3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .vimeo import VimeoIE
51 from .dailymotion import DailymotionCloudIE
52 from .onionstudios import OnionStudiosIE
53 from .snagfilms import SnagFilmsEmbedIE
54 from .screenwavemedia import ScreenwaveMediaIE
55 from .mtv import MTVServicesEmbeddedIE
58 class GenericIE(InfoExtractor):
59 IE_DESC = 'Generic downloader that works on some sites'
63 # Direct link to a video
65 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
66 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
71 'upload_date': '20100513',
74 # Direct link to media delivered compressed (until Accept-Encoding is *)
76 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
77 'md5': '128c42e68b13950268b648275386fc74',
79 'id': 'FictionJunction-Parallel_Hearts',
81 'title': 'FictionJunction-Parallel_Hearts',
82 'upload_date': '20140522',
84 'expected_warnings': [
85 'URL could be a direct video link, returning it as such.'
88 # Direct download with broken HEAD
90 'url': 'http://ai-radio.org:8000/radio.opus',
97 'skip_download': True, # infinite live stream
99 'expected_warnings': [
100 r'501.*Not Implemented'
103 # Direct link with incorrect MIME type
105 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
106 'md5': '4ccbebe5f36706d85221f204d7eb5913',
108 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
109 'id': '5_Lennart_Poettering_-_Systemd',
111 'title': '5_Lennart_Poettering_-_Systemd',
112 'upload_date': '20141120',
114 'expected_warnings': [
115 'URL could be a direct video link, returning it as such.'
120 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
122 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
123 'title': 'Zero Punctuation',
124 'description': 're:.*groundbreaking video review series.*'
126 'playlist_mincount': 11,
128 # RSS feed with enclosure
130 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
132 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
134 'upload_date': '20150228',
135 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
138 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
140 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
144 'title': 'Automatics, robotics and biocybernetics',
145 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
146 'upload_date': '20130627',
147 'formats': 'mincount:16',
148 'subtitles': 'mincount:1',
151 'force_generic_extractor': True,
152 'skip_download': True,
155 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
157 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
162 'formats': 'mincount:1',
165 'skip_download': True,
168 # SMIL from https://www.restudy.dk/video/play/id/1637
170 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
174 'title': 'video_1637',
175 'formats': 'mincount:3',
178 'skip_download': True,
181 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
183 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
185 'id': 'smil-service',
187 'title': 'smil-service',
188 'formats': 'mincount:1',
191 'skip_download': True,
194 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
196 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
200 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
201 'formats': 'mincount:3',
204 'skip_download': True,
207 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
209 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
211 'id': 'mZlp2ctYIUEB',
213 'title': 'Tikibad ontruimd wegens brand',
214 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
215 'thumbnail': 're:^https?://.*\.jpg$',
219 'skip_download': True,
224 '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',
228 'upload_date': '20130224',
229 'uploader_id': 'TheVerge',
230 'description': 're:^Chris Ziegler takes a look at the\.*',
231 'uploader': 'The Verge',
232 'title': 'First Firefox OS phones side-by-side',
235 'skip_download': False,
239 # redirect in Refresh HTTP header
240 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
244 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
245 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
246 'upload_date': '20150917',
247 'uploader_id': 'brtvofficial',
248 'uploader': 'Boiler Room',
251 'skip_download': False,
255 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
256 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
258 'id': '13601338388002',
260 'uploader': 'www.hodiho.fr',
261 'title': 'R\u00e9gis plante sa Jeep',
264 # bandcamp page with custom domain
266 'add_ie': ['Bandcamp'],
267 'url': 'http://bronyrock.com/track/the-pony-mash',
271 'title': 'The Pony Mash',
272 'uploader': 'M_Pallante',
274 'skip': 'There is a limit of 200 free downloads / month for the test song',
276 # embedded brightcove video
277 # it also tests brightcove videos that need to set the 'Referer' in the
280 'add_ie': ['BrightcoveLegacy'],
281 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
283 'id': '2765128793001',
285 'title': 'Le cours de bourse : l’analyse technique',
286 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
287 'uploader': 'BFM BUSINESS',
290 'skip_download': True,
294 # https://github.com/rg3/youtube-dl/issues/2253
295 'url': 'http://bcove.me/i6nfkrc3',
296 'md5': '0ba9446db037002366bab3b3eb30c88c',
298 'id': '3101154703001',
300 'title': 'Still no power',
301 'uploader': 'thestar.com',
302 '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.',
304 'add_ie': ['BrightcoveLegacy'],
307 'url': 'http://www.championat.com/video/football/v/87/87499.html',
308 'md5': 'fb973ecf6e4a78a67453647444222983',
310 'id': '3414141473001',
312 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
313 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
314 'uploader': 'Championat',
318 # https://github.com/rg3/youtube-dl/issues/3541
319 'add_ie': ['BrightcoveLegacy'],
320 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
322 'id': '3866516442001',
324 'title': 'Leer mij vrouwen kennen: Aflevering 1',
325 'description': 'Leer mij vrouwen kennen: Aflevering 1',
326 'uploader': 'SBS Broadcasting',
328 'skip': 'Restricted to Netherlands',
330 'skip_download': True, # m3u8 download
335 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
336 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
338 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
340 'title': '2cc213299525360.mov', # that's what we get
342 'add_ie': ['Ooyala'],
345 # ooyala video embedded with http://player.ooyala.com/iframe.js
346 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
348 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
350 'title': '"Steve Jobs: Man in the Machine" trailer',
351 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
354 'skip_download': True,
357 # multiple ooyala embeds on SBN network websites
359 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
361 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
362 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
364 'playlist_mincount': 3,
366 'skip_download': True,
368 'add_ie': ['Ooyala'],
372 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
376 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
377 'upload_date': '20140225',
378 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
379 'uploader': 'Tested',
380 'uploader_id': 'testedcom',
382 # No need to test YoutubeIE here
384 'skip_download': True,
389 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
393 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
394 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
399 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
403 'title': 'Охотское море стало целиком российским',
404 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
408 'skip_download': True,
413 '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/',
417 'title': 'Дошкольное воспитание',
422 'url': 'http://www.vestifinance.ru/articles/25753',
425 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
430 'title': 'Госзаказ. День 3',
436 'title': 'Госзаказ. День 2',
442 'title': 'Госзаказ. День 1',
448 'skip_download': True,
453 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
455 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
457 'title': 'Ужастики, русский трейлер (2015)',
458 'thumbnail': 're:^https?://.*\.jpg$',
464 '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',
467 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
469 'playlist_mincount': 7,
473 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
474 'md5': '65fdff94098e4a607385a60c5177c638',
478 'title': 'Hidden miracles of the natural world',
479 'uploader': 'Louie Schwartzberg',
480 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
483 # Embeded Ustream video
485 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
486 'md5': '27b99cdb639c9b12a79bca876a073417',
490 'uploader': 'AU SPA: The NSA and Privacy',
491 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
494 # nowvideo embed hidden behind percent encoding
496 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
497 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
499 'id': '06e53103ca9aa',
501 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
502 'description': 'No description',
507 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
508 'md5': '7653032cbb25bf6c80d80f217055fa43',
510 'id': '048195-004_PLUS7-F',
513 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
514 'upload_date': '20140320',
517 'skip_download': 'Requires rtmpdump'
522 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
526 'title': 'Alcaline, le concert avec Calogero',
527 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
528 'upload_date': '20150226',
529 'timestamp': 1424989860,
534 'skip_download': True,
536 'expected_warnings': [
542 'url': 'http://www.wired.com/2014/04/honda-asimo/',
543 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
545 'id': '53501be369702d3275860000',
547 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
552 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
553 'md5': '441aeeb82eb72c422c7f14ec533999cd',
555 'id': 'k2mm4bCdJ6CQ2i7c8o2',
557 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
560 'add_ie': ['Dailymotion'],
564 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
568 'title': 'The NBL Auction 2014',
569 'uploader': 'BADMINTON England',
570 'uploader_id': 'BADMINTONEvents',
571 'upload_date': '20140603',
572 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
574 'add_ie': ['Youtube'],
576 'skip_download': True,
581 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
582 'md5': '35727f82f58c76d996fc188f9755b0d5',
584 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
587 'description': 'Mario\'s life in the fast lane has never looked so good.',
590 # YouTube embed via <data-embed-url="">
592 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
596 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
597 'uploader': 'Gameloft',
598 'uploader_id': 'gameloft',
599 'upload_date': '20140828',
600 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
603 'skip_download': True,
608 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
610 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
612 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
613 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
618 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
620 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
621 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
627 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
632 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
633 'md5': '9d65602bf31c6e20014319c7d07fba27',
635 'id': '5123ea6d5e5a7',
638 'uploader': 'www.handjobhub.com',
639 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
642 # Multiple brightcove videos
643 # https://github.com/rg3/youtube-dl/issues/2283
645 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
647 'id': 'always-never',
648 'title': 'Always / Never - The New Yorker',
652 'extract_flat': False,
653 'skip_download': True,
658 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
659 'md5': '96f09a37e44da40dd083e12d9a683327',
663 'title': 'Ump changes call to ball',
664 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
666 'timestamp': 1401537900,
667 'upload_date': '20140531',
668 'thumbnail': 're:^https?://.*\.jpg$',
673 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
674 'md5': '8788b683c777a5cf25621eaf286d0c23',
678 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
680 'filesize': 182808282,
681 'uploader': 'education-portal.com',
685 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
686 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
690 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
692 'uploader': 'thoughtworks.wistia.com',
697 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
701 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
702 'uploader': 'Sophos Security',
703 'title': 'Chet Chat 171 - Oct 29, 2014',
704 'upload_date': '20141029',
709 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
713 'upload_date': '20141112',
714 'title': 'Rosetta #CometLanding webcast HL 10',
719 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
722 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
724 'playlist_mincount': 2,
728 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
732 'upload_date': '20141126',
733 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
738 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
740 'id': '730m_DandD_1901_512k',
742 'uploader': 'www.abc.net.au',
743 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
746 # embedded viddler video
748 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
752 'uploader': 'deadspin',
753 'title': 'WALL-TO-GORTAT',
754 'timestamp': 1422285291,
755 'upload_date': '20150126',
757 'add_ie': ['Viddler'],
761 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
765 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
766 'description': 'md5:601cb790edd05908957dae8aaa866465',
767 'upload_date': '20150220',
772 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
776 'upload_date': '20150212',
777 'uploader': 'The National Archives UK',
778 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
779 'uploader_id': 'NationalArchives08',
780 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
785 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
786 'playlist_mincount': 5,
788 'id': 'aanslagen-kopenhagen',
789 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
794 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
798 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
803 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
807 'upload_date': '20150226',
808 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
810 'title': 'John Carlson Postgame 2/25/15',
813 # Kaltura embed (different embed code)
815 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
819 'upload_date': '20150127',
820 'uploader_id': 'PremierMedia',
822 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
825 # Kaltura embed protected with referrer
827 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
831 'title': 'Violetta - Achter De Schermen - Ruggero',
832 'description': 'Achter de schermen met Ruggero',
833 'timestamp': 1435133761,
834 'upload_date': '20150624',
835 'uploader_id': 'echojecka',
838 # Eagle.Platform embed (generic URL)
840 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
844 'title': 'Навальный вышел на свободу',
845 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
846 'thumbnail': 're:^https?://.*\.jpg$',
852 # ClipYou (Eagle.Platform) embed (custom URL)
854 'url': 'http://muz-tv.ru/play/7129/',
858 'title': "'O Sole Mio",
859 'thumbnail': 're:^https?://.*\.jpg$',
866 'url': 'http://muz-tv.ru/kinozal/view/7400/',
870 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
871 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
872 'thumbnail': 're:^https?://.*\.jpg$',
879 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
883 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
884 'thumbnail': 're:^https?://.*\.png$',
890 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
891 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
895 'title': 'Facebook Creates "On This Day" | Crunch Report',
900 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
904 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
909 # Crooks and Liars embed
911 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
915 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
916 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
917 'timestamp': 1428207000,
918 'upload_date': '20150405',
919 'uploader': 'Heather',
922 # Crooks and Liars external embed
924 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
926 'id': 'MTE3MjUtMzQ2MzA',
928 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
929 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
930 'timestamp': 1265032391,
931 'upload_date': '20100201',
932 'uploader': 'Heather',
935 # NBC Sports vplayer embed
937 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
939 'id': 'ln7x1qSThw4k',
941 'title': "PFT Live: New leader in the 'new-look' defense",
942 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
947 'url': 'http://www.udn.com/news/story/7314/822787',
948 'md5': 'fd2060e988c326991037b9aff9df21a6',
952 'title': '中一中男師變性 全校師生力挺',
953 'thumbnail': 're:^https?://.*\.jpg$',
958 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
960 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
962 'description': 'VIDEO: Index/Match versus VLOOKUP.',
963 'title': 'This is what separates the Excel masters from the wannabes',
967 'skip_download': True,
970 # Contains a SMIL manifest
972 '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',
976 'title': '+ Football: Lottery Champions League Europe',
977 'uploader': 'www.telewebion.com',
981 'skip_download': True,
984 # Brightcove URL in single quotes
986 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
987 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
989 'id': '4255764656001',
991 'title': 'SN Presents: Russell Martin, World Citizen',
992 '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.',
993 'uploader': 'Rogers Sportsnet',
996 # Dailymotion Cloud video
998 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
999 'md5': '49444254273501a64675a7e68c502681',
1001 'id': '5585de919473990de4bee11b',
1003 'title': 'Le débat',
1004 'thumbnail': 're:^https?://.*\.jpe?g$',
1007 # OnionStudios embed
1009 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1013 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1014 'thumbnail': 're:^https?://.*\.jpe?g$',
1015 'uploader': 'ClickHole',
1016 'uploader_id': 'clickhole',
1021 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1023 'id': '74849a00-85a9-11e1-9660-123139220831',
1025 'title': '#whilewewatch',
1028 # AdobeTVVideo embed
1030 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1031 'md5': '43662b577c018ad707a63766462b1e87',
1035 'title': 'New experience with Acrobat DC',
1036 'description': 'New experience with Acrobat DC',
1037 'duration': 248.667,
1040 # ScreenwaveMedia embed
1042 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1043 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1045 'id': 'cinemasnob-55d26273809dd',
1047 'title': 'cinemasnob',
1050 # BrightcoveInPageEmbed embed
1052 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1054 'id': '4238694884001',
1056 'title': 'Tabletop: Dread, Last Thoughts',
1057 'description': 'Tabletop: Dread, Last Thoughts',
1061 # JWPlayer with M3U8
1063 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1067 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1068 'uploader': 'ren.tv',
1072 'skip_download': True,
1077 def report_following_redirect(self, new_url):
1078 """Report information extraction."""
1079 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1081 def _extract_rss(self, url, video_id, doc):
1082 playlist_title = doc.find('./channel/title').text
1083 playlist_desc_el = doc.find('./channel/description')
1084 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1087 for it in doc.findall('./channel/item'):
1088 next_url = xpath_text(it, 'link', fatal=False)
1090 enclosure_nodes = it.findall('./enclosure')
1091 for e in enclosure_nodes:
1092 next_url = e.attrib.get('url')
1102 'title': it.find('title').text,
1106 '_type': 'playlist',
1108 'title': playlist_title,
1109 'description': playlist_desc,
1113 def _extract_camtasia(self, url, video_id, webpage):
1114 """ Returns None if no camtasia video can be found. """
1116 camtasia_cfg = self._search_regex(
1117 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1118 webpage, 'camtasia configuration file', default=None)
1119 if camtasia_cfg is None:
1122 title = self._html_search_meta('DC.title', webpage, fatal=True)
1124 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1125 camtasia_cfg = self._download_xml(
1126 camtasia_url, video_id,
1127 note='Downloading camtasia configuration',
1128 errnote='Failed to download camtasia configuration')
1129 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1132 for n in fileset_node.getchildren():
1133 url_n = n.find('./uri')
1138 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1139 'title': '%s - %s' % (title, n.tag),
1140 'url': compat_urlparse.urljoin(url, url_n.text),
1141 'duration': float_or_none(n.find('./duration').text),
1145 '_type': 'playlist',
1150 def _real_extract(self, url):
1151 if url.startswith('//'):
1154 'url': self.http_scheme() + url,
1157 parsed_url = compat_urlparse.urlparse(url)
1158 if not parsed_url.scheme:
1159 default_search = self._downloader.params.get('default_search')
1160 if default_search is None:
1161 default_search = 'fixup_error'
1163 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1165 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1166 return self.url_result('http://' + url)
1167 elif default_search != 'fixup_error':
1168 if default_search == 'auto_warning':
1169 if re.match(r'^(?:url|URL)$', url):
1170 raise ExtractorError(
1171 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1174 self._downloader.report_warning(
1175 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1176 return self.url_result('ytsearch:' + url)
1178 if default_search in ('error', 'fixup_error'):
1179 raise ExtractorError(
1180 '%r is not a valid URL. '
1181 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1182 % (url, url), expected=True)
1184 if ':' not in default_search:
1185 default_search += ':'
1186 return self.url_result(default_search + url)
1188 url, smuggled_data = unsmuggle_url(url)
1189 force_videoid = None
1190 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1191 if smuggled_data and 'force_videoid' in smuggled_data:
1192 force_videoid = smuggled_data['force_videoid']
1193 video_id = force_videoid
1195 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1197 self.to_screen('%s: Requesting header' % video_id)
1199 head_req = HEADRequest(url)
1200 head_response = self._request_webpage(
1202 note=False, errnote='Could not send HEAD request to %s' % url,
1205 if head_response is not False:
1206 # Check for redirect
1207 new_url = head_response.geturl()
1209 self.report_following_redirect(new_url)
1211 new_url = smuggle_url(
1212 new_url, {'force_videoid': force_videoid})
1213 return self.url_result(new_url)
1215 full_response = None
1216 if head_response is False:
1217 request = sanitized_Request(url)
1218 request.add_header('Accept-Encoding', '*')
1219 full_response = self._request_webpage(request, video_id)
1220 head_response = full_response
1222 # Check for direct link to a video
1223 content_type = head_response.headers.get('Content-Type', '')
1224 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1226 upload_date = unified_strdate(
1227 head_response.headers.get('Last-Modified'))
1230 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1233 'format_id': m.group('format_id'),
1235 'vcodec': 'none' if m.group('type') == 'audio' else None
1237 'upload_date': upload_date,
1240 if not self._downloader.params.get('test', False) and not is_intentional:
1241 force = self._downloader.params.get('force_generic_extractor', False)
1242 self._downloader.report_warning(
1243 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1245 if not full_response:
1246 request = sanitized_Request(url)
1247 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1248 # making it impossible to download only chunk of the file (yet we need only 512kB to
1249 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1250 # that will always result in downloading the whole file that is not desirable.
1251 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1252 # to accept raw bytes and being able to download only a chunk.
1253 # It may probably better to solve this by checking Content-Type for application/octet-stream
1254 # after HEAD request finishes, but not sure if we can rely on this.
1255 request.add_header('Accept-Encoding', '*')
1256 full_response = self._request_webpage(request, video_id)
1258 # Maybe it's a direct link to a video?
1259 # Be careful not to download the whole thing!
1260 first_bytes = full_response.read(512)
1261 if not is_html(first_bytes):
1262 self._downloader.report_warning(
1263 'URL could be a direct video link, returning it as such.')
1264 upload_date = unified_strdate(
1265 head_response.headers.get('Last-Modified'))
1268 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1271 'upload_date': upload_date,
1274 webpage = self._webpage_read_content(
1275 full_response, url, video_id, prefix=first_bytes)
1277 self.report_extraction(video_id)
1279 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1281 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1282 if doc.tag == 'rss':
1283 return self._extract_rss(url, video_id, doc)
1284 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1285 return self._parse_smil(doc, url, video_id)
1286 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1287 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1288 except compat_xml_parse_error:
1291 # Is it a Camtasia project?
1292 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1293 if camtasia_res is not None:
1296 # Sometimes embedded video player is hidden behind percent encoding
1297 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1298 # Unescaping the whole page allows to handle those cases in a generic way
1299 webpage = compat_urllib_parse_unquote(webpage)
1301 # it's tempting to parse this further, but you would
1302 # have to take into account all the variations like
1303 # Video Title - Site Name
1304 # Site Name | Video Title
1305 # Video Title - Tagline | Site Name
1306 # and so on and so forth; it's just not practical
1307 video_title = self._html_search_regex(
1308 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1311 # Try to detect age limit automatically
1312 age_limit = self._rta_search(webpage)
1313 # And then there are the jokers who advertise that they use RTA,
1314 # but actually don't.
1315 AGE_LIMIT_MARKERS = [
1316 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1318 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1321 # video uploader is domain name
1322 video_uploader = self._search_regex(
1323 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1326 def _playlist_from_matches(matches, getter=None, ie=None):
1328 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1330 return self.playlist_result(
1331 urlrs, playlist_id=video_id, playlist_title=video_title)
1333 # Look for Brightcove Legacy Studio embeds
1334 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1336 self.to_screen('Brightcove video detected.')
1339 'url': smuggle_url(bc_url, {'Referer': url}),
1340 'ie_key': 'BrightcoveLegacy'
1341 } for bc_url in bc_urls]
1344 '_type': 'playlist',
1345 'title': video_title,
1350 # Look for Brightcove New Studio embeds
1351 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1353 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1355 # Look for embedded rtl.nl player
1356 matches = re.findall(
1357 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1360 return _playlist_from_matches(matches, ie='RtlNl')
1362 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1363 if vimeo_url is not None:
1364 return self.url_result(vimeo_url)
1366 vid_me_embed_url = self._search_regex(
1367 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1368 webpage, 'vid.me embed', default=None)
1369 if vid_me_embed_url is not None:
1370 return self.url_result(vid_me_embed_url, 'Vidme')
1372 # Look for embedded YouTube player
1373 matches = re.findall(r'''(?x)
1382 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1386 return _playlist_from_matches(
1387 matches, lambda m: unescapeHTML(m[1]))
1389 # Look for lazyYT YouTube embed
1390 matches = re.findall(
1391 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1393 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1395 # Look for embedded Dailymotion player
1396 matches = re.findall(
1397 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1399 return _playlist_from_matches(
1400 matches, lambda m: unescapeHTML(m[1]))
1402 # Look for embedded Dailymotion playlist player (#3822)
1404 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1406 playlists = re.findall(
1407 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1409 return _playlist_from_matches(
1410 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1412 # Look for embedded Wistia player
1414 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1416 embed_url = self._proto_relative_url(
1417 unescapeHTML(match.group('url')))
1419 '_type': 'url_transparent',
1422 'uploader': video_uploader,
1423 'title': video_title,
1427 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1430 '_type': 'url_transparent',
1431 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1433 'uploader': video_uploader,
1434 'title': video_title,
1435 'id': match.group('id')
1438 # Look for SVT player
1439 svt_url = SVTIE._extract_url(webpage)
1441 return self.url_result(svt_url, 'SVT')
1443 # Look for embedded condenast player
1444 matches = re.findall(
1445 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1449 '_type': 'playlist',
1452 'ie_key': 'CondeNast',
1454 } for ma in matches],
1455 'title': video_title,
1459 # Look for Bandcamp pages with custom domain
1460 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1461 if mobj is not None:
1462 burl = unescapeHTML(mobj.group(1))
1463 # Don't set the extractor because it can be a track url or an album
1464 return self.url_result(burl)
1466 # Look for embedded Vevo player
1468 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1469 if mobj is not None:
1470 return self.url_result(mobj.group('url'))
1472 # Look for embedded Viddler player
1474 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1476 if mobj is not None:
1477 return self.url_result(mobj.group('url'))
1479 # Look for NYTimes player
1481 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1483 if mobj is not None:
1484 return self.url_result(mobj.group('url'))
1486 # Look for Libsyn player
1488 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1489 if mobj is not None:
1490 return self.url_result(mobj.group('url'))
1492 # Look for Ooyala videos
1493 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1494 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1495 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1496 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1497 if mobj is not None:
1498 return OoyalaIE._build_url_result(mobj.group('ec'))
1500 # Look for multiple Ooyala embeds on SBN network websites
1501 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1502 if mobj is not None:
1503 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1505 return _playlist_from_matches(
1506 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1508 # Look for Aparat videos
1509 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1510 if mobj is not None:
1511 return self.url_result(mobj.group(1), 'Aparat')
1513 # Look for MPORA videos
1514 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1515 if mobj is not None:
1516 return self.url_result(mobj.group(1), 'Mpora')
1518 # Look for embedded NovaMov-based player
1520 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1521 (?P<url>http://(?:(?:embed|www)\.)?
1523 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1524 videoweed\.(?:es|com)|
1525 movshare\.(?:net|sx|ag)|
1526 divxstage\.(?:eu|net|ch|co|at|ag))
1527 /embed\.php.+?)\1''', webpage)
1528 if mobj is not None:
1529 return self.url_result(mobj.group('url'))
1531 # Look for embedded Facebook player
1533 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1534 if mobj is not None:
1535 return self.url_result(mobj.group('url'), 'Facebook')
1537 # Look for embedded VK player
1538 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1539 if mobj is not None:
1540 return self.url_result(mobj.group('url'), 'VK')
1542 # Look for embedded ivi player
1543 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1544 if mobj is not None:
1545 return self.url_result(mobj.group('url'), 'Ivi')
1547 # Look for embedded Huffington Post player
1549 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1550 if mobj is not None:
1551 return self.url_result(mobj.group('url'), 'HuffPost')
1554 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1555 if mobj is not None:
1556 return self.url_result(mobj.group('url'))
1557 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1558 if mobj is not None:
1559 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1561 # Look for funnyordie embed
1562 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1564 return _playlist_from_matches(
1565 matches, getter=unescapeHTML, ie='FunnyOrDie')
1567 # Look for BBC iPlayer embed
1568 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1570 return _playlist_from_matches(matches, ie='BBCCoUk')
1572 # Look for embedded RUTV player
1573 rutv_url = RUTVIE._extract_url(webpage)
1575 return self.url_result(rutv_url, 'RUTV')
1577 # Look for embedded TVC player
1578 tvc_url = TVCIE._extract_url(webpage)
1580 return self.url_result(tvc_url, 'TVC')
1582 # Look for embedded SportBox player
1583 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1585 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1587 # Look for embedded PornHub player
1588 pornhub_url = PornHubIE._extract_url(webpage)
1590 return self.url_result(pornhub_url, 'PornHub')
1592 # Look for embedded XHamster player
1593 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1595 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1597 # Look for embedded Tvigle player
1599 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1600 if mobj is not None:
1601 return self.url_result(mobj.group('url'), 'Tvigle')
1603 # Look for embedded TED player
1605 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1606 if mobj is not None:
1607 return self.url_result(mobj.group('url'), 'TED')
1609 # Look for embedded Ustream videos
1611 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1612 if mobj is not None:
1613 return self.url_result(mobj.group('url'), 'Ustream')
1615 # Look for embedded arte.tv player
1617 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1619 if mobj is not None:
1620 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1622 # Look for embedded francetv player
1624 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1626 if mobj is not None:
1627 return self.url_result(mobj.group('url'))
1629 # Look for embedded smotri.com player
1630 smotri_url = SmotriIE._extract_url(webpage)
1632 return self.url_result(smotri_url, 'Smotri')
1634 # Look for embedded Myvi.ru player
1635 myvi_url = MyviIE._extract_url(webpage)
1637 return self.url_result(myvi_url)
1639 # Look for embeded soundcloud player
1641 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1643 if mobj is not None:
1644 url = unescapeHTML(mobj.group('url'))
1645 return self.url_result(url)
1647 # Look for embedded vulture.com player
1649 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1651 if mobj is not None:
1652 url = unescapeHTML(mobj.group('url'))
1653 return self.url_result(url, ie='Vulture')
1655 # Look for embedded mtvservices player
1656 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1658 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1660 # Look for embedded yahoo player
1662 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1664 if mobj is not None:
1665 return self.url_result(mobj.group('url'), 'Yahoo')
1667 # Look for embedded sbs.com.au player
1671 <meta\s+property="og:video"\s+content=|
1674 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1676 if mobj is not None:
1677 return self.url_result(mobj.group('url'), 'SBS')
1679 # Look for embedded Cinchcast player
1681 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'), 'Cinchcast')
1687 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1691 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1693 if mobj is not None:
1694 return self.url_result(mobj.group('url'), 'MLB')
1697 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1699 if mobj is not None:
1700 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1703 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1705 if mobj is not None:
1706 return self.url_result(mobj.group('url'), 'Livestream')
1708 # Look for Zapiks embed
1710 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1711 if mobj is not None:
1712 return self.url_result(mobj.group('url'), 'Zapiks')
1714 # Look for Kaltura embeds
1715 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1716 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1717 if mobj is not None:
1718 return self.url_result(smuggle_url(
1719 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1720 {'source_url': url}), 'Kaltura')
1722 # Look for Eagle.Platform embeds
1724 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1725 if mobj is not None:
1726 return self.url_result(mobj.group('url'), 'EaglePlatform')
1728 # Look for ClipYou (uses Eagle.Platform) embeds
1730 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1731 if mobj is not None:
1732 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1734 # Look for Pladform embeds
1736 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1737 if mobj is not None:
1738 return self.url_result(mobj.group('url'), 'Pladform')
1740 # Look for Playwire embeds
1742 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1743 if mobj is not None:
1744 return self.url_result(mobj.group('url'))
1746 # Look for 5min embeds
1748 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1749 if mobj is not None:
1750 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1752 # Look for Crooks and Liars embeds
1754 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1755 if mobj is not None:
1756 return self.url_result(mobj.group('url'))
1758 # Look for NBC Sports VPlayer embeds
1759 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1761 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1763 # Look for UDN embeds
1765 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1766 if mobj is not None:
1767 return self.url_result(
1768 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1770 # Look for Senate ISVP iframe
1771 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1773 return self.url_result(senate_isvp_url, 'SenateISVP')
1775 # Look for Dailymotion Cloud videos
1776 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1778 return self.url_result(dmcloud_url, 'DailymotionCloud')
1780 # Look for OnionStudios embeds
1781 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1782 if onionstudios_url:
1783 return self.url_result(onionstudios_url)
1785 # Look for SnagFilms embeds
1786 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1788 return self.url_result(snagfilms_url)
1790 # Look for ScreenwaveMedia embeds
1791 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1792 if mobj is not None:
1793 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1795 # Look for AdobeTVVideo embeds
1797 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1799 if mobj is not None:
1800 return self.url_result(
1801 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1804 def check_video(vurl):
1805 if YoutubeIE.suitable(vurl):
1807 vpath = compat_urlparse.urlparse(vurl).path
1808 vext = determine_ext(vpath)
1809 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1811 def filter_video(urls):
1812 return list(filter(check_video, urls))
1814 # Start with something easy: JW Player in SWFObject
1815 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1817 # Look for gorilla-vid style embedding
1818 found = filter_video(re.findall(r'''(?sx)
1822 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1825 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1827 # Broaden the search a little bit
1828 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1830 # Broaden the findall a little bit: JWPlayer JS loader
1831 found = filter_video(re.findall(
1832 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1835 found = filter_video(re.findall(r'''(?xs)
1836 flowplayer\("[^"]+",\s*
1838 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1839 ["']?url["']?\s*:\s*["']([^"']+)["']
1844 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1846 # Try to find twitter cards info
1847 found = filter_video(re.findall(
1848 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1850 # We look for Open Graph info:
1851 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1852 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1853 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1854 if m_video_type is not None:
1855 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1858 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1860 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1862 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1863 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1866 # Look also in Refresh HTTP header
1867 refresh_header = head_response.headers.get('Refresh')
1869 # In python 2 response HTTP headers are bytestrings
1870 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1871 refresh_header = refresh_header.decode('iso-8859-1')
1872 found = re.search(REDIRECT_REGEX, refresh_header)
1874 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1875 self.report_following_redirect(new_url)
1881 raise UnsupportedError(url)
1884 for video_url in found:
1885 video_url = video_url.replace('\\/', '/')
1886 video_url = compat_urlparse.urljoin(url, video_url)
1887 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1889 # Sometimes, jwplayer extraction will result in a YouTube URL
1890 if YoutubeIE.suitable(video_url):
1891 entries.append(self.url_result(video_url, 'Youtube'))
1894 # here's a fun little line of code for you:
1895 video_id = os.path.splitext(video_id)[0]
1899 'uploader': video_uploader,
1900 'title': video_title,
1901 'age_limit': age_limit,
1904 ext = determine_ext(video_url)
1906 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1908 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1910 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1912 entry_info_dict['url'] = video_url
1914 entries.append(entry_info_dict)
1916 if len(entries) == 1:
1919 for num, e in enumerate(entries, start=1):
1920 # 'url' results don't have a title
1921 if e.get('title') is not None:
1922 e['title'] = '%s (%d)' % (e['title'], num)
1924 '_type': 'playlist',