than 8.000.000 results _MAX_RESULTS = float('inf') IE_NAME = 'youtube:search' _SEARCH_KEY = 'ytsearch' - _EXTRA_QUERY_ARGS = {} + _SEARCH_PARAMS = None _TESTS = [] + def _entries(self, query, n): + data = { + 'context': { + 'client': { + 'clientName': 'WEB', + 'clientVersion': '2.20201021.03.00', + } + }, + 'query': query, + } + if self._SEARCH_PARAMS: + data['params'] = self._SEARCH_PARAMS + total = 0 + for page_num in itertools.count(1): + search = self._download_json( + 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', + video_id='query "%s"' % query, + note='Downloading page %s' % page_num, + errnote='Unable to download API page', fatal=False, + data=json.dumps(data).encode('utf8'), + headers={'content-type': 'application/json'}) + if not search: + break + slr_contents = try_get( + search, + (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'], + lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']), + list) + if not slr_contents: + break + isr_contents = try_get( + slr_contents, + lambda x: x[0]['itemSectionRenderer']['contents'], + list) + if not isr_contents: + break + for content in isr_contents: + if not isinstance(content, dict): + continue + video = content.get('videoRenderer') + if not isinstance(video, dict): + continue + video_id = video.get('videoId') + if not video_id: + continue + title = try_get(video, lambda x: x['title']['runs'][0]['text'], compat_str) + description = try_get(video, lambda x: x['descriptionSnippet']['runs'][0]['text'], compat_str) + duration = parse_duration(try_get(video, lambda x: x['lengthText']['simpleText'], compat_str)) + view_count_text = try_get(video, lambda x: x['viewCountText']['simpleText'], compat_str) or '' + view_count = int_or_none(self._search_regex( + r'^(\d+)', re.sub(r'\s', '', view_count_text), + 'view count', default=None)) + uploader = try_get(video, lambda x: x['ownerText']['runs'][0]['text'], compat_str) + total += 1 + yield { + '_type': 'url_transparent', + 'ie_key': YoutubeIE.ie_key(), + 'id': video_id, + 'url': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'view_count': view_count, + 'uploader': uploader, + } + if total == n: + return + token = try_get( + slr_contents, + lambda x: x[1]['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'], + compat_str) + if not token: + break + data['continuation'] = token + def _get_n_results(self, query, n): """Get a specified number of results for a query""" - - videos = [] - limit = n - - url_query = { - 'search_query': query.encode('utf-8'), - } - url_query.update(self._EXTRA_QUERY_ARGS) - result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query) - - for pagenum in itertools.count(1): - data = self._download_json( - result_url, video_id='query "%s"' % query, - note='Downloading page %s' % pagenum, - errnote='Unable to download API page', - query={'spf': 'navigate'}) - html_content = data[1]['body']['content'] - - if 'class="search-message' in html_content: - raise ExtractorError( - '[youtube] No video results', expected=True) - - new_videos = list(self._process_page(html_content)) - videos += new_videos - if not new_videos or len(videos) > limit: - break - next_link = self._html_search_regex( - r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next', - html_content, 'next link', default=None) - if next_link is None: - break - result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link) - - if len(videos) > n: - videos = videos[:n] - return self.playlist_result(videos, query) + return self.playlist_result(self._entries(query, n), query) class YoutubeSearchDateIE(YoutubeSearchIE): IE_NAME = YoutubeSearchIE.IE_NAME + ':date' _SEARCH_KEY = 'ytsearchdate' IE_DESC = 'YouTube.com searches, newest videos first' - _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} + _SEARCH_PARAMS = 'CAI%3D' -class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): +r""" +class YoutubeSearchURLIE(YoutubeSearchIE): IE_DESC = 'YouTube.com search URLs' IE_NAME = 'youtube:search_url' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' @@ -3251,25 +3267,7 @@ class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): query = compat_urllib_parse_unquote_plus(mobj.group('query')) webpage = self._download_webpage(url, query) return self.playlist_result(self._process_page(webpage), playlist_title=query) - - -class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): - IE_DESC = 'YouTube.com (multi-season) shows' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)' - IE_NAME = 'youtube:show' - _TESTS = [{ - 'url': 'https://www.youtube.com/show/airdisasters', - 'playlist_mincount': 5, - 'info_dict': { - 'id': 'airdisasters', - 'title': 'Air Disasters', - } - }] - - def _real_extract(self, url): - playlist_id = self._match_id(url) - return super(YoutubeShowIE, self)._real_extract( - 'https://www.youtube.com/show/%s/playlists' % playlist_id) +""" class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): @@ -3326,37 +3324,22 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): self._entries(page), playlist_title=self._PLAYLIST_TITLE) -class YoutubeWatchLaterIE(YoutubePlaylistIE): +class YoutubeWatchLaterIE(InfoExtractor): IE_NAME = 'youtube:watchlater' IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater' + _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/watch_later|:ytwatchlater' _TESTS = [{ - 'url': 'https://www.youtube.com/playlist?list=WL', + 'url': 'https://www.youtube.com/feed/watch_later', 'only_matching': True, }, { - 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL', + 'url': ':ytwatchlater', 'only_matching': True, }] def _real_extract(self, url): - _, video = self._check_download_just_video(url, 'WL') - if video: - return video - _, playlist = self._extract_playlist('WL') - return playlist - - -class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): - IE_NAME = 'youtube:favorites' - IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?' - _LOGIN_REQUIRED = True - - def _real_extract(self, url): - webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') - playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') - return self.url_result(playlist_id, 'YoutubePlaylist') + return self.url_result( + 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 737e2810e..8cefafd79 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2458,7 +2458,7 @@ class XAttrMetadataError(YoutubeDLError): # Parsing code and msg if (self.code in (errno.ENOSPC, errno.EDQUOT) - or 'No space left' in self.msg or 'Disk quota excedded' in self.msg): + or 'No space left' in self.msg or 'Disk quota exceeded' in self.msg): self.reason = 'NO_SPACE' elif self.code == errno.E2BIG or 'Argument list too long' in self.msg: self.reason = 'VALUE_TOO_LONG' @@ -4078,7 +4078,7 @@ def js_to_json(code): v = m.group(0) if v in ('true', 'false', 'null'): return v - elif v.startswith('/*') or v.startswith('//') or v == ',': + elif v.startswith('/*') or v.startswith('//') or v.startswith('!') or v == ',': return "" if v[0] in ("'", '"'): @@ -4103,7 +4103,8 @@ def js_to_json(code): {comment}|,(?={skip}[\]}}])| (?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*| \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?| - [0-9]+(?={skip}:) + [0-9]+(?={skip}:)| + !+ '''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code) @@ -4206,10 +4207,10 @@ def parse_codecs(codecs_str): # http://tools.ietf.org/html/rfc6381 if not codecs_str: return {} - splited_codecs = list(filter(None, map( + split_codecs = list(filter(None, map( lambda str: str.strip(), codecs_str.strip().strip(',').split(',')))) vcodec, acodec = None, None - for full_codec in splited_codecs: + for full_codec in split_codecs: codec = full_codec.split('.')[0] if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01', 'theora'): if not vcodec: @@ -4220,10 +4221,10 @@ def parse_codecs(codecs_str): else: write_string('WARNING: Unknown codec %s\n' % full_codec, sys.stderr) if not vcodec and not acodec: - if len(splited_codecs) == 2: + if len(split_codecs) == 2: return { - 'vcodec': splited_codecs[0], - 'acodec': splited_codecs[1], + 'vcodec': split_codecs[0], + 'acodec': split_codecs[1], } else: return { @@ -5462,7 +5463,7 @@ def encode_base_n(num, n, table=None): def decode_packed_codes(code): mobj = re.search(PACKED_CODES_RE, code) - obfucasted_code, base, count, symbols = mobj.groups() + obfuscated_code, base, count, symbols = mobj.groups() base = int(base) count = int(count) symbols = symbols.split('|') @@ -5475,7 +5476,7 @@ def decode_packed_codes(code): return re.sub( r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)], - obfucasted_code) + obfuscated_code) def caesar(s, alphabet, shift): diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 709e5c74c..d7e901521 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.09.20' +__version__ = '2020.11.21.1'