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 .viewlift import ViewLiftEmbedIE
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
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
66 class GenericIE(InfoExtractor):
67 IE_DESC = 'Generic downloader that works on some sites'
71 # Direct link to a video
73 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
74 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
79 'upload_date': '20100513',
82 # Direct link to media delivered compressed (until Accept-Encoding is *)
84 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
85 'md5': '128c42e68b13950268b648275386fc74',
87 'id': 'FictionJunction-Parallel_Hearts',
89 'title': 'FictionJunction-Parallel_Hearts',
90 'upload_date': '20140522',
92 'expected_warnings': [
93 'URL could be a direct video link, returning it as such.'
96 # Direct download with broken HEAD
98 'url': 'http://ai-radio.org:8000/radio.opus',
105 'skip_download': True, # infinite live stream
107 'expected_warnings': [
108 r'501.*Not Implemented',
112 # Direct link with incorrect MIME type
114 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
115 'md5': '4ccbebe5f36706d85221f204d7eb5913',
117 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
118 'id': '5_Lennart_Poettering_-_Systemd',
120 'title': '5_Lennart_Poettering_-_Systemd',
121 'upload_date': '20141120',
123 'expected_warnings': [
124 'URL could be a direct video link, returning it as such.'
129 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
131 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
132 'title': 'Zero Punctuation',
133 'description': 're:.*groundbreaking video review series.*'
135 'playlist_mincount': 11,
137 # RSS feed with enclosure
139 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
141 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
143 'upload_date': '20150228',
144 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
147 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
149 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
153 'title': 'Automatics, robotics and biocybernetics',
154 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
155 'upload_date': '20130627',
156 'formats': 'mincount:16',
157 'subtitles': 'mincount:1',
160 'force_generic_extractor': True,
161 'skip_download': True,
164 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
166 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
171 'formats': 'mincount:1',
174 'skip_download': True,
177 # SMIL from https://www.restudy.dk/video/play/id/1637
179 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
183 'title': 'video_1637',
184 'formats': 'mincount:3',
187 'skip_download': True,
190 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
192 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
194 'id': 'smil-service',
196 'title': 'smil-service',
197 'formats': 'mincount:1',
200 'skip_download': True,
203 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
205 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
209 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
210 'formats': 'mincount:3',
213 'skip_download': True,
216 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
218 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
220 'id': 'mZlp2ctYIUEB',
222 'title': 'Tikibad ontruimd wegens brand',
223 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
224 'thumbnail': 're:^https?://.*\.jpg$',
228 'skip_download': True,
231 # MPD from http://dash-mse-test.appspot.com/media.html
233 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
234 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
236 'id': 'car-20120827-manifest',
238 'title': 'car-20120827-manifest',
239 'formats': 'mincount:9',
240 'upload_date': '20130904',
243 'format': 'bestvideo',
246 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
248 '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',
253 'formats': 'mincount:8',
257 'skip_download': True,
260 # m3u8 served with Content-Type: text/plain
262 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
267 'upload_date': '20140720',
268 'formats': 'mincount:11',
272 'skip_download': True,
277 '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',
281 'upload_date': '20130224',
282 'uploader_id': 'TheVerge',
283 'description': 're:^Chris Ziegler takes a look at the\.*',
284 'uploader': 'The Verge',
285 'title': 'First Firefox OS phones side-by-side',
288 'skip_download': False,
292 # redirect in Refresh HTTP header
293 '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',
297 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
298 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
299 'upload_date': '20150917',
300 'uploader_id': 'brtvofficial',
301 'uploader': 'Boiler Room',
304 'skip_download': False,
308 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
309 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
311 'id': '13601338388002',
313 'uploader': 'www.hodiho.fr',
314 'title': 'R\u00e9gis plante sa Jeep',
317 # bandcamp page with custom domain
319 'add_ie': ['Bandcamp'],
320 'url': 'http://bronyrock.com/track/the-pony-mash',
324 'title': 'The Pony Mash',
325 'uploader': 'M_Pallante',
327 'skip': 'There is a limit of 200 free downloads / month for the test song',
329 # embedded brightcove video
330 # it also tests brightcove videos that need to set the 'Referer' in the
333 'add_ie': ['BrightcoveLegacy'],
334 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
336 'id': '2765128793001',
338 'title': 'Le cours de bourse : l’analyse technique',
339 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
340 'uploader': 'BFM BUSINESS',
343 'skip_download': True,
347 # https://github.com/rg3/youtube-dl/issues/2253
348 'url': 'http://bcove.me/i6nfkrc3',
349 'md5': '0ba9446db037002366bab3b3eb30c88c',
351 'id': '3101154703001',
353 'title': 'Still no power',
354 'uploader': 'thestar.com',
355 '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.',
357 'add_ie': ['BrightcoveLegacy'],
360 'url': 'http://www.championat.com/video/football/v/87/87499.html',
361 'md5': 'fb973ecf6e4a78a67453647444222983',
363 'id': '3414141473001',
365 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
366 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
367 'uploader': 'Championat',
371 # https://github.com/rg3/youtube-dl/issues/3541
372 'add_ie': ['BrightcoveLegacy'],
373 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
375 'id': '3866516442001',
377 'title': 'Leer mij vrouwen kennen: Aflevering 1',
378 'description': 'Leer mij vrouwen kennen: Aflevering 1',
379 'uploader': 'SBS Broadcasting',
381 'skip': 'Restricted to Netherlands',
383 'skip_download': True, # m3u8 download
388 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
389 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
391 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
393 'title': '2cc213299525360.mov', # that's what we get
396 'add_ie': ['Ooyala'],
399 # ooyala video embedded with http://player.ooyala.com/iframe.js
400 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
402 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
404 'title': '"Steve Jobs: Man in the Machine" trailer',
405 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
409 'skip_download': True,
414 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
418 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
419 'upload_date': '20140225',
420 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
421 'uploader': 'Tested',
422 'uploader_id': 'testedcom',
424 # No need to test YoutubeIE here
426 'skip_download': True,
431 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
435 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
436 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
441 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
445 'title': 'Охотское море стало целиком российским',
446 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
450 'skip_download': True,
455 '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/',
459 'title': 'Дошкольное воспитание',
464 'url': 'http://www.vestifinance.ru/articles/25753',
467 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
472 'title': 'Госзаказ. День 3',
478 'title': 'Госзаказ. День 2',
484 'title': 'Госзаказ. День 1',
490 'skip_download': True,
495 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
497 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
499 'title': 'Ужастики, русский трейлер (2015)',
500 'thumbnail': 're:^https?://.*\.jpg$',
506 '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',
509 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
511 'playlist_mincount': 7,
515 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
516 'md5': '65fdff94098e4a607385a60c5177c638',
520 'title': 'Hidden miracles of the natural world',
521 'uploader': 'Louie Schwartzberg',
522 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
525 # Embedded Ustream video
527 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
528 'md5': '27b99cdb639c9b12a79bca876a073417',
532 'uploader': 'AU SPA: The NSA and Privacy',
533 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
536 # nowvideo embed hidden behind percent encoding
538 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
539 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
541 'id': '06e53103ca9aa',
543 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
544 'description': 'No description',
549 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
550 'md5': '7653032cbb25bf6c80d80f217055fa43',
552 'id': '048195-004_PLUS7-F',
555 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
556 'upload_date': '20140320',
559 'skip_download': 'Requires rtmpdump'
564 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
568 'title': 'Alcaline, le concert avec Calogero',
569 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
570 'upload_date': '20150226',
571 'timestamp': 1424989860,
576 'skip_download': True,
578 'expected_warnings': [
584 'url': 'http://www.wired.com/2014/04/honda-asimo/',
585 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
587 'id': '53501be369702d3275860000',
589 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
594 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
595 'md5': '441aeeb82eb72c422c7f14ec533999cd',
597 'id': 'k2mm4bCdJ6CQ2i7c8o2',
599 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
600 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
602 'uploader_id': 'xgditw',
603 'upload_date': '20140425',
604 'timestamp': 1398441542,
606 'add_ie': ['Dailymotion'],
610 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
614 'title': 'The NBL Auction 2014',
615 'uploader': 'BADMINTON England',
616 'uploader_id': 'BADMINTONEvents',
617 'upload_date': '20140603',
618 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
620 'add_ie': ['Youtube'],
622 'skip_download': True,
627 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
628 'md5': '35727f82f58c76d996fc188f9755b0d5',
630 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
633 'description': 'Mario\'s life in the fast lane has never looked so good.',
636 # YouTube embed via <data-embed-url="">
638 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
642 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
643 'uploader': 'Gameloft',
644 'uploader_id': 'gameloft',
645 'upload_date': '20140828',
646 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
649 'skip_download': True,
654 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
656 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
658 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
659 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
664 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
666 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
667 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
673 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
678 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
679 'md5': '9d65602bf31c6e20014319c7d07fba27',
681 'id': '5123ea6d5e5a7',
684 'uploader': 'www.handjobhub.com',
685 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
688 # Multiple brightcove videos
689 # https://github.com/rg3/youtube-dl/issues/2283
691 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
693 'id': 'always-never',
694 'title': 'Always / Never - The New Yorker',
698 'extract_flat': False,
699 'skip_download': True,
704 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
705 'md5': '96f09a37e44da40dd083e12d9a683327',
709 'title': 'Ump changes call to ball',
710 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
712 'timestamp': 1401537900,
713 'upload_date': '20140531',
714 'thumbnail': 're:^https?://.*\.jpg$',
719 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
720 'md5': '8788b683c777a5cf25621eaf286d0c23',
724 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
726 'filesize': 182808282,
727 'uploader': 'education-portal.com',
731 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
732 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
736 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
737 'description': 'a Martin Fowler video from ThoughtWorks',
739 'uploader': 'thoughtworks.wistia.com',
740 'upload_date': '20140603',
741 'timestamp': 1401832161,
746 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
750 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
751 'uploader': 'Sophos Security',
752 'title': 'Chet Chat 171 - Oct 29, 2014',
753 'upload_date': '20141029',
758 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
762 'upload_date': '20141112',
763 'title': 'Rosetta #CometLanding webcast HL 10',
768 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
771 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
773 'playlist_mincount': 2,
777 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
781 'upload_date': '20141126',
782 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
787 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
789 'id': '730m_DandD_1901_512k',
791 'uploader': 'www.abc.net.au',
792 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
795 # embedded viddler video
797 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
801 'uploader': 'deadspin',
802 'title': 'WALL-TO-GORTAT',
803 'timestamp': 1422285291,
804 'upload_date': '20150126',
806 'add_ie': ['Viddler'],
810 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
814 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
815 'description': 'md5:601cb790edd05908957dae8aaa866465',
816 'upload_date': '20150220',
821 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
825 'upload_date': '20150212',
826 'uploader': 'The National Archives UK',
827 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
828 'uploader_id': 'NationalArchives08',
829 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
834 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
835 'playlist_mincount': 5,
837 'id': 'aanslagen-kopenhagen',
838 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
843 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
847 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
852 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
856 'upload_date': '20150226',
857 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
859 'title': 'John Carlson Postgame 2/25/15',
862 # Kaltura embed (different embed code)
864 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
868 'upload_date': '20150127',
869 'uploader_id': 'PremierMedia',
871 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
874 # Kaltura embed protected with referrer
876 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
880 'title': 'Violetta - Achter De Schermen - Ruggero',
881 'description': 'Achter de schermen met Ruggero',
882 'timestamp': 1435133761,
883 'upload_date': '20150624',
884 'uploader_id': 'echojecka',
887 # Eagle.Platform embed (generic URL)
889 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
890 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
894 'title': 'Навальный вышел на свободу',
895 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
896 'thumbnail': 're:^https?://.*\.jpg$',
902 # ClipYou (Eagle.Platform) embed (custom URL)
904 'url': 'http://muz-tv.ru/play/7129/',
905 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
909 'title': "'O Sole Mio",
910 'thumbnail': 're:^https?://.*\.jpg$',
917 'url': 'http://muz-tv.ru/kinozal/view/7400/',
921 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
922 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
923 'thumbnail': 're:^https?://.*\.jpg$',
930 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
934 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
935 'thumbnail': 're:^https?://.*\.png$',
941 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
942 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
946 'title': 'Facebook Creates "On This Day" | Crunch Report',
951 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
955 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
960 # Crooks and Liars embed
962 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
966 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
967 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
968 'timestamp': 1428207000,
969 'upload_date': '20150405',
970 'uploader': 'Heather',
973 # Crooks and Liars external embed
975 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
977 'id': 'MTE3MjUtMzQ2MzA',
979 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
980 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
981 'timestamp': 1265032391,
982 'upload_date': '20100201',
983 'uploader': 'Heather',
986 # NBC Sports vplayer embed
988 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
990 'id': 'ln7x1qSThw4k',
992 'title': "PFT Live: New leader in the 'new-look' defense",
993 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
994 'uploader': 'NBCU-SPORTS',
995 'upload_date': '20140107',
996 'timestamp': 1389118457,
1001 'url': 'http://www.udn.com/news/story/7314/822787',
1002 'md5': 'fd2060e988c326991037b9aff9df21a6',
1006 'title': '中一中男師變性 全校師生力挺',
1007 'thumbnail': 're:^https?://.*\.jpg$',
1012 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1014 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1016 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1017 'title': 'This is what separates the Excel masters from the wannabes',
1018 'duration': 191.933,
1022 'skip_download': True,
1025 # Contains a SMIL manifest
1027 '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',
1031 'title': '+ Football: Lottery Champions League Europe',
1032 'uploader': 'www.telewebion.com',
1036 'skip_download': True,
1039 # Brightcove URL in single quotes
1041 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1042 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1044 'id': '4255764656001',
1046 'title': 'SN Presents: Russell Martin, World Citizen',
1047 '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.',
1048 'uploader': 'Rogers Sportsnet',
1049 'uploader_id': '1704050871',
1050 'upload_date': '20150525',
1051 'timestamp': 1432570283,
1054 # Dailymotion Cloud video
1056 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1057 'md5': '49444254273501a64675a7e68c502681',
1059 'id': '5585de919473990de4bee11b',
1061 'title': 'Le débat',
1062 'thumbnail': 're:^https?://.*\.jpe?g$',
1065 # OnionStudios embed
1067 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1071 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1072 'thumbnail': 're:^https?://.*\.jpe?g$',
1073 'uploader': 'ClickHole',
1074 'uploader_id': 'clickhole',
1079 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1081 'id': '74849a00-85a9-11e1-9660-123139220831',
1083 'title': '#whilewewatch',
1086 # AdobeTVVideo embed
1088 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1089 'md5': '43662b577c018ad707a63766462b1e87',
1093 'title': 'New experience with Acrobat DC',
1094 'description': 'New experience with Acrobat DC',
1095 'duration': 248.667,
1098 # ScreenwaveMedia embed
1100 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1101 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1103 'id': 'cinemasnob-55d26273809dd',
1105 'title': 'cinemasnob',
1108 # BrightcoveInPageEmbed embed
1110 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1112 'id': '4238694884001',
1114 'title': 'Tabletop: Dread, Last Thoughts',
1115 'description': 'Tabletop: Dread, Last Thoughts',
1119 # JWPlayer with M3U8
1121 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1125 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1126 'uploader': 'ren.tv',
1130 'skip_download': True,
1133 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1134 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1136 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1138 'id': '4785848093001',
1140 'title': 'The Cardinal Pell Interview',
1141 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1142 'uploader': 'GlobeCast Australia - GlobeStream',
1143 'uploader_id': '2733773828001',
1144 'upload_date': '20160304',
1145 'timestamp': 1457083087,
1149 'skip_download': True,
1152 # Another form of arte.tv embed
1154 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1155 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1157 'id': '030273-562_PLUS7-F',
1159 'title': 'ARTE Reportage - Nulle part, en France',
1160 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1161 'upload_date': '20160409',
1166 'url': 'http://www.wykop.pl/link/3088787/',
1167 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1169 'id': '874_1459135191',
1171 'title': 'Man shows poor quality of new apartment building',
1172 'description': 'The wall is like a sand pile.',
1173 'uploader': 'Lake8737',
1178 def report_following_redirect(self, new_url):
1179 """Report information extraction."""
1180 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1182 def _extract_rss(self, url, video_id, doc):
1183 playlist_title = doc.find('./channel/title').text
1184 playlist_desc_el = doc.find('./channel/description')
1185 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1188 for it in doc.findall('./channel/item'):
1189 next_url = xpath_text(it, 'link', fatal=False)
1191 enclosure_nodes = it.findall('./enclosure')
1192 for e in enclosure_nodes:
1193 next_url = e.attrib.get('url')
1203 'title': it.find('title').text,
1207 '_type': 'playlist',
1209 'title': playlist_title,
1210 'description': playlist_desc,
1214 def _extract_camtasia(self, url, video_id, webpage):
1215 """ Returns None if no camtasia video can be found. """
1217 camtasia_cfg = self._search_regex(
1218 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1219 webpage, 'camtasia configuration file', default=None)
1220 if camtasia_cfg is None:
1223 title = self._html_search_meta('DC.title', webpage, fatal=True)
1225 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1226 camtasia_cfg = self._download_xml(
1227 camtasia_url, video_id,
1228 note='Downloading camtasia configuration',
1229 errnote='Failed to download camtasia configuration')
1230 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1233 for n in fileset_node.getchildren():
1234 url_n = n.find('./uri')
1239 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1240 'title': '%s - %s' % (title, n.tag),
1241 'url': compat_urlparse.urljoin(url, url_n.text),
1242 'duration': float_or_none(n.find('./duration').text),
1246 '_type': 'playlist',
1251 def _real_extract(self, url):
1252 if url.startswith('//'):
1255 'url': self.http_scheme() + url,
1258 parsed_url = compat_urlparse.urlparse(url)
1259 if not parsed_url.scheme:
1260 default_search = self._downloader.params.get('default_search')
1261 if default_search is None:
1262 default_search = 'fixup_error'
1264 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1266 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1267 return self.url_result('http://' + url)
1268 elif default_search != 'fixup_error':
1269 if default_search == 'auto_warning':
1270 if re.match(r'^(?:url|URL)$', url):
1271 raise ExtractorError(
1272 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1275 self._downloader.report_warning(
1276 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1277 return self.url_result('ytsearch:' + url)
1279 if default_search in ('error', 'fixup_error'):
1280 raise ExtractorError(
1281 '%r is not a valid URL. '
1282 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1283 % (url, url), expected=True)
1285 if ':' not in default_search:
1286 default_search += ':'
1287 return self.url_result(default_search + url)
1289 url, smuggled_data = unsmuggle_url(url)
1290 force_videoid = None
1291 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1292 if smuggled_data and 'force_videoid' in smuggled_data:
1293 force_videoid = smuggled_data['force_videoid']
1294 video_id = force_videoid
1296 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1298 self.to_screen('%s: Requesting header' % video_id)
1300 head_req = HEADRequest(url)
1301 head_response = self._request_webpage(
1303 note=False, errnote='Could not send HEAD request to %s' % url,
1306 if head_response is not False:
1307 # Check for redirect
1308 new_url = head_response.geturl()
1310 self.report_following_redirect(new_url)
1312 new_url = smuggle_url(
1313 new_url, {'force_videoid': force_videoid})
1314 return self.url_result(new_url)
1316 full_response = None
1317 if head_response is False:
1318 request = sanitized_Request(url)
1319 request.add_header('Accept-Encoding', '*')
1320 full_response = self._request_webpage(request, video_id)
1321 head_response = full_response
1325 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1326 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1329 # Check for direct link to a video
1330 content_type = head_response.headers.get('Content-Type', '').lower()
1331 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1333 format_id = m.group('format_id')
1334 if format_id.endswith('mpegurl'):
1335 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1336 elif format_id == 'f4m':
1337 formats = self._extract_f4m_formats(url, video_id)
1340 'format_id': m.group('format_id'),
1342 'vcodec': 'none' if m.group('type') == 'audio' else None
1344 info_dict['direct'] = True
1345 self._sort_formats(formats)
1346 info_dict['formats'] = formats
1349 if not self._downloader.params.get('test', False) and not is_intentional:
1350 force = self._downloader.params.get('force_generic_extractor', False)
1351 self._downloader.report_warning(
1352 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1354 if not full_response:
1355 request = sanitized_Request(url)
1356 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1357 # making it impossible to download only chunk of the file (yet we need only 512kB to
1358 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1359 # that will always result in downloading the whole file that is not desirable.
1360 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1361 # to accept raw bytes and being able to download only a chunk.
1362 # It may probably better to solve this by checking Content-Type for application/octet-stream
1363 # after HEAD request finishes, but not sure if we can rely on this.
1364 request.add_header('Accept-Encoding', '*')
1365 full_response = self._request_webpage(request, video_id)
1367 first_bytes = full_response.read(512)
1369 # Is it an M3U playlist?
1370 if first_bytes.startswith(b'#EXTM3U'):
1371 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1372 self._sort_formats(info_dict['formats'])
1375 # Maybe it's a direct link to a video?
1376 # Be careful not to download the whole thing!
1377 if not is_html(first_bytes):
1378 self._downloader.report_warning(
1379 'URL could be a direct video link, returning it as such.')
1386 webpage = self._webpage_read_content(
1387 full_response, url, video_id, prefix=first_bytes)
1389 self.report_extraction(video_id)
1391 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1393 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1394 if doc.tag == 'rss':
1395 return self._extract_rss(url, video_id, doc)
1396 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1397 smil = self._parse_smil(doc, url, video_id)
1398 self._sort_formats(smil['formats'])
1400 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1401 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1402 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1403 info_dict['formats'] = self._parse_mpd_formats(
1404 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1405 self._sort_formats(info_dict['formats'])
1407 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1408 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1409 self._sort_formats(info_dict['formats'])
1411 except compat_xml_parse_error:
1414 # Is it a Camtasia project?
1415 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1416 if camtasia_res is not None:
1419 # Sometimes embedded video player is hidden behind percent encoding
1420 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1421 # Unescaping the whole page allows to handle those cases in a generic way
1422 webpage = compat_urllib_parse_unquote(webpage)
1424 # it's tempting to parse this further, but you would
1425 # have to take into account all the variations like
1426 # Video Title - Site Name
1427 # Site Name | Video Title
1428 # Video Title - Tagline | Site Name
1429 # and so on and so forth; it's just not practical
1430 video_title = self._html_search_regex(
1431 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1434 # Try to detect age limit automatically
1435 age_limit = self._rta_search(webpage)
1436 # And then there are the jokers who advertise that they use RTA,
1437 # but actually don't.
1438 AGE_LIMIT_MARKERS = [
1439 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1441 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1444 # video uploader is domain name
1445 video_uploader = self._search_regex(
1446 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1449 def _playlist_from_matches(matches, getter=None, ie=None):
1451 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1453 return self.playlist_result(
1454 urlrs, playlist_id=video_id, playlist_title=video_title)
1456 # Look for Brightcove Legacy Studio embeds
1457 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1459 self.to_screen('Brightcove video detected.')
1462 'url': smuggle_url(bc_url, {'Referer': url}),
1463 'ie_key': 'BrightcoveLegacy'
1464 } for bc_url in bc_urls]
1467 '_type': 'playlist',
1468 'title': video_title,
1473 # Look for Brightcove New Studio embeds
1474 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1476 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1478 # Look for embedded rtl.nl player
1479 matches = re.findall(
1480 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1483 return _playlist_from_matches(matches, ie='RtlNl')
1485 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1486 if vimeo_url is not None:
1487 return self.url_result(vimeo_url)
1489 vid_me_embed_url = self._search_regex(
1490 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1491 webpage, 'vid.me embed', default=None)
1492 if vid_me_embed_url is not None:
1493 return self.url_result(vid_me_embed_url, 'Vidme')
1495 # Look for embedded YouTube player
1496 matches = re.findall(r'''(?x)
1505 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1509 return _playlist_from_matches(
1510 matches, lambda m: unescapeHTML(m[1]))
1512 # Look for lazyYT YouTube embed
1513 matches = re.findall(
1514 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1516 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1518 # Look for embedded Dailymotion player
1519 matches = re.findall(
1520 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1522 return _playlist_from_matches(
1523 matches, lambda m: unescapeHTML(m[1]))
1525 # Look for embedded Dailymotion playlist player (#3822)
1527 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1529 playlists = re.findall(
1530 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1532 return _playlist_from_matches(
1533 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1535 # Look for embedded Wistia player
1537 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1539 embed_url = self._proto_relative_url(
1540 unescapeHTML(match.group('url')))
1542 '_type': 'url_transparent',
1545 'uploader': video_uploader,
1546 'title': video_title,
1550 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1553 '_type': 'url_transparent',
1554 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1556 'uploader': video_uploader,
1557 'title': video_title,
1558 'id': match.group('id')
1561 # Look for SVT player
1562 svt_url = SVTIE._extract_url(webpage)
1564 return self.url_result(svt_url, 'SVT')
1566 # Look for embedded condenast player
1567 matches = re.findall(
1568 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1572 '_type': 'playlist',
1575 'ie_key': 'CondeNast',
1577 } for ma in matches],
1578 'title': video_title,
1582 # Look for Bandcamp pages with custom domain
1583 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1584 if mobj is not None:
1585 burl = unescapeHTML(mobj.group(1))
1586 # Don't set the extractor because it can be a track url or an album
1587 return self.url_result(burl)
1589 # Look for embedded Vevo player
1591 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1592 if mobj is not None:
1593 return self.url_result(mobj.group('url'))
1595 # Look for embedded Viddler player
1597 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1599 if mobj is not None:
1600 return self.url_result(mobj.group('url'))
1602 # Look for NYTimes player
1604 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1606 if mobj is not None:
1607 return self.url_result(mobj.group('url'))
1609 # Look for Libsyn player
1611 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1612 if mobj is not None:
1613 return self.url_result(mobj.group('url'))
1615 # Look for Ooyala videos
1616 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1617 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1618 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1619 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1620 if mobj is not None:
1621 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1623 # Look for multiple Ooyala embeds on SBN network websites
1624 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1625 if mobj is not None:
1626 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1628 return _playlist_from_matches(
1629 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1631 # Look for Aparat videos
1632 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1633 if mobj is not None:
1634 return self.url_result(mobj.group(1), 'Aparat')
1636 # Look for MPORA videos
1637 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1638 if mobj is not None:
1639 return self.url_result(mobj.group(1), 'Mpora')
1641 # Look for embedded NovaMov-based player
1643 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1644 (?P<url>http://(?:(?:embed|www)\.)?
1646 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1647 videoweed\.(?:es|com)|
1648 movshare\.(?:net|sx|ag)|
1649 divxstage\.(?:eu|net|ch|co|at|ag))
1650 /embed\.php.+?)\1''', webpage)
1651 if mobj is not None:
1652 return self.url_result(mobj.group('url'))
1654 # Look for embedded Facebook player
1656 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1657 if mobj is not None:
1658 return self.url_result(mobj.group('url'), 'Facebook')
1660 # Look for embedded VK player
1661 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1662 if mobj is not None:
1663 return self.url_result(mobj.group('url'), 'VK')
1665 # Look for embedded Odnoklassniki player
1666 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1667 if mobj is not None:
1668 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1670 # Look for embedded ivi player
1671 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1672 if mobj is not None:
1673 return self.url_result(mobj.group('url'), 'Ivi')
1675 # Look for embedded Huffington Post player
1677 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1678 if mobj is not None:
1679 return self.url_result(mobj.group('url'), 'HuffPost')
1682 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'))
1685 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1686 if mobj is not None:
1687 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1689 # Look for funnyordie embed
1690 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1692 return _playlist_from_matches(
1693 matches, getter=unescapeHTML, ie='FunnyOrDie')
1695 # Look for BBC iPlayer embed
1696 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1698 return _playlist_from_matches(matches, ie='BBCCoUk')
1700 # Look for embedded RUTV player
1701 rutv_url = RUTVIE._extract_url(webpage)
1703 return self.url_result(rutv_url, 'RUTV')
1705 # Look for embedded TVC player
1706 tvc_url = TVCIE._extract_url(webpage)
1708 return self.url_result(tvc_url, 'TVC')
1710 # Look for embedded SportBox player
1711 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1713 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1715 # Look for embedded PornHub player
1716 pornhub_url = PornHubIE._extract_url(webpage)
1718 return self.url_result(pornhub_url, 'PornHub')
1720 # Look for embedded XHamster player
1721 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1723 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1725 # Look for embedded TNAFlixNetwork player
1726 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1728 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1730 # Look for embedded Tvigle player
1732 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1733 if mobj is not None:
1734 return self.url_result(mobj.group('url'), 'Tvigle')
1736 # Look for embedded TED player
1738 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1739 if mobj is not None:
1740 return self.url_result(mobj.group('url'), 'TED')
1742 # Look for embedded Ustream videos
1744 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1745 if mobj is not None:
1746 return self.url_result(mobj.group('url'), 'Ustream')
1748 # Look for embedded arte.tv player
1750 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1755 # Look for embedded francetv player
1757 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1759 if mobj is not None:
1760 return self.url_result(mobj.group('url'))
1762 # Look for embedded smotri.com player
1763 smotri_url = SmotriIE._extract_url(webpage)
1765 return self.url_result(smotri_url, 'Smotri')
1767 # Look for embedded Myvi.ru player
1768 myvi_url = MyviIE._extract_url(webpage)
1770 return self.url_result(myvi_url)
1772 # Look for embedded soundcloud player
1774 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1776 if mobj is not None:
1777 url = unescapeHTML(mobj.group('url'))
1778 return self.url_result(url)
1780 # Look for embedded vulture.com player
1782 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1784 if mobj is not None:
1785 url = unescapeHTML(mobj.group('url'))
1786 return self.url_result(url, ie='Vulture')
1788 # Look for embedded mtvservices player
1789 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1791 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1793 # Look for embedded yahoo player
1795 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1797 if mobj is not None:
1798 return self.url_result(mobj.group('url'), 'Yahoo')
1800 # Look for embedded sbs.com.au player
1804 <meta\s+property="og:video"\s+content=|
1807 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1809 if mobj is not None:
1810 return self.url_result(mobj.group('url'), 'SBS')
1812 # Look for embedded Cinchcast player
1814 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1816 if mobj is not None:
1817 return self.url_result(mobj.group('url'), 'Cinchcast')
1820 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1824 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1826 if mobj is not None:
1827 return self.url_result(mobj.group('url'), 'MLB')
1830 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1832 if mobj is not None:
1833 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1836 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1838 if mobj is not None:
1839 return self.url_result(mobj.group('url'), 'Livestream')
1841 # Look for Zapiks embed
1843 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1844 if mobj is not None:
1845 return self.url_result(mobj.group('url'), 'Zapiks')
1847 # Look for Kaltura embeds
1848 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1849 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))
1850 if mobj is not None:
1851 return self.url_result(smuggle_url(
1852 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1853 {'source_url': url}), 'Kaltura')
1855 # Look for Eagle.Platform embeds
1857 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1858 if mobj is not None:
1859 return self.url_result(mobj.group('url'), 'EaglePlatform')
1861 # Look for ClipYou (uses Eagle.Platform) embeds
1863 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1864 if mobj is not None:
1865 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1867 # Look for Pladform embeds
1868 pladform_url = PladformIE._extract_url(webpage)
1870 return self.url_result(pladform_url)
1872 # Look for Videomore embeds
1873 videomore_url = VideomoreIE._extract_url(webpage)
1875 return self.url_result(videomore_url)
1877 # Look for Playwire embeds
1879 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1880 if mobj is not None:
1881 return self.url_result(mobj.group('url'))
1883 # Look for 5min embeds
1885 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1886 if mobj is not None:
1887 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1889 # Look for Crooks and Liars embeds
1891 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1892 if mobj is not None:
1893 return self.url_result(mobj.group('url'))
1895 # Look for NBC Sports VPlayer embeds
1896 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1898 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1900 # Look for Google Drive embeds
1901 google_drive_url = GoogleDriveIE._extract_url(webpage)
1902 if google_drive_url:
1903 return self.url_result(google_drive_url, 'GoogleDrive')
1905 # Look for UDN embeds
1907 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1908 if mobj is not None:
1909 return self.url_result(
1910 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1912 # Look for Senate ISVP iframe
1913 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1915 return self.url_result(senate_isvp_url, 'SenateISVP')
1917 # Look for Dailymotion Cloud videos
1918 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1920 return self.url_result(dmcloud_url, 'DailymotionCloud')
1922 # Look for OnionStudios embeds
1923 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1924 if onionstudios_url:
1925 return self.url_result(onionstudios_url)
1927 # Look for ViewLift embeds
1928 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1930 return self.url_result(viewlift_url)
1932 # Look for JWPlatform embeds
1933 jwplatform_url = JWPlatformIE._extract_url(webpage)
1935 return self.url_result(jwplatform_url, 'JWPlatform')
1937 # Look for ScreenwaveMedia embeds
1938 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1939 if mobj is not None:
1940 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1942 # Look for Digiteka embeds
1943 digiteka_url = DigitekaIE._extract_url(webpage)
1945 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1947 # Look for Limelight embeds
1948 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1952 'Channel': 'channel',
1953 'ChannelList': 'channel_list',
1955 return self.url_result('limelight:%s:%s' % (
1956 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1958 # Look for AdobeTVVideo embeds
1960 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1962 if mobj is not None:
1963 return self.url_result(
1964 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1967 # Look for Vine embeds
1969 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1971 if mobj is not None:
1972 return self.url_result(
1973 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1975 # Look for Instagram embeds
1976 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
1977 if instagram_embed_url is not None:
1978 return self.url_result(
1979 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
1981 # Look for LiveLeak embeds
1982 liveleak_url = LiveLeakIE._extract_url(webpage)
1984 return self.url_result(liveleak_url, 'LiveLeak')
1986 def check_video(vurl):
1987 if YoutubeIE.suitable(vurl):
1989 vpath = compat_urlparse.urlparse(vurl).path
1990 vext = determine_ext(vpath)
1991 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1993 def filter_video(urls):
1994 return list(filter(check_video, urls))
1996 # Start with something easy: JW Player in SWFObject
1997 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1999 # Look for gorilla-vid style embedding
2000 found = filter_video(re.findall(r'''(?sx)
2004 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2007 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2009 # Broaden the search a little bit
2010 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2012 # Broaden the findall a little bit: JWPlayer JS loader
2013 found = filter_video(re.findall(
2014 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2017 found = filter_video(re.findall(r'''(?xs)
2018 flowplayer\("[^"]+",\s*
2020 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2021 ["']?url["']?\s*:\s*["']([^"']+)["']
2026 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2028 # Try to find twitter cards info
2029 found = filter_video(re.findall(
2030 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2032 # We look for Open Graph info:
2033 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2034 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2035 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2036 if m_video_type is not None:
2037 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2040 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2042 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2044 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2045 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2048 # Look also in Refresh HTTP header
2049 refresh_header = head_response.headers.get('Refresh')
2051 # In python 2 response HTTP headers are bytestrings
2052 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2053 refresh_header = refresh_header.decode('iso-8859-1')
2054 found = re.search(REDIRECT_REGEX, refresh_header)
2056 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2057 self.report_following_redirect(new_url)
2063 raise UnsupportedError(url)
2066 for video_url in found:
2067 video_url = unescapeHTML(video_url)
2068 video_url = video_url.replace('\\/', '/')
2069 video_url = compat_urlparse.urljoin(url, video_url)
2070 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2072 # Sometimes, jwplayer extraction will result in a YouTube URL
2073 if YoutubeIE.suitable(video_url):
2074 entries.append(self.url_result(video_url, 'Youtube'))
2077 # here's a fun little line of code for you:
2078 video_id = os.path.splitext(video_id)[0]
2082 'uploader': video_uploader,
2083 'title': video_title,
2084 'age_limit': age_limit,
2087 ext = determine_ext(video_url)
2089 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2091 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2093 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2095 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2097 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2099 entry_info_dict['url'] = video_url
2101 if entry_info_dict.get('formats'):
2102 self._sort_formats(entry_info_dict['formats'])
2104 entries.append(entry_info_dict)
2106 if len(entries) == 1:
2109 for num, e in enumerate(entries, start=1):
2110 # 'url' results don't have a title
2111 if e.get('title') is not None:
2112 e['title'] = '%s (%d)' % (e['title'], num)
2114 '_type': 'playlist',