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.tsprod.com/replay-du-concert-alcaline-de-calogero',
416 'title': 'Alcaline, le concert avec Calogero',
417 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
418 'upload_date': '20150226',
419 'timestamp': 1424989860,
424 'skip_download': True,
426 'expected_warnings': [
432 'url': 'http://www.wired.com/2014/04/honda-asimo/',
433 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
435 'id': '53501be369702d3275860000',
437 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
442 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
443 'md5': '441aeeb82eb72c422c7f14ec533999cd',
445 'id': 'k2mm4bCdJ6CQ2i7c8o2',
447 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
450 'add_ie': ['Dailymotion'],
454 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
458 'title': 'The NBL Auction 2014',
459 'uploader': 'BADMINTON England',
460 'uploader_id': 'BADMINTONEvents',
461 'upload_date': '20140603',
462 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
464 'add_ie': ['Youtube'],
466 'skip_download': True,
471 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
472 'md5': '35727f82f58c76d996fc188f9755b0d5',
474 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
477 'description': 'Mario\'s life in the fast lane has never looked so good.',
480 # YouTube embed via <data-embed-url="">
482 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
486 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
487 'uploader': 'Gameloft',
488 'uploader_id': 'gameloft',
489 'upload_date': '20140828',
490 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
493 'skip_download': True,
498 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
500 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
502 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
503 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
508 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
510 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
511 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
517 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
522 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
523 'md5': '9d65602bf31c6e20014319c7d07fba27',
525 'id': '5123ea6d5e5a7',
528 'uploader': 'www.handjobhub.com',
529 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
532 # Multiple brightcove videos
533 # https://github.com/rg3/youtube-dl/issues/2283
535 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
537 'id': 'always-never',
538 'title': 'Always / Never - The New Yorker',
542 'extract_flat': False,
543 'skip_download': True,
548 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
549 'md5': '96f09a37e44da40dd083e12d9a683327',
553 'title': 'Ump changes call to ball',
554 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
556 'timestamp': 1401537900,
557 'upload_date': '20140531',
558 'thumbnail': 're:^https?://.*\.jpg$',
563 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
564 'md5': '8788b683c777a5cf25621eaf286d0c23',
568 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
570 'filesize': 182808282,
571 'uploader': 'education-portal.com',
575 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
576 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
580 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
582 'uploader': 'thoughtworks.wistia.com',
587 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
591 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
592 'uploader': 'Sophos Security',
593 'title': 'Chet Chat 171 - Oct 29, 2014',
594 'upload_date': '20141029',
599 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
603 'upload_date': '20141112',
604 'title': 'Rosetta #CometLanding webcast HL 10',
609 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
612 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
614 'playlist_mincount': 2,
618 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
622 'upload_date': '20141126',
623 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
628 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
630 'id': '730m_DandD_1901_512k',
632 'uploader': 'www.abc.net.au',
633 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
636 # embedded viddler video
638 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
642 'uploader': 'deadspin',
643 'title': 'WALL-TO-GORTAT',
644 'timestamp': 1422285291,
645 'upload_date': '20150126',
647 'add_ie': ['Viddler'],
651 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
655 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
656 'description': 'md5:601cb790edd05908957dae8aaa866465',
657 'upload_date': '20150220',
662 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
666 'upload_date': '20150212',
667 'uploader': 'The National Archives UK',
668 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
669 'uploader_id': 'NationalArchives08',
670 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
675 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
676 'playlist_mincount': 5,
678 'id': 'aanslagen-kopenhagen',
679 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
684 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
688 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
693 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
697 'upload_date': '20150226',
698 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
700 'title': 'John Carlson Postgame 2/25/15',
703 # Kaltura embed (different embed code)
705 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
709 'upload_date': '20150127',
710 'uploader_id': 'PremierMedia',
712 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
715 # Eagle.Platform embed (generic URL)
717 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
721 'title': 'Навальный вышел на свободу',
722 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
723 'thumbnail': 're:^https?://.*\.jpg$',
729 # ClipYou (Eagle.Platform) embed (custom URL)
731 'url': 'http://muz-tv.ru/play/7129/',
735 'title': "'O Sole Mio",
736 'thumbnail': 're:^https?://.*\.jpg$',
743 'url': 'http://muz-tv.ru/kinozal/view/7400/',
747 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
748 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
749 'thumbnail': 're:^https?://.*\.jpg$',
756 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
760 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
761 'thumbnail': 're:^https?://.*\.png$',
767 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
768 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
772 'title': 'Facebook Creates "On This Day" | Crunch Report',
777 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
781 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
786 # Crooks and Liars embed
788 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
792 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
793 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
794 'timestamp': 1428207000,
795 'upload_date': '20150405',
796 'uploader': 'Heather',
799 # Crooks and Liars external embed
801 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
803 'id': 'MTE3MjUtMzQ2MzA',
805 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
806 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
807 'timestamp': 1265032391,
808 'upload_date': '20100201',
809 'uploader': 'Heather',
812 # NBC Sports vplayer embed
814 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
816 'id': 'ln7x1qSThw4k',
818 'title': "PFT Live: New leader in the 'new-look' defense",
819 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
824 'url': 'http://www.udn.com/news/story/7314/822787',
825 'md5': 'fd2060e988c326991037b9aff9df21a6',
829 'title': '中一中男師變性 全校師生力挺',
830 'thumbnail': 're:^https?://.*\.jpg$',
835 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
837 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
839 'description': 'VIDEO: Index/Match versus VLOOKUP.',
840 'title': 'This is what separates the Excel masters from the wannabes',
844 'skip_download': True,
847 # Contains a SMIL manifest
849 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
853 'title': '+ Football: Lottery Champions League Europe',
854 'uploader': 'www.telewebion.com',
858 'skip_download': True,
861 # Brightcove URL in single quotes
863 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
864 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
866 'id': '4255764656001',
868 'title': 'SN Presents: Russell Martin, World Citizen',
869 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
870 'uploader': 'Rogers Sportsnet',
873 # Dailymotion Cloud video
875 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
876 'md5': '49444254273501a64675a7e68c502681',
878 'id': '5585de919473990de4bee11b',
881 'thumbnail': 're:^https?://.*\.jpe?g$',
886 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
890 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
891 'thumbnail': 're:^https?://.*\.jpe?g$',
892 'uploader': 'ClickHole',
893 'uploader_id': 'clickhole',
898 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
900 'id': '74849a00-85a9-11e1-9660-123139220831',
902 'title': '#whilewewatch',
907 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
908 'md5': '43662b577c018ad707a63766462b1e87',
912 'title': 'New experience with Acrobat DC',
913 'description': 'New experience with Acrobat DC',
919 def report_following_redirect(self, new_url):
920 """Report information extraction."""
921 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
923 def _extract_rss(self, url, video_id, doc):
924 playlist_title = doc.find('./channel/title').text
925 playlist_desc_el = doc.find('./channel/description')
926 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
929 for it in doc.findall('./channel/item'):
930 next_url = xpath_text(it, 'link', fatal=False)
932 enclosure_nodes = it.findall('./enclosure')
933 for e in enclosure_nodes:
934 next_url = e.attrib.get('url')
944 'title': it.find('title').text,
950 'title': playlist_title,
951 'description': playlist_desc,
955 def _extract_camtasia(self, url, video_id, webpage):
956 """ Returns None if no camtasia video can be found. """
958 camtasia_cfg = self._search_regex(
959 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
960 webpage, 'camtasia configuration file', default=None)
961 if camtasia_cfg is None:
964 title = self._html_search_meta('DC.title', webpage, fatal=True)
966 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
967 camtasia_cfg = self._download_xml(
968 camtasia_url, video_id,
969 note='Downloading camtasia configuration',
970 errnote='Failed to download camtasia configuration')
971 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
974 for n in fileset_node.getchildren():
975 url_n = n.find('./uri')
980 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
981 'title': '%s - %s' % (title, n.tag),
982 'url': compat_urlparse.urljoin(url, url_n.text),
983 'duration': float_or_none(n.find('./duration').text),
992 def _real_extract(self, url):
993 if url.startswith('//'):
996 'url': self.http_scheme() + url,
999 parsed_url = compat_urlparse.urlparse(url)
1000 if not parsed_url.scheme:
1001 default_search = self._downloader.params.get('default_search')
1002 if default_search is None:
1003 default_search = 'fixup_error'
1005 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1007 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1008 return self.url_result('http://' + url)
1009 elif default_search != 'fixup_error':
1010 if default_search == 'auto_warning':
1011 if re.match(r'^(?:url|URL)$', url):
1012 raise ExtractorError(
1013 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1016 self._downloader.report_warning(
1017 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1018 return self.url_result('ytsearch:' + url)
1020 if default_search in ('error', 'fixup_error'):
1021 raise ExtractorError(
1022 '%r is not a valid URL. '
1023 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1024 % (url, url), expected=True)
1026 if ':' not in default_search:
1027 default_search += ':'
1028 return self.url_result(default_search + url)
1030 url, smuggled_data = unsmuggle_url(url)
1031 force_videoid = None
1032 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1033 if smuggled_data and 'force_videoid' in smuggled_data:
1034 force_videoid = smuggled_data['force_videoid']
1035 video_id = force_videoid
1037 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1039 self.to_screen('%s: Requesting header' % video_id)
1041 head_req = HEADRequest(url)
1042 head_response = self._request_webpage(
1044 note=False, errnote='Could not send HEAD request to %s' % url,
1047 if head_response is not False:
1048 # Check for redirect
1049 new_url = head_response.geturl()
1051 self.report_following_redirect(new_url)
1053 new_url = smuggle_url(
1054 new_url, {'force_videoid': force_videoid})
1055 return self.url_result(new_url)
1057 full_response = None
1058 if head_response is False:
1059 request = compat_urllib_request.Request(url)
1060 request.add_header('Accept-Encoding', '*')
1061 full_response = self._request_webpage(request, video_id)
1062 head_response = full_response
1064 # Check for direct link to a video
1065 content_type = head_response.headers.get('Content-Type', '')
1066 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1068 upload_date = unified_strdate(
1069 head_response.headers.get('Last-Modified'))
1072 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1075 'format_id': m.group('format_id'),
1077 'vcodec': 'none' if m.group('type') == 'audio' else None
1079 'upload_date': upload_date,
1082 if not self._downloader.params.get('test', False) and not is_intentional:
1083 force = self._downloader.params.get('force_generic_extractor', False)
1084 self._downloader.report_warning(
1085 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1087 if not full_response:
1088 request = compat_urllib_request.Request(url)
1089 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1090 # making it impossible to download only chunk of the file (yet we need only 512kB to
1091 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1092 # that will always result in downloading the whole file that is not desirable.
1093 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1094 # to accept raw bytes and being able to download only a chunk.
1095 # It may probably better to solve this by checking Content-Type for application/octet-stream
1096 # after HEAD request finishes, but not sure if we can rely on this.
1097 request.add_header('Accept-Encoding', '*')
1098 full_response = self._request_webpage(request, video_id)
1100 # Maybe it's a direct link to a video?
1101 # Be careful not to download the whole thing!
1102 first_bytes = full_response.read(512)
1103 if not is_html(first_bytes):
1104 self._downloader.report_warning(
1105 'URL could be a direct video link, returning it as such.')
1106 upload_date = unified_strdate(
1107 head_response.headers.get('Last-Modified'))
1110 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1113 'upload_date': upload_date,
1116 webpage = self._webpage_read_content(
1117 full_response, url, video_id, prefix=first_bytes)
1119 self.report_extraction(video_id)
1121 # Is it an RSS feed?
1123 doc = parse_xml(webpage)
1124 if doc.tag == 'rss':
1125 return self._extract_rss(url, video_id, doc)
1126 except compat_xml_parse_error:
1129 # Is it a Camtasia project?
1130 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1131 if camtasia_res is not None:
1134 # Sometimes embedded video player is hidden behind percent encoding
1135 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1136 # Unescaping the whole page allows to handle those cases in a generic way
1137 webpage = compat_urllib_parse_unquote(webpage)
1139 # it's tempting to parse this further, but you would
1140 # have to take into account all the variations like
1141 # Video Title - Site Name
1142 # Site Name | Video Title
1143 # Video Title - Tagline | Site Name
1144 # and so on and so forth; it's just not practical
1145 video_title = self._html_search_regex(
1146 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1149 # Try to detect age limit automatically
1150 age_limit = self._rta_search(webpage)
1151 # And then there are the jokers who advertise that they use RTA,
1152 # but actually don't.
1153 AGE_LIMIT_MARKERS = [
1154 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1156 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1159 # video uploader is domain name
1160 video_uploader = self._search_regex(
1161 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1164 def _playlist_from_matches(matches, getter=None, ie=None):
1166 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1168 return self.playlist_result(
1169 urlrs, playlist_id=video_id, playlist_title=video_title)
1171 # Look for BrightCove:
1172 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1174 self.to_screen('Brightcove video detected.')
1177 'url': smuggle_url(bc_url, {'Referer': url}),
1178 'ie_key': 'Brightcove'
1179 } for bc_url in bc_urls]
1182 '_type': 'playlist',
1183 'title': video_title,
1188 # Look for embedded rtl.nl player
1189 matches = re.findall(
1190 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1193 return _playlist_from_matches(matches, ie='RtlNl')
1195 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1196 if vimeo_url is not None:
1197 return self.url_result(vimeo_url)
1199 # Look for embedded YouTube player
1200 matches = re.findall(r'''(?x)
1209 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1213 return _playlist_from_matches(
1214 matches, lambda m: unescapeHTML(m[1]))
1216 # Look for lazyYT YouTube embed
1217 matches = re.findall(
1218 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1220 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1222 # Look for embedded Dailymotion player
1223 matches = re.findall(
1224 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1226 return _playlist_from_matches(
1227 matches, lambda m: unescapeHTML(m[1]))
1229 # Look for embedded Dailymotion playlist player (#3822)
1231 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1233 playlists = re.findall(
1234 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1236 return _playlist_from_matches(
1237 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1239 # Look for embedded Wistia player
1241 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1243 embed_url = self._proto_relative_url(
1244 unescapeHTML(match.group('url')))
1246 '_type': 'url_transparent',
1249 'uploader': video_uploader,
1250 'title': video_title,
1254 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1257 '_type': 'url_transparent',
1258 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1260 'uploader': video_uploader,
1261 'title': video_title,
1262 'id': match.group('id')
1265 # Look for embedded blip.tv player
1266 bliptv_url = BlipTVIE._extract_url(webpage)
1268 return self.url_result(bliptv_url, 'BlipTV')
1270 # Look for SVT player
1271 svt_url = SVTIE._extract_url(webpage)
1273 return self.url_result(svt_url, 'SVT')
1275 # Look for embedded condenast player
1276 matches = re.findall(
1277 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1281 '_type': 'playlist',
1284 'ie_key': 'CondeNast',
1286 } for ma in matches],
1287 'title': video_title,
1291 # Look for Bandcamp pages with custom domain
1292 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1293 if mobj is not None:
1294 burl = unescapeHTML(mobj.group(1))
1295 # Don't set the extractor because it can be a track url or an album
1296 return self.url_result(burl)
1298 # Look for embedded Vevo player
1300 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1301 if mobj is not None:
1302 return self.url_result(mobj.group('url'))
1304 # Look for embedded Viddler player
1306 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1308 if mobj is not None:
1309 return self.url_result(mobj.group('url'))
1311 # Look for NYTimes player
1313 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1315 if mobj is not None:
1316 return self.url_result(mobj.group('url'))
1318 # Look for Libsyn player
1320 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1321 if mobj is not None:
1322 return self.url_result(mobj.group('url'))
1324 # Look for Ooyala videos
1325 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1326 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1327 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1328 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1329 if mobj is not None:
1330 return OoyalaIE._build_url_result(mobj.group('ec'))
1332 # Look for multiple Ooyala embeds on SBN network websites
1333 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1334 if mobj is not None:
1335 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1337 return _playlist_from_matches(
1338 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1340 # Look for Aparat videos
1341 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1342 if mobj is not None:
1343 return self.url_result(mobj.group(1), 'Aparat')
1345 # Look for MPORA videos
1346 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1347 if mobj is not None:
1348 return self.url_result(mobj.group(1), 'Mpora')
1350 # Look for embedded NovaMov-based player
1352 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1353 (?P<url>http://(?:(?:embed|www)\.)?
1355 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1356 videoweed\.(?:es|com)|
1357 movshare\.(?:net|sx|ag)|
1358 divxstage\.(?:eu|net|ch|co|at|ag))
1359 /embed\.php.+?)\1''', webpage)
1360 if mobj is not None:
1361 return self.url_result(mobj.group('url'))
1363 # Look for embedded Facebook player
1365 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1366 if mobj is not None:
1367 return self.url_result(mobj.group('url'), 'Facebook')
1369 # Look for embedded VK player
1370 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1371 if mobj is not None:
1372 return self.url_result(mobj.group('url'), 'VK')
1374 # Look for embedded ivi player
1375 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1376 if mobj is not None:
1377 return self.url_result(mobj.group('url'), 'Ivi')
1379 # Look for embedded Huffington Post player
1381 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1382 if mobj is not None:
1383 return self.url_result(mobj.group('url'), 'HuffPost')
1386 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1387 if mobj is not None:
1388 return self.url_result(mobj.group('url'))
1389 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1390 if mobj is not None:
1391 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1393 # Look for funnyordie embed
1394 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1396 return _playlist_from_matches(
1397 matches, getter=unescapeHTML, ie='FunnyOrDie')
1399 # Look for BBC iPlayer embed
1400 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1402 return _playlist_from_matches(matches, ie='BBCCoUk')
1404 # Look for embedded RUTV player
1405 rutv_url = RUTVIE._extract_url(webpage)
1407 return self.url_result(rutv_url, 'RUTV')
1409 # Look for embedded TVC player
1410 tvc_url = TVCIE._extract_url(webpage)
1412 return self.url_result(tvc_url, 'TVC')
1414 # Look for embedded SportBox player
1415 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1417 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1419 # Look for embedded PornHub player
1420 pornhub_url = PornHubIE._extract_url(webpage)
1422 return self.url_result(pornhub_url, 'PornHub')
1424 # Look for embedded XHamster player
1425 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1427 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1429 # Look for embedded Tvigle player
1431 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1432 if mobj is not None:
1433 return self.url_result(mobj.group('url'), 'Tvigle')
1435 # Look for embedded TED player
1437 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1438 if mobj is not None:
1439 return self.url_result(mobj.group('url'), 'TED')
1441 # Look for embedded Ustream videos
1443 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1444 if mobj is not None:
1445 return self.url_result(mobj.group('url'), 'Ustream')
1447 # Look for embedded arte.tv player
1449 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1451 if mobj is not None:
1452 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1454 # Look for embedded francetv player
1456 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1458 if mobj is not None:
1459 return self.url_result(mobj.group('url'))
1461 # Look for embedded smotri.com player
1462 smotri_url = SmotriIE._extract_url(webpage)
1464 return self.url_result(smotri_url, 'Smotri')
1466 # Look for embedded Myvi.ru player
1467 myvi_url = MyviIE._extract_url(webpage)
1469 return self.url_result(myvi_url)
1471 # Look for embeded soundcloud player
1473 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1475 if mobj is not None:
1476 url = unescapeHTML(mobj.group('url'))
1477 return self.url_result(url)
1479 # Look for embedded vulture.com player
1481 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1483 if mobj is not None:
1484 url = unescapeHTML(mobj.group('url'))
1485 return self.url_result(url, ie='Vulture')
1487 # Look for embedded mtvservices player
1489 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1491 if mobj is not None:
1492 url = unescapeHTML(mobj.group('url'))
1493 return self.url_result(url, ie='MTVServicesEmbedded')
1495 # Look for embedded yahoo player
1497 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1499 if mobj is not None:
1500 return self.url_result(mobj.group('url'), 'Yahoo')
1502 # Look for embedded sbs.com.au player
1506 <meta\s+property="og:video"\s+content=|
1509 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1511 if mobj is not None:
1512 return self.url_result(mobj.group('url'), 'SBS')
1514 # Look for embedded Cinchcast player
1516 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1518 if mobj is not None:
1519 return self.url_result(mobj.group('url'), 'Cinchcast')
1522 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1526 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1528 if mobj is not None:
1529 return self.url_result(mobj.group('url'), 'MLB')
1532 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1534 if mobj is not None:
1535 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1538 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1540 if mobj is not None:
1541 return self.url_result(mobj.group('url'), 'Livestream')
1543 # Look for Zapiks embed
1545 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1546 if mobj is not None:
1547 return self.url_result(mobj.group('url'), 'Zapiks')
1549 # Look for Kaltura embeds
1550 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1551 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))
1552 if mobj is not None:
1553 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1555 # Look for Eagle.Platform embeds
1557 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1558 if mobj is not None:
1559 return self.url_result(mobj.group('url'), 'EaglePlatform')
1561 # Look for ClipYou (uses Eagle.Platform) embeds
1563 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1564 if mobj is not None:
1565 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1567 # Look for Pladform embeds
1569 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1570 if mobj is not None:
1571 return self.url_result(mobj.group('url'), 'Pladform')
1573 # Look for Playwire embeds
1575 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1576 if mobj is not None:
1577 return self.url_result(mobj.group('url'))
1579 # Look for 5min embeds
1581 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1582 if mobj is not None:
1583 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1585 # Look for Crooks and Liars embeds
1587 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1588 if mobj is not None:
1589 return self.url_result(mobj.group('url'))
1591 # Look for NBC Sports VPlayer embeds
1592 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1594 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1596 # Look for UDN embeds
1598 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1599 if mobj is not None:
1600 return self.url_result(
1601 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1603 # Look for Senate ISVP iframe
1604 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1606 return self.url_result(senate_isvp_url, 'SenateISVP')
1608 # Look for Dailymotion Cloud videos
1609 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1611 return self.url_result(dmcloud_url, 'DailymotionCloud')
1613 # Look for OnionStudios embeds
1614 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1615 if onionstudios_url:
1616 return self.url_result(onionstudios_url)
1618 # Look for SnagFilms embeds
1619 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1621 return self.url_result(snagfilms_url)
1623 # Look for AdobeTVVideo embeds
1625 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1627 if mobj is not None:
1628 return self.url_result(
1629 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1632 def check_video(vurl):
1633 if YoutubeIE.suitable(vurl):
1635 vpath = compat_urlparse.urlparse(vurl).path
1636 vext = determine_ext(vpath)
1637 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1639 def filter_video(urls):
1640 return list(filter(check_video, urls))
1642 # Start with something easy: JW Player in SWFObject
1643 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1645 # Look for gorilla-vid style embedding
1646 found = filter_video(re.findall(r'''(?sx)
1650 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1653 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1655 # Broaden the search a little bit
1656 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1658 # Broaden the findall a little bit: JWPlayer JS loader
1659 found = filter_video(re.findall(
1660 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1663 found = filter_video(re.findall(r'''(?xs)
1664 flowplayer\("[^"]+",\s*
1666 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1667 ["']?url["']?\s*:\s*["']([^"']+)["']
1672 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1674 # Try to find twitter cards info
1675 found = filter_video(re.findall(
1676 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1678 # We look for Open Graph info:
1679 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1680 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1681 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1682 if m_video_type is not None:
1683 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1686 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1688 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1690 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1691 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1694 # Look also in Refresh HTTP header
1695 refresh_header = head_response.headers.get('Refresh')
1697 found = re.search(REDIRECT_REGEX, refresh_header)
1699 new_url = compat_urlparse.urljoin(url, found.group(1))
1700 self.report_following_redirect(new_url)
1706 raise UnsupportedError(url)
1709 for video_url in found:
1710 video_url = compat_urlparse.urljoin(url, video_url)
1711 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1713 # Sometimes, jwplayer extraction will result in a YouTube URL
1714 if YoutubeIE.suitable(video_url):
1715 entries.append(self.url_result(video_url, 'Youtube'))
1718 # here's a fun little line of code for you:
1719 video_id = os.path.splitext(video_id)[0]
1721 if determine_ext(video_url) == 'smil':
1724 'formats': self._extract_smil_formats(video_url, video_id),
1725 'uploader': video_uploader,
1726 'title': video_title,
1727 'age_limit': age_limit,
1733 'uploader': video_uploader,
1734 'title': video_title,
1735 'age_limit': age_limit,
1738 if len(entries) == 1:
1741 for num, e in enumerate(entries, start=1):
1742 # 'url' results don't have a title
1743 if e.get('title') is not None:
1744 e['title'] = '%s (%d)' % (e['title'], num)
1746 '_type': 'playlist',