3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
12 compat_urllib_parse_unquote,
13 compat_urllib_request,
15 compat_xml_parse_error,
33 from .brightcove import BrightcoveIE
34 from .nbc import NBCSportsVPlayerIE
35 from .ooyala import OoyalaIE
36 from .rutv import RUTVIE
37 from .tvc import TVCIE
38 from .sportbox import SportBoxEmbedIE
39 from .smotri import SmotriIE
40 from .myvi import MyviEmbedIE
41 from .condenast import CondeNastIE
42 from .udn import UDNEmbedIE
43 from .senateisvp import SenateISVPIE
44 from .bliptv import BlipTVIE
45 from .svt import SVTIE
46 from .pornhub import PornHubIE
47 from .xhamster import XHamsterEmbedIE
48 from .vimeo import VimeoIE
49 from .dailymotion import DailymotionCloudIE
50 from .onionstudios import OnionStudiosIE
51 from .snagfilms import SnagFilmsEmbedIE
54 class GenericIE(InfoExtractor):
55 IE_DESC = 'Generic downloader that works on some sites'
59 # Direct link to a video
61 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
62 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
67 'upload_date': '20100513',
70 # Direct link to media delivered compressed (until Accept-Encoding is *)
72 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
73 'md5': '128c42e68b13950268b648275386fc74',
75 'id': 'FictionJunction-Parallel_Hearts',
77 'title': 'FictionJunction-Parallel_Hearts',
78 'upload_date': '20140522',
80 'expected_warnings': [
81 'URL could be a direct video link, returning it as such.'
84 # Direct download with broken HEAD
86 'url': 'http://ai-radio.org:8000/radio.opus',
93 'skip_download': True, # infinite live stream
95 'expected_warnings': [
96 r'501.*Not Implemented'
99 # Direct link with incorrect MIME type
101 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
102 'md5': '4ccbebe5f36706d85221f204d7eb5913',
104 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
105 'id': '5_Lennart_Poettering_-_Systemd',
107 'title': '5_Lennart_Poettering_-_Systemd',
108 'upload_date': '20141120',
110 'expected_warnings': [
111 'URL could be a direct video link, returning it as such.'
116 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
119 'title': 'Zero Punctuation',
120 'description': 're:.*groundbreaking video review series.*'
122 'playlist_mincount': 11,
124 # RSS feed with enclosure
126 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
128 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
130 'upload_date': '20150228',
131 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
136 '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',
140 'upload_date': '20130224',
141 'uploader_id': 'TheVerge',
142 'description': 're:^Chris Ziegler takes a look at the\.*',
143 'uploader': 'The Verge',
144 'title': 'First Firefox OS phones side-by-side',
147 'skip_download': False,
151 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
152 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
154 'id': '13601338388002',
156 'uploader': 'www.hodiho.fr',
157 'title': 'R\u00e9gis plante sa Jeep',
160 # bandcamp page with custom domain
162 'add_ie': ['Bandcamp'],
163 'url': 'http://bronyrock.com/track/the-pony-mash',
167 'title': 'The Pony Mash',
168 'uploader': 'M_Pallante',
170 'skip': 'There is a limit of 200 free downloads / month for the test song',
172 # embedded brightcove video
173 # it also tests brightcove videos that need to set the 'Referer' in the
176 'add_ie': ['Brightcove'],
177 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
179 'id': '2765128793001',
181 'title': 'Le cours de bourse : l’analyse technique',
182 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
183 'uploader': 'BFM BUSINESS',
186 'skip_download': True,
190 # https://github.com/rg3/youtube-dl/issues/2253
191 'url': 'http://bcove.me/i6nfkrc3',
192 'md5': '0ba9446db037002366bab3b3eb30c88c',
194 'id': '3101154703001',
196 'title': 'Still no power',
197 'uploader': 'thestar.com',
198 '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.',
200 'add_ie': ['Brightcove'],
203 'url': 'http://www.championat.com/video/football/v/87/87499.html',
204 'md5': 'fb973ecf6e4a78a67453647444222983',
206 'id': '3414141473001',
208 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
209 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
210 'uploader': 'Championat',
214 # https://github.com/rg3/youtube-dl/issues/3541
215 'add_ie': ['Brightcove'],
216 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
218 'id': '3866516442001',
220 'title': 'Leer mij vrouwen kennen: Aflevering 1',
221 'description': 'Leer mij vrouwen kennen: Aflevering 1',
222 'uploader': 'SBS Broadcasting',
224 'skip': 'Restricted to Netherlands',
226 'skip_download': True, # m3u8 download
231 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
232 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
234 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
236 'title': '2cc213299525360.mov', # that's what we get
238 'add_ie': ['Ooyala'],
240 # multiple ooyala embeds on SBN network websites
242 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
244 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
245 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
247 'playlist_mincount': 3,
249 'skip_download': True,
251 'add_ie': ['Ooyala'],
255 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
259 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
260 'upload_date': '20140225',
261 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
262 'uploader': 'Tested',
263 'uploader_id': 'testedcom',
265 # No need to test YoutubeIE here
267 'skip_download': True,
272 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
276 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
277 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
282 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
284 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
286 'playlist_mincount': 18,
290 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
294 'title': 'Охотское море стало целиком российским',
295 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
299 'skip_download': True,
304 '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/',
308 'title': 'Дошкольное воспитание',
313 'url': 'http://www.vestifinance.ru/articles/25753',
316 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
321 'title': 'Госзаказ. День 3',
327 'title': 'Госзаказ. День 2',
333 'title': 'Госзаказ. День 1',
339 'skip_download': True,
344 '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',
347 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
349 'playlist_mincount': 7,
353 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
354 'md5': '65fdff94098e4a607385a60c5177c638',
358 'title': 'Hidden miracles of the natural world',
359 'uploader': 'Louie Schwartzberg',
360 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
363 # Embeded Ustream video
365 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
366 'md5': '27b99cdb639c9b12a79bca876a073417',
370 'uploader': 'AU SPA: The NSA and Privacy',
371 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
374 # nowvideo embed hidden behind percent encoding
376 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
377 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
379 'id': '06e53103ca9aa',
381 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
382 'description': 'No description',
387 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
388 'md5': '7653032cbb25bf6c80d80f217055fa43',
390 'id': '048195-004_PLUS7-F',
393 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
394 'upload_date': '20140320',
397 'skip_download': 'Requires rtmpdump'
402 'url': 'http://www.wired.com/2014/04/honda-asimo/',
403 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
405 'id': '53501be369702d3275860000',
407 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
412 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
413 'md5': '441aeeb82eb72c422c7f14ec533999cd',
415 'id': 'k2mm4bCdJ6CQ2i7c8o2',
417 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
420 'add_ie': ['Dailymotion'],
424 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
428 'title': 'The NBL Auction 2014',
429 'uploader': 'BADMINTON England',
430 'uploader_id': 'BADMINTONEvents',
431 'upload_date': '20140603',
432 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
434 'add_ie': ['Youtube'],
436 'skip_download': True,
441 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
442 'md5': '35727f82f58c76d996fc188f9755b0d5',
444 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
447 'description': 'Mario\'s life in the fast lane has never looked so good.',
450 # YouTube embed via <data-embed-url="">
452 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
456 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
457 'uploader': 'Gameloft',
458 'uploader_id': 'gameloft',
459 'upload_date': '20140828',
460 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
463 'skip_download': True,
468 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
470 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
472 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
473 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
478 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
480 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
481 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
487 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
492 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
493 'md5': '9d65602bf31c6e20014319c7d07fba27',
495 'id': '5123ea6d5e5a7',
498 'uploader': 'www.handjobhub.com',
499 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
502 # Multiple brightcove videos
503 # https://github.com/rg3/youtube-dl/issues/2283
505 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
507 'id': 'always-never',
508 'title': 'Always / Never - The New Yorker',
512 'extract_flat': False,
513 'skip_download': True,
518 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
519 'md5': '96f09a37e44da40dd083e12d9a683327',
523 'title': 'Ump changes call to ball',
524 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
526 'timestamp': 1401537900,
527 'upload_date': '20140531',
528 'thumbnail': 're:^https?://.*\.jpg$',
533 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
534 'md5': '8788b683c777a5cf25621eaf286d0c23',
538 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
540 'filesize': 182808282,
541 'uploader': 'education-portal.com',
545 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
546 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
550 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
552 'uploader': 'thoughtworks.wistia.com',
557 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
561 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
562 'uploader': 'Sophos Security',
563 'title': 'Chet Chat 171 - Oct 29, 2014',
564 'upload_date': '20141029',
569 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
573 'upload_date': '20141112',
574 'title': 'Rosetta #CometLanding webcast HL 10',
579 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
582 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
584 'playlist_mincount': 2,
588 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
592 'upload_date': '20141126',
593 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
598 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
600 'id': '730m_DandD_1901_512k',
602 'uploader': 'www.abc.net.au',
603 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
606 # embedded viddler video
608 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
612 'uploader': 'deadspin',
613 'title': 'WALL-TO-GORTAT',
614 'timestamp': 1422285291,
615 'upload_date': '20150126',
617 'add_ie': ['Viddler'],
621 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
625 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
626 'description': 'md5:601cb790edd05908957dae8aaa866465',
627 'upload_date': '20150220',
632 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
636 'upload_date': '20150212',
637 'uploader': 'The National Archives UK',
638 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
639 'uploader_id': 'NationalArchives08',
640 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
645 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
646 'playlist_mincount': 5,
648 'id': 'aanslagen-kopenhagen',
649 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
654 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
658 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
663 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
667 'upload_date': '20150226',
668 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
670 'title': 'John Carlson Postgame 2/25/15',
673 # Kaltura embed (different embed code)
675 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
679 'upload_date': '20150127',
680 'uploader_id': 'PremierMedia',
682 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
685 # Eagle.Platform embed (generic URL)
687 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
691 'title': 'Навальный вышел на свободу',
692 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
693 'thumbnail': 're:^https?://.*\.jpg$',
699 # ClipYou (Eagle.Platform) embed (custom URL)
701 'url': 'http://muz-tv.ru/play/7129/',
705 'title': "'O Sole Mio",
706 'thumbnail': 're:^https?://.*\.jpg$',
713 'url': 'http://muz-tv.ru/kinozal/view/7400/',
717 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
718 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
719 'thumbnail': 're:^https?://.*\.jpg$',
726 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
730 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
731 'thumbnail': 're:^https?://.*\.png$',
737 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
738 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
742 'title': 'Facebook Creates "On This Day" | Crunch Report',
747 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
751 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
756 # Crooks and Liars embed
758 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
762 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
763 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
764 'timestamp': 1428207000,
765 'upload_date': '20150405',
766 'uploader': 'Heather',
769 # Crooks and Liars external embed
771 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
773 'id': 'MTE3MjUtMzQ2MzA',
775 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
776 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
777 'timestamp': 1265032391,
778 'upload_date': '20100201',
779 'uploader': 'Heather',
782 # NBC Sports vplayer embed
784 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
786 'id': 'ln7x1qSThw4k',
788 'title': "PFT Live: New leader in the 'new-look' defense",
789 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
794 'url': 'http://www.udn.com/news/story/7314/822787',
795 'md5': 'fd2060e988c326991037b9aff9df21a6',
799 'title': '中一中男師變性 全校師生力挺',
800 'thumbnail': 're:^https?://.*\.jpg$',
805 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
807 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
809 'description': 'VIDEO: Index/Match versus VLOOKUP.',
810 'title': 'This is what separates the Excel masters from the wannabes',
814 'skip_download': True,
817 # Contains a SMIL manifest
819 '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',
823 'title': '+ Football: Lottery Champions League Europe',
824 'uploader': 'www.telewebion.com',
828 'skip_download': True,
831 # Brightcove URL in single quotes
833 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
834 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
836 'id': '4255764656001',
838 'title': 'SN Presents: Russell Martin, World Citizen',
839 '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.',
840 'uploader': 'Rogers Sportsnet',
843 # Dailymotion Cloud video
845 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
846 'md5': '49444254273501a64675a7e68c502681',
848 'id': '5585de919473990de4bee11b',
851 'thumbnail': 're:^https?://.*\.jpe?g$',
856 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
860 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
861 'thumbnail': 're:^https?://.*\.jpe?g$',
862 'uploader': 'ClickHole',
863 'uploader_id': 'clickhole',
868 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
870 'id': '74849a00-85a9-11e1-9660-123139220831',
872 'title': '#whilewewatch',
877 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
878 'md5': '43662b577c018ad707a63766462b1e87',
882 'title': 'New experience with Acrobat DC',
883 'description': 'New experience with Acrobat DC',
889 def report_following_redirect(self, new_url):
890 """Report information extraction."""
891 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
893 def _extract_rss(self, url, video_id, doc):
894 playlist_title = doc.find('./channel/title').text
895 playlist_desc_el = doc.find('./channel/description')
896 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
899 for it in doc.findall('./channel/item'):
900 next_url = xpath_text(it, 'link', fatal=False)
902 enclosure_nodes = it.findall('./enclosure')
903 for e in enclosure_nodes:
904 next_url = e.attrib.get('url')
914 'title': it.find('title').text,
920 'title': playlist_title,
921 'description': playlist_desc,
925 def _extract_camtasia(self, url, video_id, webpage):
926 """ Returns None if no camtasia video can be found. """
928 camtasia_cfg = self._search_regex(
929 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
930 webpage, 'camtasia configuration file', default=None)
931 if camtasia_cfg is None:
934 title = self._html_search_meta('DC.title', webpage, fatal=True)
936 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
937 camtasia_cfg = self._download_xml(
938 camtasia_url, video_id,
939 note='Downloading camtasia configuration',
940 errnote='Failed to download camtasia configuration')
941 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
944 for n in fileset_node.getchildren():
945 url_n = n.find('./uri')
950 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
951 'title': '%s - %s' % (title, n.tag),
952 'url': compat_urlparse.urljoin(url, url_n.text),
953 'duration': float_or_none(n.find('./duration').text),
962 def _real_extract(self, url):
963 if url.startswith('//'):
966 'url': self.http_scheme() + url,
969 parsed_url = compat_urlparse.urlparse(url)
970 if not parsed_url.scheme:
971 default_search = self._downloader.params.get('default_search')
972 if default_search is None:
973 default_search = 'fixup_error'
975 if default_search in ('auto', 'auto_warning', 'fixup_error'):
977 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
978 return self.url_result('http://' + url)
979 elif default_search != 'fixup_error':
980 if default_search == 'auto_warning':
981 if re.match(r'^(?:url|URL)$', url):
982 raise ExtractorError(
983 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
986 self._downloader.report_warning(
987 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
988 return self.url_result('ytsearch:' + url)
990 if default_search in ('error', 'fixup_error'):
991 raise ExtractorError(
992 '%r is not a valid URL. '
993 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
994 % (url, url), expected=True)
996 if ':' not in default_search:
997 default_search += ':'
998 return self.url_result(default_search + url)
1000 url, smuggled_data = unsmuggle_url(url)
1001 force_videoid = None
1002 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1003 if smuggled_data and 'force_videoid' in smuggled_data:
1004 force_videoid = smuggled_data['force_videoid']
1005 video_id = force_videoid
1007 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1009 self.to_screen('%s: Requesting header' % video_id)
1011 head_req = HEADRequest(url)
1012 head_response = self._request_webpage(
1014 note=False, errnote='Could not send HEAD request to %s' % url,
1017 if head_response is not False:
1018 # Check for redirect
1019 new_url = head_response.geturl()
1021 self.report_following_redirect(new_url)
1023 new_url = smuggle_url(
1024 new_url, {'force_videoid': force_videoid})
1025 return self.url_result(new_url)
1027 full_response = None
1028 if head_response is False:
1029 request = compat_urllib_request.Request(url)
1030 request.add_header('Accept-Encoding', '*')
1031 full_response = self._request_webpage(request, video_id)
1032 head_response = full_response
1034 # Check for direct link to a video
1035 content_type = head_response.headers.get('Content-Type', '')
1036 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1038 upload_date = unified_strdate(
1039 head_response.headers.get('Last-Modified'))
1042 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1045 'format_id': m.group('format_id'),
1047 'vcodec': 'none' if m.group('type') == 'audio' else None
1049 'upload_date': upload_date,
1052 if not self._downloader.params.get('test', False) and not is_intentional:
1053 force = self._downloader.params.get('force_generic_extractor', False)
1054 self._downloader.report_warning(
1055 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1057 if not full_response:
1058 request = compat_urllib_request.Request(url)
1059 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1060 # making it impossible to download only chunk of the file (yet we need only 512kB to
1061 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1062 # that will always result in downloading the whole file that is not desirable.
1063 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1064 # to accept raw bytes and being able to download only a chunk.
1065 # It may probably better to solve this by checking Content-Type for application/octet-stream
1066 # after HEAD request finishes, but not sure if we can rely on this.
1067 request.add_header('Accept-Encoding', '*')
1068 full_response = self._request_webpage(request, video_id)
1070 # Maybe it's a direct link to a video?
1071 # Be careful not to download the whole thing!
1072 first_bytes = full_response.read(512)
1073 if not is_html(first_bytes):
1074 self._downloader.report_warning(
1075 'URL could be a direct video link, returning it as such.')
1076 upload_date = unified_strdate(
1077 head_response.headers.get('Last-Modified'))
1080 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1083 'upload_date': upload_date,
1086 webpage = self._webpage_read_content(
1087 full_response, url, video_id, prefix=first_bytes)
1089 self.report_extraction(video_id)
1091 # Is it an RSS feed?
1093 doc = parse_xml(webpage)
1094 if doc.tag == 'rss':
1095 return self._extract_rss(url, video_id, doc)
1096 except compat_xml_parse_error:
1099 # Is it a Camtasia project?
1100 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1101 if camtasia_res is not None:
1104 # Sometimes embedded video player is hidden behind percent encoding
1105 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1106 # Unescaping the whole page allows to handle those cases in a generic way
1107 webpage = compat_urllib_parse.unquote(webpage)
1109 # it's tempting to parse this further, but you would
1110 # have to take into account all the variations like
1111 # Video Title - Site Name
1112 # Site Name | Video Title
1113 # Video Title - Tagline | Site Name
1114 # and so on and so forth; it's just not practical
1115 video_title = self._html_search_regex(
1116 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1119 # Try to detect age limit automatically
1120 age_limit = self._rta_search(webpage)
1121 # And then there are the jokers who advertise that they use RTA,
1122 # but actually don't.
1123 AGE_LIMIT_MARKERS = [
1124 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1126 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1129 # video uploader is domain name
1130 video_uploader = self._search_regex(
1131 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1134 def _playlist_from_matches(matches, getter=None, ie=None):
1136 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1138 return self.playlist_result(
1139 urlrs, playlist_id=video_id, playlist_title=video_title)
1141 # Look for BrightCove:
1142 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1144 self.to_screen('Brightcove video detected.')
1147 'url': smuggle_url(bc_url, {'Referer': url}),
1148 'ie_key': 'Brightcove'
1149 } for bc_url in bc_urls]
1152 '_type': 'playlist',
1153 'title': video_title,
1158 # Look for embedded rtl.nl player
1159 matches = re.findall(
1160 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1163 return _playlist_from_matches(matches, ie='RtlNl')
1165 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1166 if vimeo_url is not None:
1167 return self.url_result(vimeo_url)
1169 # Look for embedded YouTube player
1170 matches = re.findall(r'''(?x)
1179 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1183 return _playlist_from_matches(
1184 matches, lambda m: unescapeHTML(m[1]))
1186 # Look for lazyYT YouTube embed
1187 matches = re.findall(
1188 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1190 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1192 # Look for embedded Dailymotion player
1193 matches = re.findall(
1194 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1196 return _playlist_from_matches(
1197 matches, lambda m: unescapeHTML(m[1]))
1199 # Look for embedded Dailymotion playlist player (#3822)
1201 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1203 playlists = re.findall(
1204 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1206 return _playlist_from_matches(
1207 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1209 # Look for embedded Wistia player
1211 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1213 embed_url = self._proto_relative_url(
1214 unescapeHTML(match.group('url')))
1216 '_type': 'url_transparent',
1219 'uploader': video_uploader,
1220 'title': video_title,
1224 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1227 '_type': 'url_transparent',
1228 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1230 'uploader': video_uploader,
1231 'title': video_title,
1232 'id': match.group('id')
1235 # Look for embedded blip.tv player
1236 bliptv_url = BlipTVIE._extract_url(webpage)
1238 return self.url_result(bliptv_url, 'BlipTV')
1240 # Look for SVT player
1241 svt_url = SVTIE._extract_url(webpage)
1243 return self.url_result(svt_url, 'SVT')
1245 # Look for embedded condenast player
1246 matches = re.findall(
1247 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1251 '_type': 'playlist',
1254 'ie_key': 'CondeNast',
1256 } for ma in matches],
1257 'title': video_title,
1261 # Look for Bandcamp pages with custom domain
1262 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1263 if mobj is not None:
1264 burl = unescapeHTML(mobj.group(1))
1265 # Don't set the extractor because it can be a track url or an album
1266 return self.url_result(burl)
1268 # Look for embedded Vevo player
1270 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1271 if mobj is not None:
1272 return self.url_result(mobj.group('url'))
1274 # Look for embedded Viddler player
1276 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1278 if mobj is not None:
1279 return self.url_result(mobj.group('url'))
1281 # Look for NYTimes player
1283 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1285 if mobj is not None:
1286 return self.url_result(mobj.group('url'))
1288 # Look for Libsyn player
1290 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1291 if mobj is not None:
1292 return self.url_result(mobj.group('url'))
1294 # Look for Ooyala videos
1295 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1296 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1297 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1298 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1299 if mobj is not None:
1300 return OoyalaIE._build_url_result(mobj.group('ec'))
1302 # Look for multiple Ooyala embeds on SBN network websites
1303 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1304 if mobj is not None:
1305 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1307 return _playlist_from_matches(
1308 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1310 # Look for Aparat videos
1311 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1312 if mobj is not None:
1313 return self.url_result(mobj.group(1), 'Aparat')
1315 # Look for MPORA videos
1316 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1317 if mobj is not None:
1318 return self.url_result(mobj.group(1), 'Mpora')
1320 # Look for embedded NovaMov-based player
1322 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1323 (?P<url>http://(?:(?:embed|www)\.)?
1325 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1326 videoweed\.(?:es|com)|
1327 movshare\.(?:net|sx|ag)|
1328 divxstage\.(?:eu|net|ch|co|at|ag))
1329 /embed\.php.+?)\1''', webpage)
1330 if mobj is not None:
1331 return self.url_result(mobj.group('url'))
1333 # Look for embedded Facebook player
1335 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1336 if mobj is not None:
1337 return self.url_result(mobj.group('url'), 'Facebook')
1339 # Look for embedded VK player
1340 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1341 if mobj is not None:
1342 return self.url_result(mobj.group('url'), 'VK')
1344 # Look for embedded ivi player
1345 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1346 if mobj is not None:
1347 return self.url_result(mobj.group('url'), 'Ivi')
1349 # Look for embedded Huffington Post player
1351 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1352 if mobj is not None:
1353 return self.url_result(mobj.group('url'), 'HuffPost')
1356 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1357 if mobj is not None:
1358 return self.url_result(mobj.group('url'))
1359 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1360 if mobj is not None:
1361 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1363 # Look for funnyordie embed
1364 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1366 return _playlist_from_matches(
1367 matches, getter=unescapeHTML, ie='FunnyOrDie')
1369 # Look for BBC iPlayer embed
1370 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1372 return _playlist_from_matches(matches, ie='BBCCoUk')
1374 # Look for embedded RUTV player
1375 rutv_url = RUTVIE._extract_url(webpage)
1377 return self.url_result(rutv_url, 'RUTV')
1379 # Look for embedded TVC player
1380 tvc_url = TVCIE._extract_url(webpage)
1382 return self.url_result(tvc_url, 'TVC')
1384 # Look for embedded SportBox player
1385 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1387 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1389 # Look for embedded PornHub player
1390 pornhub_url = PornHubIE._extract_url(webpage)
1392 return self.url_result(pornhub_url, 'PornHub')
1394 # Look for embedded XHamster player
1395 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1397 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1399 # Look for embedded Tvigle player
1401 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1402 if mobj is not None:
1403 return self.url_result(mobj.group('url'), 'Tvigle')
1405 # Look for embedded TED player
1407 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1408 if mobj is not None:
1409 return self.url_result(mobj.group('url'), 'TED')
1411 # Look for embedded Ustream videos
1413 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1414 if mobj is not None:
1415 return self.url_result(mobj.group('url'), 'Ustream')
1417 # Look for embedded arte.tv player
1419 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1421 if mobj is not None:
1422 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1424 # Look for embedded smotri.com player
1425 smotri_url = SmotriIE._extract_url(webpage)
1427 return self.url_result(smotri_url, 'Smotri')
1429 # Look for embedded Myvi.ru player
1430 myvi_url = MyviEmbedIE._extract_url(webpage)
1432 return self.url_result(myvi_url)
1434 # Look for embeded soundcloud player
1436 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1438 if mobj is not None:
1439 url = unescapeHTML(mobj.group('url'))
1440 return self.url_result(url)
1442 # Look for embedded vulture.com player
1444 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1446 if mobj is not None:
1447 url = unescapeHTML(mobj.group('url'))
1448 return self.url_result(url, ie='Vulture')
1450 # Look for embedded mtvservices player
1452 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1454 if mobj is not None:
1455 url = unescapeHTML(mobj.group('url'))
1456 return self.url_result(url, ie='MTVServicesEmbedded')
1458 # Look for embedded yahoo player
1460 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1462 if mobj is not None:
1463 return self.url_result(mobj.group('url'), 'Yahoo')
1465 # Look for embedded sbs.com.au player
1469 <meta\s+property="og:video"\s+content=|
1472 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1474 if mobj is not None:
1475 return self.url_result(mobj.group('url'), 'SBS')
1477 # Look for embedded Cinchcast player
1479 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1481 if mobj is not None:
1482 return self.url_result(mobj.group('url'), 'Cinchcast')
1485 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1489 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1491 if mobj is not None:
1492 return self.url_result(mobj.group('url'), 'MLB')
1495 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1497 if mobj is not None:
1498 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1501 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1503 if mobj is not None:
1504 return self.url_result(mobj.group('url'), 'Livestream')
1506 # Look for Zapiks embed
1508 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1509 if mobj is not None:
1510 return self.url_result(mobj.group('url'), 'Zapiks')
1512 # Look for Kaltura embeds
1513 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1514 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))
1515 if mobj is not None:
1516 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1518 # Look for Eagle.Platform embeds
1520 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1521 if mobj is not None:
1522 return self.url_result(mobj.group('url'), 'EaglePlatform')
1524 # Look for ClipYou (uses Eagle.Platform) embeds
1526 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1527 if mobj is not None:
1528 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1530 # Look for Pladform embeds
1532 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1533 if mobj is not None:
1534 return self.url_result(mobj.group('url'), 'Pladform')
1536 # Look for Playwire embeds
1538 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1539 if mobj is not None:
1540 return self.url_result(mobj.group('url'))
1542 # Look for 5min embeds
1544 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1545 if mobj is not None:
1546 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1548 # Look for Crooks and Liars embeds
1550 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1551 if mobj is not None:
1552 return self.url_result(mobj.group('url'))
1554 # Look for NBC Sports VPlayer embeds
1555 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1557 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1559 # Look for UDN embeds
1561 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1562 if mobj is not None:
1563 return self.url_result(
1564 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1566 # Look for Senate ISVP iframe
1567 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1569 return self.url_result(senate_isvp_url, 'SenateISVP')
1571 # Look for Dailymotion Cloud videos
1572 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1574 return self.url_result(dmcloud_url, 'DailymotionCloud')
1576 # Look for OnionStudios embeds
1577 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1578 if onionstudios_url:
1579 return self.url_result(onionstudios_url)
1581 # Look for SnagFilms embeds
1582 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1584 return self.url_result(snagfilms_url)
1586 # Look for AdobeTVVideo embeds
1588 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1590 if mobj is not None:
1591 return self.url_result(
1592 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1595 def check_video(vurl):
1596 if YoutubeIE.suitable(vurl):
1598 vpath = compat_urlparse.urlparse(vurl).path
1599 vext = determine_ext(vpath)
1600 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1602 def filter_video(urls):
1603 return list(filter(check_video, urls))
1605 # Start with something easy: JW Player in SWFObject
1606 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1608 # Look for gorilla-vid style embedding
1609 found = filter_video(re.findall(r'''(?sx)
1613 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1616 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1618 # Broaden the search a little bit
1619 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1621 # Broaden the findall a little bit: JWPlayer JS loader
1622 found = filter_video(re.findall(
1623 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1626 found = filter_video(re.findall(r'''(?xs)
1627 flowplayer\("[^"]+",\s*
1629 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1630 ["']?url["']?\s*:\s*["']([^"']+)["']
1635 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1637 # Try to find twitter cards info
1638 found = filter_video(re.findall(
1639 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1641 # We look for Open Graph info:
1642 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1643 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1644 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1645 if m_video_type is not None:
1646 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1649 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1651 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1653 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1654 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1657 # Look also in Refresh HTTP header
1658 refresh_header = head_response.headers.get('Refresh')
1660 found = re.search(REDIRECT_REGEX, refresh_header)
1662 new_url = compat_urlparse.urljoin(url, found.group(1))
1663 self.report_following_redirect(new_url)
1669 raise UnsupportedError(url)
1672 for video_url in found:
1673 video_url = compat_urlparse.urljoin(url, video_url)
1674 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1676 # Sometimes, jwplayer extraction will result in a YouTube URL
1677 if YoutubeIE.suitable(video_url):
1678 entries.append(self.url_result(video_url, 'Youtube'))
1681 # here's a fun little line of code for you:
1682 video_id = os.path.splitext(video_id)[0]
1684 if determine_ext(video_url) == 'smil':
1687 'formats': self._extract_smil_formats(video_url, video_id),
1688 'uploader': video_uploader,
1689 'title': video_title,
1690 'age_limit': age_limit,
1696 'uploader': video_uploader,
1697 'title': video_title,
1698 'age_limit': age_limit,
1701 if len(entries) == 1:
1704 for num, e in enumerate(entries, start=1):
1705 # 'url' results don't have a title
1706 if e.get('title') is not None:
1707 e['title'] = '%s (%d)' % (e['title'], num)
1709 '_type': 'playlist',