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 (
56 from .onionstudios import OnionStudiosIE
57 from .viewlift import ViewLiftEmbedIE
58 from .screenwavemedia import ScreenwaveMediaIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .googledrive import GoogleDriveIE
63 from .jwplatform import JWPlatformIE
64 from .digiteka import DigitekaIE
65 from .arkena import ArkenaIE
66 from .instagram import InstagramIE
67 from .liveleak import LiveLeakIE
68 from .threeqsdn import ThreeQSDNIE
69 from .theplatform import ThePlatformIE
70 from .vessel import VesselIE
71 from .kaltura import KalturaIE
72 from .eagleplatform import EaglePlatformIE
73 from .facebook import FacebookIE
76 class GenericIE(InfoExtractor):
77 IE_DESC = 'Generic downloader that works on some sites'
81 # Direct link to a video
83 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
84 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
89 'upload_date': '20100513',
92 # Direct link to media delivered compressed (until Accept-Encoding is *)
94 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
95 'md5': '128c42e68b13950268b648275386fc74',
97 'id': 'FictionJunction-Parallel_Hearts',
99 'title': 'FictionJunction-Parallel_Hearts',
100 'upload_date': '20140522',
102 'expected_warnings': [
103 'URL could be a direct video link, returning it as such.'
106 # Direct download with broken HEAD
108 'url': 'http://ai-radio.org:8000/radio.opus',
115 'skip_download': True, # infinite live stream
117 'expected_warnings': [
118 r'501.*Not Implemented',
122 # Direct link with incorrect MIME type
124 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
125 'md5': '4ccbebe5f36706d85221f204d7eb5913',
127 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
128 'id': '5_Lennart_Poettering_-_Systemd',
130 'title': '5_Lennart_Poettering_-_Systemd',
131 'upload_date': '20141120',
133 'expected_warnings': [
134 'URL could be a direct video link, returning it as such.'
139 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
141 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
142 'title': 'Zero Punctuation',
143 'description': 're:.*groundbreaking video review series.*'
145 'playlist_mincount': 11,
147 # RSS feed with enclosure
149 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
151 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
153 'upload_date': '20150228',
154 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
157 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
159 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
163 'title': 'Automatics, robotics and biocybernetics',
164 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
165 'upload_date': '20130627',
166 'formats': 'mincount:16',
167 'subtitles': 'mincount:1',
170 'force_generic_extractor': True,
171 'skip_download': True,
174 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
176 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
181 'formats': 'mincount:1',
184 'skip_download': True,
187 # SMIL from https://www.restudy.dk/video/play/id/1637
189 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
193 'title': 'video_1637',
194 'formats': 'mincount:3',
197 'skip_download': True,
200 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
202 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
204 'id': 'smil-service',
206 'title': 'smil-service',
207 'formats': 'mincount:1',
210 'skip_download': True,
213 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
215 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
219 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
220 'formats': 'mincount:3',
223 'skip_download': True,
226 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
228 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
230 'id': 'mZlp2ctYIUEB',
232 'title': 'Tikibad ontruimd wegens brand',
233 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
234 'thumbnail': 're:^https?://.*\.jpg$',
238 'skip_download': True,
241 # MPD from http://dash-mse-test.appspot.com/media.html
243 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
244 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
246 'id': 'car-20120827-manifest',
248 'title': 'car-20120827-manifest',
249 'formats': 'mincount:9',
250 'upload_date': '20130904',
253 'format': 'bestvideo',
256 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
258 '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',
263 'formats': 'mincount:8',
267 'skip_download': True,
270 # m3u8 served with Content-Type: text/plain
272 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
277 'upload_date': '20140720',
278 'formats': 'mincount:11',
282 'skip_download': True,
287 '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',
291 'upload_date': '20130224',
292 'uploader_id': 'TheVerge',
293 'description': 're:^Chris Ziegler takes a look at the\.*',
294 'uploader': 'The Verge',
295 'title': 'First Firefox OS phones side-by-side',
298 'skip_download': False,
302 # redirect in Refresh HTTP header
303 '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',
307 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
308 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
309 'upload_date': '20150917',
310 'uploader_id': 'brtvofficial',
311 'uploader': 'Boiler Room',
314 'skip_download': False,
318 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
319 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
321 'id': '13601338388002',
323 'uploader': 'www.hodiho.fr',
324 'title': 'R\u00e9gis plante sa Jeep',
327 # bandcamp page with custom domain
329 'add_ie': ['Bandcamp'],
330 'url': 'http://bronyrock.com/track/the-pony-mash',
334 'title': 'The Pony Mash',
335 'uploader': 'M_Pallante',
337 'skip': 'There is a limit of 200 free downloads / month for the test song',
339 # embedded brightcove video
340 # it also tests brightcove videos that need to set the 'Referer' in the
343 'add_ie': ['BrightcoveLegacy'],
344 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
346 'id': '2765128793001',
348 'title': 'Le cours de bourse : l’analyse technique',
349 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
350 'uploader': 'BFM BUSINESS',
353 'skip_download': True,
357 # https://github.com/rg3/youtube-dl/issues/2253
358 'url': 'http://bcove.me/i6nfkrc3',
359 'md5': '0ba9446db037002366bab3b3eb30c88c',
361 'id': '3101154703001',
363 'title': 'Still no power',
364 'uploader': 'thestar.com',
365 '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.',
367 'add_ie': ['BrightcoveLegacy'],
370 'url': 'http://www.championat.com/video/football/v/87/87499.html',
371 'md5': 'fb973ecf6e4a78a67453647444222983',
373 'id': '3414141473001',
375 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
376 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
377 'uploader': 'Championat',
381 # https://github.com/rg3/youtube-dl/issues/3541
382 'add_ie': ['BrightcoveLegacy'],
383 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
385 'id': '3866516442001',
387 'title': 'Leer mij vrouwen kennen: Aflevering 1',
388 'description': 'Leer mij vrouwen kennen: Aflevering 1',
389 'uploader': 'SBS Broadcasting',
391 'skip': 'Restricted to Netherlands',
393 'skip_download': True, # m3u8 download
398 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
399 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
401 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
403 'title': '2cc213299525360.mov', # that's what we get
406 'add_ie': ['Ooyala'],
409 # ooyala video embedded with http://player.ooyala.com/iframe.js
410 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
412 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
414 'title': '"Steve Jobs: Man in the Machine" trailer',
415 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
419 'skip_download': True,
424 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
428 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
429 'upload_date': '20140225',
430 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
431 'uploader': 'Tested',
432 'uploader_id': 'testedcom',
434 # No need to test YoutubeIE here
436 'skip_download': True,
441 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
445 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
446 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
451 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
455 'title': 'Охотское море стало целиком российским',
456 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
460 'skip_download': True,
465 '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/',
469 'title': 'Дошкольное воспитание',
474 'url': 'http://www.vestifinance.ru/articles/25753',
477 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
482 'title': 'Госзаказ. День 3',
488 'title': 'Госзаказ. День 2',
494 'title': 'Госзаказ. День 1',
500 'skip_download': True,
505 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
507 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
509 'title': 'Ужастики, русский трейлер (2015)',
510 'thumbnail': 're:^https?://.*\.jpg$',
516 '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',
519 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
521 'playlist_mincount': 7,
525 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
526 'md5': '65fdff94098e4a607385a60c5177c638',
530 'title': 'Hidden miracles of the natural world',
531 'uploader': 'Louie Schwartzberg',
532 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
535 # Embedded Ustream video
537 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
538 'md5': '27b99cdb639c9b12a79bca876a073417',
542 'uploader': 'AU SPA: The NSA and Privacy',
543 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
546 # nowvideo embed hidden behind percent encoding
548 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
549 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
551 'id': '06e53103ca9aa',
553 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
554 'description': 'No description',
559 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
560 'md5': '7653032cbb25bf6c80d80f217055fa43',
562 'id': '048195-004_PLUS7-F',
565 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
566 'upload_date': '20140320',
569 'skip_download': 'Requires rtmpdump'
574 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
578 'title': 'Alcaline, le concert avec Calogero',
579 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
580 'upload_date': '20150226',
581 'timestamp': 1424989860,
586 'skip_download': True,
588 'expected_warnings': [
594 'url': 'http://www.wired.com/2014/04/honda-asimo/',
595 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
597 'id': '53501be369702d3275860000',
599 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
604 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
605 'md5': '441aeeb82eb72c422c7f14ec533999cd',
607 'id': 'k2mm4bCdJ6CQ2i7c8o2',
609 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
610 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
612 'uploader_id': 'xgditw',
613 'upload_date': '20140425',
614 'timestamp': 1398441542,
616 'add_ie': ['Dailymotion'],
620 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
624 'title': 'The NBL Auction 2014',
625 'uploader': 'BADMINTON England',
626 'uploader_id': 'BADMINTONEvents',
627 'upload_date': '20140603',
628 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
630 'add_ie': ['Youtube'],
632 'skip_download': True,
637 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
638 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
640 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
642 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
643 'description': 'Two valets share their love for movie star Liam Neesons.',
644 'timestamp': 1349922600,
645 'upload_date': '20121011',
648 # YouTube embed via <data-embed-url="">
650 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
654 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
655 'uploader': 'Gameloft',
656 'uploader_id': 'gameloft',
657 'upload_date': '20140828',
658 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
661 'skip_download': True,
666 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
668 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
670 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
671 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
676 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
678 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
679 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
685 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
690 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
691 'md5': '9d65602bf31c6e20014319c7d07fba27',
693 'id': '5123ea6d5e5a7',
696 'uploader': 'www.handjobhub.com',
697 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
700 # Multiple brightcove videos
701 # https://github.com/rg3/youtube-dl/issues/2283
703 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
705 'id': 'always-never',
706 'title': 'Always / Never - The New Yorker',
710 'extract_flat': False,
711 'skip_download': True,
716 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
717 'md5': '96f09a37e44da40dd083e12d9a683327',
721 'title': 'Ump changes call to ball',
722 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
724 'timestamp': 1401537900,
725 'upload_date': '20140531',
726 'thumbnail': 're:^https?://.*\.jpg$',
731 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
732 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
736 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
737 'description': 'a Paywall Videos video from Remilon',
739 'uploader': 'study.com',
740 'timestamp': 1459678540,
741 'upload_date': '20160403',
742 'filesize': 24687186,
746 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
747 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
751 'title': 'Conversation about Hexagonal Rails Part 1',
752 'description': 'a Martin Fowler video from ThoughtWorks',
754 'uploader': 'thoughtworks.wistia.com',
755 'timestamp': 1401832161,
756 'upload_date': '20140603',
759 # Wistia standard embed (async)
761 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
765 'title': 'Drip Brennan Dunn Workshop',
766 'description': 'a JV Webinars video from getdrip-1',
768 'timestamp': 1463607249,
769 'upload_date': '20160518',
772 'skip_download': True,
777 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
781 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
782 'uploader': 'Sophos Security',
783 'title': 'Chet Chat 171 - Oct 29, 2014',
784 'upload_date': '20141029',
789 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
793 'upload_date': '20141112',
794 'title': 'Rosetta #CometLanding webcast HL 10',
797 # Another Livestream embed, without 'new.' in URL
799 'url': 'https://www.freespeech.org/',
803 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
807 'skip_download': True,
812 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
815 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
817 'playlist_mincount': 2,
821 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
825 'upload_date': '20141126',
826 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
831 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
833 'id': '730m_DandD_1901_512k',
835 'uploader': 'www.abc.net.au',
836 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
839 # embedded viddler video
841 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
845 'uploader': 'deadspin',
846 'title': 'WALL-TO-GORTAT',
847 'timestamp': 1422285291,
848 'upload_date': '20150126',
850 'add_ie': ['Viddler'],
854 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
858 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
859 'description': 'md5:601cb790edd05908957dae8aaa866465',
860 'upload_date': '20150220',
862 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
866 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
870 'upload_date': '20150212',
871 'uploader': 'The National Archives UK',
872 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
873 'uploader_id': 'NationalArchives08',
874 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
879 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
880 'playlist_mincount': 5,
882 'id': 'aanslagen-kopenhagen',
883 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
888 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
892 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
895 # Kaltura embed (different embed code)
897 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
901 'upload_date': '20150127',
902 'uploader_id': 'PremierMedia',
904 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
907 # Kaltura embed protected with referrer
909 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
913 'title': 'Violetta - Achter De Schermen - Ruggero',
914 'description': 'Achter de schermen met Ruggero',
915 'timestamp': 1435133761,
916 'upload_date': '20150624',
917 'uploader_id': 'echojecka',
920 # Kaltura embed with single quotes
922 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
927 'timestamp': 1355743100,
928 'upload_date': '20121217',
929 'uploader_id': 'batchUser',
931 'add_ie': ['Kaltura'],
934 # Kaltura embedded via quoted entry_id
935 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
939 'title': '06_matthew_brender_raj_dutt',
940 'timestamp': 1466638791,
941 'upload_date': '20160622',
943 'add_ie': ['Kaltura'],
944 'expected_warnings': [
945 'Could not send HEAD request'
948 'skip_download': True,
951 # Eagle.Platform embed (generic URL)
953 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
954 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
958 'title': 'Навальный вышел на свободу',
959 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
960 'thumbnail': 're:^https?://.*\.jpg$',
966 # ClipYou (Eagle.Platform) embed (custom URL)
968 'url': 'http://muz-tv.ru/play/7129/',
969 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
973 'title': "'O Sole Mio",
974 'thumbnail': 're:^https?://.*\.jpg$',
981 'url': 'http://muz-tv.ru/kinozal/view/7400/',
985 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
986 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
987 'thumbnail': 're:^https?://.*\.jpg$',
994 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
998 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
999 'thumbnail': 're:^https?://.*\.png$',
1005 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1006 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1010 'title': 'Facebook Creates "On This Day" | Crunch Report',
1015 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1019 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1024 # Crooks and Liars embed
1026 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1030 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1031 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1032 'timestamp': 1428207000,
1033 'upload_date': '20150405',
1034 'uploader': 'Heather',
1037 # Crooks and Liars external embed
1039 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1041 'id': 'MTE3MjUtMzQ2MzA',
1043 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1044 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1045 'timestamp': 1265032391,
1046 'upload_date': '20100201',
1047 'uploader': 'Heather',
1050 # NBC Sports vplayer embed
1052 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1054 'id': 'ln7x1qSThw4k',
1056 'title': "PFT Live: New leader in the 'new-look' defense",
1057 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1058 'uploader': 'NBCU-SPORTS',
1059 'upload_date': '20140107',
1060 'timestamp': 1389118457,
1065 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1066 'md5': '1aa589c675898ae6d37a17913cf68d66',
1068 'id': '701714499682',
1070 'title': 'PREVIEW: On Assignment: David Letterman',
1071 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1076 'url': 'https://video.udn.com/news/300346',
1077 'md5': 'fd2060e988c326991037b9aff9df21a6',
1081 'title': '中一中男師變性 全校師生力挺',
1082 'thumbnail': 're:^https?://.*\.jpg$',
1086 'skip_download': True,
1091 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1093 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1095 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1096 'title': 'This is what separates the Excel masters from the wannabes',
1097 'duration': 191.933,
1101 'skip_download': True,
1104 # Brightcove URL in single quotes
1106 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1107 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1109 'id': '4255764656001',
1111 'title': 'SN Presents: Russell Martin, World Citizen',
1112 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1113 'uploader': 'Rogers Sportsnet',
1114 'uploader_id': '1704050871',
1115 'upload_date': '20150525',
1116 'timestamp': 1432570283,
1119 # Dailymotion Cloud video
1121 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1122 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1126 'title': 'Sauvons les abeilles ! - Le débat',
1127 'description': 'md5:d9082128b1c5277987825d684939ca26',
1128 'thumbnail': 're:^https?://.*\.jpe?g$',
1129 'timestamp': 1434970506,
1130 'upload_date': '20150622',
1131 'uploader': 'Public Sénat',
1132 'uploader_id': 'xa9gza',
1135 # OnionStudios embed
1137 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1141 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1142 'thumbnail': 're:^https?://.*\.jpe?g$',
1143 'uploader': 'ClickHole',
1144 'uploader_id': 'clickhole',
1149 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1151 'id': '74849a00-85a9-11e1-9660-123139220831',
1153 'title': '#whilewewatch',
1156 # AdobeTVVideo embed
1158 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1159 'md5': '43662b577c018ad707a63766462b1e87',
1163 'title': 'New experience with Acrobat DC',
1164 'description': 'New experience with Acrobat DC',
1165 'duration': 248.667,
1168 # ScreenwaveMedia embed
1170 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1171 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1173 'id': 'cinemasnob-55d26273809dd',
1175 'title': 'cinemasnob',
1178 # BrightcoveInPageEmbed embed
1180 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1182 'id': '4238694884001',
1184 'title': 'Tabletop: Dread, Last Thoughts',
1185 'description': 'Tabletop: Dread, Last Thoughts',
1189 # JWPlayer with M3U8
1191 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1195 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1196 'uploader': 'ren.tv',
1200 'skip_download': True,
1203 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1204 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1206 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1208 'id': '4785848093001',
1210 'title': 'The Cardinal Pell Interview',
1211 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1212 'uploader': 'GlobeCast Australia - GlobeStream',
1213 'uploader_id': '2733773828001',
1214 'upload_date': '20160304',
1215 'timestamp': 1457083087,
1219 'skip_download': True,
1222 # Another form of arte.tv embed
1224 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1225 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1227 'id': '030273-562_PLUS7-F',
1229 'title': 'ARTE Reportage - Nulle part, en France',
1230 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1231 'upload_date': '20160409',
1236 'url': 'http://www.wykop.pl/link/3088787/',
1237 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1239 'id': '874_1459135191',
1241 'title': 'Man shows poor quality of new apartment building',
1242 'description': 'The wall is like a sand pile.',
1243 'uploader': 'Lake8737',
1246 # Duplicated embedded video URLs
1248 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1250 'id': '149298443_480_16c25b74_2',
1252 'title': 'vs. Blue Orange Spring Game',
1253 'uploader': 'www.hudl.com',
1256 # twitter:player:stream embed
1258 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1262 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1263 'uploader': 'www.rtl.be',
1267 'skip_download': True,
1270 # twitter:player embed
1272 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1273 'md5': 'a3e0df96369831de324f0778e126653c',
1275 'id': '4909620399001',
1277 'title': 'What Do Black Holes Sound Like?',
1278 'description': 'what do black holes sound like',
1279 'upload_date': '20160524',
1280 'uploader_id': '29913724001',
1281 'timestamp': 1464107587,
1282 'uploader': 'TheAtlantic',
1284 'add_ie': ['BrightcoveLegacy'],
1286 # Facebook <iframe> embed
1288 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1289 'md5': 'fbcde74f534176ecb015849146dd3aee',
1291 'id': '599637780109885',
1293 'title': 'Facebook video #599637780109885',
1296 # Facebook API embed
1298 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1299 'md5': 'a47372ee61b39a7b90287094d447d94e',
1301 'id': '10153467542406923',
1303 'title': 'Facebook video #10153467542406923',
1306 # Wordpress "YouTube Video Importer" plugin
1308 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1309 'md5': 'd16797741b560b485194eddda8121b48',
1311 'id': 'HNTXWDXV9Is',
1313 'title': 'Blue Devils Drumline Stanford lot 2016',
1314 'upload_date': '20160627',
1315 'uploader_id': 'GENOCIDE8GENERAL10',
1316 'uploader': 'cylus cyrus',
1320 # video stored on custom kaltura server
1321 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1322 'md5': '537617d06e64dfed891fa1593c4b30cc',
1326 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1327 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1328 'uploader_id': 'videos.expansion@el-mundo.net',
1329 'upload_date': '20150429',
1330 'timestamp': 1430303472,
1332 'add_ie': ['Kaltura'],
1335 # Non-standard Vimeo embed
1336 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1337 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1341 'title': 'Understanding the web - Teaser',
1342 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1343 'upload_date': '20151214',
1344 'uploader': 'OpenClassrooms',
1345 'uploader_id': 'openclassrooms',
1347 'add_ie': ['Vimeo'],
1350 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1351 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1353 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1355 'title': 'Big Buck Bunny',
1356 'description': 'Royalty free test video',
1357 'timestamp': 1432816365,
1358 'upload_date': '20150528',
1362 'skip_download': True,
1364 'add_ie': [ArkenaIE.ie_key()],
1367 # # TODO: find another test
1368 # # http://schema.org/VideoObject
1369 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1370 # 'md5': '888dcf08b7ea671381f00fab74692755',
1372 # 'id': 'nyvTSJMKId',
1374 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1375 # 'description': '#love for cats.',
1376 # 'timestamp': 1461244995,
1377 # 'upload_date': '20160421',
1380 # 'force_generic_extractor': True,
1385 def report_following_redirect(self, new_url):
1386 """Report information extraction."""
1387 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1389 def _extract_rss(self, url, video_id, doc):
1390 playlist_title = doc.find('./channel/title').text
1391 playlist_desc_el = doc.find('./channel/description')
1392 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1395 for it in doc.findall('./channel/item'):
1396 next_url = xpath_text(it, 'link', fatal=False)
1398 enclosure_nodes = it.findall('./enclosure')
1399 for e in enclosure_nodes:
1400 next_url = e.attrib.get('url')
1410 'title': it.find('title').text,
1414 '_type': 'playlist',
1416 'title': playlist_title,
1417 'description': playlist_desc,
1421 def _extract_camtasia(self, url, video_id, webpage):
1422 """ Returns None if no camtasia video can be found. """
1424 camtasia_cfg = self._search_regex(
1425 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1426 webpage, 'camtasia configuration file', default=None)
1427 if camtasia_cfg is None:
1430 title = self._html_search_meta('DC.title', webpage, fatal=True)
1432 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1433 camtasia_cfg = self._download_xml(
1434 camtasia_url, video_id,
1435 note='Downloading camtasia configuration',
1436 errnote='Failed to download camtasia configuration')
1437 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1440 for n in fileset_node.getchildren():
1441 url_n = n.find('./uri')
1446 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1447 'title': '%s - %s' % (title, n.tag),
1448 'url': compat_urlparse.urljoin(url, url_n.text),
1449 'duration': float_or_none(n.find('./duration').text),
1453 '_type': 'playlist',
1458 def _real_extract(self, url):
1459 if url.startswith('//'):
1462 'url': self.http_scheme() + url,
1465 parsed_url = compat_urlparse.urlparse(url)
1466 if not parsed_url.scheme:
1467 default_search = self._downloader.params.get('default_search')
1468 if default_search is None:
1469 default_search = 'fixup_error'
1471 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1473 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1474 return self.url_result('http://' + url)
1475 elif default_search != 'fixup_error':
1476 if default_search == 'auto_warning':
1477 if re.match(r'^(?:url|URL)$', url):
1478 raise ExtractorError(
1479 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1482 self._downloader.report_warning(
1483 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1484 return self.url_result('ytsearch:' + url)
1486 if default_search in ('error', 'fixup_error'):
1487 raise ExtractorError(
1488 '%r is not a valid URL. '
1489 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1490 % (url, url), expected=True)
1492 if ':' not in default_search:
1493 default_search += ':'
1494 return self.url_result(default_search + url)
1496 url, smuggled_data = unsmuggle_url(url)
1497 force_videoid = None
1498 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1499 if smuggled_data and 'force_videoid' in smuggled_data:
1500 force_videoid = smuggled_data['force_videoid']
1501 video_id = force_videoid
1503 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1505 self.to_screen('%s: Requesting header' % video_id)
1507 head_req = HEADRequest(url)
1508 head_response = self._request_webpage(
1510 note=False, errnote='Could not send HEAD request to %s' % url,
1513 if head_response is not False:
1514 # Check for redirect
1515 new_url = head_response.geturl()
1517 self.report_following_redirect(new_url)
1519 new_url = smuggle_url(
1520 new_url, {'force_videoid': force_videoid})
1521 return self.url_result(new_url)
1523 full_response = None
1524 if head_response is False:
1525 request = sanitized_Request(url)
1526 request.add_header('Accept-Encoding', '*')
1527 full_response = self._request_webpage(request, video_id)
1528 head_response = full_response
1532 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1533 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1536 # Check for direct link to a video
1537 content_type = head_response.headers.get('Content-Type', '').lower()
1538 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1540 format_id = m.group('format_id')
1541 if format_id.endswith('mpegurl'):
1542 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1543 elif format_id == 'f4m':
1544 formats = self._extract_f4m_formats(url, video_id)
1547 'format_id': m.group('format_id'),
1549 'vcodec': 'none' if m.group('type') == 'audio' else None
1551 info_dict['direct'] = True
1552 self._sort_formats(formats)
1553 info_dict['formats'] = formats
1556 if not self._downloader.params.get('test', False) and not is_intentional:
1557 force = self._downloader.params.get('force_generic_extractor', False)
1558 self._downloader.report_warning(
1559 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1561 if not full_response:
1562 request = sanitized_Request(url)
1563 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1564 # making it impossible to download only chunk of the file (yet we need only 512kB to
1565 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1566 # that will always result in downloading the whole file that is not desirable.
1567 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1568 # to accept raw bytes and being able to download only a chunk.
1569 # It may probably better to solve this by checking Content-Type for application/octet-stream
1570 # after HEAD request finishes, but not sure if we can rely on this.
1571 request.add_header('Accept-Encoding', '*')
1572 full_response = self._request_webpage(request, video_id)
1574 first_bytes = full_response.read(512)
1576 # Is it an M3U playlist?
1577 if first_bytes.startswith(b'#EXTM3U'):
1578 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1579 self._sort_formats(info_dict['formats'])
1582 # Maybe it's a direct link to a video?
1583 # Be careful not to download the whole thing!
1584 if not is_html(first_bytes):
1585 self._downloader.report_warning(
1586 'URL could be a direct video link, returning it as such.')
1593 webpage = self._webpage_read_content(
1594 full_response, url, video_id, prefix=first_bytes)
1596 self.report_extraction(video_id)
1598 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1600 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1601 if doc.tag == 'rss':
1602 return self._extract_rss(url, video_id, doc)
1603 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1604 smil = self._parse_smil(doc, url, video_id)
1605 self._sort_formats(smil['formats'])
1607 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1608 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1609 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1610 info_dict['formats'] = self._parse_mpd_formats(
1611 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1612 self._sort_formats(info_dict['formats'])
1614 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1615 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1616 self._sort_formats(info_dict['formats'])
1618 except compat_xml_parse_error:
1621 # Is it a Camtasia project?
1622 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1623 if camtasia_res is not None:
1626 # Sometimes embedded video player is hidden behind percent encoding
1627 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1628 # Unescaping the whole page allows to handle those cases in a generic way
1629 webpage = compat_urllib_parse_unquote(webpage)
1631 # it's tempting to parse this further, but you would
1632 # have to take into account all the variations like
1633 # Video Title - Site Name
1634 # Site Name | Video Title
1635 # Video Title - Tagline | Site Name
1636 # and so on and so forth; it's just not practical
1637 video_title = self._og_search_title(
1638 webpage, default=None) or self._html_search_regex(
1639 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1642 # Try to detect age limit automatically
1643 age_limit = self._rta_search(webpage)
1644 # And then there are the jokers who advertise that they use RTA,
1645 # but actually don't.
1646 AGE_LIMIT_MARKERS = [
1647 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1649 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1652 # video uploader is domain name
1653 video_uploader = self._search_regex(
1654 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1656 video_description = self._og_search_description(webpage, default=None)
1657 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1660 def _playlist_from_matches(matches, getter=None, ie=None):
1662 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1664 return self.playlist_result(
1665 urlrs, playlist_id=video_id, playlist_title=video_title)
1667 # Look for Brightcove Legacy Studio embeds
1668 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1670 self.to_screen('Brightcove video detected.')
1673 'url': smuggle_url(bc_url, {'Referer': url}),
1674 'ie_key': 'BrightcoveLegacy'
1675 } for bc_url in bc_urls]
1678 '_type': 'playlist',
1679 'title': video_title,
1684 # Look for Brightcove New Studio embeds
1685 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1687 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1689 # Look for ThePlatform embeds
1690 tp_urls = ThePlatformIE._extract_urls(webpage)
1692 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1694 # Look for Vessel embeds
1695 vessel_urls = VesselIE._extract_urls(webpage)
1697 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1699 # Look for embedded rtl.nl player
1700 matches = re.findall(
1701 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1704 return _playlist_from_matches(matches, ie='RtlNl')
1706 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1707 if vimeo_url is not None:
1708 return self.url_result(vimeo_url)
1710 vid_me_embed_url = self._search_regex(
1711 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1712 webpage, 'vid.me embed', default=None)
1713 if vid_me_embed_url is not None:
1714 return self.url_result(vid_me_embed_url, 'Vidme')
1716 # Look for embedded YouTube player
1717 matches = re.findall(r'''(?x)
1726 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1730 return _playlist_from_matches(
1731 matches, lambda m: unescapeHTML(m[1]))
1733 # Look for lazyYT YouTube embed
1734 matches = re.findall(
1735 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1737 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1739 # Look for Wordpress "YouTube Video Importer" plugin
1740 matches = re.findall(r'''(?x)<div[^>]+
1741 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1742 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1744 return _playlist_from_matches(matches, lambda m: m[-1])
1746 matches = DailymotionIE._extract_urls(webpage)
1748 return _playlist_from_matches(matches)
1750 # Look for embedded Dailymotion playlist player (#3822)
1752 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1754 playlists = re.findall(
1755 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1757 return _playlist_from_matches(
1758 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1760 # Look for embedded Wistia player
1762 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1764 embed_url = self._proto_relative_url(
1765 unescapeHTML(match.group('url')))
1767 '_type': 'url_transparent',
1770 'uploader': video_uploader,
1773 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1776 '_type': 'url_transparent',
1777 'url': 'wistia:%s' % match.group('id'),
1779 'uploader': video_uploader,
1784 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1785 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1788 return self.url_result(self._proto_relative_url(
1789 'wistia:%s' % match.group('id')), 'Wistia')
1791 # Look for SVT player
1792 svt_url = SVTIE._extract_url(webpage)
1794 return self.url_result(svt_url, 'SVT')
1796 # Look for embedded condenast player
1797 matches = re.findall(
1798 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1802 '_type': 'playlist',
1805 'ie_key': 'CondeNast',
1807 } for ma in matches],
1808 'title': video_title,
1812 # Look for Bandcamp pages with custom domain
1813 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1814 if mobj is not None:
1815 burl = unescapeHTML(mobj.group(1))
1816 # Don't set the extractor because it can be a track url or an album
1817 return self.url_result(burl)
1819 # Look for embedded Vevo player
1821 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1822 if mobj is not None:
1823 return self.url_result(mobj.group('url'))
1825 # Look for embedded Viddler player
1827 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1829 if mobj is not None:
1830 return self.url_result(mobj.group('url'))
1832 # Look for NYTimes player
1834 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1836 if mobj is not None:
1837 return self.url_result(mobj.group('url'))
1839 # Look for Libsyn player
1841 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1842 if mobj is not None:
1843 return self.url_result(mobj.group('url'))
1845 # Look for Ooyala videos
1846 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1847 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1848 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1849 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1850 if mobj is not None:
1851 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1853 # Look for multiple Ooyala embeds on SBN network websites
1854 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1855 if mobj is not None:
1856 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1858 return _playlist_from_matches(
1859 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1861 # Look for Aparat videos
1862 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1863 if mobj is not None:
1864 return self.url_result(mobj.group(1), 'Aparat')
1866 # Look for MPORA videos
1867 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1868 if mobj is not None:
1869 return self.url_result(mobj.group(1), 'Mpora')
1871 # Look for embedded NovaMov-based player
1873 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1874 (?P<url>http://(?:(?:embed|www)\.)?
1876 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1877 videoweed\.(?:es|com)|
1878 movshare\.(?:net|sx|ag)|
1879 divxstage\.(?:eu|net|ch|co|at|ag))
1880 /embed\.php.+?)\1''', webpage)
1881 if mobj is not None:
1882 return self.url_result(mobj.group('url'))
1884 # Look for embedded Facebook player
1885 facebook_url = FacebookIE._extract_url(webpage)
1886 if facebook_url is not None:
1887 return self.url_result(facebook_url, 'Facebook')
1889 # Look for embedded VK player
1890 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1891 if mobj is not None:
1892 return self.url_result(mobj.group('url'), 'VK')
1894 # Look for embedded Odnoklassniki player
1895 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1896 if mobj is not None:
1897 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1899 # Look for embedded ivi player
1900 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1901 if mobj is not None:
1902 return self.url_result(mobj.group('url'), 'Ivi')
1904 # Look for embedded Huffington Post player
1906 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1907 if mobj is not None:
1908 return self.url_result(mobj.group('url'), 'HuffPost')
1911 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1912 if mobj is not None:
1913 return self.url_result(mobj.group('url'))
1914 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1915 if mobj is not None:
1916 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1918 # Look for funnyordie embed
1919 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1921 return _playlist_from_matches(
1922 matches, getter=unescapeHTML, ie='FunnyOrDie')
1924 # Look for BBC iPlayer embed
1925 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1927 return _playlist_from_matches(matches, ie='BBCCoUk')
1929 # Look for embedded RUTV player
1930 rutv_url = RUTVIE._extract_url(webpage)
1932 return self.url_result(rutv_url, 'RUTV')
1934 # Look for embedded TVC player
1935 tvc_url = TVCIE._extract_url(webpage)
1937 return self.url_result(tvc_url, 'TVC')
1939 # Look for embedded SportBox player
1940 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1942 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1944 # Look for embedded PornHub player
1945 pornhub_url = PornHubIE._extract_url(webpage)
1947 return self.url_result(pornhub_url, 'PornHub')
1949 # Look for embedded XHamster player
1950 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1952 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1954 # Look for embedded TNAFlixNetwork player
1955 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1957 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1959 # Look for embedded Tvigle player
1961 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1962 if mobj is not None:
1963 return self.url_result(mobj.group('url'), 'Tvigle')
1965 # Look for embedded TED player
1967 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1968 if mobj is not None:
1969 return self.url_result(mobj.group('url'), 'TED')
1971 # Look for embedded Ustream videos
1973 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1974 if mobj is not None:
1975 return self.url_result(mobj.group('url'), 'Ustream')
1977 # Look for embedded arte.tv player
1979 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1981 if mobj is not None:
1982 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1984 # Look for embedded francetv player
1986 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1988 if mobj is not None:
1989 return self.url_result(mobj.group('url'))
1991 # Look for embedded smotri.com player
1992 smotri_url = SmotriIE._extract_url(webpage)
1994 return self.url_result(smotri_url, 'Smotri')
1996 # Look for embedded Myvi.ru player
1997 myvi_url = MyviIE._extract_url(webpage)
1999 return self.url_result(myvi_url)
2001 # Look for embedded soundcloud player
2003 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
2005 if mobj is not None:
2006 url = unescapeHTML(mobj.group('url'))
2007 return self.url_result(url)
2009 # Look for embedded mtvservices player
2010 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2012 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2014 # Look for embedded yahoo player
2016 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2018 if mobj is not None:
2019 return self.url_result(mobj.group('url'), 'Yahoo')
2021 # Look for embedded sbs.com.au player
2025 <meta\s+property="og:video"\s+content=|
2028 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2030 if mobj is not None:
2031 return self.url_result(mobj.group('url'), 'SBS')
2033 # Look for embedded Cinchcast player
2035 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2037 if mobj is not None:
2038 return self.url_result(mobj.group('url'), 'Cinchcast')
2041 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2045 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2047 if mobj is not None:
2048 return self.url_result(mobj.group('url'), 'MLB')
2051 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2053 if mobj is not None:
2054 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2057 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2059 if mobj is not None:
2060 return self.url_result(mobj.group('url'), 'Livestream')
2062 # Look for Zapiks embed
2064 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2065 if mobj is not None:
2066 return self.url_result(mobj.group('url'), 'Zapiks')
2068 # Look for Kaltura embeds
2069 kaltura_url = KalturaIE._extract_url(webpage)
2071 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2073 # Look for Eagle.Platform embeds
2074 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2075 if eagleplatform_url:
2076 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2078 # Look for ClipYou (uses Eagle.Platform) embeds
2080 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2081 if mobj is not None:
2082 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2084 # Look for Pladform embeds
2085 pladform_url = PladformIE._extract_url(webpage)
2087 return self.url_result(pladform_url)
2089 # Look for Videomore embeds
2090 videomore_url = VideomoreIE._extract_url(webpage)
2092 return self.url_result(videomore_url)
2094 # Look for Playwire embeds
2096 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2097 if mobj is not None:
2098 return self.url_result(mobj.group('url'))
2100 # Look for 5min embeds
2102 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2103 if mobj is not None:
2104 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2106 # Look for Crooks and Liars embeds
2108 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2109 if mobj is not None:
2110 return self.url_result(mobj.group('url'))
2112 # Look for NBC Sports VPlayer embeds
2113 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2115 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2117 # Look for NBC News embeds
2118 nbc_news_embed_url = re.search(
2119 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2120 if nbc_news_embed_url:
2121 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2123 # Look for Google Drive embeds
2124 google_drive_url = GoogleDriveIE._extract_url(webpage)
2125 if google_drive_url:
2126 return self.url_result(google_drive_url, 'GoogleDrive')
2128 # Look for UDN embeds
2130 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2131 if mobj is not None:
2132 return self.url_result(
2133 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2135 # Look for Senate ISVP iframe
2136 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2138 return self.url_result(senate_isvp_url, 'SenateISVP')
2140 # Look for Dailymotion Cloud videos
2141 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2143 return self.url_result(dmcloud_url, 'DailymotionCloud')
2145 # Look for OnionStudios embeds
2146 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2147 if onionstudios_url:
2148 return self.url_result(onionstudios_url)
2150 # Look for ViewLift embeds
2151 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2153 return self.url_result(viewlift_url)
2155 # Look for JWPlatform embeds
2156 jwplatform_url = JWPlatformIE._extract_url(webpage)
2158 return self.url_result(jwplatform_url, 'JWPlatform')
2160 # Look for ScreenwaveMedia embeds
2161 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2162 if mobj is not None:
2163 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2165 # Look for Digiteka embeds
2166 digiteka_url = DigitekaIE._extract_url(webpage)
2168 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2170 # Look for Arkena embeds
2171 arkena_url = ArkenaIE._extract_url(webpage)
2173 return self.url_result(arkena_url, ArkenaIE.ie_key())
2175 # Look for Limelight embeds
2176 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2180 'Channel': 'channel',
2181 'ChannelList': 'channel_list',
2183 return self.url_result('limelight:%s:%s' % (
2184 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2186 # Look for AdobeTVVideo embeds
2188 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2190 if mobj is not None:
2191 return self.url_result(
2192 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2195 # Look for Vine embeds
2197 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2199 if mobj is not None:
2200 return self.url_result(
2201 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2203 # Look for Instagram embeds
2204 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2205 if instagram_embed_url is not None:
2206 return self.url_result(
2207 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2209 # Look for LiveLeak embeds
2210 liveleak_url = LiveLeakIE._extract_url(webpage)
2212 return self.url_result(liveleak_url, 'LiveLeak')
2214 # Look for 3Q SDN embeds
2215 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2218 '_type': 'url_transparent',
2219 'ie_key': ThreeQSDNIE.ie_key(),
2220 'url': self._proto_relative_url(threeqsdn_url),
2221 'title': video_title,
2222 'description': video_description,
2223 'thumbnail': video_thumbnail,
2224 'uploader': video_uploader,
2227 # Looking for http://schema.org/VideoObject
2228 json_ld = self._search_json_ld(
2229 webpage, video_id, default=None, expected_type='VideoObject')
2230 if json_ld and json_ld.get('url'):
2232 'title': video_title or info_dict['title'],
2233 'description': video_description,
2234 'thumbnail': video_thumbnail,
2235 'age_limit': age_limit
2237 info_dict.update(json_ld)
2240 def check_video(vurl):
2241 if YoutubeIE.suitable(vurl):
2243 vpath = compat_urlparse.urlparse(vurl).path
2244 vext = determine_ext(vpath)
2245 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2247 def filter_video(urls):
2248 return list(filter(check_video, urls))
2250 # Start with something easy: JW Player in SWFObject
2251 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2253 # Look for gorilla-vid style embedding
2254 found = filter_video(re.findall(r'''(?sx)
2258 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2261 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2263 # Broaden the search a little bit
2264 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2266 # Broaden the findall a little bit: JWPlayer JS loader
2267 found = filter_video(re.findall(
2268 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2271 found = filter_video(re.findall(r'''(?xs)
2272 flowplayer\("[^"]+",\s*
2274 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2275 ["']?url["']?\s*:\s*["']([^"']+)["']
2280 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2282 # Try to find twitter cards info
2283 # twitter:player:stream should be checked before twitter:player since
2284 # it is expected to contain a raw stream (see
2285 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2286 found = filter_video(re.findall(
2287 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2289 # We look for Open Graph info:
2290 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2291 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2292 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2293 if m_video_type is not None:
2294 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2297 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2299 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2301 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2302 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2305 # Look also in Refresh HTTP header
2306 refresh_header = head_response.headers.get('Refresh')
2308 # In python 2 response HTTP headers are bytestrings
2309 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2310 refresh_header = refresh_header.decode('iso-8859-1')
2311 found = re.search(REDIRECT_REGEX, refresh_header)
2313 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2314 self.report_following_redirect(new_url)
2321 # twitter:player is a https URL to iframe player that may or may not
2322 # be supported by youtube-dl thus this is checked the very last (see
2323 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2324 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2326 return self.url_result(embed_url)
2329 raise UnsupportedError(url)
2332 for video_url in orderedSet(found):
2333 video_url = unescapeHTML(video_url)
2334 video_url = video_url.replace('\\/', '/')
2335 video_url = compat_urlparse.urljoin(url, video_url)
2336 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2338 # Sometimes, jwplayer extraction will result in a YouTube URL
2339 if YoutubeIE.suitable(video_url):
2340 entries.append(self.url_result(video_url, 'Youtube'))
2343 # here's a fun little line of code for you:
2344 video_id = os.path.splitext(video_id)[0]
2348 'uploader': video_uploader,
2349 'title': video_title,
2350 'age_limit': age_limit,
2353 ext = determine_ext(video_url)
2355 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2357 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2359 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2361 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2363 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2365 entry_info_dict['url'] = video_url
2367 if entry_info_dict.get('formats'):
2368 self._sort_formats(entry_info_dict['formats'])
2370 entries.append(entry_info_dict)
2372 if len(entries) == 1:
2375 for num, e in enumerate(entries, start=1):
2376 # 'url' results don't have a title
2377 if e.get('title') is not None:
2378 e['title'] = '%s (%d)' % (e['title'], num)
2380 '_type': 'playlist',