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
64 from .threeqsdn
import ThreeQSDNIE
65 from .theplatform
import ThePlatformIE
68 class GenericIE(InfoExtractor
):
69 IE_DESC
= 'Generic downloader that works on some sites'
73 # Direct link to a video
75 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
76 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
81 'upload_date': '20100513',
84 # Direct link to media delivered compressed (until Accept-Encoding is *)
86 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
87 'md5': '128c42e68b13950268b648275386fc74',
89 'id': 'FictionJunction-Parallel_Hearts',
91 'title': 'FictionJunction-Parallel_Hearts',
92 'upload_date': '20140522',
94 'expected_warnings': [
95 'URL could be a direct video link, returning it as such.'
98 # Direct download with broken HEAD
100 'url': 'http://ai-radio.org:8000/radio.opus',
107 'skip_download': True, # infinite live stream
109 'expected_warnings': [
110 r
'501.*Not Implemented',
114 # Direct link with incorrect MIME type
116 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
117 'md5': '4ccbebe5f36706d85221f204d7eb5913',
119 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
120 'id': '5_Lennart_Poettering_-_Systemd',
122 'title': '5_Lennart_Poettering_-_Systemd',
123 'upload_date': '20141120',
125 'expected_warnings': [
126 'URL could be a direct video link, returning it as such.'
131 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
133 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
134 'title': 'Zero Punctuation',
135 'description': 're:.*groundbreaking video review series.*'
137 'playlist_mincount': 11,
139 # RSS feed with enclosure
141 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
143 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
145 'upload_date': '20150228',
146 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
149 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
151 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
155 'title': 'Automatics, robotics and biocybernetics',
156 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
157 'upload_date': '20130627',
158 'formats': 'mincount:16',
159 'subtitles': 'mincount:1',
162 'force_generic_extractor': True,
163 'skip_download': True,
166 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
168 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
173 'formats': 'mincount:1',
176 'skip_download': True,
179 # SMIL from https://www.restudy.dk/video/play/id/1637
181 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
185 'title': 'video_1637',
186 'formats': 'mincount:3',
189 'skip_download': True,
192 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
194 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
196 'id': 'smil-service',
198 'title': 'smil-service',
199 'formats': 'mincount:1',
202 'skip_download': True,
205 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
207 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
211 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
212 'formats': 'mincount:3',
215 'skip_download': True,
218 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
220 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
222 'id': 'mZlp2ctYIUEB',
224 'title': 'Tikibad ontruimd wegens brand',
225 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
226 'thumbnail': 're:^https?://.*\.jpg$',
230 'skip_download': True,
233 # MPD from http://dash-mse-test.appspot.com/media.html
235 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
236 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
238 'id': 'car-20120827-manifest',
240 'title': 'car-20120827-manifest',
241 'formats': 'mincount:9',
242 'upload_date': '20130904',
245 'format': 'bestvideo',
248 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
250 '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',
255 'formats': 'mincount:8',
259 'skip_download': True,
262 # m3u8 served with Content-Type: text/plain
264 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
269 'upload_date': '20140720',
270 'formats': 'mincount:11',
274 'skip_download': True,
279 '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',
283 'upload_date': '20130224',
284 'uploader_id': 'TheVerge',
285 'description': 're:^Chris Ziegler takes a look at the\.*',
286 'uploader': 'The Verge',
287 'title': 'First Firefox OS phones side-by-side',
290 'skip_download': False,
294 # redirect in Refresh HTTP header
295 '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',
299 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
300 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
301 'upload_date': '20150917',
302 'uploader_id': 'brtvofficial',
303 'uploader': 'Boiler Room',
306 'skip_download': False,
310 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
311 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
313 'id': '13601338388002',
315 'uploader': 'www.hodiho.fr',
316 'title': 'R\u00e9gis plante sa Jeep',
319 # bandcamp page with custom domain
321 'add_ie': ['Bandcamp'],
322 'url': 'http://bronyrock.com/track/the-pony-mash',
326 'title': 'The Pony Mash',
327 'uploader': 'M_Pallante',
329 'skip': 'There is a limit of 200 free downloads / month for the test song',
331 # embedded brightcove video
332 # it also tests brightcove videos that need to set the 'Referer' in the
335 'add_ie': ['BrightcoveLegacy'],
336 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
338 'id': '2765128793001',
340 'title': 'Le cours de bourse : l’analyse technique',
341 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
342 'uploader': 'BFM BUSINESS',
345 'skip_download': True,
349 # https://github.com/rg3/youtube-dl/issues/2253
350 'url': 'http://bcove.me/i6nfkrc3',
351 'md5': '0ba9446db037002366bab3b3eb30c88c',
353 'id': '3101154703001',
355 'title': 'Still no power',
356 'uploader': 'thestar.com',
357 '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.',
359 'add_ie': ['BrightcoveLegacy'],
362 'url': 'http://www.championat.com/video/football/v/87/87499.html',
363 'md5': 'fb973ecf6e4a78a67453647444222983',
365 'id': '3414141473001',
367 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
368 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
369 'uploader': 'Championat',
373 # https://github.com/rg3/youtube-dl/issues/3541
374 'add_ie': ['BrightcoveLegacy'],
375 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
377 'id': '3866516442001',
379 'title': 'Leer mij vrouwen kennen: Aflevering 1',
380 'description': 'Leer mij vrouwen kennen: Aflevering 1',
381 'uploader': 'SBS Broadcasting',
383 'skip': 'Restricted to Netherlands',
385 'skip_download': True, # m3u8 download
390 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
391 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
393 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
395 'title': '2cc213299525360.mov', # that's what we get
398 'add_ie': ['Ooyala'],
401 # ooyala video embedded with http://player.ooyala.com/iframe.js
402 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
404 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
406 'title': '"Steve Jobs: Man in the Machine" trailer',
407 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
411 'skip_download': True,
416 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
420 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
421 'upload_date': '20140225',
422 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
423 'uploader': 'Tested',
424 'uploader_id': 'testedcom',
426 # No need to test YoutubeIE here
428 'skip_download': True,
433 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
437 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
438 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
443 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
447 'title': 'Охотское море стало целиком российским',
448 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
452 'skip_download': True,
457 '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/',
461 'title': 'Дошкольное воспитание',
466 'url': 'http://www.vestifinance.ru/articles/25753',
469 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
474 'title': 'Госзаказ. День 3',
480 'title': 'Госзаказ. День 2',
486 'title': 'Госзаказ. День 1',
492 'skip_download': True,
497 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
499 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
501 'title': 'Ужастики, русский трейлер (2015)',
502 'thumbnail': 're:^https?://.*\.jpg$',
508 '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',
511 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
513 'playlist_mincount': 7,
517 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
518 'md5': '65fdff94098e4a607385a60c5177c638',
522 'title': 'Hidden miracles of the natural world',
523 'uploader': 'Louie Schwartzberg',
524 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
527 # Embedded Ustream video
529 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
530 'md5': '27b99cdb639c9b12a79bca876a073417',
534 'uploader': 'AU SPA: The NSA and Privacy',
535 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
538 # nowvideo embed hidden behind percent encoding
540 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
541 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
543 'id': '06e53103ca9aa',
545 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
546 'description': 'No description',
551 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
552 'md5': '7653032cbb25bf6c80d80f217055fa43',
554 'id': '048195-004_PLUS7-F',
557 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
558 'upload_date': '20140320',
561 'skip_download': 'Requires rtmpdump'
566 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
570 'title': 'Alcaline, le concert avec Calogero',
571 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
572 'upload_date': '20150226',
573 'timestamp': 1424989860,
578 'skip_download': True,
580 'expected_warnings': [
586 'url': 'http://www.wired.com/2014/04/honda-asimo/',
587 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
589 'id': '53501be369702d3275860000',
591 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
596 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
597 'md5': '441aeeb82eb72c422c7f14ec533999cd',
599 'id': 'k2mm4bCdJ6CQ2i7c8o2',
601 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
602 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
604 'uploader_id': 'xgditw',
605 'upload_date': '20140425',
606 'timestamp': 1398441542,
608 'add_ie': ['Dailymotion'],
612 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
616 'title': 'The NBL Auction 2014',
617 'uploader': 'BADMINTON England',
618 'uploader_id': 'BADMINTONEvents',
619 'upload_date': '20140603',
620 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
622 'add_ie': ['Youtube'],
624 'skip_download': True,
629 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
630 'md5': '35727f82f58c76d996fc188f9755b0d5',
632 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
635 'description': 'Mario\'s life in the fast lane has never looked so good.',
638 # YouTube embed via <data-embed-url="">
640 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
644 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
645 'uploader': 'Gameloft',
646 'uploader_id': 'gameloft',
647 'upload_date': '20140828',
648 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
651 'skip_download': True,
656 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
658 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
660 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
661 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
666 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
668 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
669 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
675 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
680 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
681 'md5': '9d65602bf31c6e20014319c7d07fba27',
683 'id': '5123ea6d5e5a7',
686 'uploader': 'www.handjobhub.com',
687 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
690 # Multiple brightcove videos
691 # https://github.com/rg3/youtube-dl/issues/2283
693 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
695 'id': 'always-never',
696 'title': 'Always / Never - The New Yorker',
700 'extract_flat': False,
701 'skip_download': True,
706 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
707 'md5': '96f09a37e44da40dd083e12d9a683327',
711 'title': 'Ump changes call to ball',
712 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
714 'timestamp': 1401537900,
715 'upload_date': '20140531',
716 'thumbnail': 're:^https?://.*\.jpg$',
721 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
722 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
726 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
727 'description': 'a Paywall Videos video from Remilon',
729 'uploader': 'study.com',
730 'timestamp': 1459678540,
731 'upload_date': '20160403',
732 'filesize': 24687186,
736 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
737 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
741 'title': 'Conversation about Hexagonal Rails Part 1',
742 'description': 'a Martin Fowler video from ThoughtWorks',
744 'uploader': 'thoughtworks.wistia.com',
745 'timestamp': 1401832161,
746 'upload_date': '20140603',
749 # Wistia standard embed (async)
751 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
755 'title': 'Drip Brennan Dunn Workshop',
756 'description': 'a JV Webinars video from getdrip-1',
758 'timestamp': 1463607249,
759 'upload_date': '20160518',
762 'skip_download': True,
767 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
771 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
772 'uploader': 'Sophos Security',
773 'title': 'Chet Chat 171 - Oct 29, 2014',
774 'upload_date': '20141029',
779 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
783 'upload_date': '20141112',
784 'title': 'Rosetta #CometLanding webcast HL 10',
787 # Another Livestream embed, without 'new.' in URL
789 'url': 'https://www.freespeech.org/',
793 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
797 'skip_download': True,
802 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
805 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
807 'playlist_mincount': 2,
811 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
815 'upload_date': '20141126',
816 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
821 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
823 'id': '730m_DandD_1901_512k',
825 'uploader': 'www.abc.net.au',
826 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
829 # embedded viddler video
831 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
835 'uploader': 'deadspin',
836 'title': 'WALL-TO-GORTAT',
837 'timestamp': 1422285291,
838 'upload_date': '20150126',
840 'add_ie': ['Viddler'],
844 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
848 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
849 'description': 'md5:601cb790edd05908957dae8aaa866465',
850 'upload_date': '20150220',
855 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
859 'upload_date': '20150212',
860 'uploader': 'The National Archives UK',
861 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
862 'uploader_id': 'NationalArchives08',
863 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
868 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
869 'playlist_mincount': 5,
871 'id': 'aanslagen-kopenhagen',
872 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
877 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
881 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
886 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
890 'upload_date': '20150226',
891 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
893 'title': 'John Carlson Postgame 2/25/15',
896 # Kaltura embed (different embed code)
898 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
902 'upload_date': '20150127',
903 'uploader_id': 'PremierMedia',
905 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
908 # Kaltura embed protected with referrer
910 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
914 'title': 'Violetta - Achter De Schermen - Ruggero',
915 'description': 'Achter de schermen met Ruggero',
916 'timestamp': 1435133761,
917 'upload_date': '20150624',
918 'uploader_id': 'echojecka',
921 # Kaltura embed with single quotes
923 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
928 'timestamp': 1355743100,
929 'upload_date': '20121217',
930 'uploader_id': 'batchUser',
932 'add_ie': ['Kaltura'],
934 # Eagle.Platform embed (generic URL)
936 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
937 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
941 'title': 'Навальный вышел на свободу',
942 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
943 'thumbnail': 're:^https?://.*\.jpg$',
949 # ClipYou (Eagle.Platform) embed (custom URL)
951 'url': 'http://muz-tv.ru/play/7129/',
952 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
956 'title': "'O Sole Mio",
957 'thumbnail': 're:^https?://.*\.jpg$',
964 'url': 'http://muz-tv.ru/kinozal/view/7400/',
968 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
969 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
970 'thumbnail': 're:^https?://.*\.jpg$',
977 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
981 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
982 'thumbnail': 're:^https?://.*\.png$',
988 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
989 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
993 'title': 'Facebook Creates "On This Day" | Crunch Report',
998 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1002 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1007 # Crooks and Liars embed
1009 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1013 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1014 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1015 'timestamp': 1428207000,
1016 'upload_date': '20150405',
1017 'uploader': 'Heather',
1020 # Crooks and Liars external embed
1022 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1024 'id': 'MTE3MjUtMzQ2MzA',
1026 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1027 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1028 'timestamp': 1265032391,
1029 'upload_date': '20100201',
1030 'uploader': 'Heather',
1033 # NBC Sports vplayer embed
1035 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1037 'id': 'ln7x1qSThw4k',
1039 'title': "PFT Live: New leader in the 'new-look' defense",
1040 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1041 'uploader': 'NBCU-SPORTS',
1042 'upload_date': '20140107',
1043 'timestamp': 1389118457,
1048 'url': 'http://www.udn.com/news/story/7314/822787',
1049 'md5': 'fd2060e988c326991037b9aff9df21a6',
1053 'title': '中一中男師變性 全校師生力挺',
1054 'thumbnail': 're:^https?://.*\.jpg$',
1059 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1061 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1063 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1064 'title': 'This is what separates the Excel masters from the wannabes',
1065 'duration': 191.933,
1069 'skip_download': True,
1072 # Contains a SMIL manifest
1074 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
1078 'title': '+ Football: Lottery Champions League Europe',
1079 'uploader': 'www.telewebion.com',
1083 'skip_download': True,
1086 # Brightcove URL in single quotes
1088 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1089 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1091 'id': '4255764656001',
1093 'title': 'SN Presents: Russell Martin, World Citizen',
1094 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1095 'uploader': 'Rogers Sportsnet',
1096 'uploader_id': '1704050871',
1097 'upload_date': '20150525',
1098 'timestamp': 1432570283,
1101 # Dailymotion Cloud video
1103 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1104 'md5': '49444254273501a64675a7e68c502681',
1106 'id': '5585de919473990de4bee11b',
1108 'title': 'Le débat',
1109 'thumbnail': 're:^https?://.*\.jpe?g$',
1112 # OnionStudios embed
1114 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1118 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1119 'thumbnail': 're:^https?://.*\.jpe?g$',
1120 'uploader': 'ClickHole',
1121 'uploader_id': 'clickhole',
1126 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1128 'id': '74849a00-85a9-11e1-9660-123139220831',
1130 'title': '#whilewewatch',
1133 # AdobeTVVideo embed
1135 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1136 'md5': '43662b577c018ad707a63766462b1e87',
1140 'title': 'New experience with Acrobat DC',
1141 'description': 'New experience with Acrobat DC',
1142 'duration': 248.667,
1145 # ScreenwaveMedia embed
1147 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1148 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1150 'id': 'cinemasnob-55d26273809dd',
1152 'title': 'cinemasnob',
1155 # BrightcoveInPageEmbed embed
1157 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1159 'id': '4238694884001',
1161 'title': 'Tabletop: Dread, Last Thoughts',
1162 'description': 'Tabletop: Dread, Last Thoughts',
1166 # JWPlayer with M3U8
1168 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1172 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1173 'uploader': 'ren.tv',
1177 'skip_download': True,
1180 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1181 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1183 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1185 'id': '4785848093001',
1187 'title': 'The Cardinal Pell Interview',
1188 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1189 'uploader': 'GlobeCast Australia - GlobeStream',
1190 'uploader_id': '2733773828001',
1191 'upload_date': '20160304',
1192 'timestamp': 1457083087,
1196 'skip_download': True,
1199 # Another form of arte.tv embed
1201 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1202 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1204 'id': '030273-562_PLUS7-F',
1206 'title': 'ARTE Reportage - Nulle part, en France',
1207 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1208 'upload_date': '20160409',
1213 'url': 'http://www.wykop.pl/link/3088787/',
1214 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1216 'id': '874_1459135191',
1218 'title': 'Man shows poor quality of new apartment building',
1219 'description': 'The wall is like a sand pile.',
1220 'uploader': 'Lake8737',
1223 # Duplicated embedded video URLs
1225 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1227 'id': '149298443_480_16c25b74_2',
1229 'title': 'vs. Blue Orange Spring Game',
1230 'uploader': 'www.hudl.com',
1235 def report_following_redirect(self
, new_url
):
1236 """Report information extraction."""
1237 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
1239 def _extract_rss(self
, url
, video_id
, doc
):
1240 playlist_title
= doc
.find('./channel/title').text
1241 playlist_desc_el
= doc
.find('./channel/description')
1242 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
1245 for it
in doc
.findall('./channel/item'):
1246 next_url
= xpath_text(it
, 'link', fatal
=False)
1248 enclosure_nodes
= it
.findall('./enclosure')
1249 for e
in enclosure_nodes
:
1250 next_url
= e
.attrib
.get('url')
1260 'title': it
.find('title').text
,
1264 '_type': 'playlist',
1266 'title': playlist_title
,
1267 'description': playlist_desc
,
1271 def _extract_camtasia(self
, url
, video_id
, webpage
):
1272 """ Returns None if no camtasia video can be found. """
1274 camtasia_cfg
= self
._search
_regex
(
1275 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1276 webpage
, 'camtasia configuration file', default
=None)
1277 if camtasia_cfg
is None:
1280 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
1282 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
1283 camtasia_cfg
= self
._download
_xml
(
1284 camtasia_url
, video_id
,
1285 note
='Downloading camtasia configuration',
1286 errnote
='Failed to download camtasia configuration')
1287 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
1290 for n
in fileset_node
.getchildren():
1291 url_n
= n
.find('./uri')
1296 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
1297 'title': '%s - %s' % (title
, n
.tag
),
1298 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
1299 'duration': float_or_none(n
.find('./duration').text
),
1303 '_type': 'playlist',
1308 def _real_extract(self
, url
):
1309 if url
.startswith('//'):
1312 'url': self
.http_scheme() + url
,
1315 parsed_url
= compat_urlparse
.urlparse(url
)
1316 if not parsed_url
.scheme
:
1317 default_search
= self
._downloader
.params
.get('default_search')
1318 if default_search
is None:
1319 default_search
= 'fixup_error'
1321 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
1323 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
1324 return self
.url_result('http://' + url
)
1325 elif default_search
!= 'fixup_error':
1326 if default_search
== 'auto_warning':
1327 if re
.match(r
'^(?:url|URL)$', url
):
1328 raise ExtractorError(
1329 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
1332 self
._downloader
.report_warning(
1333 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
1334 return self
.url_result('ytsearch:' + url
)
1336 if default_search
in ('error', 'fixup_error'):
1337 raise ExtractorError(
1338 '%r is not a valid URL. '
1339 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1340 % (url
, url
), expected
=True)
1342 if ':' not in default_search
:
1343 default_search
+= ':'
1344 return self
.url_result(default_search
+ url
)
1346 url
, smuggled_data
= unsmuggle_url(url
)
1347 force_videoid
= None
1348 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
1349 if smuggled_data
and 'force_videoid' in smuggled_data
:
1350 force_videoid
= smuggled_data
['force_videoid']
1351 video_id
= force_videoid
1353 video_id
= compat_urllib_parse_unquote(os
.path
.splitext(url
.rstrip('/').split('/')[-1])[0])
1355 self
.to_screen('%s: Requesting header' % video_id
)
1357 head_req
= HEADRequest(url
)
1358 head_response
= self
._request
_webpage
(
1360 note
=False, errnote
='Could not send HEAD request to %s' % url
,
1363 if head_response
is not False:
1364 # Check for redirect
1365 new_url
= head_response
.geturl()
1367 self
.report_following_redirect(new_url
)
1369 new_url
= smuggle_url(
1370 new_url
, {'force_videoid': force_videoid}
)
1371 return self
.url_result(new_url
)
1373 full_response
= None
1374 if head_response
is False:
1375 request
= sanitized_Request(url
)
1376 request
.add_header('Accept-Encoding', '*')
1377 full_response
= self
._request
_webpage
(request
, video_id
)
1378 head_response
= full_response
1382 'title': compat_urllib_parse_unquote(os
.path
.splitext(url_basename(url
))[0]),
1383 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
1386 # Check for direct link to a video
1387 content_type
= head_response
.headers
.get('Content-Type', '').lower()
1388 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
1390 format_id
= m
.group('format_id')
1391 if format_id
.endswith('mpegurl'):
1392 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1393 elif format_id
== 'f4m':
1394 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
1397 'format_id': m
.group('format_id'),
1399 'vcodec': 'none' if m
.group('type') == 'audio' else None
1401 info_dict
['direct'] = True
1402 self
._sort
_formats
(formats
)
1403 info_dict
['formats'] = formats
1406 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
1407 force
= self
._downloader
.params
.get('force_generic_extractor', False)
1408 self
._downloader
.report_warning(
1409 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
1411 if not full_response
:
1412 request
= sanitized_Request(url
)
1413 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1414 # making it impossible to download only chunk of the file (yet we need only 512kB to
1415 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1416 # that will always result in downloading the whole file that is not desirable.
1417 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1418 # to accept raw bytes and being able to download only a chunk.
1419 # It may probably better to solve this by checking Content-Type for application/octet-stream
1420 # after HEAD request finishes, but not sure if we can rely on this.
1421 request
.add_header('Accept-Encoding', '*')
1422 full_response
= self
._request
_webpage
(request
, video_id
)
1424 first_bytes
= full_response
.read(512)
1426 # Is it an M3U playlist?
1427 if first_bytes
.startswith(b
'#EXTM3U'):
1428 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1429 self
._sort
_formats
(info_dict
['formats'])
1432 # Maybe it's a direct link to a video?
1433 # Be careful not to download the whole thing!
1434 if not is_html(first_bytes
):
1435 self
._downloader
.report_warning(
1436 'URL could be a direct video link, returning it as such.')
1443 webpage
= self
._webpage
_read
_content
(
1444 full_response
, url
, video_id
, prefix
=first_bytes
)
1446 self
.report_extraction(video_id
)
1448 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1450 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
1451 if doc
.tag
== 'rss':
1452 return self
._extract
_rss
(url
, video_id
, doc
)
1453 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
1454 smil
= self
._parse
_smil
(doc
, url
, video_id
)
1455 self
._sort
_formats
(smil
['formats'])
1457 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
1458 return self
.playlist_result(self
._parse
_xspf
(doc
, video_id
), video_id
)
1459 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
1460 info_dict
['formats'] = self
._parse
_mpd
_formats
(
1461 doc
, video_id
, mpd_base_url
=url
.rpartition('/')[0])
1462 self
._sort
_formats
(info_dict
['formats'])
1464 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
1465 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
1466 self
._sort
_formats
(info_dict
['formats'])
1468 except compat_xml_parse_error
:
1471 # Is it a Camtasia project?
1472 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
1473 if camtasia_res
is not None:
1476 # Sometimes embedded video player is hidden behind percent encoding
1477 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1478 # Unescaping the whole page allows to handle those cases in a generic way
1479 webpage
= compat_urllib_parse_unquote(webpage
)
1481 # it's tempting to parse this further, but you would
1482 # have to take into account all the variations like
1483 # Video Title - Site Name
1484 # Site Name | Video Title
1485 # Video Title - Tagline | Site Name
1486 # and so on and so forth; it's just not practical
1487 video_title
= self
._og
_search
_title
(
1488 webpage
, default
=None) or self
._html
_search
_regex
(
1489 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
1492 # Try to detect age limit automatically
1493 age_limit
= self
._rta
_search
(webpage
)
1494 # And then there are the jokers who advertise that they use RTA,
1495 # but actually don't.
1496 AGE_LIMIT_MARKERS
= [
1497 r
'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1499 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
1502 # video uploader is domain name
1503 video_uploader
= self
._search
_regex
(
1504 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
1506 video_description
= self
._og
_search
_description
(webpage
, default
=None)
1507 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
1510 def _playlist_from_matches(matches
, getter
=None, ie
=None):
1512 self
.url_result(self
._proto
_relative
_url
(getter(m
) if getter
else m
), ie
)
1514 return self
.playlist_result(
1515 urlrs
, playlist_id
=video_id
, playlist_title
=video_title
)
1517 # Look for Brightcove Legacy Studio embeds
1518 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
1520 self
.to_screen('Brightcove video detected.')
1523 'url': smuggle_url(bc_url
, {'Referer': url}
),
1524 'ie_key': 'BrightcoveLegacy'
1525 } for bc_url
in bc_urls
]
1528 '_type': 'playlist',
1529 'title': video_title
,
1534 # Look for Brightcove New Studio embeds
1535 bc_urls
= BrightcoveNewIE
._extract
_urls
(webpage
)
1537 return _playlist_from_matches(bc_urls
, ie
='BrightcoveNew')
1539 # Look for ThePlatform embeds
1540 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
1542 return _playlist_from_matches(tp_urls
, ie
='ThePlatform')
1544 # Look for embedded rtl.nl player
1545 matches
= re
.findall(
1546 r
'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1549 return _playlist_from_matches(matches
, ie
='RtlNl')
1551 vimeo_url
= VimeoIE
._extract
_vimeo
_url
(url
, webpage
)
1552 if vimeo_url
is not None:
1553 return self
.url_result(vimeo_url
)
1555 vid_me_embed_url
= self
._search
_regex
(
1556 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1557 webpage, 'vid.me embed', default=None)
1558 if vid_me_embed_url is not None:
1559 return self.url_result(vid_me_embed_url, 'Vidme')
1561 # Look for embedded YouTube player
1562 matches = re.findall(r'''(?x)
1571 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1575 return _playlist_from_matches(
1576 matches, lambda m: unescapeHTML(m[1]))
1578 # Look for lazyYT YouTube embed
1579 matches = re.findall(
1580 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1582 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1584 # Look for embedded Dailymotion player
1585 matches = re.findall(
1586 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1588 return _playlist_from_matches(
1589 matches, lambda m: unescapeHTML(m[1]))
1591 # Look for embedded Dailymotion playlist player (#3822)
1593 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1595 playlists = re.findall(
1596 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1598 return _playlist_from_matches(
1599 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1601 # Look for embedded Wistia player
1603 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1605 embed_url = self._proto_relative_url(
1606 unescapeHTML(match.group('url')))
1608 '_type': 'url_transparent',
1611 'uploader': video_uploader,
1614 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1617 '_type': 'url_transparent',
1618 'url': 'wistia:%s' % match.group('id'),
1620 'uploader': video_uploader,
1625 <script
[^
>]+src
=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1626 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1629 return self.url_result(self._proto_relative_url(
1630 'wistia
:%s' % match.group('id')), 'Wistia
')
1632 # Look for SVT player
1633 svt_url = SVTIE._extract_url(webpage)
1635 return self.url_result(svt_url, 'SVT
')
1637 # Look for embedded condenast player
1638 matches = re.findall(
1639 r'<iframe\s
+(?
:[a
-zA
-Z
-]+="[^"]+"\s+)*?src="(https?
://player\
.cnevids\
.com
/embed
/[^
"]+")',
1643 '_type
': 'playlist
',
1646 'ie_key
': 'CondeNast
',
1648 } for ma in matches],
1649 'title
': video_title,
1653 # Look for Bandcamp pages with custom domain
1654 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
1655 if mobj is not None:
1656 burl = unescapeHTML(mobj.group(1))
1657 # Don't
set the extractor because it can be a track url
or an album
1658 return self
.url_result(burl
)
1660 # Look for embedded Vevo player
1662 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
1663 if mobj is not None:
1664 return self.url_result(mobj.group('url
'))
1666 # Look for embedded Viddler player
1668 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1670 if mobj is not None:
1671 return self.url_result(mobj.group('url'))
1673 # Look for NYTimes player
1675 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
1677 if mobj is not None:
1678 return self.url_result(mobj.group('url
'))
1680 # Look for Libsyn player
1682 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'))
1686 # Look for Ooyala videos
1687 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1688 re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage) or
1689 re.search(r'SBN\
.VideoLinkset\
.ooyala\
([\'"](?P<ec>.{32})[\'"]\
)', webpage) or
1690 re.search(r'data
-ooyala
-video
-id\s
*=\s
*[\'"](?P<ec>.{32})[\'"]', webpage))
1691 if mobj is not None:
1692 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec
'), {'domain': url}))
1694 # Look for multiple Ooyala embeds on SBN network websites
1695 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
1696 if mobj is not None:
1697 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1699 return _playlist_from_matches(
1700 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
1702 # Look for Aparat videos
1703 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1704 if mobj is not None:
1705 return self.url_result(mobj.group(1), 'Aparat')
1707 # Look for MPORA videos
1708 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
1709 if mobj is not None:
1710 return self.url_result(mobj.group(1), 'Mpora
')
1712 # Look for embedded NovaMov-based player
1714 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1715 (?P<url>http://(?:(?:embed|www)\.)?
1717 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1718 videoweed\.(?:es|com)|
1719 movshare\.(?:net|sx|ag)|
1720 divxstage\.(?:eu|net|ch|co|at|ag))
1721 /embed\.php.+?)\1''', webpage)
1722 if mobj is not None:
1723 return self.url_result(mobj.group('url
'))
1725 # Look for embedded Facebook player
1727 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1728 if mobj is not None:
1729 return self.url_result(mobj.group('url'), 'Facebook')
1731 # Look for embedded VK player
1732 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://vk\
.com
/video_ext\
.php
.+?
)\
1', webpage)
1733 if mobj is not None:
1734 return self.url_result(mobj.group('url
'), 'VK
')
1736 # Look for embedded Odnoklassniki player
1737 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1738 if mobj is not None:
1739 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1741 # Look for embedded ivi player
1742 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
1743 if mobj is not None:
1744 return self.url_result(mobj.group('url
'), 'Ivi
')
1746 # Look for embedded Huffington Post player
1748 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1749 if mobj is not None:
1750 return self.url_result(mobj.group('url'), 'HuffPost')
1753 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
1754 if mobj is not None:
1755 return self.url_result(mobj.group('url'))
1756 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
1757 if mobj is not None:
1758 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1760 # Look for funnyordie embed
1761 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
1763 return _playlist_from_matches(
1764 matches, getter=unescapeHTML, ie='FunnyOrDie
')
1766 # Look for BBC iPlayer embed
1767 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
1769 return _playlist_from_matches(matches, ie='BBCCoUk
')
1771 # Look for embedded RUTV player
1772 rutv_url = RUTVIE._extract_url(webpage)
1774 return self.url_result(rutv_url, 'RUTV
')
1776 # Look for embedded TVC player
1777 tvc_url = TVCIE._extract_url(webpage)
1779 return self.url_result(tvc_url, 'TVC
')
1781 # Look for embedded SportBox player
1782 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1784 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed
')
1786 # Look for embedded PornHub player
1787 pornhub_url = PornHubIE._extract_url(webpage)
1789 return self.url_result(pornhub_url, 'PornHub
')
1791 # Look for embedded XHamster player
1792 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1794 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed
')
1796 # Look for embedded TNAFlixNetwork player
1797 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1799 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1801 # Look for embedded Tvigle player
1803 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1804 if mobj is not None:
1805 return self.url_result(mobj.group('url'), 'Tvigle')
1807 # Look for embedded TED player
1809 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
1810 if mobj is not None:
1811 return self.url_result(mobj.group('url
'), 'TED
')
1813 # Look for embedded Ustream videos
1815 r'<iframe
[^
>]+?src
=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1816 if mobj is not None:
1817 return self.url_result(mobj.group('url'), 'Ustream')
1819 # Look for embedded arte.tv player
1821 r'<(?:script|iframe) [^>]*?src="(?P
<url
>http
://www\
.arte\
.tv
/(?
:playerv2
/embed|arte_vp
/index
)[^
"]+)"',
1823 if mobj is not None:
1824 return self.url_result(mobj.group('url
'), 'ArteTVEmbed
')
1826 # Look for embedded francetv player
1828 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1830 if mobj is not None:
1831 return self.url_result(mobj.group('url'))
1833 # Look for embedded smotri.com player
1834 smotri_url = SmotriIE._extract_url(webpage)
1836 return self.url_result(smotri_url, 'Smotri')
1838 # Look for embedded Myvi.ru player
1839 myvi_url = MyviIE._extract_url(webpage)
1841 return self.url_result(myvi_url)
1843 # Look for embedded soundcloud player
1845 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^
"]+"\s
+)*src
="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1847 if mobj is not None:
1848 url = unescapeHTML(mobj.group('url'))
1849 return self.url_result(url)
1851 # Look for embedded vulture.com player
1853 r'<iframe src="(?P
<url
>https?
://video\
.vulture\
.com
/[^
"]+)"',
1855 if mobj is not None:
1856 url = unescapeHTML(mobj.group('url
'))
1857 return self.url_result(url, ie='Vulture
')
1859 # Look for embedded mtvservices player
1860 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1862 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded
')
1864 # Look for embedded yahoo player
1866 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1868 if mobj is not None:
1869 return self.url_result(mobj.group('url'), 'Yahoo')
1871 # Look for embedded sbs.com.au player
1875 <meta\s+property="og
:video
"\s+content=|
1878 (["\'])(?P
<url
>https?
://(?
:www\
.)?sbs\
.com\
.au
/ondemand
/video
/.+?
)\
1''',
1880 if mobj is not None:
1881 return self.url_result(mobj.group('url'), 'SBS')
1883 # Look for embedded Cinchcast player
1885 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1887 if mobj is not None:
1888 return self.url_result(mobj.group('url'), 'Cinchcast')
1891 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1895 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1897 if mobj is not None:
1898 return self.url_result(mobj.group('url'), 'MLB')
1901 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1903 if mobj is not None:
1904 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1907 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1909 if mobj is not None:
1910 return self.url_result(mobj.group('url'), 'Livestream')
1912 # Look for Zapiks embed
1914 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1915 if mobj is not None:
1916 return self.url_result(mobj.group('url'), 'Zapiks')
1918 # Look for Kaltura embeds
1919 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?(?P<q1>['\"])wid(?P=q1)\s*:\s*(?P<q2>['\"])_?(?P<partner_id>[^'\"]+)(?P=q2),.*?(?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*(?P<q4>['\"])(?P<id>[^'\"]+)(?P=q4),", webpage) or
1920 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))
1921 if mobj is not None:
1922 return self.url_result(smuggle_url(
1923 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1924 {'source_url': url}), 'Kaltura')
1926 # Look for Eagle.Platform embeds
1928 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1929 if mobj is not None:
1930 return self.url_result(mobj.group('url'), 'EaglePlatform')
1932 # Look for ClipYou (uses Eagle.Platform) embeds
1934 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1935 if mobj is not None:
1936 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1938 # Look for Pladform embeds
1939 pladform_url = PladformIE._extract_url(webpage)
1941 return self.url_result(pladform_url)
1943 # Look for Videomore embeds
1944 videomore_url = VideomoreIE._extract_url(webpage)
1946 return self.url_result(videomore_url)
1948 # Look for Playwire embeds
1950 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1951 if mobj is not None:
1952 return self.url_result(mobj.group('url'))
1954 # Look for 5min embeds
1956 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1957 if mobj is not None:
1958 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1960 # Look for Crooks and Liars embeds
1962 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1963 if mobj is not None:
1964 return self.url_result(mobj.group('url'))
1966 # Look for NBC Sports VPlayer embeds
1967 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1969 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1971 # Look for Google Drive embeds
1972 google_drive_url = GoogleDriveIE._extract_url(webpage)
1973 if google_drive_url:
1974 return self.url_result(google_drive_url, 'GoogleDrive')
1976 # Look for UDN embeds
1978 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1979 if mobj is not None:
1980 return self.url_result(
1981 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1983 # Look for Senate ISVP iframe
1984 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1986 return self.url_result(senate_isvp_url, 'SenateISVP')
1988 # Look for Dailymotion Cloud videos
1989 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1991 return self.url_result(dmcloud_url, 'DailymotionCloud')
1993 # Look for OnionStudios embeds
1994 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1995 if onionstudios_url:
1996 return self.url_result(onionstudios_url)
1998 # Look for ViewLift embeds
1999 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2001 return self.url_result(viewlift_url)
2003 # Look for JWPlatform embeds
2004 jwplatform_url = JWPlatformIE._extract_url(webpage)
2006 return self.url_result(jwplatform_url, 'JWPlatform')
2008 # Look for ScreenwaveMedia embeds
2009 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2010 if mobj is not None:
2011 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2013 # Look for Digiteka embeds
2014 digiteka_url = DigitekaIE._extract_url(webpage)
2016 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2018 # Look for Limelight embeds
2019 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2023 'Channel': 'channel',
2024 'ChannelList': 'channel_list',
2026 return self.url_result('limelight:%s:%s' % (
2027 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2029 # Look for AdobeTVVideo embeds
2031 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2033 if mobj is not None:
2034 return self.url_result(
2035 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2038 # Look for Vine embeds
2040 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2042 if mobj is not None:
2043 return self.url_result(
2044 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2046 # Look for Instagram embeds
2047 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2048 if instagram_embed_url is not None:
2049 return self.url_result(
2050 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2052 # Look for LiveLeak embeds
2053 liveleak_url = LiveLeakIE._extract_url(webpage)
2055 return self.url_result(liveleak_url, 'LiveLeak')
2057 # Look for 3Q SDN embeds
2058 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2061 '_type': 'url_transparent',
2062 'ie_key': ThreeQSDNIE.ie_key(),
2063 'url': self._proto_relative_url(threeqsdn_url),
2064 'title': video_title,
2065 'description': video_description,
2066 'thumbnail': video_thumbnail,
2067 'uploader': video_uploader,
2070 def check_video(vurl):
2071 if YoutubeIE.suitable(vurl):
2073 vpath = compat_urlparse.urlparse(vurl).path
2074 vext = determine_ext(vpath)
2075 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2077 def filter_video(urls):
2078 return list(filter(check_video, urls))
2080 # Start with something easy: JW Player in SWFObject
2081 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2083 # Look for gorilla-vid style embedding
2084 found = filter_video(re.findall(r'''(?sx
)
2088 jwplayer\s
*\
(\s
*["'][^'"]+["']\s*\)\s*\.setup
2091 ['"]?
file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2093 # Broaden the search a little bit
2094 found = filter_video(re.findall(r'[^A
-Za
-z0
-9]?
(?
:file|source
)=(http
[^
\'"&]*)', webpage))
2096 # Broaden the findall a little bit: JWPlayer JS loader
2097 found = filter_video(re.findall(
2098 r'[^A-Za-z0-9]?(?:file|video_url)["\']?
:\s
*["\'](http(?![^\'"]+\
.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2101 found = filter_video(re.findall(r'''(?xs)
2102 flowplayer\("[^
"]+",\s
*
2104 \s
*\{[^}
]+?
["']?clip["']?\s*:\s*\{\s*
2105 ["']?url
["']?\s*:\s*["']([^"']+)["']
2110 r"cinerama\
.embedPlayer\
(\s
*\'[^
']+\',\s*'([^
']+)'", webpage)
2112 # Try to find twitter cards info
2113 found = filter_video(re.findall(
2114 r'<meta (?:property|name)="twitter
:player
:stream
" (?:content|value)="(.+?
)"', webpage))
2116 # We look for Open Graph info:
2117 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2118 m_video_type = re.findall(r'<meta.*?property="og
:video
:type".*?content="video
/(.*?
)"', webpage)
2119 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2120 if m_video_type is not None:
2121 found = filter_video(re.findall(r'<meta.*?property="og
:video
".*?content="(.*?
)"', webpage))
2124 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?
)["\']', webpage)
2126 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2128 r'(?i
)<meta\s
+(?
=(?
:[a
-z
-]+="[^"]+"\s+)*http-equiv="refresh
")'
2129 r'(?:[a-z-]+="[^
"]+"\s
+)*?content
="%s' % REDIRECT_REGEX,
2132 # Look also in Refresh HTTP header
2133 refresh_header = head_response.headers.get('Refresh')
2135 # In python 2 response HTTP headers are bytestrings
2136 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2137 refresh_header = refresh_header.decode('iso-8859-1')
2138 found = re.search(REDIRECT_REGEX, refresh_header)
2140 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2141 self.report_following_redirect(new_url)
2147 raise UnsupportedError(url)
2150 for video_url in orderedSet(found):
2151 video_url = unescapeHTML(video_url)
2152 video_url = video_url.replace('\\/', '/')
2153 video_url = compat_urlparse.urljoin(url, video_url)
2154 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2156 # Sometimes, jwplayer extraction will result in a YouTube URL
2157 if YoutubeIE.suitable(video_url):
2158 entries.append(self.url_result(video_url, 'Youtube'))
2161 # here's a fun little line of code for you:
2162 video_id = os.path.splitext(video_id)[0]
2166 'uploader': video_uploader,
2167 'title': video_title,
2168 'age_limit': age_limit,
2171 ext = determine_ext(video_url)
2173 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2175 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2177 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2179 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2181 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2183 entry_info_dict['url'] = video_url
2185 if entry_info_dict.get('formats'):
2186 self._sort_formats(entry_info_dict['formats'])
2188 entries.append(entry_info_dict)
2190 if len(entries) == 1:
2193 for num, e in enumerate(entries, start=1):
2194 # 'url' results don't have a title
2195 if e.get('title') is not None:
2196 e['title'] = '%s (%d)' % (e['title'], num)
2198 '_type': 'playlist',