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 .commonprotocols
import RtmpIE
34 from .brightcove
import (
38 from .nbc
import NBCSportsVPlayerIE
39 from .ooyala
import OoyalaIE
40 from .rutv
import RUTVIE
41 from .tvc
import TVCIE
42 from .sportbox
import SportBoxEmbedIE
43 from .smotri
import SmotriIE
44 from .myvi
import MyviIE
45 from .condenast
import CondeNastIE
46 from .udn
import UDNEmbedIE
47 from .senateisvp
import SenateISVPIE
48 from .svt
import SVTIE
49 from .pornhub
import PornHubIE
50 from .xhamster
import XHamsterEmbedIE
51 from .tnaflix
import TNAFlixNetworkEmbedIE
52 from .drtuber
import DrTuberIE
53 from .redtube
import RedTubeIE
54 from .vimeo
import VimeoIE
55 from .dailymotion
import (
59 from .onionstudios
import OnionStudiosIE
60 from .viewlift
import ViewLiftEmbedIE
61 from .mtv
import MTVServicesEmbeddedIE
62 from .pladform
import PladformIE
63 from .videomore
import VideomoreIE
64 from .webcaster
import WebcasterFeedIE
65 from .googledrive
import GoogleDriveIE
66 from .jwplatform
import JWPlatformIE
67 from .digiteka
import DigitekaIE
68 from .arkena
import ArkenaIE
69 from .instagram
import InstagramIE
70 from .liveleak
import LiveLeakIE
71 from .threeqsdn
import ThreeQSDNIE
72 from .theplatform
import ThePlatformIE
73 from .vessel
import VesselIE
74 from .kaltura
import KalturaIE
75 from .eagleplatform
import EaglePlatformIE
76 from .facebook
import FacebookIE
77 from .soundcloud
import SoundcloudIE
78 from .tunein
import TuneInBaseIE
79 from .vbox7
import Vbox7IE
80 from .dbtv
import DBTVIE
81 from .piksel
import PikselIE
82 from .videa
import VideaIE
83 from .twentymin
import TwentyMinutenIE
84 from .ustream
import UstreamIE
85 from .openload
import OpenloadIE
86 from .videopress
import VideoPressIE
87 from .rutube
import RutubeIE
90 class GenericIE(InfoExtractor
):
91 IE_DESC
= 'Generic downloader that works on some sites'
95 # Direct link to a video
97 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
98 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
103 'upload_date': '20100513',
106 # Direct link to media delivered compressed (until Accept-Encoding is *)
108 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
109 'md5': '128c42e68b13950268b648275386fc74',
111 'id': 'FictionJunction-Parallel_Hearts',
113 'title': 'FictionJunction-Parallel_Hearts',
114 'upload_date': '20140522',
116 'expected_warnings': [
117 'URL could be a direct video link, returning it as such.'
119 'skip': 'URL invalid',
121 # Direct download with broken HEAD
123 'url': 'http://ai-radio.org:8000/radio.opus',
130 'skip_download': True, # infinite live stream
132 'expected_warnings': [
133 r
'501.*Not Implemented',
137 # Direct link with incorrect MIME type
139 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
140 'md5': '4ccbebe5f36706d85221f204d7eb5913',
142 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
143 'id': '5_Lennart_Poettering_-_Systemd',
145 'title': '5_Lennart_Poettering_-_Systemd',
146 'upload_date': '20141120',
148 'expected_warnings': [
149 'URL could be a direct video link, returning it as such.'
154 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
156 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'title': 'Zero Punctuation',
158 'description': 're:.*groundbreaking video review series.*'
160 'playlist_mincount': 11,
162 # RSS feed with enclosure
164 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
166 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
168 'upload_date': '20150228',
169 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
172 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
174 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
178 'title': 'Automatics, robotics and biocybernetics',
179 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
180 'upload_date': '20130627',
181 'formats': 'mincount:16',
182 'subtitles': 'mincount:1',
185 'force_generic_extractor': True,
186 'skip_download': True,
189 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
191 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
196 'formats': 'mincount:1',
199 'skip_download': True,
202 # SMIL from https://www.restudy.dk/video/play/id/1637
204 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
208 'title': 'video_1637',
209 'formats': 'mincount:3',
212 'skip_download': True,
215 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
217 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
219 'id': 'smil-service',
221 'title': 'smil-service',
222 'formats': 'mincount:1',
225 'skip_download': True,
228 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
230 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
234 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
235 'formats': 'mincount:3',
238 'skip_download': True,
241 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
243 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
245 'id': 'mZlp2ctYIUEB',
247 'title': 'Tikibad ontruimd wegens brand',
248 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
249 'thumbnail': r
're:^https?://.*\.jpg$',
253 'skip_download': True,
256 # MPD from http://dash-mse-test.appspot.com/media.html
258 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
259 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
261 'id': 'car-20120827-manifest',
263 'title': 'car-20120827-manifest',
264 'formats': 'mincount:9',
265 'upload_date': '20130904',
268 'format': 'bestvideo',
271 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
273 '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',
278 'formats': 'mincount:8',
282 'skip_download': True,
284 'skip': 'video gone',
286 # m3u8 served with Content-Type: text/plain
288 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
293 'upload_date': '20140720',
294 'formats': 'mincount:11',
298 'skip_download': True,
300 'skip': 'video gone',
304 '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',
308 'upload_date': '20130224',
309 'uploader_id': 'TheVerge',
310 'description': r
're:^Chris Ziegler takes a look at the\.*',
311 'uploader': 'The Verge',
312 'title': 'First Firefox OS phones side-by-side',
315 'skip_download': False,
319 # redirect in Refresh HTTP header
320 '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',
324 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
325 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
326 'upload_date': '20150917',
327 'uploader_id': 'brtvofficial',
328 'uploader': 'Boiler Room',
331 'skip_download': False,
335 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
336 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
338 'id': '13601338388002',
340 'uploader': 'www.hodiho.fr',
341 'title': 'R\u00e9gis plante sa Jeep',
344 # bandcamp page with custom domain
346 'add_ie': ['Bandcamp'],
347 'url': 'http://bronyrock.com/track/the-pony-mash',
351 'title': 'The Pony Mash',
352 'uploader': 'M_Pallante',
354 'skip': 'There is a limit of 200 free downloads / month for the test song',
357 # embedded brightcove video
358 # it also tests brightcove videos that need to set the 'Referer'
359 # in the http requests
360 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
363 'id': '2765128793001',
365 'title': 'Le cours de bourse : lāanalyse technique',
366 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
367 'uploader': 'BFM BUSINESS',
370 'skip_download': True,
374 # embedded with itemprop embedURL and video id spelled as `idVideo`
375 'add_id': ['BrightcoveLegacy'],
376 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
378 'id': '5255628253001',
380 'title': 'md5:37c519b1128915607601e75a87995fc0',
381 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
382 'uploader': 'BFM BUSINESS',
383 'uploader_id': '876450612001',
384 'timestamp': 1482255315,
385 'upload_date': '20161220',
388 'skip_download': True,
392 # https://github.com/rg3/youtube-dl/issues/2253
393 'url': 'http://bcove.me/i6nfkrc3',
394 'md5': '0ba9446db037002366bab3b3eb30c88c',
396 'id': '3101154703001',
398 'title': 'Still no power',
399 'uploader': 'thestar.com',
400 '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.',
402 'add_ie': ['BrightcoveLegacy'],
403 'skip': 'video gone',
406 'url': 'http://www.championat.com/video/football/v/87/87499.html',
407 'md5': 'fb973ecf6e4a78a67453647444222983',
409 'id': '3414141473001',
411 'title': 'ŠŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ ŠŠ·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠŠ)',
412 'description': 'ŠŠ½Š»Š°Š¹Š½-ŃŃŠ°Š½ŃŠ»ŃŃŠøŃ Š¼Š°ŃŃŠ° Š¦Š”ŠŠ - "ŠŠ¾Š»Š³Š°"',
413 'uploader': 'Championat',
417 # https://github.com/rg3/youtube-dl/issues/3541
418 'add_ie': ['BrightcoveLegacy'],
419 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
421 'id': '3866516442001',
423 'title': 'Leer mij vrouwen kennen: Aflevering 1',
424 'description': 'Leer mij vrouwen kennen: Aflevering 1',
425 'uploader': 'SBS Broadcasting',
427 'skip': 'Restricted to Netherlands',
429 'skip_download': True, # m3u8 download
433 # Brightcove with alternative playerID key
434 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
436 'id': 'nmeth.2062_SV1',
437 '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',
441 'id': '2228375078001',
443 'title': 'nmeth.2062-sv1',
444 'description': 'nmeth.2062-sv1',
445 'timestamp': 1363357591,
446 'upload_date': '20130315',
447 'uploader': 'Nature Publishing Group',
448 'uploader_id': '1964492299001',
454 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
455 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
457 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
459 'title': '2cc213299525360.mov', # that's what we get
462 'add_ie': ['Ooyala'],
465 # ooyala video embedded with http://player.ooyala.com/iframe.js
466 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
468 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
470 'title': '"Steve Jobs: Man in the Machine" trailer',
471 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
475 'skip_download': True,
477 'skip': 'movie expired',
481 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
485 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
486 'upload_date': '20140225',
487 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
488 'uploader': 'Tested',
489 'uploader_id': 'testedcom',
491 # No need to test YoutubeIE here
493 'skip_download': True,
498 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
502 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
503 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
505 # HEAD requests lead to endless 301, while GET is OK
506 'expected_warnings': ['301'],
510 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
514 'title': 'ŠŃ
Š¾ŃŃŠŗŠ¾Šµ Š¼Š¾ŃŠµ ŃŃŠ°Š»Š¾ ŃŠµŠ»ŠøŠŗŠ¾Š¼ ŃŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
515 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
519 'skip_download': True,
524 '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/',
528 'title': 'ŠŠ¾ŃŠŗŠ¾Š»ŃŠ½Š¾Šµ Š²Š¾ŃŠæŠøŃŠ°Š½ŠøŠµ',
533 'url': 'http://www.vestifinance.ru/articles/25753',
536 'title': 'ŠŃŃŠ¼ŃŠµ ŃŃŠ°Š½ŃŠ»ŃŃŠøŠø Ń Š¤Š¾ŃŃŠ¼Š°-Š²ŃŃŃŠ°Š²ŠŗŠø "ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
541 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 3',
547 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 2',
553 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 1',
559 'skip_download': True,
564 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
566 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
568 'title': 'Š£Š¶Š°ŃŃŠøŠŗŠø, ŃŃŃŃŠŗŠøŠ¹ ŃŃŠµŠ¹Š»ŠµŃ (2015)',
569 'thumbnail': r
're:^https?://.*\.jpg$',
575 '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',
578 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
580 'playlist_mincount': 7,
581 # This forum does not allow <iframe> syntaxes anymore
582 # Now HTML tags are displayed as-is
583 'skip': 'No videos on this page',
587 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
588 'md5': '65fdff94098e4a607385a60c5177c638',
592 'title': 'Hidden miracles of the natural world',
593 'uploader': 'Louie Schwartzberg',
594 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
597 # nowvideo embed hidden behind percent encoding
599 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
600 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
602 'id': '06e53103ca9aa',
604 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
605 'description': 'No description',
610 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
611 'md5': '7653032cbb25bf6c80d80f217055fa43',
613 'id': '048195-004_PLUS7-F',
616 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
617 'upload_date': '20140320',
620 'skip_download': 'Requires rtmpdump'
622 'skip': 'video gone',
626 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
630 'title': 'Alcaline, le concert avec Calogero',
631 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
632 'upload_date': '20150226',
633 'timestamp': 1424989860,
638 'skip_download': True,
640 'expected_warnings': [
646 'url': 'http://www.wired.com/2014/04/honda-asimo/',
647 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
649 'id': '53501be369702d3275860000',
651 'title': 'Hondaās New Asimo Robot Is More Human Than Ever',
656 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
657 'md5': '441aeeb82eb72c422c7f14ec533999cd',
659 'id': 'k2mm4bCdJ6CQ2i7c8o2',
661 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
662 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
664 'uploader_id': 'xgditw',
665 'upload_date': '20140425',
666 'timestamp': 1398441542,
668 'add_ie': ['Dailymotion'],
672 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
676 'title': 'The NBL Auction 2014',
677 'uploader': 'BADMINTON England',
678 'uploader_id': 'BADMINTONEvents',
679 'upload_date': '20140603',
680 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
682 'add_ie': ['Youtube'],
684 'skip_download': True,
689 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
690 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
692 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
694 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
695 'description': 'Two valets share their love for movie star Liam Neesons.',
696 'timestamp': 1349922600,
697 'upload_date': '20121011',
700 # YouTube embed via <data-embed-url="">
702 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
706 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
707 'uploader': 'Gameloft',
708 'uploader_id': 'gameloft',
709 'upload_date': '20140828',
710 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
713 'skip_download': True,
718 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
720 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
722 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
723 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
728 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
730 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
731 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
737 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
742 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
743 'md5': '9d65602bf31c6e20014319c7d07fba27',
745 'id': '5123ea6d5e5a7',
748 'uploader': 'www.handjobhub.com',
749 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
752 # Multiple brightcove videos
753 # https://github.com/rg3/youtube-dl/issues/2283
755 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
757 'id': 'always-never',
758 'title': 'Always / Never - The New Yorker',
762 'extract_flat': False,
763 'skip_download': True,
768 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
769 'md5': '96f09a37e44da40dd083e12d9a683327',
773 'title': 'Ump changes call to ball',
774 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
776 'timestamp': 1401537900,
777 'upload_date': '20140531',
778 'thumbnail': r
're:^https?://.*\.jpg$',
783 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
784 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
788 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
789 'description': 'a Paywall Videos video from Remilon',
791 'uploader': 'study.com',
792 'timestamp': 1459678540,
793 'upload_date': '20160403',
794 'filesize': 24687186,
798 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
799 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
803 'title': 'Conversation about Hexagonal Rails Part 1',
804 'description': 'a Martin Fowler video from ThoughtWorks',
806 'uploader': 'thoughtworks.wistia.com',
807 'timestamp': 1401832161,
808 'upload_date': '20140603',
811 # Wistia standard embed (async)
813 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
817 'title': 'Drip Brennan Dunn Workshop',
818 'description': 'a JV Webinars video from getdrip-1',
820 'timestamp': 1463607249,
821 'upload_date': '20160518',
824 'skip_download': True,
829 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
833 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
834 'uploader': 'Sophos Security',
835 'title': 'Chet Chat 171 - Oct 29, 2014',
836 'upload_date': '20141029',
839 # Soundcloud multiple embeds
841 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
844 'title': 'Guitar Essentials: Legato WorkoutāOne-Hour to Fluid Performance | TAB + AUDIO',
846 'playlist_mincount': 7,
848 # TuneIn station embed
850 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
855 'location': 'Paris, France',
860 'skip_download': True,
865 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
869 'upload_date': '20141112',
870 'title': 'Rosetta #CometLanding webcast HL 10',
873 # Another Livestream embed, without 'new.' in URL
875 'url': 'https://www.freespeech.org/',
879 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
883 'skip_download': True,
888 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
891 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
893 'playlist_mincount': 2,
897 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
901 'upload_date': '20141126',
902 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
907 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
909 'id': '730m_DandD_1901_512k',
911 'uploader': 'www.abc.net.au',
912 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
915 # embedded viddler video
917 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
921 'uploader': 'deadspin',
922 'title': 'WALL-TO-GORTAT',
923 'timestamp': 1422285291,
924 'upload_date': '20150126',
926 'add_ie': ['Viddler'],
930 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
934 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
935 'description': 'md5:601cb790edd05908957dae8aaa866465',
936 'upload_date': '20150220',
938 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
942 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
946 'upload_date': '20150212',
947 'uploader': 'The National Archives UK',
948 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
949 'uploader_id': 'NationalArchives08',
950 'title': 'Webinar: Using Discovery, The National Archivesā online catalogue',
955 'url': 'http://www.suffolk.edu/sjc/',
959 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
960 'uploader': 'www.suffolk.edu',
963 'skip_download': True,
968 'url': 'http://www.indiedb.com/games/king-machine/videos',
972 'title': 'king machine trailer 1',
973 'thumbnail': r
're:^https?://.*\.jpg$',
978 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
979 'playlist_mincount': 5,
981 'id': 'aanslagen-kopenhagen',
982 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
987 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
991 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
994 # Kaltura embed (different embed code)
996 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1000 'upload_date': '20150127',
1001 'uploader_id': 'PremierMedia',
1003 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1006 # Kaltura embed with single quotes
1008 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1013 'timestamp': 1355743100,
1014 'upload_date': '20121217',
1015 'uploader_id': 'batchUser',
1017 'add_ie': ['Kaltura'],
1020 # Kaltura embedded via quoted entry_id
1021 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1025 'title': '06_matthew_brender_raj_dutt',
1026 'timestamp': 1466638791,
1027 'upload_date': '20160622',
1029 'add_ie': ['Kaltura'],
1030 'expected_warnings': [
1031 'Could not send HEAD request'
1034 'skip_download': True,
1038 # Kaltura embedded, some fileExt broken (#11480)
1039 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1043 'title': 'Our "Standard Models" of particle physics and cosmology',
1044 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1045 'timestamp': 1321158993,
1046 'upload_date': '20111113',
1047 'uploader_id': 'kps1',
1049 'add_ie': ['Kaltura'],
1051 # Eagle.Platform embed (generic URL)
1053 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1054 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1058 'title': 'ŠŠ°Š²Š°Š»ŃŠ½ŃŠ¹ Š²ŃŃŠµŠ» Š½Š° ŃŠ²Š¾Š±Š¾Š“Ń',
1059 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1060 'thumbnail': r
're:^https?://.*\.jpg$',
1066 # ClipYou (Eagle.Platform) embed (custom URL)
1068 'url': 'http://muz-tv.ru/play/7129/',
1069 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1073 'title': "'O Sole Mio",
1074 'thumbnail': r
're:^https?://.*\.jpg$',
1081 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1085 'title': 'Š¢Š°Š¹Š½Ń ŠæŠµŃŠµŠ²Š°Š»Š° ŠŃŃŠ»Š¾Š²Š° ā¢ 1 ŃŠµŃŠøŃ 2 ŃŠ°ŃŃŃ',
1086 'description': 'ŠŠ¾ŠŗŃŠ¼ŠµŠ½ŃŠ°Š»ŃŠ½ŃŠ¹ ŃŠµŃŠøŠ°Š»-ŃŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· ŃŠ°Š¼ŃŃ
Š¶ŃŃŠŗŠøŃ
ŃŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1087 'thumbnail': r
're:^https?://.*\.jpg$',
1094 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1098 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1099 'thumbnail': r
're:^https?://.*\.png$',
1105 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1106 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1110 'title': 'Facebook Creates "On This Day" | Crunch Report',
1115 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1119 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1124 # Crooks and Liars embed
1126 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1130 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1131 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1132 'timestamp': 1428207000,
1133 'upload_date': '20150405',
1134 'uploader': 'Heather',
1137 # Crooks and Liars external embed
1139 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1141 'id': 'MTE3MjUtMzQ2MzA',
1143 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1144 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1145 'timestamp': 1265032391,
1146 'upload_date': '20100201',
1147 'uploader': 'Heather',
1150 # NBC Sports vplayer embed
1152 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1154 'id': 'ln7x1qSThw4k',
1156 'title': "PFT Live: New leader in the 'new-look' defense",
1157 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1158 'uploader': 'NBCU-SPORTS',
1159 'upload_date': '20140107',
1160 'timestamp': 1389118457,
1165 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1166 'md5': '1aa589c675898ae6d37a17913cf68d66',
1168 'id': '701714499682',
1170 'title': 'PREVIEW: On Assignment: David Letterman',
1171 '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.',
1176 'url': 'https://video.udn.com/news/300346',
1177 'md5': 'fd2060e988c326991037b9aff9df21a6',
1181 'title': 'äøäøäøē·åø«č®ę§ å
Øę ”åø«ēåęŗ',
1182 'thumbnail': r
're:^https?://.*\.jpg$',
1186 'skip_download': True,
1191 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1193 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1195 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1196 'title': 'This is what separates the Excel masters from the wannabes',
1197 'duration': 191.933,
1201 'skip_download': True,
1204 # Brightcove URL in single quotes
1206 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1207 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1209 'id': '4255764656001',
1211 'title': 'SN Presents: Russell Martin, World Citizen',
1212 'description': 'To understand why he was the Toronto Blue Jaysā 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.',
1213 'uploader': 'Rogers Sportsnet',
1214 'uploader_id': '1704050871',
1215 'upload_date': '20150525',
1216 'timestamp': 1432570283,
1219 # Dailymotion Cloud video
1221 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1222 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1226 'title': 'Sauvons les abeilles ! - Le dƩbat',
1227 'description': 'md5:d9082128b1c5277987825d684939ca26',
1228 'thumbnail': r
're:^https?://.*\.jpe?g$',
1229 'timestamp': 1434970506,
1230 'upload_date': '20150622',
1231 'uploader': 'Public SĆ©nat',
1232 'uploader_id': 'xa9gza',
1235 # OnionStudios embed
1237 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1241 'title': 'Donāt Understand Bitcoin? This Man Will Mumble An Explanation At You',
1242 'thumbnail': r
're:^https?://.*\.jpe?g$',
1243 'uploader': 'ClickHole',
1244 'uploader_id': 'clickhole',
1249 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1251 'id': '74849a00-85a9-11e1-9660-123139220831',
1253 'title': '#whilewewatch',
1256 # AdobeTVVideo embed
1258 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1259 'md5': '43662b577c018ad707a63766462b1e87',
1263 'title': 'New experience with Acrobat DC',
1264 'description': 'New experience with Acrobat DC',
1265 'duration': 248.667,
1268 # BrightcoveInPageEmbed embed
1270 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1272 'id': '4238694884001',
1274 'title': 'Tabletop: Dread, Last Thoughts',
1275 'description': 'Tabletop: Dread, Last Thoughts',
1279 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1280 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1282 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1284 'id': '4785848093001',
1286 'title': 'The Cardinal Pell Interview',
1287 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1288 'uploader': 'GlobeCast Australia - GlobeStream',
1289 'uploader_id': '2733773828001',
1290 'upload_date': '20160304',
1291 'timestamp': 1457083087,
1295 'skip_download': True,
1298 # Another form of arte.tv embed
1300 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1301 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1303 'id': '030273-562_PLUS7-F',
1305 'title': 'ARTE Reportage - Nulle part, en France',
1306 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1307 'upload_date': '20160409',
1312 'url': 'http://www.wykop.pl/link/3088787/',
1313 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1315 'id': '874_1459135191',
1317 'title': 'Man shows poor quality of new apartment building',
1318 'description': 'The wall is like a sand pile.',
1319 'uploader': 'Lake8737',
1322 # Duplicated embedded video URLs
1324 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1326 'id': '149298443_480_16c25b74_2',
1328 'title': 'vs. Blue Orange Spring Game',
1329 'uploader': 'www.hudl.com',
1332 # twitter:player:stream embed
1334 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1338 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1339 'uploader': 'www.rtl.be',
1343 'skip_download': True,
1346 # twitter:player embed
1348 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1349 'md5': 'a3e0df96369831de324f0778e126653c',
1351 'id': '4909620399001',
1353 'title': 'What Do Black Holes Sound Like?',
1354 'description': 'what do black holes sound like',
1355 'upload_date': '20160524',
1356 'uploader_id': '29913724001',
1357 'timestamp': 1464107587,
1358 'uploader': 'TheAtlantic',
1360 'add_ie': ['BrightcoveLegacy'],
1362 # Facebook <iframe> embed
1364 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1365 'md5': 'fbcde74f534176ecb015849146dd3aee',
1367 'id': '599637780109885',
1369 'title': 'Facebook video #599637780109885',
1372 # Facebook API embed
1374 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1375 'md5': 'a47372ee61b39a7b90287094d447d94e',
1377 'id': '10153467542406923',
1379 'title': 'Facebook video #10153467542406923',
1382 # Wordpress "YouTube Video Importer" plugin
1384 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1385 'md5': 'd16797741b560b485194eddda8121b48',
1387 'id': 'HNTXWDXV9Is',
1389 'title': 'Blue Devils Drumline Stanford lot 2016',
1390 'upload_date': '20160627',
1391 'uploader_id': 'GENOCIDE8GENERAL10',
1392 'uploader': 'cylus cyrus',
1396 # video stored on custom kaltura server
1397 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1398 'md5': '537617d06e64dfed891fa1593c4b30cc',
1402 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1403 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1404 'uploader_id': 'videos.expansion@el-mundo.net',
1405 'upload_date': '20150429',
1406 'timestamp': 1430303472,
1408 'add_ie': ['Kaltura'],
1411 # Non-standard Vimeo embed
1412 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1413 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1417 'title': 'Understanding the web - Teaser',
1418 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1419 'upload_date': '20151214',
1420 'uploader': 'OpenClassrooms',
1421 'uploader_id': 'openclassrooms',
1423 'add_ie': ['Vimeo'],
1426 # generic vimeo embed that requires original URL passed as Referer
1427 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1428 'only_matching': True,
1431 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1432 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1434 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1436 'title': 'Big Buck Bunny',
1437 'description': 'Royalty free test video',
1438 'timestamp': 1432816365,
1439 'upload_date': '20150528',
1443 'skip_download': True,
1445 'add_ie': [ArkenaIE
.ie_key()],
1448 '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/',
1452 'title': 'ŠŠ ŠŠŠ”ŠŖŠ ŠŠ¢ ŠŠŠ ŠŠ: ŠŠ·ŃŠøŃŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃŠ°Š½ŃŠøŃ Š² ŠŠ»Š¾Š²Š“ŠøŠ²',
1455 'skip_download': True,
1457 'add_ie': [Vbox7IE
.ie_key()],
1461 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1464 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1466 'playlist_mincount': 3,
1470 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1472 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1473 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1475 'playlist_mincount': 2,
1479 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1483 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1484 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1487 'skip_download': True,
1489 'add_ie': [TwentyMinutenIE
.ie_key()],
1493 'url': 'https://en.support.wordpress.com/videopress/',
1497 'title': 'IMG_5786',
1498 'timestamp': 1435711927,
1499 'upload_date': '20150701',
1502 'skip_download': True,
1504 'add_ie': [VideoPressIE
.ie_key()],
1508 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1510 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1512 'title': 'ŠŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠŠ°Š·Š°Š½Ń 2',
1513 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1514 'uploader': 'ŠŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1515 'upload_date': '20170228',
1516 'uploader_id': '996642',
1519 'skip_download': True,
1521 'add_ie': [RutubeIE
.ie_key()],
1524 # ThePlatform embedded with whitespaces in URLs
1525 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1526 'only_matching': True,
1529 # # TODO: find another test
1530 # # http://schema.org/VideoObject
1531 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1532 # 'md5': '888dcf08b7ea671381f00fab74692755',
1534 # 'id': 'nyvTSJMKId',
1536 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1537 # 'description': '#love for cats.',
1538 # 'timestamp': 1461244995,
1539 # 'upload_date': '20160421',
1542 # 'force_generic_extractor': True,
1547 def report_following_redirect(self
, new_url
):
1548 """Report information extraction."""
1549 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
1551 def _extract_rss(self
, url
, video_id
, doc
):
1552 playlist_title
= doc
.find('./channel/title').text
1553 playlist_desc_el
= doc
.find('./channel/description')
1554 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
1557 for it
in doc
.findall('./channel/item'):
1558 next_url
= xpath_text(it
, 'link', fatal
=False)
1560 enclosure_nodes
= it
.findall('./enclosure')
1561 for e
in enclosure_nodes
:
1562 next_url
= e
.attrib
.get('url')
1572 'title': it
.find('title').text
,
1576 '_type': 'playlist',
1578 'title': playlist_title
,
1579 'description': playlist_desc
,
1583 def _extract_camtasia(self
, url
, video_id
, webpage
):
1584 """ Returns None if no camtasia video can be found. """
1586 camtasia_cfg
= self
._search
_regex
(
1587 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1588 webpage
, 'camtasia configuration file', default
=None)
1589 if camtasia_cfg
is None:
1592 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
1594 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
1595 camtasia_cfg
= self
._download
_xml
(
1596 camtasia_url
, video_id
,
1597 note
='Downloading camtasia configuration',
1598 errnote
='Failed to download camtasia configuration')
1599 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
1602 for n
in fileset_node
.getchildren():
1603 url_n
= n
.find('./uri')
1608 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
1609 'title': '%s - %s' % (title
, n
.tag
),
1610 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
1611 'duration': float_or_none(n
.find('./duration').text
),
1615 '_type': 'playlist',
1620 def _real_extract(self
, url
):
1621 if url
.startswith('//'):
1624 'url': self
.http_scheme() + url
,
1627 parsed_url
= compat_urlparse
.urlparse(url
)
1628 if not parsed_url
.scheme
:
1629 default_search
= self
._downloader
.params
.get('default_search')
1630 if default_search
is None:
1631 default_search
= 'fixup_error'
1633 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
1635 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
1636 return self
.url_result('http://' + url
)
1637 elif default_search
!= 'fixup_error':
1638 if default_search
== 'auto_warning':
1639 if re
.match(r
'^(?:url|URL)$', url
):
1640 raise ExtractorError(
1641 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
1644 self
._downloader
.report_warning(
1645 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
1646 return self
.url_result('ytsearch:' + url
)
1648 if default_search
in ('error', 'fixup_error'):
1649 raise ExtractorError(
1650 '%r is not a valid URL. '
1651 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1652 % (url
, url
), expected
=True)
1654 if ':' not in default_search
:
1655 default_search
+= ':'
1656 return self
.url_result(default_search
+ url
)
1658 url
, smuggled_data
= unsmuggle_url(url
)
1659 force_videoid
= None
1660 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
1661 if smuggled_data
and 'force_videoid' in smuggled_data
:
1662 force_videoid
= smuggled_data
['force_videoid']
1663 video_id
= force_videoid
1665 video_id
= self
._generic
_id
(url
)
1667 self
.to_screen('%s: Requesting header' % video_id
)
1669 head_req
= HEADRequest(url
)
1670 head_response
= self
._request
_webpage
(
1672 note
=False, errnote
='Could not send HEAD request to %s' % url
,
1675 if head_response
is not False:
1676 # Check for redirect
1677 new_url
= head_response
.geturl()
1679 self
.report_following_redirect(new_url
)
1681 new_url
= smuggle_url(
1682 new_url
, {'force_videoid': force_videoid
})
1683 return self
.url_result(new_url
)
1685 full_response
= None
1686 if head_response
is False:
1687 request
= sanitized_Request(url
)
1688 request
.add_header('Accept-Encoding', '*')
1689 full_response
= self
._request
_webpage
(request
, video_id
)
1690 head_response
= full_response
1694 'title': self
._generic
_title
(url
),
1695 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
1698 # Check for direct link to a video
1699 content_type
= head_response
.headers
.get('Content-Type', '').lower()
1700 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
1702 format_id
= m
.group('format_id')
1703 if format_id
.endswith('mpegurl'):
1704 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1705 elif format_id
== 'f4m':
1706 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
1709 'format_id': m
.group('format_id'),
1711 'vcodec': 'none' if m
.group('type') == 'audio' else None
1713 info_dict
['direct'] = True
1714 self
._sort
_formats
(formats
)
1715 info_dict
['formats'] = formats
1718 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
1719 force
= self
._downloader
.params
.get('force_generic_extractor', False)
1720 self
._downloader
.report_warning(
1721 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
1723 if not full_response
:
1724 request
= sanitized_Request(url
)
1725 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1726 # making it impossible to download only chunk of the file (yet we need only 512kB to
1727 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1728 # that will always result in downloading the whole file that is not desirable.
1729 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1730 # to accept raw bytes and being able to download only a chunk.
1731 # It may probably better to solve this by checking Content-Type for application/octet-stream
1732 # after HEAD request finishes, but not sure if we can rely on this.
1733 request
.add_header('Accept-Encoding', '*')
1734 full_response
= self
._request
_webpage
(request
, video_id
)
1736 first_bytes
= full_response
.read(512)
1738 # Is it an M3U playlist?
1739 if first_bytes
.startswith(b
'#EXTM3U'):
1740 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1741 self
._sort
_formats
(info_dict
['formats'])
1744 # Maybe it's a direct link to a video?
1745 # Be careful not to download the whole thing!
1746 if not is_html(first_bytes
):
1747 self
._downloader
.report_warning(
1748 'URL could be a direct video link, returning it as such.')
1755 webpage
= self
._webpage
_read
_content
(
1756 full_response
, url
, video_id
, prefix
=first_bytes
)
1758 self
.report_extraction(video_id
)
1760 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1762 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
1763 if doc
.tag
== 'rss':
1764 return self
._extract
_rss
(url
, video_id
, doc
)
1765 elif doc
.tag
== 'SmoothStreamingMedia':
1766 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
1767 self
._sort
_formats
(info_dict
['formats'])
1769 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
1770 smil
= self
._parse
_smil
(doc
, url
, video_id
)
1771 self
._sort
_formats
(smil
['formats'])
1773 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
1774 return self
.playlist_result(self
._parse
_xspf
(doc
, video_id
), video_id
)
1775 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
1776 info_dict
['formats'] = self
._parse
_mpd
_formats
(
1778 mpd_base_url
=full_response
.geturl().rpartition('/')[0],
1780 self
._sort
_formats
(info_dict
['formats'])
1782 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
1783 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
1784 self
._sort
_formats
(info_dict
['formats'])
1786 except compat_xml_parse_error
:
1789 # Is it a Camtasia project?
1790 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
1791 if camtasia_res
is not None:
1794 # Sometimes embedded video player is hidden behind percent encoding
1795 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1796 # Unescaping the whole page allows to handle those cases in a generic way
1797 webpage
= compat_urllib_parse_unquote(webpage
)
1799 # it's tempting to parse this further, but you would
1800 # have to take into account all the variations like
1801 # Video Title - Site Name
1802 # Site Name | Video Title
1803 # Video Title - Tagline | Site Name
1804 # and so on and so forth; it's just not practical
1805 video_title
= self
._og
_search
_title
(
1806 webpage
, default
=None) or self
._html
_search
_regex
(
1807 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
1810 # Try to detect age limit automatically
1811 age_limit
= self
._rta
_search
(webpage
)
1812 # And then there are the jokers who advertise that they use RTA,
1813 # but actually don't.
1814 AGE_LIMIT_MARKERS
= [
1815 r
'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1817 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
1820 # video uploader is domain name
1821 video_uploader
= self
._search
_regex
(
1822 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
1824 video_description
= self
._og
_search
_description
(webpage
, default
=None)
1825 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
1828 def _playlist_from_matches(matches
, getter
=None, ie
=None):
1830 self
.url_result(self
._proto
_relative
_url
(getter(m
) if getter
else m
), ie
)
1832 return self
.playlist_result(
1833 urlrs
, playlist_id
=video_id
, playlist_title
=video_title
)
1835 # Look for Brightcove Legacy Studio embeds
1836 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
1838 self
.to_screen('Brightcove video detected.')
1841 'url': smuggle_url(bc_url
, {'Referer': url
}),
1842 'ie_key': 'BrightcoveLegacy'
1843 } for bc_url
in bc_urls
]
1846 '_type': 'playlist',
1847 'title': video_title
,
1852 # Look for Brightcove New Studio embeds
1853 bc_urls
= BrightcoveNewIE
._extract
_urls
(webpage
)
1855 return _playlist_from_matches(bc_urls
, ie
='BrightcoveNew')
1857 # Look for ThePlatform embeds
1858 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
1860 return _playlist_from_matches(tp_urls
, ie
='ThePlatform')
1862 # Look for Vessel embeds
1863 vessel_urls
= VesselIE
._extract
_urls
(webpage
)
1865 return _playlist_from_matches(vessel_urls
, ie
=VesselIE
.ie_key())
1867 # Look for embedded rtl.nl player
1868 matches
= re
.findall(
1869 r
'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1872 return _playlist_from_matches(matches
, ie
='RtlNl')
1874 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
1876 return _playlist_from_matches(vimeo_urls
, ie
=VimeoIE
.ie_key())
1878 vid_me_embed_url
= self
._search
_regex
(
1879 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1880 webpage, 'vid.me embed', default=None)
1881 if vid_me_embed_url is not None:
1882 return self.url_result(vid_me_embed_url, 'Vidme')
1884 # Look for embedded YouTube player
1885 matches = re.findall(r'''(?x)
1894 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1898 return _playlist_from_matches(
1899 matches, lambda m: unescapeHTML(m[1]))
1901 # Look for lazyYT YouTube embed
1902 matches = re.findall(
1903 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1905 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1907 # Look for Wordpress "YouTube Video Importer" plugin
1908 matches = re.findall(r'''(?x
)<div
[^
>]+
1909 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1910 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1912 return _playlist_from_matches(matches, lambda m: m[-1])
1914 matches = DailymotionIE._extract_urls(webpage)
1916 return _playlist_from_matches(matches)
1918 # Look for embedded Dailymotion playlist player (#3822)
1920 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}/widget
/jukebox
\?.+?
)\
1', webpage)
1922 playlists = re.findall(
1923 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
1925 return _playlist_from_matches(
1926 playlists, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
1928 # Look for embedded Wistia player
1930 r'<(?
:meta
[^
>]+?content|iframe
[^
>]+?src
)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1932 embed_url = self._proto_relative_url(
1933 unescapeHTML(match.group('url')))
1935 '_type': 'url_transparent',
1938 'uploader': video_uploader,
1941 match = re.search(r'(?:id=["\']wistia_|data
-wistia
-?
id=["\']|Wistia\.embed\(["\'])(?P
<id>[^
"\']+)', webpage)
1944 '_type': 'url_transparent',
1945 'url': 'wistia:%s' % match.group('id'),
1947 'uploader': video_uploader,
1952 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1953 <div[^>]+class=(["']).*?
\bwistia
_async
_(?P
<id>[a
-z0
-9]+)\b.*?\
2
1956 return self.url_result(self._proto_relative_url(
1957 'wistia:%s' % match.group('id')), 'Wistia')
1959 # Look for SVT player
1960 svt_url = SVTIE._extract_url(webpage)
1962 return self.url_result(svt_url, 'SVT')
1964 # Look for embedded condenast player
1965 matches = re.findall(
1966 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1970 '_type': 'playlist',
1973 'ie_key': 'CondeNast',
1975 } for ma in matches],
1976 'title': video_title,
1980 # Look for Bandcamp pages with custom domain
1981 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1982 if mobj is not None:
1983 burl = unescapeHTML(mobj.group(1))
1984 # Don't set the extractor because it can be a track url or an album
1985 return self.url_result(burl)
1987 # Look for embedded Vevo player
1989 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1990 if mobj is not None:
1991 return self.url_result(mobj.group('url'))
1993 # Look for embedded Viddler player
1995 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1997 if mobj is not None:
1998 return self.url_result(mobj.group('url'))
2000 # Look for NYTimes player
2002 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2004 if mobj is not None:
2005 return self.url_result(mobj.group('url'))
2007 # Look for Libsyn player
2009 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2010 if mobj is not None:
2011 return self.url_result(mobj.group('url'))
2013 # Look for Ooyala videos
2014 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2015 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2016 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2017 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2018 if mobj is not None:
2019 embed_token = self._search_regex(
2020 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2021 webpage, 'ooyala embed token', default=None)
2022 return OoyalaIE._build_url_result(smuggle_url(
2025 'embed_token': embed_token,
2028 # Look for multiple Ooyala embeds on SBN network websites
2029 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2030 if mobj is not None:
2031 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2033 return _playlist_from_matches(
2034 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2036 # Look for Aparat videos
2037 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2038 if mobj is not None:
2039 return self.url_result(mobj.group(1), 'Aparat')
2041 # Look for MPORA videos
2042 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2043 if mobj is not None:
2044 return self.url_result(mobj.group(1), 'Mpora')
2046 # Look for embedded NovaMov-based player
2048 r'''(?x
)<(?
:pagespeed_
)?iframe
[^
>]+?src
=(["\'])
2049 (?P<url>http://(?:(?:embed|www)\.)?
2051 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2052 videoweed\.(?:es|com)|
2053 movshare\.(?:net|sx|ag)|
2054 divxstage\.(?:eu|net|ch|co|at|ag))
2055 /embed\.php.+?)\1''', webpage)
2056 if mobj is not None:
2057 return self.url_result(mobj.group('url'))
2059 # Look for embedded Facebook player
2060 facebook_url = FacebookIE._extract_url(webpage)
2061 if facebook_url is not None:
2062 return self.url_result(facebook_url, 'Facebook')
2064 # Look for embedded VK player
2065 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://vk\
.com
/video_ext\
.php
.+?
)\
1', webpage)
2066 if mobj is not None:
2067 return self.url_result(mobj.group('url
'), 'VK
')
2069 # Look for embedded Odnoklassniki player
2070 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2071 if mobj is not None:
2072 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2074 # Look for embedded ivi player
2075 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
2076 if mobj is not None:
2077 return self.url_result(mobj.group('url
'), 'Ivi
')
2079 # Look for embedded Huffington Post player
2081 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2082 if mobj is not None:
2083 return self.url_result(mobj.group('url'), 'HuffPost')
2086 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
2087 if mobj is not None:
2088 return self.url_result(mobj.group('url'))
2089 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
2090 if mobj is not None:
2091 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2093 # Look for funnyordie embed
2094 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
2096 return _playlist_from_matches(
2097 matches, getter=unescapeHTML, ie='FunnyOrDie
')
2099 # Look for BBC iPlayer embed
2100 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
2102 return _playlist_from_matches(matches, ie='BBCCoUk
')
2104 # Look for embedded RUTV player
2105 rutv_url = RUTVIE._extract_url(webpage)
2107 return self.url_result(rutv_url, 'RUTV
')
2109 # Look for embedded TVC player
2110 tvc_url = TVCIE._extract_url(webpage)
2112 return self.url_result(tvc_url, 'TVC
')
2114 # Look for embedded SportBox player
2115 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2117 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed
')
2119 # Look for embedded XHamster player
2120 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2122 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed
')
2124 # Look for embedded TNAFlixNetwork player
2125 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2127 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2129 # Look for embedded PornHub player
2130 pornhub_urls = PornHubIE._extract_urls(webpage)
2132 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2134 # Look for embedded DrTuber player
2135 drtuber_urls = DrTuberIE._extract_urls(webpage)
2137 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2139 # Look for embedded RedTube player
2140 redtube_urls = RedTubeIE._extract_urls(webpage)
2142 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2144 # Look for embedded Tvigle player
2146 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2147 if mobj is not None:
2148 return self.url_result(mobj.group('url'), 'Tvigle')
2150 # Look for embedded TED player
2152 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
2153 if mobj is not None:
2154 return self.url_result(mobj.group('url
'), 'TED
')
2156 # Look for embedded Ustream videos
2157 ustream_url = UstreamIE._extract_url(webpage)
2159 return self.url_result(ustream_url, UstreamIE.ie_key())
2161 # Look for embedded arte.tv player
2163 r'<(?
:script|iframe
) [^
>]*?src
="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2165 if mobj is not None:
2166 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2168 # Look for embedded francetv player
2170 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
://)?embed\
.francetv\
.fr
/\?ue
=.+?
)\
1',
2172 if mobj is not None:
2173 return self.url_result(mobj.group('url
'))
2175 # Look for embedded smotri.com player
2176 smotri_url = SmotriIE._extract_url(webpage)
2178 return self.url_result(smotri_url, 'Smotri
')
2180 # Look for embedded Myvi.ru player
2181 myvi_url = MyviIE._extract_url(webpage)
2183 return self.url_result(myvi_url)
2185 # Look for embedded soundcloud player
2186 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2188 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2190 # Look for tunein player
2191 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2193 return _playlist_from_matches(tunein_urls)
2195 # Look for embedded mtvservices player
2196 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2198 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded
')
2200 # Look for embedded yahoo player
2202 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2204 if mobj is not None:
2205 return self.url_result(mobj.group('url'), 'Yahoo')
2207 # Look for embedded sbs.com.au player
2211 <meta\s+property="og
:video
"\s+content=|
2214 (["\'])(?P
<url
>https?
://(?
:www\
.)?sbs\
.com\
.au
/ondemand
/video
/.+?
)\
1''',
2216 if mobj is not None:
2217 return self.url_result(mobj.group('url'), 'SBS')
2219 # Look for embedded Cinchcast player
2221 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2223 if mobj is not None:
2224 return self.url_result(mobj.group('url'), 'Cinchcast')
2227 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2231 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2233 if mobj is not None:
2234 return self.url_result(mobj.group('url'), 'MLB')
2237 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2239 if mobj is not None:
2240 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2243 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2245 if mobj is not None:
2246 return self.url_result(mobj.group('url'), 'Livestream')
2248 # Look for Zapiks embed
2250 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2251 if mobj is not None:
2252 return self.url_result(mobj.group('url'), 'Zapiks')
2254 # Look for Kaltura embeds
2255 kaltura_url = KalturaIE._extract_url(webpage)
2257 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2259 # Look for Eagle.Platform embeds
2260 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2261 if eagleplatform_url:
2262 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2264 # Look for ClipYou (uses Eagle.Platform) embeds
2266 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2267 if mobj is not None:
2268 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2270 # Look for Pladform embeds
2271 pladform_url = PladformIE._extract_url(webpage)
2273 return self.url_result(pladform_url)
2275 # Look for Videomore embeds
2276 videomore_url = VideomoreIE._extract_url(webpage)
2278 return self.url_result(videomore_url)
2280 # Look for Webcaster embeds
2281 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2283 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2285 # Look for Playwire embeds
2287 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2288 if mobj is not None:
2289 return self.url_result(mobj.group('url'))
2291 # Look for 5min embeds
2293 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2294 if mobj is not None:
2295 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2297 # Look for Crooks and Liars embeds
2299 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2300 if mobj is not None:
2301 return self.url_result(mobj.group('url'))
2303 # Look for NBC Sports VPlayer embeds
2304 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2306 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2308 # Look for NBC News embeds
2309 nbc_news_embed_url = re.search(
2310 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2311 if nbc_news_embed_url:
2312 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2314 # Look for Google Drive embeds
2315 google_drive_url = GoogleDriveIE._extract_url(webpage)
2316 if google_drive_url:
2317 return self.url_result(google_drive_url, 'GoogleDrive')
2319 # Look for UDN embeds
2321 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2322 if mobj is not None:
2323 return self.url_result(
2324 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2326 # Look for Senate ISVP iframe
2327 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2329 return self.url_result(senate_isvp_url, 'SenateISVP')
2331 # Look for Dailymotion Cloud videos
2332 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2334 return self.url_result(dmcloud_url, 'DailymotionCloud')
2336 # Look for OnionStudios embeds
2337 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2338 if onionstudios_url:
2339 return self.url_result(onionstudios_url)
2341 # Look for ViewLift embeds
2342 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2344 return self.url_result(viewlift_url)
2346 # Look for JWPlatform embeds
2347 jwplatform_url = JWPlatformIE._extract_url(webpage)
2349 return self.url_result(jwplatform_url, 'JWPlatform')
2351 # Look for Digiteka embeds
2352 digiteka_url = DigitekaIE._extract_url(webpage)
2354 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2356 # Look for Arkena embeds
2357 arkena_url = ArkenaIE._extract_url(webpage)
2359 return self.url_result(arkena_url, ArkenaIE.ie_key())
2361 # Look for Piksel embeds
2362 piksel_url = PikselIE._extract_url(webpage)
2364 return self.url_result(piksel_url, PikselIE.ie_key())
2366 # Look for Limelight embeds
2367 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2371 'Channel': 'channel',
2372 'ChannelList': 'channel_list',
2374 return self.url_result(smuggle_url('limelight:%s:%s' % (
2375 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2376 'Limelight%s' % mobj.group(1), mobj.group(2))
2380 <object[^
>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2382 name=(["\'])flashVars\
2[^
>]+
2383 value
=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2386 return self.url_result(smuggle_url(
2387 'limelight:media:%s' % mobj.group('id'),
2388 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2390 # Look for AdobeTVVideo embeds
2392 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//video\
.tv\
.adobe\
.com
/v
/\d
+[^
"]+)[\'"]',
2394 if mobj is not None:
2395 return self.url_result(
2396 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2399 # Look for Vine embeds
2401 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2403 if mobj is not None:
2404 return self.url_result(
2405 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2407 # Look for VODPlatform embeds
2409 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?vod
-platform\
.net
/[eE
]mbed
/.+?
)\
1',
2411 if mobj is not None:
2412 return self.url_result(
2413 self._proto_relative_url(unescapeHTML(mobj.group('url
'))), 'VODPlatform
')
2415 # Look for Mangomolo embeds
2417 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2419 video\?.*?\bid=(?P<video_id>\d+)|
2420 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2421 ).+?)\1''', webpage)
2422 if mobj is not None:
2424 '_type
': 'url_transparent
',
2425 'url
': self._proto_relative_url(unescapeHTML(mobj.group('url
'))),
2426 'title
': video_title,
2427 'description
': video_description,
2428 'thumbnail
': video_thumbnail,
2429 'uploader
': video_uploader,
2431 video_id = mobj.group('video_id
')
2434 'ie_key
': 'MangomoloVideo
',
2439 'ie_key
': 'MangomoloLive
',
2440 'id': mobj.group('channel_id
'),
2444 # Look for Instagram embeds
2445 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2446 if instagram_embed_url is not None:
2447 return self.url_result(
2448 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2450 # Look for LiveLeak embeds
2451 liveleak_url = LiveLeakIE._extract_url(webpage)
2453 return self.url_result(liveleak_url, 'LiveLeak
')
2455 # Look for 3Q SDN embeds
2456 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2459 '_type
': 'url_transparent
',
2460 'ie_key
': ThreeQSDNIE.ie_key(),
2461 'url
': self._proto_relative_url(threeqsdn_url),
2462 'title
': video_title,
2463 'description
': video_description,
2464 'thumbnail
': video_thumbnail,
2465 'uploader
': video_uploader,
2468 # Look for VBOX7 embeds
2469 vbox7_url = Vbox7IE._extract_url(webpage)
2471 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2473 # Look for DBTV embeds
2474 dbtv_urls = DBTVIE._extract_urls(webpage)
2476 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2478 # Look for Videa embeds
2479 videa_urls = VideaIE._extract_urls(webpage)
2481 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2483 # Look for 20 minuten embeds
2484 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2486 return _playlist_from_matches(
2487 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2489 # Look for Openload embeds
2490 openload_urls = OpenloadIE._extract_urls(webpage)
2492 return _playlist_from_matches(
2493 openload_urls, ie=OpenloadIE.ie_key())
2495 # Look for VideoPress embeds
2496 videopress_urls = VideoPressIE._extract_urls(webpage)
2498 return _playlist_from_matches(
2499 videopress_urls, ie=VideoPressIE.ie_key())
2501 # Look for Rutube embeds
2502 rutube_urls = RutubeIE._extract_urls(webpage)
2504 return _playlist_from_matches(
2505 rutube_urls, ie=RutubeIE.ie_key())
2507 # Looking for http://schema.org/VideoObject
2508 json_ld = self._search_json_ld(
2509 webpage, video_id, default={}, expected_type='VideoObject
')
2510 if json_ld.get('url
'):
2512 'title
': video_title or info_dict['title
'],
2513 'description
': video_description,
2514 'thumbnail
': video_thumbnail,
2515 'age_limit
': age_limit
2517 info_dict.update(json_ld)
2520 # Look for HTML5 media
2521 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls
')
2523 for entry in entries:
2526 'title
': video_title,
2528 self._sort_formats(entry['formats
'])
2529 return self.playlist_result(entries)
2531 jwplayer_data_str = self._find_jwplayer_data(webpage)
2532 if jwplayer_data_str:
2534 jwplayer_data = self._parse_json(
2535 jwplayer_data_str, video_id, transform_source=js_to_json)
2536 return self._parse_jwplayer_data(jwplayer_data, video_id)
2537 except ExtractorError:
2540 def check_video(vurl):
2541 if YoutubeIE.suitable(vurl):
2543 if RtmpIE.suitable(vurl):
2545 vpath = compat_urlparse.urlparse(vurl).path
2546 vext = determine_ext(vpath)
2547 return '.' in vpath and vext not in ('swf
', 'png
', 'jpg
', 'srt
', 'sbv
', 'sub
', 'vtt
', 'ttml
', 'js
')
2549 def filter_video(urls):
2550 return list(filter(check_video, urls))
2552 # Start with something easy: JW Player in SWFObject
2553 found = filter_video(re.findall(r'flashvars
: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2555 # Look for gorilla-vid style embedding
2556 found = filter_video(re.findall(r'''(?sx)
2560 jwplayer\s*\(\s*["'][^
'"]+["']\s
*\
)\s
*\
.setup
2563 ['"]?file['"]?\s*:\s*["\'](.*?
)["\']''', webpage))
2565 # Broaden the search a little bit
2566 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2568 # Broaden the findall a little bit: JWPlayer JS loader
2569 found = filter_video(re.findall(
2570 r'[^A
-Za
-z0
-9]?
(?
:file|video_url
)["\']?:\s*["\'](http(?
![^
\'"]+\.[0-9]+[\'"])[^
\'"]+)["\']', webpage))
2573 found = filter_video(re.findall(r'''(?xs)
2574 flowplayer\("[^"]+",\s*
2576 \s*\{[^}]+? ["']?clip
["']?\s*:\s*\{\s*
2577 ["']?url["']?\s
*:\s
*["']([^"']+)["']
2582 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2584 # Try to find twitter cards info
2585 # twitter:player:stream should be checked before twitter:player since
2586 # it is expected to contain a raw stream (see
2587 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2588 found = filter_video(re.findall(
2589 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2591 # We look for Open Graph info:
2592 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2593 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2594 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2595 if m_video_type is not None:
2596 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2598 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2600 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2601 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2604 # Look also in Refresh HTTP header
2605 refresh_header = head_response.headers.get('Refresh')
2607 # In python 2 response HTTP headers are bytestrings
2608 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2609 refresh_header = refresh_header.decode('iso-8859-1')
2610 found = re.search(REDIRECT_REGEX, refresh_header)
2612 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2613 self.report_following_redirect(new_url)
2620 # twitter:player is a https URL to iframe player that may or may not
2621 # be supported by youtube-dl thus this is checked the very last (see
2622 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2623 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2625 return self.url_result(embed_url)
2628 raise UnsupportedError(url)
2631 for video_url in orderedSet(found):
2632 video_url = unescapeHTML(video_url)
2633 video_url = video_url.replace('\\/', '/')
2634 video_url = compat_urlparse.urljoin(url, video_url)
2635 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2637 # Sometimes, jwplayer extraction will result in a YouTube URL
2638 if YoutubeIE.suitable(video_url):
2639 entries.append(self.url_result(video_url, 'Youtube'))
2642 # here's a fun little line of code for you:
2643 video_id = os.path.splitext(video_id)[0]
2647 'uploader': video_uploader,
2648 'title': video_title,
2649 'age_limit': age_limit,
2652 if RtmpIE.suitable(video_url):
2653 entry_info_dict.update({
2654 '_type': 'url_transparent',
2655 'ie_key': RtmpIE.ie_key(),
2658 entries.append(entry_info_dict)
2661 ext = determine_ext(video_url)
2663 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2665 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2667 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2669 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2671 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2672 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2673 # Just matching .ism/manifest is not enough to be reliably sure
2674 # whether it's actually an ISM manifest or some other streaming
2675 # manifest since there are various streaming URL formats
2676 # possible (see [1]) as well as some other shenanigans like
2677 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2679 # Thus the most reasonable way to solve this is to delegate
2680 # to generic extractor in order to look into the contents of
2681 # the manifest itself.
2682 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2683 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2684 entry_info_dict = self.url_result(
2685 smuggle_url(video_url, {'to_generic': True}),
2688 entry_info_dict['url'] = video_url
2690 if entry_info_dict.get('formats'):
2691 self._sort_formats(entry_info_dict['formats'])
2693 entries.append(entry_info_dict)
2695 if len(entries) == 1:
2698 for num, e in enumerate(entries, start=1):
2699 # 'url' results don't have a title
2700 if e.get('title') is not None:
2701 e['title'] = '%s (%d)' % (e['title'], num)
2703 '_type': 'playlist',