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 .tnaflix import TNAFlixNetworkEmbedIE
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
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
64 class GenericIE(InfoExtractor):
65 IE_DESC = 'Generic downloader that works on some sites'
69 # Direct link to a video
71 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
72 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
77 'upload_date': '20100513',
80 # Direct link to media delivered compressed (until Accept-Encoding is *)
82 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
83 'md5': '128c42e68b13950268b648275386fc74',
85 'id': 'FictionJunction-Parallel_Hearts',
87 'title': 'FictionJunction-Parallel_Hearts',
88 'upload_date': '20140522',
90 'expected_warnings': [
91 'URL could be a direct video link, returning it as such.'
94 # Direct download with broken HEAD
96 'url': 'http://ai-radio.org:8000/radio.opus',
103 'skip_download': True, # infinite live stream
105 'expected_warnings': [
106 r'501.*Not Implemented'
109 # Direct link with incorrect MIME type
111 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
112 'md5': '4ccbebe5f36706d85221f204d7eb5913',
114 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
115 'id': '5_Lennart_Poettering_-_Systemd',
117 'title': '5_Lennart_Poettering_-_Systemd',
118 'upload_date': '20141120',
120 'expected_warnings': [
121 'URL could be a direct video link, returning it as such.'
126 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
128 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
129 'title': 'Zero Punctuation',
130 'description': 're:.*groundbreaking video review series.*'
132 'playlist_mincount': 11,
134 # RSS feed with enclosure
136 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
138 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
140 'upload_date': '20150228',
141 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
144 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
146 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
150 'title': 'Automatics, robotics and biocybernetics',
151 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
152 'upload_date': '20130627',
153 'formats': 'mincount:16',
154 'subtitles': 'mincount:1',
157 'force_generic_extractor': True,
158 'skip_download': True,
161 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
163 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
168 'formats': 'mincount:1',
171 'skip_download': True,
174 # SMIL from https://www.restudy.dk/video/play/id/1637
176 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
180 'title': 'video_1637',
181 'formats': 'mincount:3',
184 'skip_download': True,
187 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
189 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
191 'id': 'smil-service',
193 'title': 'smil-service',
194 'formats': 'mincount:1',
197 'skip_download': True,
200 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
202 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
206 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
207 'formats': 'mincount:3',
210 'skip_download': True,
213 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
215 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
217 'id': 'mZlp2ctYIUEB',
219 'title': 'Tikibad ontruimd wegens brand',
220 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
221 'thumbnail': 're:^https?://.*\.jpg$',
225 'skip_download': True,
228 # MPD from http://dash-mse-test.appspot.com/media.html
230 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
231 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
233 'id': 'car-20120827-manifest',
235 'title': 'car-20120827-manifest',
236 'formats': 'mincount:9',
239 'format': 'bestvideo',
242 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
244 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
249 'formats': 'mincount:8',
253 'skip_download': True,
258 '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',
262 'upload_date': '20130224',
263 'uploader_id': 'TheVerge',
264 'description': 're:^Chris Ziegler takes a look at the\.*',
265 'uploader': 'The Verge',
266 'title': 'First Firefox OS phones side-by-side',
269 'skip_download': False,
273 # redirect in Refresh HTTP header
274 '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',
278 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
279 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
280 'upload_date': '20150917',
281 'uploader_id': 'brtvofficial',
282 'uploader': 'Boiler Room',
285 'skip_download': False,
289 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
290 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
292 'id': '13601338388002',
294 'uploader': 'www.hodiho.fr',
295 'title': 'R\u00e9gis plante sa Jeep',
298 # bandcamp page with custom domain
300 'add_ie': ['Bandcamp'],
301 'url': 'http://bronyrock.com/track/the-pony-mash',
305 'title': 'The Pony Mash',
306 'uploader': 'M_Pallante',
308 'skip': 'There is a limit of 200 free downloads / month for the test song',
310 # embedded brightcove video
311 # it also tests brightcove videos that need to set the 'Referer' in the
314 'add_ie': ['BrightcoveLegacy'],
315 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
317 'id': '2765128793001',
319 'title': 'Le cours de bourse : l’analyse technique',
320 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
321 'uploader': 'BFM BUSINESS',
324 'skip_download': True,
328 # https://github.com/rg3/youtube-dl/issues/2253
329 'url': 'http://bcove.me/i6nfkrc3',
330 'md5': '0ba9446db037002366bab3b3eb30c88c',
332 'id': '3101154703001',
334 'title': 'Still no power',
335 'uploader': 'thestar.com',
336 '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.',
338 'add_ie': ['BrightcoveLegacy'],
341 'url': 'http://www.championat.com/video/football/v/87/87499.html',
342 'md5': 'fb973ecf6e4a78a67453647444222983',
344 'id': '3414141473001',
346 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
347 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
348 'uploader': 'Championat',
352 # https://github.com/rg3/youtube-dl/issues/3541
353 'add_ie': ['BrightcoveLegacy'],
354 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
356 'id': '3866516442001',
358 'title': 'Leer mij vrouwen kennen: Aflevering 1',
359 'description': 'Leer mij vrouwen kennen: Aflevering 1',
360 'uploader': 'SBS Broadcasting',
362 'skip': 'Restricted to Netherlands',
364 'skip_download': True, # m3u8 download
369 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
370 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
372 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
374 'title': '2cc213299525360.mov', # that's what we get
377 'add_ie': ['Ooyala'],
380 # ooyala video embedded with http://player.ooyala.com/iframe.js
381 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
383 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
385 'title': '"Steve Jobs: Man in the Machine" trailer',
386 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
390 'skip_download': True,
393 # multiple ooyala embeds on SBN network websites
395 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
397 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
398 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
400 'playlist_mincount': 3,
402 'skip_download': True,
404 'add_ie': ['Ooyala'],
408 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
412 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
413 'upload_date': '20140225',
414 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
415 'uploader': 'Tested',
416 'uploader_id': 'testedcom',
418 # No need to test YoutubeIE here
420 'skip_download': True,
425 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
429 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
430 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
435 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
439 'title': 'Охотское море стало целиком российским',
440 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
444 'skip_download': True,
449 '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/',
453 'title': 'Дошкольное воспитание',
458 'url': 'http://www.vestifinance.ru/articles/25753',
461 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
466 'title': 'Госзаказ. День 3',
472 'title': 'Госзаказ. День 2',
478 'title': 'Госзаказ. День 1',
484 'skip_download': True,
489 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
491 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
493 'title': 'Ужастики, русский трейлер (2015)',
494 'thumbnail': 're:^https?://.*\.jpg$',
500 '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',
503 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
505 'playlist_mincount': 7,
509 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
510 'md5': '65fdff94098e4a607385a60c5177c638',
514 'title': 'Hidden miracles of the natural world',
515 'uploader': 'Louie Schwartzberg',
516 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
519 # Embedded Ustream video
521 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
522 'md5': '27b99cdb639c9b12a79bca876a073417',
526 'uploader': 'AU SPA: The NSA and Privacy',
527 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
530 # nowvideo embed hidden behind percent encoding
532 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
533 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
535 'id': '06e53103ca9aa',
537 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
538 'description': 'No description',
543 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
544 'md5': '7653032cbb25bf6c80d80f217055fa43',
546 'id': '048195-004_PLUS7-F',
549 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
550 'upload_date': '20140320',
553 'skip_download': 'Requires rtmpdump'
558 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
562 'title': 'Alcaline, le concert avec Calogero',
563 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
564 'upload_date': '20150226',
565 'timestamp': 1424989860,
570 'skip_download': True,
572 'expected_warnings': [
578 'url': 'http://www.wired.com/2014/04/honda-asimo/',
579 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
581 'id': '53501be369702d3275860000',
583 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
588 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
589 'md5': '441aeeb82eb72c422c7f14ec533999cd',
591 'id': 'k2mm4bCdJ6CQ2i7c8o2',
593 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
596 'add_ie': ['Dailymotion'],
600 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
604 'title': 'The NBL Auction 2014',
605 'uploader': 'BADMINTON England',
606 'uploader_id': 'BADMINTONEvents',
607 'upload_date': '20140603',
608 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
610 'add_ie': ['Youtube'],
612 'skip_download': True,
617 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
618 'md5': '35727f82f58c76d996fc188f9755b0d5',
620 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
623 'description': 'Mario\'s life in the fast lane has never looked so good.',
626 # YouTube embed via <data-embed-url="">
628 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
632 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
633 'uploader': 'Gameloft',
634 'uploader_id': 'gameloft',
635 'upload_date': '20140828',
636 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
639 'skip_download': True,
644 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
646 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
648 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
649 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
654 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
656 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
657 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
663 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
668 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
669 'md5': '9d65602bf31c6e20014319c7d07fba27',
671 'id': '5123ea6d5e5a7',
674 'uploader': 'www.handjobhub.com',
675 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
678 # Multiple brightcove videos
679 # https://github.com/rg3/youtube-dl/issues/2283
681 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
683 'id': 'always-never',
684 'title': 'Always / Never - The New Yorker',
688 'extract_flat': False,
689 'skip_download': True,
694 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
695 'md5': '96f09a37e44da40dd083e12d9a683327',
699 'title': 'Ump changes call to ball',
700 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
702 'timestamp': 1401537900,
703 'upload_date': '20140531',
704 'thumbnail': 're:^https?://.*\.jpg$',
709 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
710 'md5': '8788b683c777a5cf25621eaf286d0c23',
714 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
716 'filesize': 182808282,
717 'uploader': 'education-portal.com',
721 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
722 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
726 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
728 'uploader': 'thoughtworks.wistia.com',
733 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
737 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
738 'uploader': 'Sophos Security',
739 'title': 'Chet Chat 171 - Oct 29, 2014',
740 'upload_date': '20141029',
745 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
749 'upload_date': '20141112',
750 'title': 'Rosetta #CometLanding webcast HL 10',
755 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
758 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
760 'playlist_mincount': 2,
764 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
768 'upload_date': '20141126',
769 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
774 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
776 'id': '730m_DandD_1901_512k',
778 'uploader': 'www.abc.net.au',
779 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
782 # embedded viddler video
784 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
788 'uploader': 'deadspin',
789 'title': 'WALL-TO-GORTAT',
790 'timestamp': 1422285291,
791 'upload_date': '20150126',
793 'add_ie': ['Viddler'],
797 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
801 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
802 'description': 'md5:601cb790edd05908957dae8aaa866465',
803 'upload_date': '20150220',
808 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
812 'upload_date': '20150212',
813 'uploader': 'The National Archives UK',
814 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
815 'uploader_id': 'NationalArchives08',
816 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
821 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
822 'playlist_mincount': 5,
824 'id': 'aanslagen-kopenhagen',
825 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
830 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
834 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
839 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
843 'upload_date': '20150226',
844 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
846 'title': 'John Carlson Postgame 2/25/15',
849 # Kaltura embed (different embed code)
851 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
855 'upload_date': '20150127',
856 'uploader_id': 'PremierMedia',
858 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
861 # Kaltura embed protected with referrer
863 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
867 'title': 'Violetta - Achter De Schermen - Ruggero',
868 'description': 'Achter de schermen met Ruggero',
869 'timestamp': 1435133761,
870 'upload_date': '20150624',
871 'uploader_id': 'echojecka',
874 # Eagle.Platform embed (generic URL)
876 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
880 'title': 'Навальный вышел на свободу',
881 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
882 'thumbnail': 're:^https?://.*\.jpg$',
888 # ClipYou (Eagle.Platform) embed (custom URL)
890 'url': 'http://muz-tv.ru/play/7129/',
894 'title': "'O Sole Mio",
895 'thumbnail': 're:^https?://.*\.jpg$',
902 'url': 'http://muz-tv.ru/kinozal/view/7400/',
906 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
907 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
908 'thumbnail': 're:^https?://.*\.jpg$',
915 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
919 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
920 'thumbnail': 're:^https?://.*\.png$',
926 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
927 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
931 'title': 'Facebook Creates "On This Day" | Crunch Report',
936 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
940 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
945 # Crooks and Liars embed
947 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
951 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
952 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
953 'timestamp': 1428207000,
954 'upload_date': '20150405',
955 'uploader': 'Heather',
958 # Crooks and Liars external embed
960 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
962 'id': 'MTE3MjUtMzQ2MzA',
964 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
965 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
966 'timestamp': 1265032391,
967 'upload_date': '20100201',
968 'uploader': 'Heather',
971 # NBC Sports vplayer embed
973 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
975 'id': 'ln7x1qSThw4k',
977 'title': "PFT Live: New leader in the 'new-look' defense",
978 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
983 'url': 'http://www.udn.com/news/story/7314/822787',
984 'md5': 'fd2060e988c326991037b9aff9df21a6',
988 'title': '中一中男師變性 全校師生力挺',
989 'thumbnail': 're:^https?://.*\.jpg$',
994 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
996 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
998 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
999 'title': 'This is what separates the Excel masters from the wannabes',
1000 'duration': 191.933,
1004 'skip_download': True,
1007 # Contains a SMIL manifest
1009 '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',
1013 'title': '+ Football: Lottery Champions League Europe',
1014 'uploader': 'www.telewebion.com',
1018 'skip_download': True,
1021 # Brightcove URL in single quotes
1023 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1024 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1026 'id': '4255764656001',
1028 'title': 'SN Presents: Russell Martin, World Citizen',
1029 '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.',
1030 'uploader': 'Rogers Sportsnet',
1033 # Dailymotion Cloud video
1035 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1036 'md5': '49444254273501a64675a7e68c502681',
1038 'id': '5585de919473990de4bee11b',
1040 'title': 'Le débat',
1041 'thumbnail': 're:^https?://.*\.jpe?g$',
1044 # OnionStudios embed
1046 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1050 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1051 'thumbnail': 're:^https?://.*\.jpe?g$',
1052 'uploader': 'ClickHole',
1053 'uploader_id': 'clickhole',
1058 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1060 'id': '74849a00-85a9-11e1-9660-123139220831',
1062 'title': '#whilewewatch',
1065 # AdobeTVVideo embed
1067 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1068 'md5': '43662b577c018ad707a63766462b1e87',
1072 'title': 'New experience with Acrobat DC',
1073 'description': 'New experience with Acrobat DC',
1074 'duration': 248.667,
1077 # ScreenwaveMedia embed
1079 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1080 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1082 'id': 'cinemasnob-55d26273809dd',
1084 'title': 'cinemasnob',
1087 # BrightcoveInPageEmbed embed
1089 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1091 'id': '4238694884001',
1093 'title': 'Tabletop: Dread, Last Thoughts',
1094 'description': 'Tabletop: Dread, Last Thoughts',
1098 # JWPlayer with M3U8
1100 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1104 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1105 'uploader': 'ren.tv',
1109 'skip_download': True,
1114 def report_following_redirect(self, new_url):
1115 """Report information extraction."""
1116 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1118 def _extract_rss(self, url, video_id, doc):
1119 playlist_title = doc.find('./channel/title').text
1120 playlist_desc_el = doc.find('./channel/description')
1121 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1124 for it in doc.findall('./channel/item'):
1125 next_url = xpath_text(it, 'link', fatal=False)
1127 enclosure_nodes = it.findall('./enclosure')
1128 for e in enclosure_nodes:
1129 next_url = e.attrib.get('url')
1139 'title': it.find('title').text,
1143 '_type': 'playlist',
1145 'title': playlist_title,
1146 'description': playlist_desc,
1150 def _extract_camtasia(self, url, video_id, webpage):
1151 """ Returns None if no camtasia video can be found. """
1153 camtasia_cfg = self._search_regex(
1154 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1155 webpage, 'camtasia configuration file', default=None)
1156 if camtasia_cfg is None:
1159 title = self._html_search_meta('DC.title', webpage, fatal=True)
1161 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1162 camtasia_cfg = self._download_xml(
1163 camtasia_url, video_id,
1164 note='Downloading camtasia configuration',
1165 errnote='Failed to download camtasia configuration')
1166 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1169 for n in fileset_node.getchildren():
1170 url_n = n.find('./uri')
1175 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1176 'title': '%s - %s' % (title, n.tag),
1177 'url': compat_urlparse.urljoin(url, url_n.text),
1178 'duration': float_or_none(n.find('./duration').text),
1182 '_type': 'playlist',
1187 def _real_extract(self, url):
1188 if url.startswith('//'):
1191 'url': self.http_scheme() + url,
1194 parsed_url = compat_urlparse.urlparse(url)
1195 if not parsed_url.scheme:
1196 default_search = self._downloader.params.get('default_search')
1197 if default_search is None:
1198 default_search = 'fixup_error'
1200 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1202 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1203 return self.url_result('http://' + url)
1204 elif default_search != 'fixup_error':
1205 if default_search == 'auto_warning':
1206 if re.match(r'^(?:url|URL)$', url):
1207 raise ExtractorError(
1208 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1211 self._downloader.report_warning(
1212 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1213 return self.url_result('ytsearch:' + url)
1215 if default_search in ('error', 'fixup_error'):
1216 raise ExtractorError(
1217 '%r is not a valid URL. '
1218 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1219 % (url, url), expected=True)
1221 if ':' not in default_search:
1222 default_search += ':'
1223 return self.url_result(default_search + url)
1225 url, smuggled_data = unsmuggle_url(url)
1226 force_videoid = None
1227 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1228 if smuggled_data and 'force_videoid' in smuggled_data:
1229 force_videoid = smuggled_data['force_videoid']
1230 video_id = force_videoid
1232 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1234 self.to_screen('%s: Requesting header' % video_id)
1236 head_req = HEADRequest(url)
1237 head_response = self._request_webpage(
1239 note=False, errnote='Could not send HEAD request to %s' % url,
1242 if head_response is not False:
1243 # Check for redirect
1244 new_url = head_response.geturl()
1246 self.report_following_redirect(new_url)
1248 new_url = smuggle_url(
1249 new_url, {'force_videoid': force_videoid})
1250 return self.url_result(new_url)
1252 full_response = None
1253 if head_response is False:
1254 request = sanitized_Request(url)
1255 request.add_header('Accept-Encoding', '*')
1256 full_response = self._request_webpage(request, video_id)
1257 head_response = full_response
1261 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1262 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1265 # Check for direct link to a video
1266 content_type = head_response.headers.get('Content-Type', '').lower()
1267 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1269 format_id = m.group('format_id')
1270 if format_id.endswith('mpegurl'):
1271 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1272 elif format_id == 'f4m':
1273 formats = self._extract_f4m_formats(url, video_id)
1276 'format_id': m.group('format_id'),
1278 'vcodec': 'none' if m.group('type') == 'audio' else None
1280 info_dict['direct'] = True
1281 info_dict['formats'] = formats
1284 if not self._downloader.params.get('test', False) and not is_intentional:
1285 force = self._downloader.params.get('force_generic_extractor', False)
1286 self._downloader.report_warning(
1287 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1289 if not full_response:
1290 request = sanitized_Request(url)
1291 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1292 # making it impossible to download only chunk of the file (yet we need only 512kB to
1293 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1294 # that will always result in downloading the whole file that is not desirable.
1295 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1296 # to accept raw bytes and being able to download only a chunk.
1297 # It may probably better to solve this by checking Content-Type for application/octet-stream
1298 # after HEAD request finishes, but not sure if we can rely on this.
1299 request.add_header('Accept-Encoding', '*')
1300 full_response = self._request_webpage(request, video_id)
1302 first_bytes = full_response.read(512)
1304 # Is it an M3U playlist?
1305 if first_bytes.startswith('#EXTM3U'):
1306 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1309 # Maybe it's a direct link to a video?
1310 # Be careful not to download the whole thing!
1311 if not is_html(first_bytes):
1312 self._downloader.report_warning(
1313 'URL could be a direct video link, returning it as such.')
1320 webpage = self._webpage_read_content(
1321 full_response, url, video_id, prefix=first_bytes)
1323 self.report_extraction(video_id)
1325 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1327 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1328 if doc.tag == 'rss':
1329 return self._extract_rss(url, video_id, doc)
1330 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1331 return self._parse_smil(doc, url, video_id)
1332 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1333 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1334 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1335 info_dict['formats'] = self._parse_mpd_formats(
1336 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1338 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1339 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1341 except compat_xml_parse_error:
1344 # Is it a Camtasia project?
1345 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1346 if camtasia_res is not None:
1349 # Sometimes embedded video player is hidden behind percent encoding
1350 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1351 # Unescaping the whole page allows to handle those cases in a generic way
1352 webpage = compat_urllib_parse_unquote(webpage)
1354 # it's tempting to parse this further, but you would
1355 # have to take into account all the variations like
1356 # Video Title - Site Name
1357 # Site Name | Video Title
1358 # Video Title - Tagline | Site Name
1359 # and so on and so forth; it's just not practical
1360 video_title = self._html_search_regex(
1361 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1364 # Try to detect age limit automatically
1365 age_limit = self._rta_search(webpage)
1366 # And then there are the jokers who advertise that they use RTA,
1367 # but actually don't.
1368 AGE_LIMIT_MARKERS = [
1369 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1371 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1374 # video uploader is domain name
1375 video_uploader = self._search_regex(
1376 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1379 def _playlist_from_matches(matches, getter=None, ie=None):
1381 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1383 return self.playlist_result(
1384 urlrs, playlist_id=video_id, playlist_title=video_title)
1386 # Look for Brightcove Legacy Studio embeds
1387 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1389 self.to_screen('Brightcove video detected.')
1392 'url': smuggle_url(bc_url, {'Referer': url}),
1393 'ie_key': 'BrightcoveLegacy'
1394 } for bc_url in bc_urls]
1397 '_type': 'playlist',
1398 'title': video_title,
1403 # Look for Brightcove New Studio embeds
1404 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1406 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1408 # Look for embedded rtl.nl player
1409 matches = re.findall(
1410 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1413 return _playlist_from_matches(matches, ie='RtlNl')
1415 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1416 if vimeo_url is not None:
1417 return self.url_result(vimeo_url)
1419 vid_me_embed_url = self._search_regex(
1420 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1421 webpage, 'vid.me embed', default=None)
1422 if vid_me_embed_url is not None:
1423 return self.url_result(vid_me_embed_url, 'Vidme')
1425 # Look for embedded YouTube player
1426 matches = re.findall(r'''(?x)
1435 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1439 return _playlist_from_matches(
1440 matches, lambda m: unescapeHTML(m[1]))
1442 # Look for lazyYT YouTube embed
1443 matches = re.findall(
1444 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1446 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1448 # Look for embedded Dailymotion player
1449 matches = re.findall(
1450 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1452 return _playlist_from_matches(
1453 matches, lambda m: unescapeHTML(m[1]))
1455 # Look for embedded Dailymotion playlist player (#3822)
1457 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1459 playlists = re.findall(
1460 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1462 return _playlist_from_matches(
1463 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1465 # Look for embedded Wistia player
1467 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1469 embed_url = self._proto_relative_url(
1470 unescapeHTML(match.group('url')))
1472 '_type': 'url_transparent',
1475 'uploader': video_uploader,
1476 'title': video_title,
1480 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1483 '_type': 'url_transparent',
1484 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1486 'uploader': video_uploader,
1487 'title': video_title,
1488 'id': match.group('id')
1491 # Look for SVT player
1492 svt_url = SVTIE._extract_url(webpage)
1494 return self.url_result(svt_url, 'SVT')
1496 # Look for embedded condenast player
1497 matches = re.findall(
1498 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1502 '_type': 'playlist',
1505 'ie_key': 'CondeNast',
1507 } for ma in matches],
1508 'title': video_title,
1512 # Look for Bandcamp pages with custom domain
1513 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1514 if mobj is not None:
1515 burl = unescapeHTML(mobj.group(1))
1516 # Don't set the extractor because it can be a track url or an album
1517 return self.url_result(burl)
1519 # Look for embedded Vevo player
1521 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1522 if mobj is not None:
1523 return self.url_result(mobj.group('url'))
1525 # Look for embedded Viddler player
1527 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1529 if mobj is not None:
1530 return self.url_result(mobj.group('url'))
1532 # Look for NYTimes player
1534 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1536 if mobj is not None:
1537 return self.url_result(mobj.group('url'))
1539 # Look for Libsyn player
1541 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1542 if mobj is not None:
1543 return self.url_result(mobj.group('url'))
1545 # Look for Ooyala videos
1546 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1547 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1548 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1549 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1550 if mobj is not None:
1551 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1553 # Look for multiple Ooyala embeds on SBN network websites
1554 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1555 if mobj is not None:
1556 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1558 return _playlist_from_matches(
1559 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1561 # Look for Aparat videos
1562 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1563 if mobj is not None:
1564 return self.url_result(mobj.group(1), 'Aparat')
1566 # Look for MPORA videos
1567 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1568 if mobj is not None:
1569 return self.url_result(mobj.group(1), 'Mpora')
1571 # Look for embedded NovaMov-based player
1573 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1574 (?P<url>http://(?:(?:embed|www)\.)?
1576 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1577 videoweed\.(?:es|com)|
1578 movshare\.(?:net|sx|ag)|
1579 divxstage\.(?:eu|net|ch|co|at|ag))
1580 /embed\.php.+?)\1''', webpage)
1581 if mobj is not None:
1582 return self.url_result(mobj.group('url'))
1584 # Look for embedded Facebook player
1586 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1587 if mobj is not None:
1588 return self.url_result(mobj.group('url'), 'Facebook')
1590 # Look for embedded VK player
1591 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1592 if mobj is not None:
1593 return self.url_result(mobj.group('url'), 'VK')
1595 # Look for embedded Odnoklassniki player
1596 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1597 if mobj is not None:
1598 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1600 # Look for embedded ivi player
1601 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1602 if mobj is not None:
1603 return self.url_result(mobj.group('url'), 'Ivi')
1605 # Look for embedded Huffington Post player
1607 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1608 if mobj is not None:
1609 return self.url_result(mobj.group('url'), 'HuffPost')
1612 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1613 if mobj is not None:
1614 return self.url_result(mobj.group('url'))
1615 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1616 if mobj is not None:
1617 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1619 # Look for funnyordie embed
1620 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1622 return _playlist_from_matches(
1623 matches, getter=unescapeHTML, ie='FunnyOrDie')
1625 # Look for BBC iPlayer embed
1626 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1628 return _playlist_from_matches(matches, ie='BBCCoUk')
1630 # Look for embedded RUTV player
1631 rutv_url = RUTVIE._extract_url(webpage)
1633 return self.url_result(rutv_url, 'RUTV')
1635 # Look for embedded TVC player
1636 tvc_url = TVCIE._extract_url(webpage)
1638 return self.url_result(tvc_url, 'TVC')
1640 # Look for embedded SportBox player
1641 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1643 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1645 # Look for embedded PornHub player
1646 pornhub_url = PornHubIE._extract_url(webpage)
1648 return self.url_result(pornhub_url, 'PornHub')
1650 # Look for embedded XHamster player
1651 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1653 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1655 # Look for embedded TNAFlixNetwork player
1656 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1658 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1660 # Look for embedded Tvigle player
1662 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1663 if mobj is not None:
1664 return self.url_result(mobj.group('url'), 'Tvigle')
1666 # Look for embedded TED player
1668 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1669 if mobj is not None:
1670 return self.url_result(mobj.group('url'), 'TED')
1672 # Look for embedded Ustream videos
1674 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1675 if mobj is not None:
1676 return self.url_result(mobj.group('url'), 'Ustream')
1678 # Look for embedded arte.tv player
1680 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1682 if mobj is not None:
1683 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1685 # Look for embedded francetv player
1687 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1689 if mobj is not None:
1690 return self.url_result(mobj.group('url'))
1692 # Look for embedded smotri.com player
1693 smotri_url = SmotriIE._extract_url(webpage)
1695 return self.url_result(smotri_url, 'Smotri')
1697 # Look for embedded Myvi.ru player
1698 myvi_url = MyviIE._extract_url(webpage)
1700 return self.url_result(myvi_url)
1702 # Look for embedded soundcloud player
1704 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1706 if mobj is not None:
1707 url = unescapeHTML(mobj.group('url'))
1708 return self.url_result(url)
1710 # Look for embedded vulture.com player
1712 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1714 if mobj is not None:
1715 url = unescapeHTML(mobj.group('url'))
1716 return self.url_result(url, ie='Vulture')
1718 # Look for embedded mtvservices player
1719 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1721 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1723 # Look for embedded yahoo player
1725 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1727 if mobj is not None:
1728 return self.url_result(mobj.group('url'), 'Yahoo')
1730 # Look for embedded sbs.com.au player
1734 <meta\s+property="og:video"\s+content=|
1737 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1739 if mobj is not None:
1740 return self.url_result(mobj.group('url'), 'SBS')
1742 # Look for embedded Cinchcast player
1744 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1746 if mobj is not None:
1747 return self.url_result(mobj.group('url'), 'Cinchcast')
1750 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1754 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1756 if mobj is not None:
1757 return self.url_result(mobj.group('url'), 'MLB')
1760 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1762 if mobj is not None:
1763 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1766 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'), 'Livestream')
1771 # Look for Zapiks embed
1773 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1774 if mobj is not None:
1775 return self.url_result(mobj.group('url'), 'Zapiks')
1777 # Look for Kaltura embeds
1778 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1779 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))
1780 if mobj is not None:
1781 return self.url_result(smuggle_url(
1782 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1783 {'source_url': url}), 'Kaltura')
1785 # Look for Eagle.Platform embeds
1787 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1788 if mobj is not None:
1789 return self.url_result(mobj.group('url'), 'EaglePlatform')
1791 # Look for ClipYou (uses Eagle.Platform) embeds
1793 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1794 if mobj is not None:
1795 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1797 # Look for Pladform embeds
1798 pladform_url = PladformIE._extract_url(webpage)
1800 return self.url_result(pladform_url)
1802 # Look for Videomore embeds
1803 videomore_url = VideomoreIE._extract_url(webpage)
1805 return self.url_result(videomore_url)
1807 # Look for Playwire embeds
1809 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1810 if mobj is not None:
1811 return self.url_result(mobj.group('url'))
1813 # Look for 5min embeds
1815 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1816 if mobj is not None:
1817 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1819 # Look for Crooks and Liars embeds
1821 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1822 if mobj is not None:
1823 return self.url_result(mobj.group('url'))
1825 # Look for NBC Sports VPlayer embeds
1826 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1828 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1830 # Look for Google Drive embeds
1831 google_drive_url = GoogleDriveIE._extract_url(webpage)
1832 if google_drive_url:
1833 return self.url_result(google_drive_url, 'GoogleDrive')
1835 # Look for UDN embeds
1837 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1838 if mobj is not None:
1839 return self.url_result(
1840 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1842 # Look for Senate ISVP iframe
1843 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1845 return self.url_result(senate_isvp_url, 'SenateISVP')
1847 # Look for Dailymotion Cloud videos
1848 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1850 return self.url_result(dmcloud_url, 'DailymotionCloud')
1852 # Look for OnionStudios embeds
1853 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1854 if onionstudios_url:
1855 return self.url_result(onionstudios_url)
1857 # Look for SnagFilms embeds
1858 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1860 return self.url_result(snagfilms_url)
1862 # Look for JWPlatform embeds
1863 jwplatform_url = JWPlatformIE._extract_url(webpage)
1865 return self.url_result(jwplatform_url, 'JWPlatform')
1867 # Look for ScreenwaveMedia embeds
1868 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1869 if mobj is not None:
1870 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1872 # Look for Digiteka embeds
1873 digiteka_url = DigitekaIE._extract_url(webpage)
1875 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1877 # Look for Limelight embeds
1878 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1882 'Channel': 'channel',
1883 'ChannelList': 'channel_list',
1885 return self.url_result('limelight:%s:%s' % (
1886 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1888 # Look for AdobeTVVideo embeds
1890 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1892 if mobj is not None:
1893 return self.url_result(
1894 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1897 def check_video(vurl):
1898 if YoutubeIE.suitable(vurl):
1900 vpath = compat_urlparse.urlparse(vurl).path
1901 vext = determine_ext(vpath)
1902 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1904 def filter_video(urls):
1905 return list(filter(check_video, urls))
1907 # Start with something easy: JW Player in SWFObject
1908 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1910 # Look for gorilla-vid style embedding
1911 found = filter_video(re.findall(r'''(?sx)
1915 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1918 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1920 # Broaden the search a little bit
1921 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1923 # Broaden the findall a little bit: JWPlayer JS loader
1924 found = filter_video(re.findall(
1925 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1928 found = filter_video(re.findall(r'''(?xs)
1929 flowplayer\("[^"]+",\s*
1931 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1932 ["']?url["']?\s*:\s*["']([^"']+)["']
1937 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1939 # Try to find twitter cards info
1940 found = filter_video(re.findall(
1941 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1943 # We look for Open Graph info:
1944 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1945 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1946 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1947 if m_video_type is not None:
1948 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1951 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1953 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1955 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1956 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1959 # Look also in Refresh HTTP header
1960 refresh_header = head_response.headers.get('Refresh')
1962 # In python 2 response HTTP headers are bytestrings
1963 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1964 refresh_header = refresh_header.decode('iso-8859-1')
1965 found = re.search(REDIRECT_REGEX, refresh_header)
1967 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1968 self.report_following_redirect(new_url)
1974 raise UnsupportedError(url)
1977 for video_url in found:
1978 video_url = video_url.replace('\\/', '/')
1979 video_url = compat_urlparse.urljoin(url, video_url)
1980 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1982 # Sometimes, jwplayer extraction will result in a YouTube URL
1983 if YoutubeIE.suitable(video_url):
1984 entries.append(self.url_result(video_url, 'Youtube'))
1987 # here's a fun little line of code for you:
1988 video_id = os.path.splitext(video_id)[0]
1992 'uploader': video_uploader,
1993 'title': video_title,
1994 'age_limit': age_limit,
1997 ext = determine_ext(video_url)
1999 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2001 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2003 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2005 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2007 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2009 entry_info_dict['url'] = video_url
2011 entries.append(entry_info_dict)
2013 if len(entries) == 1:
2016 for num, e in enumerate(entries, start=1):
2017 # 'url' results don't have a title
2018 if e.get('title') is not None:
2019 e['title'] = '%s (%d)' % (e['title'], num)
2021 '_type': 'playlist',