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 .bliptv import BlipTVIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .snagfilms import SnagFilmsEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
59 class GenericIE(InfoExtractor):
60 IE_DESC = 'Generic downloader that works on some sites'
64 # Direct link to a video
66 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
67 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
72 'upload_date': '20100513',
75 # Direct link to media delivered compressed (until Accept-Encoding is *)
77 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
78 'md5': '128c42e68b13950268b648275386fc74',
80 'id': 'FictionJunction-Parallel_Hearts',
82 'title': 'FictionJunction-Parallel_Hearts',
83 'upload_date': '20140522',
85 'expected_warnings': [
86 'URL could be a direct video link, returning it as such.'
89 # Direct download with broken HEAD
91 'url': 'http://ai-radio.org:8000/radio.opus',
98 'skip_download': True, # infinite live stream
100 'expected_warnings': [
101 r'501.*Not Implemented'
104 # Direct link with incorrect MIME type
106 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
107 'md5': '4ccbebe5f36706d85221f204d7eb5913',
109 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
110 'id': '5_Lennart_Poettering_-_Systemd',
112 'title': '5_Lennart_Poettering_-_Systemd',
113 'upload_date': '20141120',
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
121 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
123 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
124 'title': 'Zero Punctuation',
125 'description': 're:.*groundbreaking video review series.*'
127 'playlist_mincount': 11,
129 # RSS feed with enclosure
131 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
133 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 'upload_date': '20150228',
136 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
139 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
141 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
145 'title': 'Automatics, robotics and biocybernetics',
146 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
147 'upload_date': '20130627',
148 'formats': 'mincount:16',
149 'subtitles': 'mincount:1',
152 'force_generic_extractor': True,
153 'skip_download': True,
156 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
158 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
163 'formats': 'mincount:1',
166 'skip_download': True,
169 # SMIL from https://www.restudy.dk/video/play/id/1637
171 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
175 'title': 'video_1637',
176 'formats': 'mincount:3',
179 'skip_download': True,
182 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
184 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
186 'id': 'smil-service',
188 'title': 'smil-service',
189 'formats': 'mincount:1',
192 'skip_download': True,
195 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
197 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
201 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
202 'formats': 'mincount:3',
205 'skip_download': True,
208 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
210 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
212 'id': 'mZlp2ctYIUEB',
214 'title': 'Tikibad ontruimd wegens brand',
215 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
216 'thumbnail': 're:^https?://.*\.jpg$',
220 'skip_download': True,
225 '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',
229 'upload_date': '20130224',
230 'uploader_id': 'TheVerge',
231 'description': 're:^Chris Ziegler takes a look at the\.*',
232 'uploader': 'The Verge',
233 'title': 'First Firefox OS phones side-by-side',
236 'skip_download': False,
240 # redirect in Refresh HTTP header
241 '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',
245 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
246 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
247 'upload_date': '20150917',
248 'uploader_id': 'brtvofficial',
249 'uploader': 'Boiler Room',
252 'skip_download': False,
256 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
257 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
259 'id': '13601338388002',
261 'uploader': 'www.hodiho.fr',
262 'title': 'R\u00e9gis plante sa Jeep',
265 # bandcamp page with custom domain
267 'add_ie': ['Bandcamp'],
268 'url': 'http://bronyrock.com/track/the-pony-mash',
272 'title': 'The Pony Mash',
273 'uploader': 'M_Pallante',
275 'skip': 'There is a limit of 200 free downloads / month for the test song',
277 # embedded brightcove video
278 # it also tests brightcove videos that need to set the 'Referer' in the
281 'add_ie': ['BrightcoveLegacy'],
282 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
284 'id': '2765128793001',
286 'title': 'Le cours de bourse : l’analyse technique',
287 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
288 'uploader': 'BFM BUSINESS',
291 'skip_download': True,
295 # https://github.com/rg3/youtube-dl/issues/2253
296 'url': 'http://bcove.me/i6nfkrc3',
297 'md5': '0ba9446db037002366bab3b3eb30c88c',
299 'id': '3101154703001',
301 'title': 'Still no power',
302 'uploader': 'thestar.com',
303 '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.',
305 'add_ie': ['BrightcoveLegacy'],
308 'url': 'http://www.championat.com/video/football/v/87/87499.html',
309 'md5': 'fb973ecf6e4a78a67453647444222983',
311 'id': '3414141473001',
313 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
314 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
315 'uploader': 'Championat',
319 # https://github.com/rg3/youtube-dl/issues/3541
320 'add_ie': ['BrightcoveLegacy'],
321 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
323 'id': '3866516442001',
325 'title': 'Leer mij vrouwen kennen: Aflevering 1',
326 'description': 'Leer mij vrouwen kennen: Aflevering 1',
327 'uploader': 'SBS Broadcasting',
329 'skip': 'Restricted to Netherlands',
331 'skip_download': True, # m3u8 download
336 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
337 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
339 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
341 'title': '2cc213299525360.mov', # that's what we get
344 'add_ie': ['Ooyala'],
347 # ooyala video embedded with http://player.ooyala.com/iframe.js
348 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
350 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
352 'title': '"Steve Jobs: Man in the Machine" trailer',
353 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
357 'skip_download': True,
360 # multiple ooyala embeds on SBN network websites
362 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
364 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
365 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
367 'playlist_mincount': 3,
369 'skip_download': True,
371 'add_ie': ['Ooyala'],
375 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
379 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
380 'upload_date': '20140225',
381 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
382 'uploader': 'Tested',
383 'uploader_id': 'testedcom',
385 # No need to test YoutubeIE here
387 'skip_download': True,
392 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
396 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
397 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
402 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
406 'title': 'Охотское море стало целиком российским',
407 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
411 'skip_download': True,
416 '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/',
420 'title': 'Дошкольное воспитание',
425 'url': 'http://www.vestifinance.ru/articles/25753',
428 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
433 'title': 'Госзаказ. День 3',
439 'title': 'Госзаказ. День 2',
445 'title': 'Госзаказ. День 1',
451 'skip_download': True,
456 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
458 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
460 'title': 'Ужастики, русский трейлер (2015)',
461 'thumbnail': 're:^https?://.*\.jpg$',
467 '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',
470 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
472 'playlist_mincount': 7,
476 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
477 'md5': '65fdff94098e4a607385a60c5177c638',
481 'title': 'Hidden miracles of the natural world',
482 'uploader': 'Louie Schwartzberg',
483 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
486 # Embeded Ustream video
488 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
489 'md5': '27b99cdb639c9b12a79bca876a073417',
493 'uploader': 'AU SPA: The NSA and Privacy',
494 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
497 # nowvideo embed hidden behind percent encoding
499 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
500 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
502 'id': '06e53103ca9aa',
504 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
505 'description': 'No description',
510 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
511 'md5': '7653032cbb25bf6c80d80f217055fa43',
513 'id': '048195-004_PLUS7-F',
516 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
517 'upload_date': '20140320',
520 'skip_download': 'Requires rtmpdump'
525 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
529 'title': 'Alcaline, le concert avec Calogero',
530 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
531 'upload_date': '20150226',
532 'timestamp': 1424989860,
537 'skip_download': True,
539 'expected_warnings': [
545 'url': 'http://www.wired.com/2014/04/honda-asimo/',
546 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
548 'id': '53501be369702d3275860000',
550 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
555 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
556 'md5': '441aeeb82eb72c422c7f14ec533999cd',
558 'id': 'k2mm4bCdJ6CQ2i7c8o2',
560 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
563 'add_ie': ['Dailymotion'],
567 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
571 'title': 'The NBL Auction 2014',
572 'uploader': 'BADMINTON England',
573 'uploader_id': 'BADMINTONEvents',
574 'upload_date': '20140603',
575 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
577 'add_ie': ['Youtube'],
579 'skip_download': True,
584 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
585 'md5': '35727f82f58c76d996fc188f9755b0d5',
587 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
590 'description': 'Mario\'s life in the fast lane has never looked so good.',
593 # YouTube embed via <data-embed-url="">
595 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
599 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
600 'uploader': 'Gameloft',
601 'uploader_id': 'gameloft',
602 'upload_date': '20140828',
603 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
606 'skip_download': True,
611 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
613 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
615 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
616 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
621 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
623 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
624 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
630 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
635 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
636 'md5': '9d65602bf31c6e20014319c7d07fba27',
638 'id': '5123ea6d5e5a7',
641 'uploader': 'www.handjobhub.com',
642 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
645 # Multiple brightcove videos
646 # https://github.com/rg3/youtube-dl/issues/2283
648 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
650 'id': 'always-never',
651 'title': 'Always / Never - The New Yorker',
655 'extract_flat': False,
656 'skip_download': True,
661 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
662 'md5': '96f09a37e44da40dd083e12d9a683327',
666 'title': 'Ump changes call to ball',
667 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
669 'timestamp': 1401537900,
670 'upload_date': '20140531',
671 'thumbnail': 're:^https?://.*\.jpg$',
676 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
677 'md5': '8788b683c777a5cf25621eaf286d0c23',
681 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
683 'filesize': 182808282,
684 'uploader': 'education-portal.com',
688 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
689 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
693 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
695 'uploader': 'thoughtworks.wistia.com',
700 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
704 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
705 'uploader': 'Sophos Security',
706 'title': 'Chet Chat 171 - Oct 29, 2014',
707 'upload_date': '20141029',
712 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
716 'upload_date': '20141112',
717 'title': 'Rosetta #CometLanding webcast HL 10',
722 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
725 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
727 'playlist_mincount': 2,
731 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
735 'upload_date': '20141126',
736 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
741 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
743 'id': '730m_DandD_1901_512k',
745 'uploader': 'www.abc.net.au',
746 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
749 # embedded viddler video
751 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
755 'uploader': 'deadspin',
756 'title': 'WALL-TO-GORTAT',
757 'timestamp': 1422285291,
758 'upload_date': '20150126',
760 'add_ie': ['Viddler'],
764 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
768 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
769 'description': 'md5:601cb790edd05908957dae8aaa866465',
770 'upload_date': '20150220',
775 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
779 'upload_date': '20150212',
780 'uploader': 'The National Archives UK',
781 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
782 'uploader_id': 'NationalArchives08',
783 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
788 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
789 'playlist_mincount': 5,
791 'id': 'aanslagen-kopenhagen',
792 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
797 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
801 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
806 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
810 'upload_date': '20150226',
811 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
813 'title': 'John Carlson Postgame 2/25/15',
816 # Kaltura embed (different embed code)
818 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
822 'upload_date': '20150127',
823 'uploader_id': 'PremierMedia',
825 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
828 # Kaltura embed protected with referrer
830 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
834 'title': 'Violetta - Achter De Schermen - Ruggero',
835 'description': 'Achter de schermen met Ruggero',
836 'timestamp': 1435133761,
837 'upload_date': '20150624',
838 'uploader_id': 'echojecka',
841 # Eagle.Platform embed (generic URL)
843 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
847 'title': 'Навальный вышел на свободу',
848 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
849 'thumbnail': 're:^https?://.*\.jpg$',
855 # ClipYou (Eagle.Platform) embed (custom URL)
857 'url': 'http://muz-tv.ru/play/7129/',
861 'title': "'O Sole Mio",
862 'thumbnail': 're:^https?://.*\.jpg$',
869 'url': 'http://muz-tv.ru/kinozal/view/7400/',
873 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
874 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
875 'thumbnail': 're:^https?://.*\.jpg$',
882 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
886 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
887 'thumbnail': 're:^https?://.*\.png$',
893 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
894 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
898 'title': 'Facebook Creates "On This Day" | Crunch Report',
903 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
907 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
912 # Crooks and Liars embed
914 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
918 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
919 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
920 'timestamp': 1428207000,
921 'upload_date': '20150405',
922 'uploader': 'Heather',
925 # Crooks and Liars external embed
927 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
929 'id': 'MTE3MjUtMzQ2MzA',
931 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
932 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
933 'timestamp': 1265032391,
934 'upload_date': '20100201',
935 'uploader': 'Heather',
938 # NBC Sports vplayer embed
940 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
942 'id': 'ln7x1qSThw4k',
944 'title': "PFT Live: New leader in the 'new-look' defense",
945 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
950 'url': 'http://www.udn.com/news/story/7314/822787',
951 'md5': 'fd2060e988c326991037b9aff9df21a6',
955 'title': '中一中男師變性 全校師生力挺',
956 'thumbnail': 're:^https?://.*\.jpg$',
961 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
963 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
965 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
966 'title': 'This is what separates the Excel masters from the wannabes',
971 'skip_download': True,
974 # Contains a SMIL manifest
976 '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',
980 'title': '+ Football: Lottery Champions League Europe',
981 'uploader': 'www.telewebion.com',
985 'skip_download': True,
988 # Brightcove URL in single quotes
990 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
991 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
993 'id': '4255764656001',
995 'title': 'SN Presents: Russell Martin, World Citizen',
996 '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.',
997 'uploader': 'Rogers Sportsnet',
1000 # Dailymotion Cloud video
1002 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1003 'md5': '49444254273501a64675a7e68c502681',
1005 'id': '5585de919473990de4bee11b',
1007 'title': 'Le débat',
1008 'thumbnail': 're:^https?://.*\.jpe?g$',
1011 # OnionStudios embed
1013 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1017 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1018 'thumbnail': 're:^https?://.*\.jpe?g$',
1019 'uploader': 'ClickHole',
1020 'uploader_id': 'clickhole',
1025 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1027 'id': '74849a00-85a9-11e1-9660-123139220831',
1029 'title': '#whilewewatch',
1032 # AdobeTVVideo embed
1034 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1035 'md5': '43662b577c018ad707a63766462b1e87',
1039 'title': 'New experience with Acrobat DC',
1040 'description': 'New experience with Acrobat DC',
1041 'duration': 248.667,
1044 # ScreenwaveMedia embed
1046 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1047 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1049 'id': 'cinemasnob-55d26273809dd',
1051 'title': 'cinemasnob',
1054 # BrightcoveInPageEmbed embed
1056 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1058 'id': '4238694884001',
1060 'title': 'Tabletop: Dread, Last Thoughts',
1061 'description': 'Tabletop: Dread, Last Thoughts',
1065 # JWPlayer with M3U8
1067 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1071 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1072 'uploader': 'ren.tv',
1076 'skip_download': True,
1081 def report_following_redirect(self, new_url):
1082 """Report information extraction."""
1083 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1085 def _extract_rss(self, url, video_id, doc):
1086 playlist_title = doc.find('./channel/title').text
1087 playlist_desc_el = doc.find('./channel/description')
1088 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1091 for it in doc.findall('./channel/item'):
1092 next_url = xpath_text(it, 'link', fatal=False)
1094 enclosure_nodes = it.findall('./enclosure')
1095 for e in enclosure_nodes:
1096 next_url = e.attrib.get('url')
1106 'title': it.find('title').text,
1110 '_type': 'playlist',
1112 'title': playlist_title,
1113 'description': playlist_desc,
1117 def _extract_camtasia(self, url, video_id, webpage):
1118 """ Returns None if no camtasia video can be found. """
1120 camtasia_cfg = self._search_regex(
1121 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1122 webpage, 'camtasia configuration file', default=None)
1123 if camtasia_cfg is None:
1126 title = self._html_search_meta('DC.title', webpage, fatal=True)
1128 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1129 camtasia_cfg = self._download_xml(
1130 camtasia_url, video_id,
1131 note='Downloading camtasia configuration',
1132 errnote='Failed to download camtasia configuration')
1133 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1136 for n in fileset_node.getchildren():
1137 url_n = n.find('./uri')
1142 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1143 'title': '%s - %s' % (title, n.tag),
1144 'url': compat_urlparse.urljoin(url, url_n.text),
1145 'duration': float_or_none(n.find('./duration').text),
1149 '_type': 'playlist',
1154 def _real_extract(self, url):
1155 if url.startswith('//'):
1158 'url': self.http_scheme() + url,
1161 parsed_url = compat_urlparse.urlparse(url)
1162 if not parsed_url.scheme:
1163 default_search = self._downloader.params.get('default_search')
1164 if default_search is None:
1165 default_search = 'fixup_error'
1167 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1169 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1170 return self.url_result('http://' + url)
1171 elif default_search != 'fixup_error':
1172 if default_search == 'auto_warning':
1173 if re.match(r'^(?:url|URL)$', url):
1174 raise ExtractorError(
1175 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1178 self._downloader.report_warning(
1179 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1180 return self.url_result('ytsearch:' + url)
1182 if default_search in ('error', 'fixup_error'):
1183 raise ExtractorError(
1184 '%r is not a valid URL. '
1185 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1186 % (url, url), expected=True)
1188 if ':' not in default_search:
1189 default_search += ':'
1190 return self.url_result(default_search + url)
1192 url, smuggled_data = unsmuggle_url(url)
1193 force_videoid = None
1194 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1195 if smuggled_data and 'force_videoid' in smuggled_data:
1196 force_videoid = smuggled_data['force_videoid']
1197 video_id = force_videoid
1199 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1201 self.to_screen('%s: Requesting header' % video_id)
1203 head_req = HEADRequest(url)
1204 head_response = self._request_webpage(
1206 note=False, errnote='Could not send HEAD request to %s' % url,
1209 if head_response is not False:
1210 # Check for redirect
1211 new_url = head_response.geturl()
1213 self.report_following_redirect(new_url)
1215 new_url = smuggle_url(
1216 new_url, {'force_videoid': force_videoid})
1217 return self.url_result(new_url)
1219 full_response = None
1220 if head_response is False:
1221 request = sanitized_Request(url)
1222 request.add_header('Accept-Encoding', '*')
1223 full_response = self._request_webpage(request, video_id)
1224 head_response = full_response
1226 # Check for direct link to a video
1227 content_type = head_response.headers.get('Content-Type', '')
1228 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1230 upload_date = unified_strdate(
1231 head_response.headers.get('Last-Modified'))
1234 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1237 'format_id': m.group('format_id'),
1239 'vcodec': 'none' if m.group('type') == 'audio' else None
1241 'upload_date': upload_date,
1244 if not self._downloader.params.get('test', False) and not is_intentional:
1245 force = self._downloader.params.get('force_generic_extractor', False)
1246 self._downloader.report_warning(
1247 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1249 if not full_response:
1250 request = sanitized_Request(url)
1251 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1252 # making it impossible to download only chunk of the file (yet we need only 512kB to
1253 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1254 # that will always result in downloading the whole file that is not desirable.
1255 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1256 # to accept raw bytes and being able to download only a chunk.
1257 # It may probably better to solve this by checking Content-Type for application/octet-stream
1258 # after HEAD request finishes, but not sure if we can rely on this.
1259 request.add_header('Accept-Encoding', '*')
1260 full_response = self._request_webpage(request, video_id)
1262 # Maybe it's a direct link to a video?
1263 # Be careful not to download the whole thing!
1264 first_bytes = full_response.read(512)
1265 if not is_html(first_bytes):
1266 self._downloader.report_warning(
1267 'URL could be a direct video link, returning it as such.')
1268 upload_date = unified_strdate(
1269 head_response.headers.get('Last-Modified'))
1272 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1275 'upload_date': upload_date,
1278 webpage = self._webpage_read_content(
1279 full_response, url, video_id, prefix=first_bytes)
1281 self.report_extraction(video_id)
1283 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1285 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1286 if doc.tag == 'rss':
1287 return self._extract_rss(url, video_id, doc)
1288 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1289 return self._parse_smil(doc, url, video_id)
1290 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1291 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1292 except compat_xml_parse_error:
1295 # Is it a Camtasia project?
1296 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1297 if camtasia_res is not None:
1300 # Sometimes embedded video player is hidden behind percent encoding
1301 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1302 # Unescaping the whole page allows to handle those cases in a generic way
1303 webpage = compat_urllib_parse_unquote(webpage)
1305 # it's tempting to parse this further, but you would
1306 # have to take into account all the variations like
1307 # Video Title - Site Name
1308 # Site Name | Video Title
1309 # Video Title - Tagline | Site Name
1310 # and so on and so forth; it's just not practical
1311 video_title = self._html_search_regex(
1312 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1315 # Try to detect age limit automatically
1316 age_limit = self._rta_search(webpage)
1317 # And then there are the jokers who advertise that they use RTA,
1318 # but actually don't.
1319 AGE_LIMIT_MARKERS = [
1320 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1322 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1325 # video uploader is domain name
1326 video_uploader = self._search_regex(
1327 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1330 def _playlist_from_matches(matches, getter=None, ie=None):
1332 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1334 return self.playlist_result(
1335 urlrs, playlist_id=video_id, playlist_title=video_title)
1337 # Look for Brightcove Legacy Studio embeds
1338 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1340 self.to_screen('Brightcove video detected.')
1343 'url': smuggle_url(bc_url, {'Referer': url}),
1344 'ie_key': 'BrightcoveLegacy'
1345 } for bc_url in bc_urls]
1348 '_type': 'playlist',
1349 'title': video_title,
1354 # Look for Brightcove New Studio embeds
1355 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1357 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1359 # Look for embedded rtl.nl player
1360 matches = re.findall(
1361 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1364 return _playlist_from_matches(matches, ie='RtlNl')
1366 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1367 if vimeo_url is not None:
1368 return self.url_result(vimeo_url)
1370 vid_me_embed_url = self._search_regex(
1371 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1372 webpage, 'vid.me embed', default=None)
1373 if vid_me_embed_url is not None:
1374 return self.url_result(vid_me_embed_url, 'Vidme')
1376 # Look for embedded YouTube player
1377 matches = re.findall(r'''(?x)
1386 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1390 return _playlist_from_matches(
1391 matches, lambda m: unescapeHTML(m[1]))
1393 # Look for lazyYT YouTube embed
1394 matches = re.findall(
1395 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1397 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1399 # Look for embedded Dailymotion player
1400 matches = re.findall(
1401 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1403 return _playlist_from_matches(
1404 matches, lambda m: unescapeHTML(m[1]))
1406 # Look for embedded Dailymotion playlist player (#3822)
1408 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1410 playlists = re.findall(
1411 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1413 return _playlist_from_matches(
1414 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1416 # Look for embedded Wistia player
1418 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1420 embed_url = self._proto_relative_url(
1421 unescapeHTML(match.group('url')))
1423 '_type': 'url_transparent',
1426 'uploader': video_uploader,
1427 'title': video_title,
1431 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1434 '_type': 'url_transparent',
1435 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1437 'uploader': video_uploader,
1438 'title': video_title,
1439 'id': match.group('id')
1442 # Look for embedded blip.tv player
1443 bliptv_url = BlipTVIE._extract_url(webpage)
1445 return self.url_result(bliptv_url, 'BlipTV')
1447 # Look for SVT player
1448 svt_url = SVTIE._extract_url(webpage)
1450 return self.url_result(svt_url, 'SVT')
1452 # Look for embedded condenast player
1453 matches = re.findall(
1454 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1458 '_type': 'playlist',
1461 'ie_key': 'CondeNast',
1463 } for ma in matches],
1464 'title': video_title,
1468 # Look for Bandcamp pages with custom domain
1469 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1470 if mobj is not None:
1471 burl = unescapeHTML(mobj.group(1))
1472 # Don't set the extractor because it can be a track url or an album
1473 return self.url_result(burl)
1475 # Look for embedded Vevo player
1477 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1478 if mobj is not None:
1479 return self.url_result(mobj.group('url'))
1481 # Look for embedded Viddler player
1483 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1485 if mobj is not None:
1486 return self.url_result(mobj.group('url'))
1488 # Look for NYTimes player
1490 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1492 if mobj is not None:
1493 return self.url_result(mobj.group('url'))
1495 # Look for Libsyn player
1497 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1498 if mobj is not None:
1499 return self.url_result(mobj.group('url'))
1501 # Look for Ooyala videos
1502 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1503 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1504 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1505 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1506 if mobj is not None:
1507 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1509 # Look for multiple Ooyala embeds on SBN network websites
1510 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1511 if mobj is not None:
1512 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1514 return _playlist_from_matches(
1515 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1517 # Look for Aparat videos
1518 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1519 if mobj is not None:
1520 return self.url_result(mobj.group(1), 'Aparat')
1522 # Look for MPORA videos
1523 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1524 if mobj is not None:
1525 return self.url_result(mobj.group(1), 'Mpora')
1527 # Look for embedded NovaMov-based player
1529 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1530 (?P<url>http://(?:(?:embed|www)\.)?
1532 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1533 videoweed\.(?:es|com)|
1534 movshare\.(?:net|sx|ag)|
1535 divxstage\.(?:eu|net|ch|co|at|ag))
1536 /embed\.php.+?)\1''', webpage)
1537 if mobj is not None:
1538 return self.url_result(mobj.group('url'))
1540 # Look for embedded Facebook player
1542 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1543 if mobj is not None:
1544 return self.url_result(mobj.group('url'), 'Facebook')
1546 # Look for embedded VK player
1547 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1548 if mobj is not None:
1549 return self.url_result(mobj.group('url'), 'VK')
1551 # Look for embedded ivi player
1552 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1553 if mobj is not None:
1554 return self.url_result(mobj.group('url'), 'Ivi')
1556 # Look for embedded Huffington Post player
1558 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1559 if mobj is not None:
1560 return self.url_result(mobj.group('url'), 'HuffPost')
1563 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1564 if mobj is not None:
1565 return self.url_result(mobj.group('url'))
1566 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1567 if mobj is not None:
1568 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1570 # Look for funnyordie embed
1571 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1573 return _playlist_from_matches(
1574 matches, getter=unescapeHTML, ie='FunnyOrDie')
1576 # Look for BBC iPlayer embed
1577 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1579 return _playlist_from_matches(matches, ie='BBCCoUk')
1581 # Look for embedded RUTV player
1582 rutv_url = RUTVIE._extract_url(webpage)
1584 return self.url_result(rutv_url, 'RUTV')
1586 # Look for embedded TVC player
1587 tvc_url = TVCIE._extract_url(webpage)
1589 return self.url_result(tvc_url, 'TVC')
1591 # Look for embedded SportBox player
1592 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1594 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1596 # Look for embedded PornHub player
1597 pornhub_url = PornHubIE._extract_url(webpage)
1599 return self.url_result(pornhub_url, 'PornHub')
1601 # Look for embedded XHamster player
1602 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1604 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1606 # Look for embedded Tvigle player
1608 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1609 if mobj is not None:
1610 return self.url_result(mobj.group('url'), 'Tvigle')
1612 # Look for embedded TED player
1614 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1615 if mobj is not None:
1616 return self.url_result(mobj.group('url'), 'TED')
1618 # Look for embedded Ustream videos
1620 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1621 if mobj is not None:
1622 return self.url_result(mobj.group('url'), 'Ustream')
1624 # Look for embedded arte.tv player
1626 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1628 if mobj is not None:
1629 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1631 # Look for embedded francetv player
1633 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1635 if mobj is not None:
1636 return self.url_result(mobj.group('url'))
1638 # Look for embedded smotri.com player
1639 smotri_url = SmotriIE._extract_url(webpage)
1641 return self.url_result(smotri_url, 'Smotri')
1643 # Look for embedded Myvi.ru player
1644 myvi_url = MyviIE._extract_url(webpage)
1646 return self.url_result(myvi_url)
1648 # Look for embeded soundcloud player
1650 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1652 if mobj is not None:
1653 url = unescapeHTML(mobj.group('url'))
1654 return self.url_result(url)
1656 # Look for embedded vulture.com player
1658 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1660 if mobj is not None:
1661 url = unescapeHTML(mobj.group('url'))
1662 return self.url_result(url, ie='Vulture')
1664 # Look for embedded mtvservices player
1665 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1667 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1669 # Look for embedded yahoo player
1671 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1673 if mobj is not None:
1674 return self.url_result(mobj.group('url'), 'Yahoo')
1676 # Look for embedded sbs.com.au player
1680 <meta\s+property="og:video"\s+content=|
1683 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1685 if mobj is not None:
1686 return self.url_result(mobj.group('url'), 'SBS')
1688 # Look for embedded Cinchcast player
1690 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1692 if mobj is not None:
1693 return self.url_result(mobj.group('url'), 'Cinchcast')
1696 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1700 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1702 if mobj is not None:
1703 return self.url_result(mobj.group('url'), 'MLB')
1706 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1708 if mobj is not None:
1709 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1712 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1714 if mobj is not None:
1715 return self.url_result(mobj.group('url'), 'Livestream')
1717 # Look for Zapiks embed
1719 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1720 if mobj is not None:
1721 return self.url_result(mobj.group('url'), 'Zapiks')
1723 # Look for Kaltura embeds
1724 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1725 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))
1726 if mobj is not None:
1727 return self.url_result(smuggle_url(
1728 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1729 {'source_url': url}), 'Kaltura')
1731 # Look for Eagle.Platform embeds
1733 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1734 if mobj is not None:
1735 return self.url_result(mobj.group('url'), 'EaglePlatform')
1737 # Look for ClipYou (uses Eagle.Platform) embeds
1739 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1740 if mobj is not None:
1741 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1743 # Look for Pladform embeds
1745 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1746 if mobj is not None:
1747 return self.url_result(mobj.group('url'), 'Pladform')
1749 # Look for Playwire embeds
1751 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'))
1755 # Look for 5min embeds
1757 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1758 if mobj is not None:
1759 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1761 # Look for Crooks and Liars embeds
1763 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1764 if mobj is not None:
1765 return self.url_result(mobj.group('url'))
1767 # Look for NBC Sports VPlayer embeds
1768 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1770 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1772 # Look for UDN embeds
1774 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1775 if mobj is not None:
1776 return self.url_result(
1777 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1779 # Look for Senate ISVP iframe
1780 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1782 return self.url_result(senate_isvp_url, 'SenateISVP')
1784 # Look for Dailymotion Cloud videos
1785 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1787 return self.url_result(dmcloud_url, 'DailymotionCloud')
1789 # Look for OnionStudios embeds
1790 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1791 if onionstudios_url:
1792 return self.url_result(onionstudios_url)
1794 # Look for SnagFilms embeds
1795 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1797 return self.url_result(snagfilms_url)
1799 # Look for ScreenwaveMedia embeds
1800 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1801 if mobj is not None:
1802 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1804 # Look for AdobeTVVideo embeds
1806 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1808 if mobj is not None:
1809 return self.url_result(
1810 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1813 def check_video(vurl):
1814 if YoutubeIE.suitable(vurl):
1816 vpath = compat_urlparse.urlparse(vurl).path
1817 vext = determine_ext(vpath)
1818 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1820 def filter_video(urls):
1821 return list(filter(check_video, urls))
1823 # Start with something easy: JW Player in SWFObject
1824 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1826 # Look for gorilla-vid style embedding
1827 found = filter_video(re.findall(r'''(?sx)
1831 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1834 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1836 # Broaden the search a little bit
1837 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1839 # Broaden the findall a little bit: JWPlayer JS loader
1840 found = filter_video(re.findall(
1841 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1844 found = filter_video(re.findall(r'''(?xs)
1845 flowplayer\("[^"]+",\s*
1847 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1848 ["']?url["']?\s*:\s*["']([^"']+)["']
1853 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1855 # Try to find twitter cards info
1856 found = filter_video(re.findall(
1857 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1859 # We look for Open Graph info:
1860 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1861 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1862 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1863 if m_video_type is not None:
1864 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1867 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1869 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1871 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1872 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1875 # Look also in Refresh HTTP header
1876 refresh_header = head_response.headers.get('Refresh')
1878 # In python 2 response HTTP headers are bytestrings
1879 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1880 refresh_header = refresh_header.decode('iso-8859-1')
1881 found = re.search(REDIRECT_REGEX, refresh_header)
1883 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1884 self.report_following_redirect(new_url)
1890 raise UnsupportedError(url)
1893 for video_url in found:
1894 video_url = video_url.replace('\\/', '/')
1895 video_url = compat_urlparse.urljoin(url, video_url)
1896 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1898 # Sometimes, jwplayer extraction will result in a YouTube URL
1899 if YoutubeIE.suitable(video_url):
1900 entries.append(self.url_result(video_url, 'Youtube'))
1903 # here's a fun little line of code for you:
1904 video_id = os.path.splitext(video_id)[0]
1908 'uploader': video_uploader,
1909 'title': video_title,
1910 'age_limit': age_limit,
1913 ext = determine_ext(video_url)
1915 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1917 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1919 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1921 entry_info_dict['url'] = video_url
1923 entries.append(entry_info_dict)
1925 if len(entries) == 1:
1928 for num, e in enumerate(entries, start=1):
1929 # 'url' results don't have a title
1930 if e.get('title') is not None:
1931 e['title'] = '%s (%d)' % (e['title'], num)
1933 '_type': 'playlist',