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,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .drtuber import DrTuberIE
51 from .redtube import RedTubeIE
52 from .vimeo import VimeoIE
53 from .dailymotion import (
57 from .onionstudios import OnionStudiosIE
58 from .viewlift import ViewLiftEmbedIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .webcaster import WebcasterFeedIE
63 from .googledrive import GoogleDriveIE
64 from .jwplatform import JWPlatformIE
65 from .digiteka import DigitekaIE
66 from .arkena import ArkenaIE
67 from .instagram import InstagramIE
68 from .liveleak import LiveLeakIE
69 from .threeqsdn import ThreeQSDNIE
70 from .theplatform import ThePlatformIE
71 from .vessel import VesselIE
72 from .kaltura import KalturaIE
73 from .eagleplatform import EaglePlatformIE
74 from .facebook import FacebookIE
75 from .soundcloud import SoundcloudIE
76 from .tunein import TuneInBaseIE
77 from .vbox7 import Vbox7IE
78 from .dbtv import DBTVIE
79 from .piksel import PikselIE
80 from .videa import VideaIE
81 from .twentymin import TwentyMinutenIE
82 from .ustream import UstreamIE
85 class GenericIE(InfoExtractor):
86 IE_DESC = 'Generic downloader that works on some sites'
90 # Direct link to a video
92 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
93 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
98 'upload_date': '20100513',
101 # Direct link to media delivered compressed (until Accept-Encoding is *)
103 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
104 'md5': '128c42e68b13950268b648275386fc74',
106 'id': 'FictionJunction-Parallel_Hearts',
108 'title': 'FictionJunction-Parallel_Hearts',
109 'upload_date': '20140522',
111 'expected_warnings': [
112 'URL could be a direct video link, returning it as such.'
114 'skip': 'URL invalid',
116 # Direct download with broken HEAD
118 'url': 'http://ai-radio.org:8000/radio.opus',
125 'skip_download': True, # infinite live stream
127 'expected_warnings': [
128 r'501.*Not Implemented',
132 # Direct link with incorrect MIME type
134 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
135 'md5': '4ccbebe5f36706d85221f204d7eb5913',
137 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
138 'id': '5_Lennart_Poettering_-_Systemd',
140 'title': '5_Lennart_Poettering_-_Systemd',
141 'upload_date': '20141120',
143 'expected_warnings': [
144 'URL could be a direct video link, returning it as such.'
149 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
151 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
152 'title': 'Zero Punctuation',
153 'description': 're:.*groundbreaking video review series.*'
155 'playlist_mincount': 11,
157 # RSS feed with enclosure
159 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
161 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
163 'upload_date': '20150228',
164 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
167 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
169 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
173 'title': 'Automatics, robotics and biocybernetics',
174 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
175 'upload_date': '20130627',
176 'formats': 'mincount:16',
177 'subtitles': 'mincount:1',
180 'force_generic_extractor': True,
181 'skip_download': True,
184 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
186 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
191 'formats': 'mincount:1',
194 'skip_download': True,
197 # SMIL from https://www.restudy.dk/video/play/id/1637
199 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
203 'title': 'video_1637',
204 'formats': 'mincount:3',
207 'skip_download': True,
210 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
212 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
214 'id': 'smil-service',
216 'title': 'smil-service',
217 'formats': 'mincount:1',
220 'skip_download': True,
223 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
225 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
229 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
230 'formats': 'mincount:3',
233 'skip_download': True,
236 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
238 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
240 'id': 'mZlp2ctYIUEB',
242 'title': 'Tikibad ontruimd wegens brand',
243 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
244 'thumbnail': r're:^https?://.*\.jpg$',
248 'skip_download': True,
251 # MPD from http://dash-mse-test.appspot.com/media.html
253 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
254 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
256 'id': 'car-20120827-manifest',
258 'title': 'car-20120827-manifest',
259 'formats': 'mincount:9',
260 'upload_date': '20130904',
263 'format': 'bestvideo',
266 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
268 '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',
273 'formats': 'mincount:8',
277 'skip_download': True,
279 'skip': 'video gone',
281 # m3u8 served with Content-Type: text/plain
283 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
288 'upload_date': '20140720',
289 'formats': 'mincount:11',
293 'skip_download': True,
295 'skip': 'video gone',
299 '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',
303 'upload_date': '20130224',
304 'uploader_id': 'TheVerge',
305 'description': r're:^Chris Ziegler takes a look at the\.*',
306 'uploader': 'The Verge',
307 'title': 'First Firefox OS phones side-by-side',
310 'skip_download': False,
314 # redirect in Refresh HTTP header
315 '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',
319 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
320 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
321 'upload_date': '20150917',
322 'uploader_id': 'brtvofficial',
323 'uploader': 'Boiler Room',
326 'skip_download': False,
330 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
331 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
333 'id': '13601338388002',
335 'uploader': 'www.hodiho.fr',
336 'title': 'R\u00e9gis plante sa Jeep',
339 # bandcamp page with custom domain
341 'add_ie': ['Bandcamp'],
342 'url': 'http://bronyrock.com/track/the-pony-mash',
346 'title': 'The Pony Mash',
347 'uploader': 'M_Pallante',
349 'skip': 'There is a limit of 200 free downloads / month for the test song',
352 # embedded brightcove video
353 # it also tests brightcove videos that need to set the 'Referer'
354 # in the http requests
355 'add_ie': ['BrightcoveLegacy'],
356 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
358 'id': '2765128793001',
360 'title': 'Le cours de bourse : l’analyse technique',
361 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
362 'uploader': 'BFM BUSINESS',
365 'skip_download': True,
369 # embedded with itemprop embedURL and video id spelled as `idVideo`
370 'add_id': ['BrightcoveLegacy'],
371 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
373 'id': '5255628253001',
375 'title': 'md5:37c519b1128915607601e75a87995fc0',
376 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
377 'uploader': 'BFM BUSINESS',
378 'uploader_id': '876450612001',
379 'timestamp': 1482255315,
380 'upload_date': '20161220',
383 'skip_download': True,
387 # https://github.com/rg3/youtube-dl/issues/2253
388 'url': 'http://bcove.me/i6nfkrc3',
389 'md5': '0ba9446db037002366bab3b3eb30c88c',
391 'id': '3101154703001',
393 'title': 'Still no power',
394 'uploader': 'thestar.com',
395 '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.',
397 'add_ie': ['BrightcoveLegacy'],
398 'skip': 'video gone',
401 'url': 'http://www.championat.com/video/football/v/87/87499.html',
402 'md5': 'fb973ecf6e4a78a67453647444222983',
404 'id': '3414141473001',
406 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
407 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
408 'uploader': 'Championat',
412 # https://github.com/rg3/youtube-dl/issues/3541
413 'add_ie': ['BrightcoveLegacy'],
414 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
416 'id': '3866516442001',
418 'title': 'Leer mij vrouwen kennen: Aflevering 1',
419 'description': 'Leer mij vrouwen kennen: Aflevering 1',
420 'uploader': 'SBS Broadcasting',
422 'skip': 'Restricted to Netherlands',
424 'skip_download': True, # m3u8 download
428 # Brightcove with alternative playerID key
429 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
431 'id': 'nmeth.2062_SV1',
432 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
436 'id': '2228375078001',
438 'title': 'nmeth.2062-sv1',
439 'description': 'nmeth.2062-sv1',
440 'timestamp': 1363357591,
441 'upload_date': '20130315',
442 'uploader': 'Nature Publishing Group',
443 'uploader_id': '1964492299001',
449 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
450 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
452 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
454 'title': '2cc213299525360.mov', # that's what we get
457 'add_ie': ['Ooyala'],
460 # ooyala video embedded with http://player.ooyala.com/iframe.js
461 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
463 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
465 'title': '"Steve Jobs: Man in the Machine" trailer',
466 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
470 'skip_download': True,
472 'skip': 'movie expired',
476 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
480 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
481 'upload_date': '20140225',
482 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
483 'uploader': 'Tested',
484 'uploader_id': 'testedcom',
486 # No need to test YoutubeIE here
488 'skip_download': True,
493 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
497 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
498 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
500 # HEAD requests lead to endless 301, while GET is OK
501 'expected_warnings': ['301'],
505 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
509 'title': 'Охотское море стало целиком российским',
510 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
514 'skip_download': True,
519 '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/',
523 'title': 'Дошкольное воспитание',
528 'url': 'http://www.vestifinance.ru/articles/25753',
531 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
536 'title': 'Госзаказ. День 3',
542 'title': 'Госзаказ. День 2',
548 'title': 'Госзаказ. День 1',
554 'skip_download': True,
559 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
561 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
563 'title': 'Ужастики, русский трейлер (2015)',
564 'thumbnail': r're:^https?://.*\.jpg$',
570 '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',
573 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
575 'playlist_mincount': 7,
576 # This forum does not allow <iframe> syntaxes anymore
577 # Now HTML tags are displayed as-is
578 'skip': 'No videos on this page',
582 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
583 'md5': '65fdff94098e4a607385a60c5177c638',
587 'title': 'Hidden miracles of the natural world',
588 'uploader': 'Louie Schwartzberg',
589 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
592 # nowvideo embed hidden behind percent encoding
594 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
595 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
597 'id': '06e53103ca9aa',
599 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
600 'description': 'No description',
605 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
606 'md5': '7653032cbb25bf6c80d80f217055fa43',
608 'id': '048195-004_PLUS7-F',
611 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
612 'upload_date': '20140320',
615 'skip_download': 'Requires rtmpdump'
617 'skip': 'video gone',
621 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
625 'title': 'Alcaline, le concert avec Calogero',
626 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
627 'upload_date': '20150226',
628 'timestamp': 1424989860,
633 'skip_download': True,
635 'expected_warnings': [
641 'url': 'http://www.wired.com/2014/04/honda-asimo/',
642 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
644 'id': '53501be369702d3275860000',
646 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
651 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
652 'md5': '441aeeb82eb72c422c7f14ec533999cd',
654 'id': 'k2mm4bCdJ6CQ2i7c8o2',
656 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
657 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
659 'uploader_id': 'xgditw',
660 'upload_date': '20140425',
661 'timestamp': 1398441542,
663 'add_ie': ['Dailymotion'],
667 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
671 'title': 'The NBL Auction 2014',
672 'uploader': 'BADMINTON England',
673 'uploader_id': 'BADMINTONEvents',
674 'upload_date': '20140603',
675 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
677 'add_ie': ['Youtube'],
679 'skip_download': True,
684 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
685 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
687 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
689 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
690 'description': 'Two valets share their love for movie star Liam Neesons.',
691 'timestamp': 1349922600,
692 'upload_date': '20121011',
695 # YouTube embed via <data-embed-url="">
697 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
701 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
702 'uploader': 'Gameloft',
703 'uploader_id': 'gameloft',
704 'upload_date': '20140828',
705 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
708 'skip_download': True,
713 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
715 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
717 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
718 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
723 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
725 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
726 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
732 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
737 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
738 'md5': '9d65602bf31c6e20014319c7d07fba27',
740 'id': '5123ea6d5e5a7',
743 'uploader': 'www.handjobhub.com',
744 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
747 # Multiple brightcove videos
748 # https://github.com/rg3/youtube-dl/issues/2283
750 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
752 'id': 'always-never',
753 'title': 'Always / Never - The New Yorker',
757 'extract_flat': False,
758 'skip_download': True,
763 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
764 'md5': '96f09a37e44da40dd083e12d9a683327',
768 'title': 'Ump changes call to ball',
769 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
771 'timestamp': 1401537900,
772 'upload_date': '20140531',
773 'thumbnail': r're:^https?://.*\.jpg$',
778 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
779 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
783 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
784 'description': 'a Paywall Videos video from Remilon',
786 'uploader': 'study.com',
787 'timestamp': 1459678540,
788 'upload_date': '20160403',
789 'filesize': 24687186,
793 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
794 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
798 'title': 'Conversation about Hexagonal Rails Part 1',
799 'description': 'a Martin Fowler video from ThoughtWorks',
801 'uploader': 'thoughtworks.wistia.com',
802 'timestamp': 1401832161,
803 'upload_date': '20140603',
806 # Wistia standard embed (async)
808 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
812 'title': 'Drip Brennan Dunn Workshop',
813 'description': 'a JV Webinars video from getdrip-1',
815 'timestamp': 1463607249,
816 'upload_date': '20160518',
819 'skip_download': True,
824 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
828 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
829 'uploader': 'Sophos Security',
830 'title': 'Chet Chat 171 - Oct 29, 2014',
831 'upload_date': '20141029',
834 # Soundcloud multiple embeds
836 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
839 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
841 'playlist_mincount': 7,
843 # TuneIn station embed
845 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
850 'location': 'Paris, France',
855 'skip_download': True,
860 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
864 'upload_date': '20141112',
865 'title': 'Rosetta #CometLanding webcast HL 10',
868 # Another Livestream embed, without 'new.' in URL
870 'url': 'https://www.freespeech.org/',
874 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
878 'skip_download': True,
883 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
886 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
888 'playlist_mincount': 2,
892 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
896 'upload_date': '20141126',
897 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
902 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
904 'id': '730m_DandD_1901_512k',
906 'uploader': 'www.abc.net.au',
907 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
910 # embedded viddler video
912 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
916 'uploader': 'deadspin',
917 'title': 'WALL-TO-GORTAT',
918 'timestamp': 1422285291,
919 'upload_date': '20150126',
921 'add_ie': ['Viddler'],
925 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
929 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
930 'description': 'md5:601cb790edd05908957dae8aaa866465',
931 'upload_date': '20150220',
933 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
937 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
941 'upload_date': '20150212',
942 'uploader': 'The National Archives UK',
943 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
944 'uploader_id': 'NationalArchives08',
945 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
950 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
951 'playlist_mincount': 5,
953 'id': 'aanslagen-kopenhagen',
954 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
959 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
963 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
966 # Kaltura embed (different embed code)
968 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
972 'upload_date': '20150127',
973 'uploader_id': 'PremierMedia',
975 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
978 # Kaltura embed protected with referrer
980 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
984 'title': 'Violetta - Achter De Schermen - Ruggero',
985 'description': 'Achter de schermen met Ruggero',
986 'timestamp': 1435133761,
987 'upload_date': '20150624',
988 'uploader_id': 'echojecka',
991 # Kaltura embed with single quotes
993 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
998 'timestamp': 1355743100,
999 'upload_date': '20121217',
1000 'uploader_id': 'batchUser',
1002 'add_ie': ['Kaltura'],
1005 # Kaltura embedded via quoted entry_id
1006 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1010 'title': '06_matthew_brender_raj_dutt',
1011 'timestamp': 1466638791,
1012 'upload_date': '20160622',
1014 'add_ie': ['Kaltura'],
1015 'expected_warnings': [
1016 'Could not send HEAD request'
1019 'skip_download': True,
1023 # Kaltura embedded, some fileExt broken (#11480)
1024 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1028 'title': 'Our "Standard Models" of particle physics and cosmology',
1029 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1030 'timestamp': 1321158993,
1031 'upload_date': '20111113',
1032 'uploader_id': 'kps1',
1034 'add_ie': ['Kaltura'],
1036 # Eagle.Platform embed (generic URL)
1038 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1039 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1043 'title': 'Навальный вышел на свободу',
1044 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1045 'thumbnail': r're:^https?://.*\.jpg$',
1051 # ClipYou (Eagle.Platform) embed (custom URL)
1053 'url': 'http://muz-tv.ru/play/7129/',
1054 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1058 'title': "'O Sole Mio",
1059 'thumbnail': r're:^https?://.*\.jpg$',
1066 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1070 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1071 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1072 'thumbnail': r're:^https?://.*\.jpg$',
1079 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1083 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1084 'thumbnail': r're:^https?://.*\.png$',
1090 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1091 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1095 'title': 'Facebook Creates "On This Day" | Crunch Report',
1100 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1104 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1109 # Crooks and Liars embed
1111 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1115 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1116 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1117 'timestamp': 1428207000,
1118 'upload_date': '20150405',
1119 'uploader': 'Heather',
1122 # Crooks and Liars external embed
1124 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1126 'id': 'MTE3MjUtMzQ2MzA',
1128 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1129 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1130 'timestamp': 1265032391,
1131 'upload_date': '20100201',
1132 'uploader': 'Heather',
1135 # NBC Sports vplayer embed
1137 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1139 'id': 'ln7x1qSThw4k',
1141 'title': "PFT Live: New leader in the 'new-look' defense",
1142 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1143 'uploader': 'NBCU-SPORTS',
1144 'upload_date': '20140107',
1145 'timestamp': 1389118457,
1150 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1151 'md5': '1aa589c675898ae6d37a17913cf68d66',
1153 'id': '701714499682',
1155 'title': 'PREVIEW: On Assignment: David Letterman',
1156 '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.',
1161 'url': 'https://video.udn.com/news/300346',
1162 'md5': 'fd2060e988c326991037b9aff9df21a6',
1166 'title': '中一中男師變性 全校師生力挺',
1167 'thumbnail': r're:^https?://.*\.jpg$',
1171 'skip_download': True,
1176 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1178 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1180 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1181 'title': 'This is what separates the Excel masters from the wannabes',
1182 'duration': 191.933,
1186 'skip_download': True,
1189 # Brightcove URL in single quotes
1191 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1192 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1194 'id': '4255764656001',
1196 'title': 'SN Presents: Russell Martin, World Citizen',
1197 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1198 'uploader': 'Rogers Sportsnet',
1199 'uploader_id': '1704050871',
1200 'upload_date': '20150525',
1201 'timestamp': 1432570283,
1204 # Dailymotion Cloud video
1206 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1207 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1211 'title': 'Sauvons les abeilles ! - Le débat',
1212 'description': 'md5:d9082128b1c5277987825d684939ca26',
1213 'thumbnail': r're:^https?://.*\.jpe?g$',
1214 'timestamp': 1434970506,
1215 'upload_date': '20150622',
1216 'uploader': 'Public Sénat',
1217 'uploader_id': 'xa9gza',
1220 # OnionStudios embed
1222 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1226 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1227 'thumbnail': r're:^https?://.*\.jpe?g$',
1228 'uploader': 'ClickHole',
1229 'uploader_id': 'clickhole',
1234 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1236 'id': '74849a00-85a9-11e1-9660-123139220831',
1238 'title': '#whilewewatch',
1241 # AdobeTVVideo embed
1243 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1244 'md5': '43662b577c018ad707a63766462b1e87',
1248 'title': 'New experience with Acrobat DC',
1249 'description': 'New experience with Acrobat DC',
1250 'duration': 248.667,
1253 # BrightcoveInPageEmbed embed
1255 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1257 'id': '4238694884001',
1259 'title': 'Tabletop: Dread, Last Thoughts',
1260 'description': 'Tabletop: Dread, Last Thoughts',
1264 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1265 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1267 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1269 'id': '4785848093001',
1271 'title': 'The Cardinal Pell Interview',
1272 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1273 'uploader': 'GlobeCast Australia - GlobeStream',
1274 'uploader_id': '2733773828001',
1275 'upload_date': '20160304',
1276 'timestamp': 1457083087,
1280 'skip_download': True,
1283 # Another form of arte.tv embed
1285 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1286 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1288 'id': '030273-562_PLUS7-F',
1290 'title': 'ARTE Reportage - Nulle part, en France',
1291 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1292 'upload_date': '20160409',
1297 'url': 'http://www.wykop.pl/link/3088787/',
1298 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1300 'id': '874_1459135191',
1302 'title': 'Man shows poor quality of new apartment building',
1303 'description': 'The wall is like a sand pile.',
1304 'uploader': 'Lake8737',
1307 # Duplicated embedded video URLs
1309 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1311 'id': '149298443_480_16c25b74_2',
1313 'title': 'vs. Blue Orange Spring Game',
1314 'uploader': 'www.hudl.com',
1317 # twitter:player:stream embed
1319 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1323 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1324 'uploader': 'www.rtl.be',
1328 'skip_download': True,
1331 # twitter:player embed
1333 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1334 'md5': 'a3e0df96369831de324f0778e126653c',
1336 'id': '4909620399001',
1338 'title': 'What Do Black Holes Sound Like?',
1339 'description': 'what do black holes sound like',
1340 'upload_date': '20160524',
1341 'uploader_id': '29913724001',
1342 'timestamp': 1464107587,
1343 'uploader': 'TheAtlantic',
1345 'add_ie': ['BrightcoveLegacy'],
1347 # Facebook <iframe> embed
1349 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1350 'md5': 'fbcde74f534176ecb015849146dd3aee',
1352 'id': '599637780109885',
1354 'title': 'Facebook video #599637780109885',
1357 # Facebook API embed
1359 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1360 'md5': 'a47372ee61b39a7b90287094d447d94e',
1362 'id': '10153467542406923',
1364 'title': 'Facebook video #10153467542406923',
1367 # Wordpress "YouTube Video Importer" plugin
1369 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1370 'md5': 'd16797741b560b485194eddda8121b48',
1372 'id': 'HNTXWDXV9Is',
1374 'title': 'Blue Devils Drumline Stanford lot 2016',
1375 'upload_date': '20160627',
1376 'uploader_id': 'GENOCIDE8GENERAL10',
1377 'uploader': 'cylus cyrus',
1381 # video stored on custom kaltura server
1382 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1383 'md5': '537617d06e64dfed891fa1593c4b30cc',
1387 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1388 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1389 'uploader_id': 'videos.expansion@el-mundo.net',
1390 'upload_date': '20150429',
1391 'timestamp': 1430303472,
1393 'add_ie': ['Kaltura'],
1396 # Non-standard Vimeo embed
1397 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1398 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1402 'title': 'Understanding the web - Teaser',
1403 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1404 'upload_date': '20151214',
1405 'uploader': 'OpenClassrooms',
1406 'uploader_id': 'openclassrooms',
1408 'add_ie': ['Vimeo'],
1411 # generic vimeo embed that requires original URL passed as Referer
1412 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1413 'only_matching': True,
1416 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1417 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1419 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1421 'title': 'Big Buck Bunny',
1422 'description': 'Royalty free test video',
1423 'timestamp': 1432816365,
1424 'upload_date': '20150528',
1428 'skip_download': True,
1430 'add_ie': [ArkenaIE.ie_key()],
1433 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1437 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1440 'skip_download': True,
1442 'add_ie': [Vbox7IE.ie_key()],
1446 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1449 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1451 'playlist_mincount': 3,
1455 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1457 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1458 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1460 'playlist_mincount': 2,
1464 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1468 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1469 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1472 'skip_download': True,
1474 'add_ie': [TwentyMinutenIE.ie_key()],
1477 # # TODO: find another test
1478 # # http://schema.org/VideoObject
1479 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1480 # 'md5': '888dcf08b7ea671381f00fab74692755',
1482 # 'id': 'nyvTSJMKId',
1484 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1485 # 'description': '#love for cats.',
1486 # 'timestamp': 1461244995,
1487 # 'upload_date': '20160421',
1490 # 'force_generic_extractor': True,
1495 def report_following_redirect(self, new_url):
1496 """Report information extraction."""
1497 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1499 def _extract_rss(self, url, video_id, doc):
1500 playlist_title = doc.find('./channel/title').text
1501 playlist_desc_el = doc.find('./channel/description')
1502 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1505 for it in doc.findall('./channel/item'):
1506 next_url = xpath_text(it, 'link', fatal=False)
1508 enclosure_nodes = it.findall('./enclosure')
1509 for e in enclosure_nodes:
1510 next_url = e.attrib.get('url')
1520 'title': it.find('title').text,
1524 '_type': 'playlist',
1526 'title': playlist_title,
1527 'description': playlist_desc,
1531 def _extract_camtasia(self, url, video_id, webpage):
1532 """ Returns None if no camtasia video can be found. """
1534 camtasia_cfg = self._search_regex(
1535 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1536 webpage, 'camtasia configuration file', default=None)
1537 if camtasia_cfg is None:
1540 title = self._html_search_meta('DC.title', webpage, fatal=True)
1542 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1543 camtasia_cfg = self._download_xml(
1544 camtasia_url, video_id,
1545 note='Downloading camtasia configuration',
1546 errnote='Failed to download camtasia configuration')
1547 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1550 for n in fileset_node.getchildren():
1551 url_n = n.find('./uri')
1556 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1557 'title': '%s - %s' % (title, n.tag),
1558 'url': compat_urlparse.urljoin(url, url_n.text),
1559 'duration': float_or_none(n.find('./duration').text),
1563 '_type': 'playlist',
1568 def _real_extract(self, url):
1569 if url.startswith('//'):
1572 'url': self.http_scheme() + url,
1575 parsed_url = compat_urlparse.urlparse(url)
1576 if not parsed_url.scheme:
1577 default_search = self._downloader.params.get('default_search')
1578 if default_search is None:
1579 default_search = 'fixup_error'
1581 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1583 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1584 return self.url_result('http://' + url)
1585 elif default_search != 'fixup_error':
1586 if default_search == 'auto_warning':
1587 if re.match(r'^(?:url|URL)$', url):
1588 raise ExtractorError(
1589 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1592 self._downloader.report_warning(
1593 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1594 return self.url_result('ytsearch:' + url)
1596 if default_search in ('error', 'fixup_error'):
1597 raise ExtractorError(
1598 '%r is not a valid URL. '
1599 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1600 % (url, url), expected=True)
1602 if ':' not in default_search:
1603 default_search += ':'
1604 return self.url_result(default_search + url)
1606 url, smuggled_data = unsmuggle_url(url)
1607 force_videoid = None
1608 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1609 if smuggled_data and 'force_videoid' in smuggled_data:
1610 force_videoid = smuggled_data['force_videoid']
1611 video_id = force_videoid
1613 video_id = self._generic_id(url)
1615 self.to_screen('%s: Requesting header' % video_id)
1617 head_req = HEADRequest(url)
1618 head_response = self._request_webpage(
1620 note=False, errnote='Could not send HEAD request to %s' % url,
1623 if head_response is not False:
1624 # Check for redirect
1625 new_url = head_response.geturl()
1627 self.report_following_redirect(new_url)
1629 new_url = smuggle_url(
1630 new_url, {'force_videoid': force_videoid})
1631 return self.url_result(new_url)
1633 full_response = None
1634 if head_response is False:
1635 request = sanitized_Request(url)
1636 request.add_header('Accept-Encoding', '*')
1637 full_response = self._request_webpage(request, video_id)
1638 head_response = full_response
1642 'title': self._generic_title(url),
1643 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1646 # Check for direct link to a video
1647 content_type = head_response.headers.get('Content-Type', '').lower()
1648 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1650 format_id = m.group('format_id')
1651 if format_id.endswith('mpegurl'):
1652 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1653 elif format_id == 'f4m':
1654 formats = self._extract_f4m_formats(url, video_id)
1657 'format_id': m.group('format_id'),
1659 'vcodec': 'none' if m.group('type') == 'audio' else None
1661 info_dict['direct'] = True
1662 self._sort_formats(formats)
1663 info_dict['formats'] = formats
1666 if not self._downloader.params.get('test', False) and not is_intentional:
1667 force = self._downloader.params.get('force_generic_extractor', False)
1668 self._downloader.report_warning(
1669 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1671 if not full_response:
1672 request = sanitized_Request(url)
1673 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1674 # making it impossible to download only chunk of the file (yet we need only 512kB to
1675 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1676 # that will always result in downloading the whole file that is not desirable.
1677 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1678 # to accept raw bytes and being able to download only a chunk.
1679 # It may probably better to solve this by checking Content-Type for application/octet-stream
1680 # after HEAD request finishes, but not sure if we can rely on this.
1681 request.add_header('Accept-Encoding', '*')
1682 full_response = self._request_webpage(request, video_id)
1684 first_bytes = full_response.read(512)
1686 # Is it an M3U playlist?
1687 if first_bytes.startswith(b'#EXTM3U'):
1688 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1689 self._sort_formats(info_dict['formats'])
1692 # Maybe it's a direct link to a video?
1693 # Be careful not to download the whole thing!
1694 if not is_html(first_bytes):
1695 self._downloader.report_warning(
1696 'URL could be a direct video link, returning it as such.')
1703 webpage = self._webpage_read_content(
1704 full_response, url, video_id, prefix=first_bytes)
1706 self.report_extraction(video_id)
1708 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1710 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1711 if doc.tag == 'rss':
1712 return self._extract_rss(url, video_id, doc)
1713 elif doc.tag == 'SmoothStreamingMedia':
1714 info_dict['formats'] = self._parse_ism_formats(doc, url)
1715 self._sort_formats(info_dict['formats'])
1717 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1718 smil = self._parse_smil(doc, url, video_id)
1719 self._sort_formats(smil['formats'])
1721 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1722 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1723 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1724 info_dict['formats'] = self._parse_mpd_formats(
1726 mpd_base_url=full_response.geturl().rpartition('/')[0],
1728 self._sort_formats(info_dict['formats'])
1730 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1731 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1732 self._sort_formats(info_dict['formats'])
1734 except compat_xml_parse_error:
1737 # Is it a Camtasia project?
1738 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1739 if camtasia_res is not None:
1742 # Sometimes embedded video player is hidden behind percent encoding
1743 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1744 # Unescaping the whole page allows to handle those cases in a generic way
1745 webpage = compat_urllib_parse_unquote(webpage)
1747 # it's tempting to parse this further, but you would
1748 # have to take into account all the variations like
1749 # Video Title - Site Name
1750 # Site Name | Video Title
1751 # Video Title - Tagline | Site Name
1752 # and so on and so forth; it's just not practical
1753 video_title = self._og_search_title(
1754 webpage, default=None) or self._html_search_regex(
1755 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1758 # Try to detect age limit automatically
1759 age_limit = self._rta_search(webpage)
1760 # And then there are the jokers who advertise that they use RTA,
1761 # but actually don't.
1762 AGE_LIMIT_MARKERS = [
1763 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1765 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1768 # video uploader is domain name
1769 video_uploader = self._search_regex(
1770 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1772 video_description = self._og_search_description(webpage, default=None)
1773 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1776 def _playlist_from_matches(matches, getter=None, ie=None):
1778 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1780 return self.playlist_result(
1781 urlrs, playlist_id=video_id, playlist_title=video_title)
1783 # Look for Brightcove Legacy Studio embeds
1784 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1786 self.to_screen('Brightcove video detected.')
1789 'url': smuggle_url(bc_url, {'Referer': url}),
1790 'ie_key': 'BrightcoveLegacy'
1791 } for bc_url in bc_urls]
1794 '_type': 'playlist',
1795 'title': video_title,
1800 # Look for Brightcove New Studio embeds
1801 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1803 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1805 # Look for ThePlatform embeds
1806 tp_urls = ThePlatformIE._extract_urls(webpage)
1808 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1810 # Look for Vessel embeds
1811 vessel_urls = VesselIE._extract_urls(webpage)
1813 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1815 # Look for embedded rtl.nl player
1816 matches = re.findall(
1817 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1820 return _playlist_from_matches(matches, ie='RtlNl')
1822 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1824 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1826 vid_me_embed_url = self._search_regex(
1827 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1828 webpage, 'vid.me embed', default=None)
1829 if vid_me_embed_url is not None:
1830 return self.url_result(vid_me_embed_url, 'Vidme')
1832 # Look for embedded YouTube player
1833 matches = re.findall(r'''(?x)
1842 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1846 return _playlist_from_matches(
1847 matches, lambda m: unescapeHTML(m[1]))
1849 # Look for lazyYT YouTube embed
1850 matches = re.findall(
1851 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1853 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1855 # Look for Wordpress "YouTube Video Importer" plugin
1856 matches = re.findall(r'''(?x)<div[^>]+
1857 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1858 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1860 return _playlist_from_matches(matches, lambda m: m[-1])
1862 matches = DailymotionIE._extract_urls(webpage)
1864 return _playlist_from_matches(matches)
1866 # Look for embedded Dailymotion playlist player (#3822)
1868 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1870 playlists = re.findall(
1871 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1873 return _playlist_from_matches(
1874 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1876 # Look for embedded Wistia player
1878 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1880 embed_url = self._proto_relative_url(
1881 unescapeHTML(match.group('url')))
1883 '_type': 'url_transparent',
1886 'uploader': video_uploader,
1889 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1892 '_type': 'url_transparent',
1893 'url': 'wistia:%s' % match.group('id'),
1895 'uploader': video_uploader,
1900 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1901 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1904 return self.url_result(self._proto_relative_url(
1905 'wistia:%s' % match.group('id')), 'Wistia')
1907 # Look for SVT player
1908 svt_url = SVTIE._extract_url(webpage)
1910 return self.url_result(svt_url, 'SVT')
1912 # Look for embedded condenast player
1913 matches = re.findall(
1914 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1918 '_type': 'playlist',
1921 'ie_key': 'CondeNast',
1923 } for ma in matches],
1924 'title': video_title,
1928 # Look for Bandcamp pages with custom domain
1929 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1930 if mobj is not None:
1931 burl = unescapeHTML(mobj.group(1))
1932 # Don't set the extractor because it can be a track url or an album
1933 return self.url_result(burl)
1935 # Look for embedded Vevo player
1937 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1938 if mobj is not None:
1939 return self.url_result(mobj.group('url'))
1941 # Look for embedded Viddler player
1943 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1945 if mobj is not None:
1946 return self.url_result(mobj.group('url'))
1948 # Look for NYTimes player
1950 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1952 if mobj is not None:
1953 return self.url_result(mobj.group('url'))
1955 # Look for Libsyn player
1957 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1958 if mobj is not None:
1959 return self.url_result(mobj.group('url'))
1961 # Look for Ooyala videos
1962 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1963 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1964 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1965 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1966 if mobj is not None:
1967 embed_token = self._search_regex(
1968 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1969 webpage, 'ooyala embed token', default=None)
1970 return OoyalaIE._build_url_result(smuggle_url(
1973 'embed_token': embed_token,
1976 # Look for multiple Ooyala embeds on SBN network websites
1977 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1978 if mobj is not None:
1979 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1981 return _playlist_from_matches(
1982 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1984 # Look for Aparat videos
1985 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1986 if mobj is not None:
1987 return self.url_result(mobj.group(1), 'Aparat')
1989 # Look for MPORA videos
1990 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1991 if mobj is not None:
1992 return self.url_result(mobj.group(1), 'Mpora')
1994 # Look for embedded NovaMov-based player
1996 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1997 (?P<url>http://(?:(?:embed|www)\.)?
1999 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2000 videoweed\.(?:es|com)|
2001 movshare\.(?:net|sx|ag)|
2002 divxstage\.(?:eu|net|ch|co|at|ag))
2003 /embed\.php.+?)\1''', webpage)
2004 if mobj is not None:
2005 return self.url_result(mobj.group('url'))
2007 # Look for embedded Facebook player
2008 facebook_url = FacebookIE._extract_url(webpage)
2009 if facebook_url is not None:
2010 return self.url_result(facebook_url, 'Facebook')
2012 # Look for embedded VK player
2013 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2014 if mobj is not None:
2015 return self.url_result(mobj.group('url'), 'VK')
2017 # Look for embedded Odnoklassniki player
2018 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2019 if mobj is not None:
2020 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2022 # Look for embedded ivi player
2023 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2024 if mobj is not None:
2025 return self.url_result(mobj.group('url'), 'Ivi')
2027 # Look for embedded Huffington Post player
2029 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2030 if mobj is not None:
2031 return self.url_result(mobj.group('url'), 'HuffPost')
2034 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2035 if mobj is not None:
2036 return self.url_result(mobj.group('url'))
2037 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2038 if mobj is not None:
2039 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2041 # Look for funnyordie embed
2042 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2044 return _playlist_from_matches(
2045 matches, getter=unescapeHTML, ie='FunnyOrDie')
2047 # Look for BBC iPlayer embed
2048 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2050 return _playlist_from_matches(matches, ie='BBCCoUk')
2052 # Look for embedded RUTV player
2053 rutv_url = RUTVIE._extract_url(webpage)
2055 return self.url_result(rutv_url, 'RUTV')
2057 # Look for embedded TVC player
2058 tvc_url = TVCIE._extract_url(webpage)
2060 return self.url_result(tvc_url, 'TVC')
2062 # Look for embedded SportBox player
2063 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2065 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2067 # Look for embedded XHamster player
2068 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2070 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2072 # Look for embedded TNAFlixNetwork player
2073 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2075 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2077 # Look for embedded PornHub player
2078 pornhub_urls = PornHubIE._extract_urls(webpage)
2080 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2082 # Look for embedded DrTuber player
2083 drtuber_urls = DrTuberIE._extract_urls(webpage)
2085 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2087 # Look for embedded RedTube player
2088 redtube_urls = RedTubeIE._extract_urls(webpage)
2090 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2092 # Look for embedded Tvigle player
2094 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2095 if mobj is not None:
2096 return self.url_result(mobj.group('url'), 'Tvigle')
2098 # Look for embedded TED player
2100 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2101 if mobj is not None:
2102 return self.url_result(mobj.group('url'), 'TED')
2104 # Look for embedded Ustream videos
2105 ustream_url = UstreamIE._extract_url(webpage)
2107 return self.url_result(ustream_url, UstreamIE.ie_key())
2109 # Look for embedded arte.tv player
2111 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2113 if mobj is not None:
2114 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2116 # Look for embedded francetv player
2118 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2120 if mobj is not None:
2121 return self.url_result(mobj.group('url'))
2123 # Look for embedded smotri.com player
2124 smotri_url = SmotriIE._extract_url(webpage)
2126 return self.url_result(smotri_url, 'Smotri')
2128 # Look for embedded Myvi.ru player
2129 myvi_url = MyviIE._extract_url(webpage)
2131 return self.url_result(myvi_url)
2133 # Look for embedded soundcloud player
2134 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2136 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2138 # Look for tunein player
2139 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2141 return _playlist_from_matches(tunein_urls)
2143 # Look for embedded mtvservices player
2144 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2146 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2148 # Look for embedded yahoo player
2150 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2152 if mobj is not None:
2153 return self.url_result(mobj.group('url'), 'Yahoo')
2155 # Look for embedded sbs.com.au player
2159 <meta\s+property="og:video"\s+content=|
2162 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2164 if mobj is not None:
2165 return self.url_result(mobj.group('url'), 'SBS')
2167 # Look for embedded Cinchcast player
2169 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2171 if mobj is not None:
2172 return self.url_result(mobj.group('url'), 'Cinchcast')
2175 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2179 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2181 if mobj is not None:
2182 return self.url_result(mobj.group('url'), 'MLB')
2185 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2187 if mobj is not None:
2188 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2191 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2193 if mobj is not None:
2194 return self.url_result(mobj.group('url'), 'Livestream')
2196 # Look for Zapiks embed
2198 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2199 if mobj is not None:
2200 return self.url_result(mobj.group('url'), 'Zapiks')
2202 # Look for Kaltura embeds
2203 kaltura_url = KalturaIE._extract_url(webpage)
2205 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2207 # Look for Eagle.Platform embeds
2208 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2209 if eagleplatform_url:
2210 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2212 # Look for ClipYou (uses Eagle.Platform) embeds
2214 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2215 if mobj is not None:
2216 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2218 # Look for Pladform embeds
2219 pladform_url = PladformIE._extract_url(webpage)
2221 return self.url_result(pladform_url)
2223 # Look for Videomore embeds
2224 videomore_url = VideomoreIE._extract_url(webpage)
2226 return self.url_result(videomore_url)
2228 # Look for Webcaster embeds
2229 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2231 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2233 # Look for Playwire embeds
2235 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2236 if mobj is not None:
2237 return self.url_result(mobj.group('url'))
2239 # Look for 5min embeds
2241 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2242 if mobj is not None:
2243 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2245 # Look for Crooks and Liars embeds
2247 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2248 if mobj is not None:
2249 return self.url_result(mobj.group('url'))
2251 # Look for NBC Sports VPlayer embeds
2252 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2254 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2256 # Look for NBC News embeds
2257 nbc_news_embed_url = re.search(
2258 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2259 if nbc_news_embed_url:
2260 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2262 # Look for Google Drive embeds
2263 google_drive_url = GoogleDriveIE._extract_url(webpage)
2264 if google_drive_url:
2265 return self.url_result(google_drive_url, 'GoogleDrive')
2267 # Look for UDN embeds
2269 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2270 if mobj is not None:
2271 return self.url_result(
2272 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2274 # Look for Senate ISVP iframe
2275 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2277 return self.url_result(senate_isvp_url, 'SenateISVP')
2279 # Look for Dailymotion Cloud videos
2280 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2282 return self.url_result(dmcloud_url, 'DailymotionCloud')
2284 # Look for OnionStudios embeds
2285 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2286 if onionstudios_url:
2287 return self.url_result(onionstudios_url)
2289 # Look for ViewLift embeds
2290 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2292 return self.url_result(viewlift_url)
2294 # Look for JWPlatform embeds
2295 jwplatform_url = JWPlatformIE._extract_url(webpage)
2297 return self.url_result(jwplatform_url, 'JWPlatform')
2299 # Look for Digiteka embeds
2300 digiteka_url = DigitekaIE._extract_url(webpage)
2302 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2304 # Look for Arkena embeds
2305 arkena_url = ArkenaIE._extract_url(webpage)
2307 return self.url_result(arkena_url, ArkenaIE.ie_key())
2309 # Look for Piksel embeds
2310 piksel_url = PikselIE._extract_url(webpage)
2312 return self.url_result(piksel_url, PikselIE.ie_key())
2314 # Look for Limelight embeds
2315 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2319 'Channel': 'channel',
2320 'ChannelList': 'channel_list',
2322 return self.url_result('limelight:%s:%s' % (
2323 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2327 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2329 name=(["\'])flashVars\2[^>]+
2330 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2333 return self.url_result('limelight:media:%s' % mobj.group('id'))
2335 # Look for AdobeTVVideo embeds
2337 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2339 if mobj is not None:
2340 return self.url_result(
2341 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2344 # Look for Vine embeds
2346 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2348 if mobj is not None:
2349 return self.url_result(
2350 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2352 # Look for VODPlatform embeds
2354 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2356 if mobj is not None:
2357 return self.url_result(
2358 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2360 # Look for Mangomolo embeds
2362 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2364 video\?.*?\bid=(?P<video_id>\d+)|
2365 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2366 ).+?)\1''', webpage)
2367 if mobj is not None:
2369 '_type': 'url_transparent',
2370 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2371 'title': video_title,
2372 'description': video_description,
2373 'thumbnail': video_thumbnail,
2374 'uploader': video_uploader,
2376 video_id = mobj.group('video_id')
2379 'ie_key': 'MangomoloVideo',
2384 'ie_key': 'MangomoloLive',
2385 'id': mobj.group('channel_id'),
2389 # Look for Instagram embeds
2390 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2391 if instagram_embed_url is not None:
2392 return self.url_result(
2393 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2395 # Look for LiveLeak embeds
2396 liveleak_url = LiveLeakIE._extract_url(webpage)
2398 return self.url_result(liveleak_url, 'LiveLeak')
2400 # Look for 3Q SDN embeds
2401 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2404 '_type': 'url_transparent',
2405 'ie_key': ThreeQSDNIE.ie_key(),
2406 'url': self._proto_relative_url(threeqsdn_url),
2407 'title': video_title,
2408 'description': video_description,
2409 'thumbnail': video_thumbnail,
2410 'uploader': video_uploader,
2413 # Look for VBOX7 embeds
2414 vbox7_url = Vbox7IE._extract_url(webpage)
2416 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2418 # Look for DBTV embeds
2419 dbtv_urls = DBTVIE._extract_urls(webpage)
2421 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2423 # Look for Videa embeds
2424 videa_urls = VideaIE._extract_urls(webpage)
2426 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2428 # Look for 20 minuten embeds
2429 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2431 return _playlist_from_matches(
2432 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2434 # Looking for http://schema.org/VideoObject
2435 json_ld = self._search_json_ld(
2436 webpage, video_id, default={}, expected_type='VideoObject')
2437 if json_ld.get('url'):
2439 'title': video_title or info_dict['title'],
2440 'description': video_description,
2441 'thumbnail': video_thumbnail,
2442 'age_limit': age_limit
2444 info_dict.update(json_ld)
2447 # Look for HTML5 media
2448 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2450 for entry in entries:
2453 'title': video_title,
2455 self._sort_formats(entry['formats'])
2456 return self.playlist_result(entries)
2458 def check_video(vurl):
2459 if YoutubeIE.suitable(vurl):
2461 vpath = compat_urlparse.urlparse(vurl).path
2462 vext = determine_ext(vpath)
2463 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2465 def filter_video(urls):
2466 return list(filter(check_video, urls))
2468 # Start with something easy: JW Player in SWFObject
2469 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2471 # Look for gorilla-vid style embedding
2472 found = filter_video(re.findall(r'''(?sx)
2476 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2479 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2481 # Broaden the search a little bit
2482 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2484 # Broaden the findall a little bit: JWPlayer JS loader
2485 found = filter_video(re.findall(
2486 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2489 found = filter_video(re.findall(r'''(?xs)
2490 flowplayer\("[^"]+",\s*
2492 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2493 ["']?url["']?\s*:\s*["']([^"']+)["']
2498 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2500 # Try to find twitter cards info
2501 # twitter:player:stream should be checked before twitter:player since
2502 # it is expected to contain a raw stream (see
2503 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2504 found = filter_video(re.findall(
2505 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2507 # We look for Open Graph info:
2508 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2509 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2510 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2511 if m_video_type is not None:
2512 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2514 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2516 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2517 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2520 # Look also in Refresh HTTP header
2521 refresh_header = head_response.headers.get('Refresh')
2523 # In python 2 response HTTP headers are bytestrings
2524 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2525 refresh_header = refresh_header.decode('iso-8859-1')
2526 found = re.search(REDIRECT_REGEX, refresh_header)
2528 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2529 self.report_following_redirect(new_url)
2536 # twitter:player is a https URL to iframe player that may or may not
2537 # be supported by youtube-dl thus this is checked the very last (see
2538 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2539 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2541 return self.url_result(embed_url)
2544 raise UnsupportedError(url)
2547 for video_url in orderedSet(found):
2548 video_url = unescapeHTML(video_url)
2549 video_url = video_url.replace('\\/', '/')
2550 video_url = compat_urlparse.urljoin(url, video_url)
2551 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2553 # Sometimes, jwplayer extraction will result in a YouTube URL
2554 if YoutubeIE.suitable(video_url):
2555 entries.append(self.url_result(video_url, 'Youtube'))
2558 # here's a fun little line of code for you:
2559 video_id = os.path.splitext(video_id)[0]
2563 'uploader': video_uploader,
2564 'title': video_title,
2565 'age_limit': age_limit,
2568 ext = determine_ext(video_url)
2570 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2572 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2574 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2576 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2578 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2579 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2580 # Just matching .ism/manifest is not enough to be reliably sure
2581 # whether it's actually an ISM manifest or some other streaming
2582 # manifest since there are various streaming URL formats
2583 # possible (see [1]) as well as some other shenanigans like
2584 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2586 # Thus the most reasonable way to solve this is to delegate
2587 # to generic extractor in order to look into the contents of
2588 # the manifest itself.
2589 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2590 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2591 entry_info_dict = self.url_result(
2592 smuggle_url(video_url, {'to_generic': True}),
2595 entry_info_dict['url'] = video_url
2597 if entry_info_dict.get('formats'):
2598 self._sort_formats(entry_info_dict['formats'])
2600 entries.append(entry_info_dict)
2602 if len(entries) == 1:
2605 for num, e in enumerate(entries, start=1):
2606 # 'url' results don't have a title
2607 if e.get('title') is not None:
2608 e['title'] = '%s (%d)' % (e['title'], num)
2610 '_type': 'playlist',