3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
11 compat_urllib_parse_unquote,
12 compat_urllib_request,
14 compat_xml_parse_error,
32 from .brightcove import BrightcoveIE
33 from .nbc import NBCSportsVPlayerIE
34 from .ooyala import OoyalaIE
35 from .rutv import RUTVIE
36 from .tvc import TVCIE
37 from .sportbox import SportBoxEmbedIE
38 from .smotri import SmotriIE
39 from .myvi import MyviIE
40 from .condenast import CondeNastIE
41 from .udn import UDNEmbedIE
42 from .senateisvp import SenateISVPIE
43 from .bliptv import BlipTVIE
44 from .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
49 from .onionstudios import OnionStudiosIE
50 from .snagfilms import SnagFilmsEmbedIE
53 class GenericIE(InfoExtractor):
54 IE_DESC = 'Generic downloader that works on some sites'
58 # Direct link to a video
60 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
61 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
66 'upload_date': '20100513',
69 # Direct link to media delivered compressed (until Accept-Encoding is *)
71 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
72 'md5': '128c42e68b13950268b648275386fc74',
74 'id': 'FictionJunction-Parallel_Hearts',
76 'title': 'FictionJunction-Parallel_Hearts',
77 'upload_date': '20140522',
79 'expected_warnings': [
80 'URL could be a direct video link, returning it as such.'
83 # Direct download with broken HEAD
85 'url': 'http://ai-radio.org:8000/radio.opus',
92 'skip_download': True, # infinite live stream
94 'expected_warnings': [
95 r'501.*Not Implemented'
98 # Direct link with incorrect MIME type
100 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
101 'md5': '4ccbebe5f36706d85221f204d7eb5913',
103 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
104 'id': '5_Lennart_Poettering_-_Systemd',
106 'title': '5_Lennart_Poettering_-_Systemd',
107 'upload_date': '20141120',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
115 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
117 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'title': 'Zero Punctuation',
119 'description': 're:.*groundbreaking video review series.*'
121 'playlist_mincount': 11,
123 # RSS feed with enclosure
125 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
127 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
129 'upload_date': '20150228',
130 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
139 'upload_date': '20130224',
140 'uploader_id': 'TheVerge',
141 'description': 're:^Chris Ziegler takes a look at the\.*',
142 'uploader': 'The Verge',
143 'title': 'First Firefox OS phones side-by-side',
146 'skip_download': False,
150 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
151 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
153 'id': '13601338388002',
155 'uploader': 'www.hodiho.fr',
156 'title': 'R\u00e9gis plante sa Jeep',
159 # bandcamp page with custom domain
161 'add_ie': ['Bandcamp'],
162 'url': 'http://bronyrock.com/track/the-pony-mash',
166 'title': 'The Pony Mash',
167 'uploader': 'M_Pallante',
169 'skip': 'There is a limit of 200 free downloads / month for the test song',
171 # embedded brightcove video
172 # it also tests brightcove videos that need to set the 'Referer' in the
175 'add_ie': ['Brightcove'],
176 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
178 'id': '2765128793001',
180 'title': 'Le cours de bourse : l’analyse technique',
181 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
182 'uploader': 'BFM BUSINESS',
185 'skip_download': True,
189 # https://github.com/rg3/youtube-dl/issues/2253
190 'url': 'http://bcove.me/i6nfkrc3',
191 'md5': '0ba9446db037002366bab3b3eb30c88c',
193 'id': '3101154703001',
195 'title': 'Still no power',
196 'uploader': 'thestar.com',
197 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
199 'add_ie': ['Brightcove'],
202 'url': 'http://www.championat.com/video/football/v/87/87499.html',
203 'md5': 'fb973ecf6e4a78a67453647444222983',
205 'id': '3414141473001',
207 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
208 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
209 'uploader': 'Championat',
213 # https://github.com/rg3/youtube-dl/issues/3541
214 'add_ie': ['Brightcove'],
215 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
217 'id': '3866516442001',
219 'title': 'Leer mij vrouwen kennen: Aflevering 1',
220 'description': 'Leer mij vrouwen kennen: Aflevering 1',
221 'uploader': 'SBS Broadcasting',
223 'skip': 'Restricted to Netherlands',
225 'skip_download': True, # m3u8 download
230 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
231 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
233 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
235 'title': '2cc213299525360.mov', # that's what we get
237 'add_ie': ['Ooyala'],
239 # multiple ooyala embeds on SBN network websites
241 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
243 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
244 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
246 'playlist_mincount': 3,
248 'skip_download': True,
250 'add_ie': ['Ooyala'],
254 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
258 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
259 'upload_date': '20140225',
260 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
261 'uploader': 'Tested',
262 'uploader_id': 'testedcom',
264 # No need to test YoutubeIE here
266 'skip_download': True,
271 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
275 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
276 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
281 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
283 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
285 'playlist_mincount': 18,
289 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
293 'title': 'Охотское море стало целиком российским',
294 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
298 'skip_download': True,
303 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
307 'title': 'Дошкольное воспитание',
312 'url': 'http://www.vestifinance.ru/articles/25753',
315 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
320 'title': 'Госзаказ. День 3',
326 'title': 'Госзаказ. День 2',
332 'title': 'Госзаказ. День 1',
338 'skip_download': True,
343 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
345 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
347 'title': 'Ужастики, русский трейлер (2015)',
348 'thumbnail': 're:^https?://.*\.jpg$',
354 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
357 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
359 'playlist_mincount': 7,
363 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
364 'md5': '65fdff94098e4a607385a60c5177c638',
368 'title': 'Hidden miracles of the natural world',
369 'uploader': 'Louie Schwartzberg',
370 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
373 # Embeded Ustream video
375 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
376 'md5': '27b99cdb639c9b12a79bca876a073417',
380 'uploader': 'AU SPA: The NSA and Privacy',
381 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
384 # nowvideo embed hidden behind percent encoding
386 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
387 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
389 'id': '06e53103ca9aa',
391 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
392 'description': 'No description',
397 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
398 'md5': '7653032cbb25bf6c80d80f217055fa43',
400 'id': '048195-004_PLUS7-F',
403 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
404 'upload_date': '20140320',
407 'skip_download': 'Requires rtmpdump'
412 'url': 'http://www.wired.com/2014/04/honda-asimo/',
413 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
415 'id': '53501be369702d3275860000',
417 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
422 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
423 'md5': '441aeeb82eb72c422c7f14ec533999cd',
425 'id': 'k2mm4bCdJ6CQ2i7c8o2',
427 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
430 'add_ie': ['Dailymotion'],
434 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
438 'title': 'The NBL Auction 2014',
439 'uploader': 'BADMINTON England',
440 'uploader_id': 'BADMINTONEvents',
441 'upload_date': '20140603',
442 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
444 'add_ie': ['Youtube'],
446 'skip_download': True,
451 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
452 'md5': '35727f82f58c76d996fc188f9755b0d5',
454 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
457 'description': 'Mario\'s life in the fast lane has never looked so good.',
460 # YouTube embed via <data-embed-url="">
462 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
466 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
467 'uploader': 'Gameloft',
468 'uploader_id': 'gameloft',
469 'upload_date': '20140828',
470 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
473 'skip_download': True,
478 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
480 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
482 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
483 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
488 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
490 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
491 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
497 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
502 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
503 'md5': '9d65602bf31c6e20014319c7d07fba27',
505 'id': '5123ea6d5e5a7',
508 'uploader': 'www.handjobhub.com',
509 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
512 # Multiple brightcove videos
513 # https://github.com/rg3/youtube-dl/issues/2283
515 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
517 'id': 'always-never',
518 'title': 'Always / Never - The New Yorker',
522 'extract_flat': False,
523 'skip_download': True,
528 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
529 'md5': '96f09a37e44da40dd083e12d9a683327',
533 'title': 'Ump changes call to ball',
534 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
536 'timestamp': 1401537900,
537 'upload_date': '20140531',
538 'thumbnail': 're:^https?://.*\.jpg$',
543 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
544 'md5': '8788b683c777a5cf25621eaf286d0c23',
548 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
550 'filesize': 182808282,
551 'uploader': 'education-portal.com',
555 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
556 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
560 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
562 'uploader': 'thoughtworks.wistia.com',
567 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
571 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
572 'uploader': 'Sophos Security',
573 'title': 'Chet Chat 171 - Oct 29, 2014',
574 'upload_date': '20141029',
579 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
583 'upload_date': '20141112',
584 'title': 'Rosetta #CometLanding webcast HL 10',
589 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
592 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
594 'playlist_mincount': 2,
598 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
602 'upload_date': '20141126',
603 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
608 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
610 'id': '730m_DandD_1901_512k',
612 'uploader': 'www.abc.net.au',
613 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
616 # embedded viddler video
618 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
622 'uploader': 'deadspin',
623 'title': 'WALL-TO-GORTAT',
624 'timestamp': 1422285291,
625 'upload_date': '20150126',
627 'add_ie': ['Viddler'],
631 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
635 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
636 'description': 'md5:601cb790edd05908957dae8aaa866465',
637 'upload_date': '20150220',
642 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
646 'upload_date': '20150212',
647 'uploader': 'The National Archives UK',
648 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
649 'uploader_id': 'NationalArchives08',
650 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
655 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
656 'playlist_mincount': 5,
658 'id': 'aanslagen-kopenhagen',
659 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
664 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
668 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
673 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
677 'upload_date': '20150226',
678 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
680 'title': 'John Carlson Postgame 2/25/15',
683 # Kaltura embed (different embed code)
685 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
689 'upload_date': '20150127',
690 'uploader_id': 'PremierMedia',
692 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
695 # Eagle.Platform embed (generic URL)
697 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
701 'title': 'Навальный вышел на свободу',
702 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
703 'thumbnail': 're:^https?://.*\.jpg$',
709 # ClipYou (Eagle.Platform) embed (custom URL)
711 'url': 'http://muz-tv.ru/play/7129/',
715 'title': "'O Sole Mio",
716 'thumbnail': 're:^https?://.*\.jpg$',
723 'url': 'http://muz-tv.ru/kinozal/view/7400/',
727 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
728 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
729 'thumbnail': 're:^https?://.*\.jpg$',
736 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
740 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
741 'thumbnail': 're:^https?://.*\.png$',
747 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
748 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
752 'title': 'Facebook Creates "On This Day" | Crunch Report',
757 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
761 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
766 # Crooks and Liars embed
768 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
772 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
773 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
774 'timestamp': 1428207000,
775 'upload_date': '20150405',
776 'uploader': 'Heather',
779 # Crooks and Liars external embed
781 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
783 'id': 'MTE3MjUtMzQ2MzA',
785 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
786 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
787 'timestamp': 1265032391,
788 'upload_date': '20100201',
789 'uploader': 'Heather',
792 # NBC Sports vplayer embed
794 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
796 'id': 'ln7x1qSThw4k',
798 'title': "PFT Live: New leader in the 'new-look' defense",
799 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
804 'url': 'http://www.udn.com/news/story/7314/822787',
805 'md5': 'fd2060e988c326991037b9aff9df21a6',
809 'title': '中一中男師變性 全校師生力挺',
810 'thumbnail': 're:^https?://.*\.jpg$',
815 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
817 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
819 'description': 'VIDEO: Index/Match versus VLOOKUP.',
820 'title': 'This is what separates the Excel masters from the wannabes',
824 'skip_download': True,
827 # Contains a SMIL manifest
829 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
833 'title': '+ Football: Lottery Champions League Europe',
834 'uploader': 'www.telewebion.com',
838 'skip_download': True,
841 # Brightcove URL in single quotes
843 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
844 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
846 'id': '4255764656001',
848 'title': 'SN Presents: Russell Martin, World Citizen',
849 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
850 'uploader': 'Rogers Sportsnet',
853 # Dailymotion Cloud video
855 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
856 'md5': '49444254273501a64675a7e68c502681',
858 'id': '5585de919473990de4bee11b',
861 'thumbnail': 're:^https?://.*\.jpe?g$',
866 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
870 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
871 'thumbnail': 're:^https?://.*\.jpe?g$',
872 'uploader': 'ClickHole',
873 'uploader_id': 'clickhole',
878 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
880 'id': '74849a00-85a9-11e1-9660-123139220831',
882 'title': '#whilewewatch',
887 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
888 'md5': '43662b577c018ad707a63766462b1e87',
892 'title': 'New experience with Acrobat DC',
893 'description': 'New experience with Acrobat DC',
899 def report_following_redirect(self, new_url):
900 """Report information extraction."""
901 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
903 def _extract_rss(self, url, video_id, doc):
904 playlist_title = doc.find('./channel/title').text
905 playlist_desc_el = doc.find('./channel/description')
906 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
909 for it in doc.findall('./channel/item'):
910 next_url = xpath_text(it, 'link', fatal=False)
912 enclosure_nodes = it.findall('./enclosure')
913 for e in enclosure_nodes:
914 next_url = e.attrib.get('url')
924 'title': it.find('title').text,
930 'title': playlist_title,
931 'description': playlist_desc,
935 def _extract_camtasia(self, url, video_id, webpage):
936 """ Returns None if no camtasia video can be found. """
938 camtasia_cfg = self._search_regex(
939 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
940 webpage, 'camtasia configuration file', default=None)
941 if camtasia_cfg is None:
944 title = self._html_search_meta('DC.title', webpage, fatal=True)
946 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
947 camtasia_cfg = self._download_xml(
948 camtasia_url, video_id,
949 note='Downloading camtasia configuration',
950 errnote='Failed to download camtasia configuration')
951 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
954 for n in fileset_node.getchildren():
955 url_n = n.find('./uri')
960 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
961 'title': '%s - %s' % (title, n.tag),
962 'url': compat_urlparse.urljoin(url, url_n.text),
963 'duration': float_or_none(n.find('./duration').text),
972 def _real_extract(self, url):
973 if url.startswith('//'):
976 'url': self.http_scheme() + url,
979 parsed_url = compat_urlparse.urlparse(url)
980 if not parsed_url.scheme:
981 default_search = self._downloader.params.get('default_search')
982 if default_search is None:
983 default_search = 'fixup_error'
985 if default_search in ('auto', 'auto_warning', 'fixup_error'):
987 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
988 return self.url_result('http://' + url)
989 elif default_search != 'fixup_error':
990 if default_search == 'auto_warning':
991 if re.match(r'^(?:url|URL)$', url):
992 raise ExtractorError(
993 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
996 self._downloader.report_warning(
997 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
998 return self.url_result('ytsearch:' + url)
1000 if default_search in ('error', 'fixup_error'):
1001 raise ExtractorError(
1002 '%r is not a valid URL. '
1003 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1004 % (url, url), expected=True)
1006 if ':' not in default_search:
1007 default_search += ':'
1008 return self.url_result(default_search + url)
1010 url, smuggled_data = unsmuggle_url(url)
1011 force_videoid = None
1012 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1013 if smuggled_data and 'force_videoid' in smuggled_data:
1014 force_videoid = smuggled_data['force_videoid']
1015 video_id = force_videoid
1017 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1019 self.to_screen('%s: Requesting header' % video_id)
1021 head_req = HEADRequest(url)
1022 head_response = self._request_webpage(
1024 note=False, errnote='Could not send HEAD request to %s' % url,
1027 if head_response is not False:
1028 # Check for redirect
1029 new_url = head_response.geturl()
1031 self.report_following_redirect(new_url)
1033 new_url = smuggle_url(
1034 new_url, {'force_videoid': force_videoid})
1035 return self.url_result(new_url)
1037 full_response = None
1038 if head_response is False:
1039 request = compat_urllib_request.Request(url)
1040 request.add_header('Accept-Encoding', '*')
1041 full_response = self._request_webpage(request, video_id)
1042 head_response = full_response
1044 # Check for direct link to a video
1045 content_type = head_response.headers.get('Content-Type', '')
1046 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1048 upload_date = unified_strdate(
1049 head_response.headers.get('Last-Modified'))
1052 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1055 'format_id': m.group('format_id'),
1057 'vcodec': 'none' if m.group('type') == 'audio' else None
1059 'upload_date': upload_date,
1062 if not self._downloader.params.get('test', False) and not is_intentional:
1063 force = self._downloader.params.get('force_generic_extractor', False)
1064 self._downloader.report_warning(
1065 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1067 if not full_response:
1068 request = compat_urllib_request.Request(url)
1069 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1070 # making it impossible to download only chunk of the file (yet we need only 512kB to
1071 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1072 # that will always result in downloading the whole file that is not desirable.
1073 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1074 # to accept raw bytes and being able to download only a chunk.
1075 # It may probably better to solve this by checking Content-Type for application/octet-stream
1076 # after HEAD request finishes, but not sure if we can rely on this.
1077 request.add_header('Accept-Encoding', '*')
1078 full_response = self._request_webpage(request, video_id)
1080 # Maybe it's a direct link to a video?
1081 # Be careful not to download the whole thing!
1082 first_bytes = full_response.read(512)
1083 if not is_html(first_bytes):
1084 self._downloader.report_warning(
1085 'URL could be a direct video link, returning it as such.')
1086 upload_date = unified_strdate(
1087 head_response.headers.get('Last-Modified'))
1090 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1093 'upload_date': upload_date,
1096 webpage = self._webpage_read_content(
1097 full_response, url, video_id, prefix=first_bytes)
1099 self.report_extraction(video_id)
1101 # Is it an RSS feed?
1103 doc = parse_xml(webpage)
1104 if doc.tag == 'rss':
1105 return self._extract_rss(url, video_id, doc)
1106 except compat_xml_parse_error:
1109 # Is it a Camtasia project?
1110 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1111 if camtasia_res is not None:
1114 # Sometimes embedded video player is hidden behind percent encoding
1115 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1116 # Unescaping the whole page allows to handle those cases in a generic way
1117 webpage = compat_urllib_parse_unquote(webpage)
1119 # it's tempting to parse this further, but you would
1120 # have to take into account all the variations like
1121 # Video Title - Site Name
1122 # Site Name | Video Title
1123 # Video Title - Tagline | Site Name
1124 # and so on and so forth; it's just not practical
1125 video_title = self._html_search_regex(
1126 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1129 # Try to detect age limit automatically
1130 age_limit = self._rta_search(webpage)
1131 # And then there are the jokers who advertise that they use RTA,
1132 # but actually don't.
1133 AGE_LIMIT_MARKERS = [
1134 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1136 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1139 # video uploader is domain name
1140 video_uploader = self._search_regex(
1141 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1144 def _playlist_from_matches(matches, getter=None, ie=None):
1146 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1148 return self.playlist_result(
1149 urlrs, playlist_id=video_id, playlist_title=video_title)
1151 # Look for BrightCove:
1152 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1154 self.to_screen('Brightcove video detected.')
1157 'url': smuggle_url(bc_url, {'Referer': url}),
1158 'ie_key': 'Brightcove'
1159 } for bc_url in bc_urls]
1162 '_type': 'playlist',
1163 'title': video_title,
1168 # Look for embedded rtl.nl player
1169 matches = re.findall(
1170 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1173 return _playlist_from_matches(matches, ie='RtlNl')
1175 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1176 if vimeo_url is not None:
1177 return self.url_result(vimeo_url)
1179 # Look for embedded YouTube player
1180 matches = re.findall(r'''(?x)
1189 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1193 return _playlist_from_matches(
1194 matches, lambda m: unescapeHTML(m[1]))
1196 # Look for lazyYT YouTube embed
1197 matches = re.findall(
1198 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1200 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1202 # Look for embedded Dailymotion player
1203 matches = re.findall(
1204 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1206 return _playlist_from_matches(
1207 matches, lambda m: unescapeHTML(m[1]))
1209 # Look for embedded Dailymotion playlist player (#3822)
1211 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1213 playlists = re.findall(
1214 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1216 return _playlist_from_matches(
1217 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1219 # Look for embedded Wistia player
1221 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1223 embed_url = self._proto_relative_url(
1224 unescapeHTML(match.group('url')))
1226 '_type': 'url_transparent',
1229 'uploader': video_uploader,
1230 'title': video_title,
1234 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1237 '_type': 'url_transparent',
1238 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1240 'uploader': video_uploader,
1241 'title': video_title,
1242 'id': match.group('id')
1245 # Look for embedded blip.tv player
1246 bliptv_url = BlipTVIE._extract_url(webpage)
1248 return self.url_result(bliptv_url, 'BlipTV')
1250 # Look for SVT player
1251 svt_url = SVTIE._extract_url(webpage)
1253 return self.url_result(svt_url, 'SVT')
1255 # Look for embedded condenast player
1256 matches = re.findall(
1257 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1261 '_type': 'playlist',
1264 'ie_key': 'CondeNast',
1266 } for ma in matches],
1267 'title': video_title,
1271 # Look for Bandcamp pages with custom domain
1272 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1273 if mobj is not None:
1274 burl = unescapeHTML(mobj.group(1))
1275 # Don't set the extractor because it can be a track url or an album
1276 return self.url_result(burl)
1278 # Look for embedded Vevo player
1280 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1281 if mobj is not None:
1282 return self.url_result(mobj.group('url'))
1284 # Look for embedded Viddler player
1286 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1288 if mobj is not None:
1289 return self.url_result(mobj.group('url'))
1291 # Look for NYTimes player
1293 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1295 if mobj is not None:
1296 return self.url_result(mobj.group('url'))
1298 # Look for Libsyn player
1300 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1301 if mobj is not None:
1302 return self.url_result(mobj.group('url'))
1304 # Look for Ooyala videos
1305 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1306 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1307 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1308 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1309 if mobj is not None:
1310 return OoyalaIE._build_url_result(mobj.group('ec'))
1312 # Look for multiple Ooyala embeds on SBN network websites
1313 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1314 if mobj is not None:
1315 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1317 return _playlist_from_matches(
1318 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1320 # Look for Aparat videos
1321 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1322 if mobj is not None:
1323 return self.url_result(mobj.group(1), 'Aparat')
1325 # Look for MPORA videos
1326 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1327 if mobj is not None:
1328 return self.url_result(mobj.group(1), 'Mpora')
1330 # Look for embedded NovaMov-based player
1332 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1333 (?P<url>http://(?:(?:embed|www)\.)?
1335 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1336 videoweed\.(?:es|com)|
1337 movshare\.(?:net|sx|ag)|
1338 divxstage\.(?:eu|net|ch|co|at|ag))
1339 /embed\.php.+?)\1''', webpage)
1340 if mobj is not None:
1341 return self.url_result(mobj.group('url'))
1343 # Look for embedded Facebook player
1345 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1346 if mobj is not None:
1347 return self.url_result(mobj.group('url'), 'Facebook')
1349 # Look for embedded VK player
1350 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1351 if mobj is not None:
1352 return self.url_result(mobj.group('url'), 'VK')
1354 # Look for embedded ivi player
1355 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1356 if mobj is not None:
1357 return self.url_result(mobj.group('url'), 'Ivi')
1359 # Look for embedded Huffington Post player
1361 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1362 if mobj is not None:
1363 return self.url_result(mobj.group('url'), 'HuffPost')
1366 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1367 if mobj is not None:
1368 return self.url_result(mobj.group('url'))
1369 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1370 if mobj is not None:
1371 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1373 # Look for funnyordie embed
1374 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1376 return _playlist_from_matches(
1377 matches, getter=unescapeHTML, ie='FunnyOrDie')
1379 # Look for BBC iPlayer embed
1380 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1382 return _playlist_from_matches(matches, ie='BBCCoUk')
1384 # Look for embedded RUTV player
1385 rutv_url = RUTVIE._extract_url(webpage)
1387 return self.url_result(rutv_url, 'RUTV')
1389 # Look for embedded TVC player
1390 tvc_url = TVCIE._extract_url(webpage)
1392 return self.url_result(tvc_url, 'TVC')
1394 # Look for embedded SportBox player
1395 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1397 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1399 # Look for embedded PornHub player
1400 pornhub_url = PornHubIE._extract_url(webpage)
1402 return self.url_result(pornhub_url, 'PornHub')
1404 # Look for embedded XHamster player
1405 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1407 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1409 # Look for embedded Tvigle player
1411 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1412 if mobj is not None:
1413 return self.url_result(mobj.group('url'), 'Tvigle')
1415 # Look for embedded TED player
1417 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1418 if mobj is not None:
1419 return self.url_result(mobj.group('url'), 'TED')
1421 # Look for embedded Ustream videos
1423 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1424 if mobj is not None:
1425 return self.url_result(mobj.group('url'), 'Ustream')
1427 # Look for embedded arte.tv player
1429 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1431 if mobj is not None:
1432 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1434 # Look for embedded smotri.com player
1435 smotri_url = SmotriIE._extract_url(webpage)
1437 return self.url_result(smotri_url, 'Smotri')
1439 # Look for embedded Myvi.ru player
1440 myvi_url = MyviIE._extract_url(webpage)
1442 return self.url_result(myvi_url)
1444 # Look for embeded soundcloud player
1446 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1448 if mobj is not None:
1449 url = unescapeHTML(mobj.group('url'))
1450 return self.url_result(url)
1452 # Look for embedded vulture.com player
1454 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1456 if mobj is not None:
1457 url = unescapeHTML(mobj.group('url'))
1458 return self.url_result(url, ie='Vulture')
1460 # Look for embedded mtvservices player
1462 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1464 if mobj is not None:
1465 url = unescapeHTML(mobj.group('url'))
1466 return self.url_result(url, ie='MTVServicesEmbedded')
1468 # Look for embedded yahoo player
1470 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1472 if mobj is not None:
1473 return self.url_result(mobj.group('url'), 'Yahoo')
1475 # Look for embedded sbs.com.au player
1479 <meta\s+property="og:video"\s+content=|
1482 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1484 if mobj is not None:
1485 return self.url_result(mobj.group('url'), 'SBS')
1487 # Look for embedded Cinchcast player
1489 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1491 if mobj is not None:
1492 return self.url_result(mobj.group('url'), 'Cinchcast')
1495 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1499 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1501 if mobj is not None:
1502 return self.url_result(mobj.group('url'), 'MLB')
1505 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1507 if mobj is not None:
1508 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1511 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1513 if mobj is not None:
1514 return self.url_result(mobj.group('url'), 'Livestream')
1516 # Look for Zapiks embed
1518 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1519 if mobj is not None:
1520 return self.url_result(mobj.group('url'), 'Zapiks')
1522 # Look for Kaltura embeds
1523 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1524 re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
1525 if mobj is not None:
1526 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1528 # Look for Eagle.Platform embeds
1530 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1531 if mobj is not None:
1532 return self.url_result(mobj.group('url'), 'EaglePlatform')
1534 # Look for ClipYou (uses Eagle.Platform) embeds
1536 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1537 if mobj is not None:
1538 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1540 # Look for Pladform embeds
1542 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1543 if mobj is not None:
1544 return self.url_result(mobj.group('url'), 'Pladform')
1546 # Look for Playwire embeds
1548 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1549 if mobj is not None:
1550 return self.url_result(mobj.group('url'))
1552 # Look for 5min embeds
1554 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1555 if mobj is not None:
1556 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1558 # Look for Crooks and Liars embeds
1560 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1561 if mobj is not None:
1562 return self.url_result(mobj.group('url'))
1564 # Look for NBC Sports VPlayer embeds
1565 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1567 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1569 # Look for UDN embeds
1571 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1572 if mobj is not None:
1573 return self.url_result(
1574 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1576 # Look for Senate ISVP iframe
1577 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1579 return self.url_result(senate_isvp_url, 'SenateISVP')
1581 # Look for Dailymotion Cloud videos
1582 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1584 return self.url_result(dmcloud_url, 'DailymotionCloud')
1586 # Look for OnionStudios embeds
1587 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1588 if onionstudios_url:
1589 return self.url_result(onionstudios_url)
1591 # Look for SnagFilms embeds
1592 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1594 return self.url_result(snagfilms_url)
1596 # Look for AdobeTVVideo embeds
1598 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1600 if mobj is not None:
1601 return self.url_result(
1602 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1605 def check_video(vurl):
1606 if YoutubeIE.suitable(vurl):
1608 vpath = compat_urlparse.urlparse(vurl).path
1609 vext = determine_ext(vpath)
1610 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1612 def filter_video(urls):
1613 return list(filter(check_video, urls))
1615 # Start with something easy: JW Player in SWFObject
1616 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1618 # Look for gorilla-vid style embedding
1619 found = filter_video(re.findall(r'''(?sx)
1623 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1626 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1628 # Broaden the search a little bit
1629 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1631 # Broaden the findall a little bit: JWPlayer JS loader
1632 found = filter_video(re.findall(
1633 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1636 found = filter_video(re.findall(r'''(?xs)
1637 flowplayer\("[^"]+",\s*
1639 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1640 ["']?url["']?\s*:\s*["']([^"']+)["']
1645 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1647 # Try to find twitter cards info
1648 found = filter_video(re.findall(
1649 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1651 # We look for Open Graph info:
1652 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1653 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1654 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1655 if m_video_type is not None:
1656 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1659 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1661 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1663 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1664 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1667 # Look also in Refresh HTTP header
1668 refresh_header = head_response.headers.get('Refresh')
1670 found = re.search(REDIRECT_REGEX, refresh_header)
1672 new_url = compat_urlparse.urljoin(url, found.group(1))
1673 self.report_following_redirect(new_url)
1679 raise UnsupportedError(url)
1682 for video_url in found:
1683 video_url = compat_urlparse.urljoin(url, video_url)
1684 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1686 # Sometimes, jwplayer extraction will result in a YouTube URL
1687 if YoutubeIE.suitable(video_url):
1688 entries.append(self.url_result(video_url, 'Youtube'))
1691 # here's a fun little line of code for you:
1692 video_id = os.path.splitext(video_id)[0]
1694 if determine_ext(video_url) == 'smil':
1697 'formats': self._extract_smil_formats(video_url, video_id),
1698 'uploader': video_uploader,
1699 'title': video_title,
1700 'age_limit': age_limit,
1706 'uploader': video_uploader,
1707 'title': video_title,
1708 'age_limit': age_limit,
1711 if len(entries) == 1:
1714 for num, e in enumerate(entries, start=1):
1715 # 'url' results don't have a title
1716 if e.get('title') is not None:
1717 e['title'] = '%s (%d)' % (e['title'], num)
1719 '_type': 'playlist',