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
88 from .limelight import LimelightBaseIE
89 from .anvato import AnvatoIE
92 class GenericIE(InfoExtractor):
93 IE_DESC = 'Generic downloader that works on some sites'
97 # Direct link to a video
99 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
100 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
105 'upload_date': '20100513',
108 # Direct link to media delivered compressed (until Accept-Encoding is *)
110 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
111 'md5': '128c42e68b13950268b648275386fc74',
113 'id': 'FictionJunction-Parallel_Hearts',
115 'title': 'FictionJunction-Parallel_Hearts',
116 'upload_date': '20140522',
118 'expected_warnings': [
119 'URL could be a direct video link, returning it as such.'
121 'skip': 'URL invalid',
123 # Direct download with broken HEAD
125 'url': 'http://ai-radio.org:8000/radio.opus',
132 'skip_download': True, # infinite live stream
134 'expected_warnings': [
135 r'501.*Not Implemented',
139 # Direct link with incorrect MIME type
141 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
142 'md5': '4ccbebe5f36706d85221f204d7eb5913',
144 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
145 'id': '5_Lennart_Poettering_-_Systemd',
147 'title': '5_Lennart_Poettering_-_Systemd',
148 'upload_date': '20141120',
150 'expected_warnings': [
151 'URL could be a direct video link, returning it as such.'
156 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
158 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
159 'title': 'Zero Punctuation',
160 'description': 're:.*groundbreaking video review series.*'
162 'playlist_mincount': 11,
164 # RSS feed with enclosure
166 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
168 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
170 'upload_date': '20150228',
171 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
174 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
176 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
180 'title': 'Automatics, robotics and biocybernetics',
181 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
182 'upload_date': '20130627',
183 'formats': 'mincount:16',
184 'subtitles': 'mincount:1',
187 'force_generic_extractor': True,
188 'skip_download': True,
191 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
193 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
198 'formats': 'mincount:1',
201 'skip_download': True,
204 # SMIL from https://www.restudy.dk/video/play/id/1637
206 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
210 'title': 'video_1637',
211 'formats': 'mincount:3',
214 'skip_download': True,
217 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
219 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
221 'id': 'smil-service',
223 'title': 'smil-service',
224 'formats': 'mincount:1',
227 'skip_download': True,
230 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
232 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
236 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
237 'formats': 'mincount:3',
240 'skip_download': True,
243 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
245 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
247 'id': 'mZlp2ctYIUEB',
249 'title': 'Tikibad ontruimd wegens brand',
250 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
251 'thumbnail': r're:^https?://.*\.jpg$',
255 'skip_download': True,
258 # MPD from http://dash-mse-test.appspot.com/media.html
260 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
261 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
263 'id': 'car-20120827-manifest',
265 'title': 'car-20120827-manifest',
266 'formats': 'mincount:9',
267 'upload_date': '20130904',
270 'format': 'bestvideo',
273 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
275 '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',
280 'formats': 'mincount:8',
284 'skip_download': True,
286 'skip': 'video gone',
288 # m3u8 served with Content-Type: text/plain
290 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
295 'upload_date': '20140720',
296 'formats': 'mincount:11',
300 'skip_download': True,
302 'skip': 'video gone',
306 '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',
310 'upload_date': '20130224',
311 'uploader_id': 'TheVerge',
312 'description': r're:^Chris Ziegler takes a look at the\.*',
313 'uploader': 'The Verge',
314 'title': 'First Firefox OS phones side-by-side',
317 'skip_download': False,
321 # redirect in Refresh HTTP header
322 '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',
326 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
327 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
328 'upload_date': '20150917',
329 'uploader_id': 'brtvofficial',
330 'uploader': 'Boiler Room',
333 'skip_download': False,
337 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
338 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
340 'id': '13601338388002',
342 'uploader': 'www.hodiho.fr',
343 'title': 'R\u00e9gis plante sa Jeep',
346 # bandcamp page with custom domain
348 'add_ie': ['Bandcamp'],
349 'url': 'http://bronyrock.com/track/the-pony-mash',
353 'title': 'The Pony Mash',
354 'uploader': 'M_Pallante',
356 'skip': 'There is a limit of 200 free downloads / month for the test song',
359 # embedded brightcove video
360 # it also tests brightcove videos that need to set the 'Referer'
361 # in the http requests
362 'add_ie': ['BrightcoveLegacy'],
363 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
365 'id': '2765128793001',
367 'title': 'Le cours de bourse : l’analyse technique',
368 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
369 'uploader': 'BFM BUSINESS',
372 'skip_download': True,
376 # embedded with itemprop embedURL and video id spelled as `idVideo`
377 'add_id': ['BrightcoveLegacy'],
378 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
380 'id': '5255628253001',
382 'title': 'md5:37c519b1128915607601e75a87995fc0',
383 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
384 'uploader': 'BFM BUSINESS',
385 'uploader_id': '876450612001',
386 'timestamp': 1482255315,
387 'upload_date': '20161220',
390 'skip_download': True,
394 # https://github.com/rg3/youtube-dl/issues/2253
395 'url': 'http://bcove.me/i6nfkrc3',
396 'md5': '0ba9446db037002366bab3b3eb30c88c',
398 'id': '3101154703001',
400 'title': 'Still no power',
401 'uploader': 'thestar.com',
402 '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.',
404 'add_ie': ['BrightcoveLegacy'],
405 'skip': 'video gone',
408 'url': 'http://www.championat.com/video/football/v/87/87499.html',
409 'md5': 'fb973ecf6e4a78a67453647444222983',
411 'id': '3414141473001',
413 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
414 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
415 'uploader': 'Championat',
419 # https://github.com/rg3/youtube-dl/issues/3541
420 'add_ie': ['BrightcoveLegacy'],
421 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
423 'id': '3866516442001',
425 'title': 'Leer mij vrouwen kennen: Aflevering 1',
426 'description': 'Leer mij vrouwen kennen: Aflevering 1',
427 'uploader': 'SBS Broadcasting',
429 'skip': 'Restricted to Netherlands',
431 'skip_download': True, # m3u8 download
435 # Brightcove video in <iframe>
436 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
437 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
439 'id': '5360463607001',
441 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
442 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
443 'uploader': 'United Nations',
444 'uploader_id': '1362235914001',
445 'timestamp': 1489593889,
446 'upload_date': '20170315',
448 'add_ie': ['BrightcoveLegacy'],
451 # Brightcove with alternative playerID key
452 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
454 'id': 'nmeth.2062_SV1',
455 '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',
459 'id': '2228375078001',
461 'title': 'nmeth.2062-sv1',
462 'description': 'nmeth.2062-sv1',
463 'timestamp': 1363357591,
464 'upload_date': '20130315',
465 'uploader': 'Nature Publishing Group',
466 'uploader_id': '1964492299001',
471 # Brightcove with UUID in videoPlayer
472 'url': 'http://www8.hp.com/cn/zh/home.html',
474 'id': '5255815316001',
476 'title': 'Sprocket Video - China',
477 'description': 'Sprocket Video - China',
478 'uploader': 'HP-Video Gallery',
479 'timestamp': 1482263210,
480 'upload_date': '20161220',
481 'uploader_id': '1107601872001',
484 'skip_download': True, # m3u8 download
486 'skip': 'video rotates...weekly?',
489 # Brightcove:new type [2].
490 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
491 'md5': '2b35148fcf48da41c9fb4591650784f3',
493 'id': '5348741021001',
495 'upload_date': '20170306',
496 'uploader_id': '4191638492001',
497 'timestamp': 1488769918,
498 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
503 # Alternative brightcove <video> attributes
504 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
506 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
507 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
510 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
512 'id': '5311302538001',
514 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
515 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
516 'timestamp': 1486321708,
517 'upload_date': '20170205',
518 'uploader_id': '800000640001',
520 'only_matching': True,
524 # Brightcove with UUID in videoPlayer
525 'url': 'http://www8.hp.com/cn/zh/home.html',
527 'id': '5255815316001',
529 'title': 'Sprocket Video - China',
530 'description': 'Sprocket Video - China',
531 'uploader': 'HP-Video Gallery',
532 'timestamp': 1482263210,
533 'upload_date': '20161220',
534 'uploader_id': '1107601872001',
537 'skip_download': True, # m3u8 download
542 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
543 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
545 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
547 'title': '2cc213299525360.mov', # that's what we get
550 'add_ie': ['Ooyala'],
553 # ooyala video embedded with http://player.ooyala.com/iframe.js
554 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
556 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
558 'title': '"Steve Jobs: Man in the Machine" trailer',
559 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
563 'skip_download': True,
565 'skip': 'movie expired',
569 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
573 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
574 'upload_date': '20140225',
575 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
576 'uploader': 'Tested',
577 'uploader_id': 'testedcom',
579 # No need to test YoutubeIE here
581 'skip_download': True,
586 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
590 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
591 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
593 # HEAD requests lead to endless 301, while GET is OK
594 'expected_warnings': ['301'],
598 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
602 'title': 'Охотское море стало целиком российским',
603 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
607 'skip_download': True,
612 '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/',
616 'title': 'Дошкольное воспитание',
621 'url': 'http://www.vestifinance.ru/articles/25753',
624 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
629 'title': 'Госзаказ. День 3',
635 'title': 'Госзаказ. День 2',
641 'title': 'Госзаказ. День 1',
647 'skip_download': True,
652 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
654 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
656 'title': 'Ужастики, русский трейлер (2015)',
657 'thumbnail': r're:^https?://.*\.jpg$',
663 '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',
666 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
668 'playlist_mincount': 7,
669 # This forum does not allow <iframe> syntaxes anymore
670 # Now HTML tags are displayed as-is
671 'skip': 'No videos on this page',
675 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
676 'md5': '65fdff94098e4a607385a60c5177c638',
680 'title': 'Hidden miracles of the natural world',
681 'uploader': 'Louie Schwartzberg',
682 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
685 # nowvideo embed hidden behind percent encoding
687 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
688 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
690 'id': '06e53103ca9aa',
692 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
693 'description': 'No description',
698 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
699 'md5': '7653032cbb25bf6c80d80f217055fa43',
701 'id': '048195-004_PLUS7-F',
704 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
705 'upload_date': '20140320',
708 'skip_download': 'Requires rtmpdump'
710 'skip': 'video gone',
714 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
718 'title': 'Alcaline, le concert avec Calogero',
719 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
720 'upload_date': '20150226',
721 'timestamp': 1424989860,
726 'skip_download': True,
728 'expected_warnings': [
734 'url': 'http://www.wired.com/2014/04/honda-asimo/',
735 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
737 'id': '53501be369702d3275860000',
739 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
744 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
745 'md5': '441aeeb82eb72c422c7f14ec533999cd',
747 'id': 'k2mm4bCdJ6CQ2i7c8o2',
749 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
750 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
752 'uploader_id': 'xgditw',
753 'upload_date': '20140425',
754 'timestamp': 1398441542,
756 'add_ie': ['Dailymotion'],
760 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
764 'title': 'The NBL Auction 2014',
765 'uploader': 'BADMINTON England',
766 'uploader_id': 'BADMINTONEvents',
767 'upload_date': '20140603',
768 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
770 'add_ie': ['Youtube'],
772 'skip_download': True,
777 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
778 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
780 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
782 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
783 'description': 'Two valets share their love for movie star Liam Neesons.',
784 'timestamp': 1349922600,
785 'upload_date': '20121011',
788 # YouTube embed via <data-embed-url="">
790 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
794 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
795 'uploader': 'Gameloft',
796 'uploader_id': 'gameloft',
797 'upload_date': '20140828',
798 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
801 'skip_download': True,
804 # YouTube <object> embed
806 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
807 'md5': '516718101ec834f74318df76259fb3cc',
811 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
812 'upload_date': '20080526',
813 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
814 'uploader': 'Christopher Sykes',
815 'uploader_id': 'ChristopherJSykes',
817 'add_ie': ['Youtube'],
821 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
823 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
825 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
826 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
831 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
833 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
834 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
840 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
845 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
846 'md5': '9d65602bf31c6e20014319c7d07fba27',
848 'id': '5123ea6d5e5a7',
851 'uploader': 'www.handjobhub.com',
852 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
855 # Multiple brightcove videos
856 # https://github.com/rg3/youtube-dl/issues/2283
858 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
860 'id': 'always-never',
861 'title': 'Always / Never - The New Yorker',
865 'extract_flat': False,
866 'skip_download': True,
871 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
872 'md5': '96f09a37e44da40dd083e12d9a683327',
876 'title': 'Ump changes call to ball',
877 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
879 'timestamp': 1401537900,
880 'upload_date': '20140531',
881 'thumbnail': r're:^https?://.*\.jpg$',
886 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
887 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
891 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
892 'description': 'a Paywall Videos video from Remilon',
894 'uploader': 'study.com',
895 'timestamp': 1459678540,
896 'upload_date': '20160403',
897 'filesize': 24687186,
901 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
902 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
906 'title': 'Conversation about Hexagonal Rails Part 1',
907 'description': 'a Martin Fowler video from ThoughtWorks',
909 'uploader': 'thoughtworks.wistia.com',
910 'timestamp': 1401832161,
911 'upload_date': '20140603',
914 # Wistia standard embed (async)
916 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
920 'title': 'Drip Brennan Dunn Workshop',
921 'description': 'a JV Webinars video from getdrip-1',
923 'timestamp': 1463607249,
924 'upload_date': '20160518',
927 'skip_download': True,
932 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
936 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
937 'uploader': 'Sophos Security',
938 'title': 'Chet Chat 171 - Oct 29, 2014',
939 'upload_date': '20141029',
942 # Soundcloud multiple embeds
944 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
947 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
949 'playlist_mincount': 7,
951 # TuneIn station embed
953 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
958 'location': 'Paris, France',
963 'skip_download': True,
968 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
972 'upload_date': '20141112',
973 'title': 'Rosetta #CometLanding webcast HL 10',
976 # Another Livestream embed, without 'new.' in URL
978 'url': 'https://www.freespeech.org/',
982 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
986 'skip_download': True,
991 'url': 'https://skiplagged.com/',
994 'title': 'Skiplagged: The smart way to find cheap flights',
996 'playlist_mincount': 1,
997 'add_ie': ['Youtube'],
1001 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1005 'upload_date': '20141126',
1006 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1011 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1013 'id': '730m_DandD_1901_512k',
1015 'uploader': 'www.abc.net.au',
1016 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1019 # embedded viddler video
1021 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1025 'uploader': 'deadspin',
1026 'title': 'WALL-TO-GORTAT',
1027 'timestamp': 1422285291,
1028 'upload_date': '20150126',
1030 'add_ie': ['Viddler'],
1034 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1038 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1039 'description': 'md5:601cb790edd05908957dae8aaa866465',
1040 'upload_date': '20150220',
1042 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1046 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1048 'id': 'Mrj4DVp2zeA',
1050 'upload_date': '20150212',
1051 'uploader': 'The National Archives UK',
1052 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1053 'uploader_id': 'NationalArchives08',
1054 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1059 'url': 'http://www.suffolk.edu/sjc/',
1063 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1064 'uploader': 'www.suffolk.edu',
1067 'skip_download': True,
1072 'url': 'http://www.indiedb.com/games/king-machine/videos',
1076 'title': 'king machine trailer 1',
1077 'thumbnail': r're:^https?://.*\.jpg$',
1081 # JWPlayer config passed as variable
1082 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1086 'title': 'ARIELE | Tube Cup',
1087 'uploader': 'www.txxx.com',
1091 'skip_download': True,
1096 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1097 'playlist_mincount': 5,
1099 'id': 'aanslagen-kopenhagen',
1100 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1105 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1109 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1112 # Kaltura embed (different embed code)
1114 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1118 'upload_date': '20150127',
1119 'uploader_id': 'PremierMedia',
1121 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1124 # Kaltura embed with single quotes
1126 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1131 'timestamp': 1355743100,
1132 'upload_date': '20121217',
1133 'uploader_id': 'batchUser',
1135 'add_ie': ['Kaltura'],
1138 # Kaltura embedded via quoted entry_id
1139 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1143 'title': '06_matthew_brender_raj_dutt',
1144 'timestamp': 1466638791,
1145 'upload_date': '20160622',
1147 'add_ie': ['Kaltura'],
1148 'expected_warnings': [
1149 'Could not send HEAD request'
1152 'skip_download': True,
1156 # Kaltura embedded, some fileExt broken (#11480)
1157 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1161 'title': 'Our "Standard Models" of particle physics and cosmology',
1162 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1163 'timestamp': 1321158993,
1164 'upload_date': '20111113',
1165 'uploader_id': 'kps1',
1167 'add_ie': ['Kaltura'],
1170 # Kaltura iframe embed
1171 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1172 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1176 'title': 'I. M. Pei: A Centennial Celebration',
1177 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1178 'upload_date': '20170403',
1179 'uploader_id': 'batchUser',
1180 'timestamp': 1491232186,
1182 'add_ie': ['Kaltura'],
1184 # Eagle.Platform embed (generic URL)
1186 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1187 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1191 'title': 'Навальный вышел на свободу',
1192 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1193 'thumbnail': r're:^https?://.*\.jpg$',
1199 # ClipYou (Eagle.Platform) embed (custom URL)
1201 'url': 'http://muz-tv.ru/play/7129/',
1202 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1206 'title': "'O Sole Mio",
1207 'thumbnail': r're:^https?://.*\.jpg$',
1214 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1218 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1219 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1220 'thumbnail': r're:^https?://.*\.jpg$',
1227 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1231 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1232 'thumbnail': r're:^https?://.*\.png$',
1238 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1239 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1243 'title': 'Facebook Creates "On This Day" | Crunch Report',
1248 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1252 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1257 # Crooks and Liars embed
1259 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1263 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1264 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1265 'timestamp': 1428207000,
1266 'upload_date': '20150405',
1267 'uploader': 'Heather',
1270 # Crooks and Liars external embed
1272 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1274 'id': 'MTE3MjUtMzQ2MzA',
1276 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1277 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1278 'timestamp': 1265032391,
1279 'upload_date': '20100201',
1280 'uploader': 'Heather',
1283 # NBC Sports vplayer embed
1285 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1287 'id': 'ln7x1qSThw4k',
1289 'title': "PFT Live: New leader in the 'new-look' defense",
1290 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1291 'uploader': 'NBCU-SPORTS',
1292 'upload_date': '20140107',
1293 'timestamp': 1389118457,
1298 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1299 'md5': '1aa589c675898ae6d37a17913cf68d66',
1301 'id': '701714499682',
1303 'title': 'PREVIEW: On Assignment: David Letterman',
1304 '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.',
1309 'url': 'https://video.udn.com/news/300346',
1310 'md5': 'fd2060e988c326991037b9aff9df21a6',
1314 'title': '中一中男師變性 全校師生力挺',
1315 'thumbnail': r're:^https?://.*\.jpg$',
1319 'skip_download': True,
1324 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1326 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1328 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1329 'title': 'This is what separates the Excel masters from the wannabes',
1330 'duration': 191.933,
1334 'skip_download': True,
1337 # Brightcove URL in single quotes
1339 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1340 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1342 'id': '4255764656001',
1344 'title': 'SN Presents: Russell Martin, World Citizen',
1345 '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.',
1346 'uploader': 'Rogers Sportsnet',
1347 'uploader_id': '1704050871',
1348 'upload_date': '20150525',
1349 'timestamp': 1432570283,
1352 # Dailymotion Cloud video
1354 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1355 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1359 'title': 'Sauvons les abeilles ! - Le débat',
1360 'description': 'md5:d9082128b1c5277987825d684939ca26',
1361 'thumbnail': r're:^https?://.*\.jpe?g$',
1362 'timestamp': 1434970506,
1363 'upload_date': '20150622',
1364 'uploader': 'Public Sénat',
1365 'uploader_id': 'xa9gza',
1368 # OnionStudios embed
1370 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1374 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1375 'thumbnail': r're:^https?://.*\.jpe?g$',
1376 'uploader': 'ClickHole',
1377 'uploader_id': 'clickhole',
1382 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1384 'id': '74849a00-85a9-11e1-9660-123139220831',
1386 'title': '#whilewewatch',
1389 # AdobeTVVideo embed
1391 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1392 'md5': '43662b577c018ad707a63766462b1e87',
1396 'title': 'New experience with Acrobat DC',
1397 'description': 'New experience with Acrobat DC',
1398 'duration': 248.667,
1401 # BrightcoveInPageEmbed embed
1403 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1405 'id': '4238694884001',
1407 'title': 'Tabletop: Dread, Last Thoughts',
1408 'description': 'Tabletop: Dread, Last Thoughts',
1412 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1413 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1415 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1417 'id': '4785848093001',
1419 'title': 'The Cardinal Pell Interview',
1420 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1421 'uploader': 'GlobeCast Australia - GlobeStream',
1422 'uploader_id': '2733773828001',
1423 'upload_date': '20160304',
1424 'timestamp': 1457083087,
1428 'skip_download': True,
1431 # Another form of arte.tv embed
1433 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1434 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1436 'id': '030273-562_PLUS7-F',
1438 'title': 'ARTE Reportage - Nulle part, en France',
1439 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1440 'upload_date': '20160409',
1445 'url': 'http://www.wykop.pl/link/3088787/',
1446 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1448 'id': '874_1459135191',
1450 'title': 'Man shows poor quality of new apartment building',
1451 'description': 'The wall is like a sand pile.',
1452 'uploader': 'Lake8737',
1455 # Duplicated embedded video URLs
1457 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1459 'id': '149298443_480_16c25b74_2',
1461 'title': 'vs. Blue Orange Spring Game',
1462 'uploader': 'www.hudl.com',
1465 # twitter:player:stream embed
1467 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1471 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1472 'uploader': 'www.rtl.be',
1476 'skip_download': True,
1479 # twitter:player embed
1481 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1482 'md5': 'a3e0df96369831de324f0778e126653c',
1484 'id': '4909620399001',
1486 'title': 'What Do Black Holes Sound Like?',
1487 'description': 'what do black holes sound like',
1488 'upload_date': '20160524',
1489 'uploader_id': '29913724001',
1490 'timestamp': 1464107587,
1491 'uploader': 'TheAtlantic',
1493 'add_ie': ['BrightcoveLegacy'],
1495 # Facebook <iframe> embed
1497 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1498 'md5': 'fbcde74f534176ecb015849146dd3aee',
1500 'id': '599637780109885',
1502 'title': 'Facebook video #599637780109885',
1505 # Facebook API embed
1507 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1508 'md5': 'a47372ee61b39a7b90287094d447d94e',
1510 'id': '10153467542406923',
1512 'title': 'Facebook video #10153467542406923',
1515 # Wordpress "YouTube Video Importer" plugin
1517 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1518 'md5': 'd16797741b560b485194eddda8121b48',
1520 'id': 'HNTXWDXV9Is',
1522 'title': 'Blue Devils Drumline Stanford lot 2016',
1523 'upload_date': '20160627',
1524 'uploader_id': 'GENOCIDE8GENERAL10',
1525 'uploader': 'cylus cyrus',
1529 # video stored on custom kaltura server
1530 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1531 'md5': '537617d06e64dfed891fa1593c4b30cc',
1535 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1536 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1537 'uploader_id': 'videos.expansion@el-mundo.net',
1538 'upload_date': '20150429',
1539 'timestamp': 1430303472,
1541 'add_ie': ['Kaltura'],
1544 # Non-standard Vimeo embed
1545 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1546 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1550 'title': 'Understanding the web - Teaser',
1551 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1552 'upload_date': '20151214',
1553 'uploader': 'OpenClassrooms',
1554 'uploader_id': 'openclassrooms',
1556 'add_ie': ['Vimeo'],
1559 # generic vimeo embed that requires original URL passed as Referer
1560 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1561 'only_matching': True,
1564 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1565 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1567 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1569 'title': 'Big Buck Bunny',
1570 'description': 'Royalty free test video',
1571 'timestamp': 1432816365,
1572 'upload_date': '20150528',
1576 'skip_download': True,
1578 'add_ie': [ArkenaIE.ie_key()],
1581 '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/',
1585 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1588 'skip_download': True,
1590 'add_ie': [Vbox7IE.ie_key()],
1594 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1597 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1599 'playlist_mincount': 3,
1603 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1605 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1606 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1608 'playlist_mincount': 2,
1612 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1616 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1617 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1620 'skip_download': True,
1622 'add_ie': [TwentyMinutenIE.ie_key()],
1626 'url': 'https://en.support.wordpress.com/videopress/',
1630 'title': 'IMG_5786',
1631 'timestamp': 1435711927,
1632 'upload_date': '20150701',
1635 'skip_download': True,
1637 'add_ie': [VideoPressIE.ie_key()],
1641 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1643 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1645 'title': 'Магаззино: Казань 2',
1646 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1647 'uploader': 'Магаззино',
1648 'upload_date': '20170228',
1649 'uploader_id': '996642',
1652 'skip_download': True,
1654 'add_ie': [RutubeIE.ie_key()],
1657 # ThePlatform embedded with whitespaces in URLs
1658 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1659 'only_matching': True,
1662 # Senate ISVP iframe https
1663 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1664 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1666 'id': 'govtaff020316',
1668 'title': 'Integrated Senate Video Player',
1670 'add_ie': [SenateISVPIE.ie_key()],
1673 # Limelight embeds (1 channel embed + 4 media embeds)
1674 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1676 'id': 'FacilitatorTraining2017',
1677 'title': 'Facilitator Training 2017',
1679 'playlist_mincount': 5,
1682 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1684 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1685 'title': 'Standoff with Walnut Creek murder suspect ends',
1686 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1688 'playlist_mincount': 4,
1691 # # TODO: find another test
1692 # # http://schema.org/VideoObject
1693 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1694 # 'md5': '888dcf08b7ea671381f00fab74692755',
1696 # 'id': 'nyvTSJMKId',
1698 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1699 # 'description': '#love for cats.',
1700 # 'timestamp': 1461244995,
1701 # 'upload_date': '20160421',
1704 # 'force_generic_extractor': True,
1709 def report_following_redirect(self, new_url):
1710 """Report information extraction."""
1711 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1713 def _extract_rss(self, url, video_id, doc):
1714 playlist_title = doc.find('./channel/title').text
1715 playlist_desc_el = doc.find('./channel/description')
1716 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1719 for it in doc.findall('./channel/item'):
1720 next_url = xpath_text(it, 'link', fatal=False)
1722 enclosure_nodes = it.findall('./enclosure')
1723 for e in enclosure_nodes:
1724 next_url = e.attrib.get('url')
1732 '_type': 'url_transparent',
1734 'title': it.find('title').text,
1738 '_type': 'playlist',
1740 'title': playlist_title,
1741 'description': playlist_desc,
1745 def _extract_camtasia(self, url, video_id, webpage):
1746 """ Returns None if no camtasia video can be found. """
1748 camtasia_cfg = self._search_regex(
1749 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1750 webpage, 'camtasia configuration file', default=None)
1751 if camtasia_cfg is None:
1754 title = self._html_search_meta('DC.title', webpage, fatal=True)
1756 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1757 camtasia_cfg = self._download_xml(
1758 camtasia_url, video_id,
1759 note='Downloading camtasia configuration',
1760 errnote='Failed to download camtasia configuration')
1761 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1764 for n in fileset_node.getchildren():
1765 url_n = n.find('./uri')
1770 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1771 'title': '%s - %s' % (title, n.tag),
1772 'url': compat_urlparse.urljoin(url, url_n.text),
1773 'duration': float_or_none(n.find('./duration').text),
1777 '_type': 'playlist',
1782 def _real_extract(self, url):
1783 if url.startswith('//'):
1786 'url': self.http_scheme() + url,
1789 parsed_url = compat_urlparse.urlparse(url)
1790 if not parsed_url.scheme:
1791 default_search = self._downloader.params.get('default_search')
1792 if default_search is None:
1793 default_search = 'fixup_error'
1795 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1797 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1798 return self.url_result('http://' + url)
1799 elif default_search != 'fixup_error':
1800 if default_search == 'auto_warning':
1801 if re.match(r'^(?:url|URL)$', url):
1802 raise ExtractorError(
1803 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1806 self._downloader.report_warning(
1807 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1808 return self.url_result('ytsearch:' + url)
1810 if default_search in ('error', 'fixup_error'):
1811 raise ExtractorError(
1812 '%r is not a valid URL. '
1813 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1814 % (url, url), expected=True)
1816 if ':' not in default_search:
1817 default_search += ':'
1818 return self.url_result(default_search + url)
1820 url, smuggled_data = unsmuggle_url(url)
1821 force_videoid = None
1822 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1823 if smuggled_data and 'force_videoid' in smuggled_data:
1824 force_videoid = smuggled_data['force_videoid']
1825 video_id = force_videoid
1827 video_id = self._generic_id(url)
1829 self.to_screen('%s: Requesting header' % video_id)
1831 head_req = HEADRequest(url)
1832 head_response = self._request_webpage(
1834 note=False, errnote='Could not send HEAD request to %s' % url,
1837 if head_response is not False:
1838 # Check for redirect
1839 new_url = head_response.geturl()
1841 self.report_following_redirect(new_url)
1843 new_url = smuggle_url(
1844 new_url, {'force_videoid': force_videoid})
1845 return self.url_result(new_url)
1847 full_response = None
1848 if head_response is False:
1849 request = sanitized_Request(url)
1850 request.add_header('Accept-Encoding', '*')
1851 full_response = self._request_webpage(request, video_id)
1852 head_response = full_response
1856 'title': self._generic_title(url),
1857 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1860 # Check for direct link to a video
1861 content_type = head_response.headers.get('Content-Type', '').lower()
1862 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1864 format_id = m.group('format_id')
1865 if format_id.endswith('mpegurl'):
1866 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1867 elif format_id == 'f4m':
1868 formats = self._extract_f4m_formats(url, video_id)
1871 'format_id': m.group('format_id'),
1873 'vcodec': 'none' if m.group('type') == 'audio' else None
1875 info_dict['direct'] = True
1876 self._sort_formats(formats)
1877 info_dict['formats'] = formats
1880 if not self._downloader.params.get('test', False) and not is_intentional:
1881 force = self._downloader.params.get('force_generic_extractor', False)
1882 self._downloader.report_warning(
1883 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1885 if not full_response:
1886 request = sanitized_Request(url)
1887 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1888 # making it impossible to download only chunk of the file (yet we need only 512kB to
1889 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1890 # that will always result in downloading the whole file that is not desirable.
1891 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1892 # to accept raw bytes and being able to download only a chunk.
1893 # It may probably better to solve this by checking Content-Type for application/octet-stream
1894 # after HEAD request finishes, but not sure if we can rely on this.
1895 request.add_header('Accept-Encoding', '*')
1896 full_response = self._request_webpage(request, video_id)
1898 first_bytes = full_response.read(512)
1900 # Is it an M3U playlist?
1901 if first_bytes.startswith(b'#EXTM3U'):
1902 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1903 self._sort_formats(info_dict['formats'])
1906 # Maybe it's a direct link to a video?
1907 # Be careful not to download the whole thing!
1908 if not is_html(first_bytes):
1909 self._downloader.report_warning(
1910 'URL could be a direct video link, returning it as such.')
1917 webpage = self._webpage_read_content(
1918 full_response, url, video_id, prefix=first_bytes)
1920 self.report_extraction(video_id)
1922 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1924 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1925 if doc.tag == 'rss':
1926 return self._extract_rss(url, video_id, doc)
1927 elif doc.tag == 'SmoothStreamingMedia':
1928 info_dict['formats'] = self._parse_ism_formats(doc, url)
1929 self._sort_formats(info_dict['formats'])
1931 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1932 smil = self._parse_smil(doc, url, video_id)
1933 self._sort_formats(smil['formats'])
1935 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1936 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1937 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1938 info_dict['formats'] = self._parse_mpd_formats(
1940 mpd_base_url=full_response.geturl().rpartition('/')[0],
1942 self._sort_formats(info_dict['formats'])
1944 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1945 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1946 self._sort_formats(info_dict['formats'])
1948 except compat_xml_parse_error:
1951 # Is it a Camtasia project?
1952 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1953 if camtasia_res is not None:
1956 # Sometimes embedded video player is hidden behind percent encoding
1957 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1958 # Unescaping the whole page allows to handle those cases in a generic way
1959 webpage = compat_urllib_parse_unquote(webpage)
1961 # it's tempting to parse this further, but you would
1962 # have to take into account all the variations like
1963 # Video Title - Site Name
1964 # Site Name | Video Title
1965 # Video Title - Tagline | Site Name
1966 # and so on and so forth; it's just not practical
1967 video_title = self._og_search_title(
1968 webpage, default=None) or self._html_search_regex(
1969 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1972 # Try to detect age limit automatically
1973 age_limit = self._rta_search(webpage)
1974 # And then there are the jokers who advertise that they use RTA,
1975 # but actually don't.
1976 AGE_LIMIT_MARKERS = [
1977 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1979 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1982 # video uploader is domain name
1983 video_uploader = self._search_regex(
1984 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1986 video_description = self._og_search_description(webpage, default=None)
1987 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1989 # Look for Brightcove Legacy Studio embeds
1990 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1994 'url': smuggle_url(bc_url, {'Referer': url}),
1995 'ie_key': 'BrightcoveLegacy'
1996 } for bc_url in bc_urls]
1999 '_type': 'playlist',
2000 'title': video_title,
2005 # Look for Brightcove New Studio embeds
2006 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2008 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2010 # Look for ThePlatform embeds
2011 tp_urls = ThePlatformIE._extract_urls(webpage)
2013 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2015 # Look for Vessel embeds
2016 vessel_urls = VesselIE._extract_urls(webpage)
2018 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2020 # Look for embedded rtl.nl player
2021 matches = re.findall(
2022 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2025 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2027 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2029 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2031 vid_me_embed_url = self._search_regex(
2032 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2033 webpage, 'vid.me embed', default=None)
2034 if vid_me_embed_url is not None:
2035 return self.url_result(vid_me_embed_url, 'Vidme')
2037 # Look for embedded YouTube player
2038 matches = re.findall(r'''(?x)
2048 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2052 return self.playlist_from_matches(
2053 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2055 # Look for lazyYT YouTube embed
2056 matches = re.findall(
2057 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2059 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2061 # Look for Wordpress "YouTube Video Importer" plugin
2062 matches = re.findall(r'''(?x)<div[^>]+
2063 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2064 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2066 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2068 matches = DailymotionIE._extract_urls(webpage)
2070 return self.playlist_from_matches(matches, video_id, video_title)
2072 # Look for embedded Dailymotion playlist player (#3822)
2074 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2076 playlists = re.findall(
2077 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2079 return self.playlist_from_matches(
2080 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2082 # Look for embedded Wistia player
2084 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
2086 embed_url = self._proto_relative_url(
2087 unescapeHTML(match.group('url')))
2089 '_type': 'url_transparent',
2092 'uploader': video_uploader,
2095 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
2098 '_type': 'url_transparent',
2099 'url': 'wistia:%s' % match.group('id'),
2101 'uploader': video_uploader,
2106 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
2107 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
2110 return self.url_result(self._proto_relative_url(
2111 'wistia:%s' % match.group('id')), 'Wistia')
2113 # Look for SVT player
2114 svt_url = SVTIE._extract_url(webpage)
2116 return self.url_result(svt_url, 'SVT')
2118 # Look for embedded condenast player
2119 matches = re.findall(
2120 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2124 '_type': 'playlist',
2127 'ie_key': 'CondeNast',
2129 } for ma in matches],
2130 'title': video_title,
2134 # Look for Bandcamp pages with custom domain
2135 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2136 if mobj is not None:
2137 burl = unescapeHTML(mobj.group(1))
2138 # Don't set the extractor because it can be a track url or an album
2139 return self.url_result(burl)
2141 # Look for embedded Vevo player
2143 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2144 if mobj is not None:
2145 return self.url_result(mobj.group('url'))
2147 # Look for embedded Viddler player
2149 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2151 if mobj is not None:
2152 return self.url_result(mobj.group('url'))
2154 # Look for NYTimes player
2156 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2158 if mobj is not None:
2159 return self.url_result(mobj.group('url'))
2161 # Look for Libsyn player
2163 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2164 if mobj is not None:
2165 return self.url_result(mobj.group('url'))
2167 # Look for Ooyala videos
2168 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2169 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2170 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2171 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2172 if mobj is not None:
2173 embed_token = self._search_regex(
2174 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2175 webpage, 'ooyala embed token', default=None)
2176 return OoyalaIE._build_url_result(smuggle_url(
2179 'embed_token': embed_token,
2182 # Look for multiple Ooyala embeds on SBN network websites
2183 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2184 if mobj is not None:
2185 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2187 return self.playlist_from_matches(
2188 embeds, video_id, video_title,
2189 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2191 # Look for Aparat videos
2192 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2193 if mobj is not None:
2194 return self.url_result(mobj.group(1), 'Aparat')
2196 # Look for MPORA videos
2197 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2198 if mobj is not None:
2199 return self.url_result(mobj.group(1), 'Mpora')
2201 # Look for embedded NovaMov-based player
2203 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2204 (?P<url>http://(?:(?:embed|www)\.)?
2206 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2207 videoweed\.(?:es|com)|
2208 movshare\.(?:net|sx|ag)|
2209 divxstage\.(?:eu|net|ch|co|at|ag))
2210 /embed\.php.+?)\1''', webpage)
2211 if mobj is not None:
2212 return self.url_result(mobj.group('url'))
2214 # Look for embedded Facebook player
2215 facebook_url = FacebookIE._extract_url(webpage)
2216 if facebook_url is not None:
2217 return self.url_result(facebook_url, 'Facebook')
2219 # Look for embedded VK player
2220 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2221 if mobj is not None:
2222 return self.url_result(mobj.group('url'), 'VK')
2224 # Look for embedded Odnoklassniki player
2225 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2226 if mobj is not None:
2227 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2229 # Look for embedded ivi player
2230 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2231 if mobj is not None:
2232 return self.url_result(mobj.group('url'), 'Ivi')
2234 # Look for embedded Huffington Post player
2236 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2237 if mobj is not None:
2238 return self.url_result(mobj.group('url'), 'HuffPost')
2241 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2242 if mobj is not None:
2243 return self.url_result(mobj.group('url'))
2244 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2245 if mobj is not None:
2246 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2248 # Look for funnyordie embed
2249 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2251 return self.playlist_from_matches(
2252 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2254 # Look for BBC iPlayer embed
2255 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2257 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2259 # Look for embedded RUTV player
2260 rutv_url = RUTVIE._extract_url(webpage)
2262 return self.url_result(rutv_url, 'RUTV')
2264 # Look for embedded TVC player
2265 tvc_url = TVCIE._extract_url(webpage)
2267 return self.url_result(tvc_url, 'TVC')
2269 # Look for embedded SportBox player
2270 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2272 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2274 # Look for embedded XHamster player
2275 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2277 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2279 # Look for embedded TNAFlixNetwork player
2280 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2282 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2284 # Look for embedded PornHub player
2285 pornhub_urls = PornHubIE._extract_urls(webpage)
2287 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2289 # Look for embedded DrTuber player
2290 drtuber_urls = DrTuberIE._extract_urls(webpage)
2292 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2294 # Look for embedded RedTube player
2295 redtube_urls = RedTubeIE._extract_urls(webpage)
2297 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2299 # Look for embedded Tvigle player
2301 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2302 if mobj is not None:
2303 return self.url_result(mobj.group('url'), 'Tvigle')
2305 # Look for embedded TED player
2307 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2308 if mobj is not None:
2309 return self.url_result(mobj.group('url'), 'TED')
2311 # Look for embedded Ustream videos
2312 ustream_url = UstreamIE._extract_url(webpage)
2314 return self.url_result(ustream_url, UstreamIE.ie_key())
2316 # Look for embedded arte.tv player
2318 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2320 if mobj is not None:
2321 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2323 # Look for embedded francetv player
2325 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2327 if mobj is not None:
2328 return self.url_result(mobj.group('url'))
2330 # Look for embedded smotri.com player
2331 smotri_url = SmotriIE._extract_url(webpage)
2333 return self.url_result(smotri_url, 'Smotri')
2335 # Look for embedded Myvi.ru player
2336 myvi_url = MyviIE._extract_url(webpage)
2338 return self.url_result(myvi_url)
2340 # Look for embedded soundcloud player
2341 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2343 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2345 # Look for tunein player
2346 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2348 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2350 # Look for embedded mtvservices player
2351 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2353 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2355 # Look for embedded yahoo player
2357 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2359 if mobj is not None:
2360 return self.url_result(mobj.group('url'), 'Yahoo')
2362 # Look for embedded sbs.com.au player
2366 <meta\s+property="og:video"\s+content=|
2369 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2371 if mobj is not None:
2372 return self.url_result(mobj.group('url'), 'SBS')
2374 # Look for embedded Cinchcast player
2376 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2378 if mobj is not None:
2379 return self.url_result(mobj.group('url'), 'Cinchcast')
2382 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2386 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2388 if mobj is not None:
2389 return self.url_result(mobj.group('url'), 'MLB')
2392 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2394 if mobj is not None:
2395 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2398 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2400 if mobj is not None:
2401 return self.url_result(mobj.group('url'), 'Livestream')
2403 # Look for Zapiks embed
2405 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2406 if mobj is not None:
2407 return self.url_result(mobj.group('url'), 'Zapiks')
2409 # Look for Kaltura embeds
2410 kaltura_url = KalturaIE._extract_url(webpage)
2412 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2414 # Look for Eagle.Platform embeds
2415 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2416 if eagleplatform_url:
2417 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2419 # Look for ClipYou (uses Eagle.Platform) embeds
2421 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2422 if mobj is not None:
2423 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2425 # Look for Pladform embeds
2426 pladform_url = PladformIE._extract_url(webpage)
2428 return self.url_result(pladform_url)
2430 # Look for Videomore embeds
2431 videomore_url = VideomoreIE._extract_url(webpage)
2433 return self.url_result(videomore_url)
2435 # Look for Webcaster embeds
2436 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2438 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2440 # Look for Playwire embeds
2442 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2443 if mobj is not None:
2444 return self.url_result(mobj.group('url'))
2446 # Look for 5min embeds
2448 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2449 if mobj is not None:
2450 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2452 # Look for Crooks and Liars embeds
2454 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2455 if mobj is not None:
2456 return self.url_result(mobj.group('url'))
2458 # Look for NBC Sports VPlayer embeds
2459 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2461 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2463 # Look for NBC News embeds
2464 nbc_news_embed_url = re.search(
2465 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2466 if nbc_news_embed_url:
2467 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2469 # Look for Google Drive embeds
2470 google_drive_url = GoogleDriveIE._extract_url(webpage)
2471 if google_drive_url:
2472 return self.url_result(google_drive_url, 'GoogleDrive')
2474 # Look for UDN embeds
2476 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2477 if mobj is not None:
2478 return self.url_result(
2479 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2481 # Look for Senate ISVP iframe
2482 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2484 return self.url_result(senate_isvp_url, 'SenateISVP')
2486 # Look for Dailymotion Cloud videos
2487 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2489 return self.url_result(dmcloud_url, 'DailymotionCloud')
2491 # Look for OnionStudios embeds
2492 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2493 if onionstudios_url:
2494 return self.url_result(onionstudios_url)
2496 # Look for ViewLift embeds
2497 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2499 return self.url_result(viewlift_url)
2501 # Look for JWPlatform embeds
2502 jwplatform_url = JWPlatformIE._extract_url(webpage)
2504 return self.url_result(jwplatform_url, 'JWPlatform')
2506 # Look for Digiteka embeds
2507 digiteka_url = DigitekaIE._extract_url(webpage)
2509 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2511 # Look for Arkena embeds
2512 arkena_url = ArkenaIE._extract_url(webpage)
2514 return self.url_result(arkena_url, ArkenaIE.ie_key())
2516 # Look for Piksel embeds
2517 piksel_url = PikselIE._extract_url(webpage)
2519 return self.url_result(piksel_url, PikselIE.ie_key())
2521 # Look for Limelight embeds
2522 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2524 return self.playlist_result(
2525 limelight_urls, video_id, video_title, video_description)
2527 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2531 'Channel': 'channel',
2532 'ChannelList': 'channel_list',
2534 return self.url_result(smuggle_url('limelight:%s:%s' % (
2535 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2536 'Limelight%s' % mobj.group(1), mobj.group(2))
2540 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2542 name=(["\'])flashVars\2[^>]+
2543 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2546 return self.url_result(smuggle_url(
2547 'limelight:media:%s' % mobj.group('id'),
2548 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2550 # Look for Anvato embeds
2551 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2553 return self.playlist_result(
2554 anvato_urls, video_id, video_title, video_description)
2556 # Look for AdobeTVVideo embeds
2558 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2560 if mobj is not None:
2561 return self.url_result(
2562 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2565 # Look for Vine embeds
2567 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2569 if mobj is not None:
2570 return self.url_result(
2571 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2573 # Look for VODPlatform embeds
2575 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2577 if mobj is not None:
2578 return self.url_result(
2579 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2581 # Look for Mangomolo embeds
2583 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2585 video\?.*?\bid=(?P<video_id>\d+)|
2586 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2587 ).+?)\1''', webpage)
2588 if mobj is not None:
2590 '_type': 'url_transparent',
2591 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2592 'title': video_title,
2593 'description': video_description,
2594 'thumbnail': video_thumbnail,
2595 'uploader': video_uploader,
2597 video_id = mobj.group('video_id')
2600 'ie_key': 'MangomoloVideo',
2605 'ie_key': 'MangomoloLive',
2606 'id': mobj.group('channel_id'),
2610 # Look for Instagram embeds
2611 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2612 if instagram_embed_url is not None:
2613 return self.url_result(
2614 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2616 # Look for LiveLeak embeds
2617 liveleak_url = LiveLeakIE._extract_url(webpage)
2619 return self.url_result(liveleak_url, 'LiveLeak')
2621 # Look for 3Q SDN embeds
2622 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2625 '_type': 'url_transparent',
2626 'ie_key': ThreeQSDNIE.ie_key(),
2627 'url': self._proto_relative_url(threeqsdn_url),
2628 'title': video_title,
2629 'description': video_description,
2630 'thumbnail': video_thumbnail,
2631 'uploader': video_uploader,
2634 # Look for VBOX7 embeds
2635 vbox7_url = Vbox7IE._extract_url(webpage)
2637 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2639 # Look for DBTV embeds
2640 dbtv_urls = DBTVIE._extract_urls(webpage)
2642 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2644 # Look for Videa embeds
2645 videa_urls = VideaIE._extract_urls(webpage)
2647 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2649 # Look for 20 minuten embeds
2650 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2652 return self.playlist_from_matches(
2653 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2655 # Look for Openload embeds
2656 openload_urls = OpenloadIE._extract_urls(webpage)
2658 return self.playlist_from_matches(
2659 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2661 # Look for VideoPress embeds
2662 videopress_urls = VideoPressIE._extract_urls(webpage)
2664 return self.playlist_from_matches(
2665 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2667 # Look for Rutube embeds
2668 rutube_urls = RutubeIE._extract_urls(webpage)
2670 return self.playlist_from_matches(
2671 rutube_urls, ie=RutubeIE.ie_key())
2673 # Looking for http://schema.org/VideoObject
2674 json_ld = self._search_json_ld(
2675 webpage, video_id, default={}, expected_type='VideoObject')
2676 if json_ld.get('url'):
2678 'title': video_title or info_dict['title'],
2679 'description': video_description,
2680 'thumbnail': video_thumbnail,
2681 'age_limit': age_limit
2683 info_dict.update(json_ld)
2686 # Look for HTML5 media
2687 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2689 for entry in entries:
2692 'title': video_title,
2694 self._sort_formats(entry['formats'])
2695 return self.playlist_result(entries)
2697 jwplayer_data = self._find_jwplayer_data(
2698 webpage, video_id, transform_source=js_to_json)
2700 info = self._parse_jwplayer_data(
2701 jwplayer_data, video_id, require_title=False, base_url=url)
2702 if not info.get('title'):
2703 info['title'] = video_title
2706 def check_video(vurl):
2707 if YoutubeIE.suitable(vurl):
2709 if RtmpIE.suitable(vurl):
2711 vpath = compat_urlparse.urlparse(vurl).path
2712 vext = determine_ext(vpath)
2713 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2715 def filter_video(urls):
2716 return list(filter(check_video, urls))
2718 # Start with something easy: JW Player in SWFObject
2719 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2721 # Look for gorilla-vid style embedding
2722 found = filter_video(re.findall(r'''(?sx)
2726 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2729 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2731 # Broaden the search a little bit
2732 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2734 # Broaden the findall a little bit: JWPlayer JS loader
2735 found = filter_video(re.findall(
2736 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2739 found = filter_video(re.findall(r'''(?xs)
2740 flowplayer\("[^"]+",\s*
2742 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2743 ["']?url["']?\s*:\s*["']([^"']+)["']
2748 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2750 # Try to find twitter cards info
2751 # twitter:player:stream should be checked before twitter:player since
2752 # it is expected to contain a raw stream (see
2753 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2754 found = filter_video(re.findall(
2755 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2757 # We look for Open Graph info:
2758 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2759 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2760 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2761 if m_video_type is not None:
2762 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2764 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2766 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2767 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2770 # Look also in Refresh HTTP header
2771 refresh_header = head_response.headers.get('Refresh')
2773 # In python 2 response HTTP headers are bytestrings
2774 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2775 refresh_header = refresh_header.decode('iso-8859-1')
2776 found = re.search(REDIRECT_REGEX, refresh_header)
2778 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2780 self.report_following_redirect(new_url)
2789 # twitter:player is a https URL to iframe player that may or may not
2790 # be supported by youtube-dl thus this is checked the very last (see
2791 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2792 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2794 return self.url_result(embed_url)
2797 raise UnsupportedError(url)
2800 for video_url in orderedSet(found):
2801 video_url = unescapeHTML(video_url)
2802 video_url = video_url.replace('\\/', '/')
2803 video_url = compat_urlparse.urljoin(url, video_url)
2804 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2806 # Sometimes, jwplayer extraction will result in a YouTube URL
2807 if YoutubeIE.suitable(video_url):
2808 entries.append(self.url_result(video_url, 'Youtube'))
2811 # here's a fun little line of code for you:
2812 video_id = os.path.splitext(video_id)[0]
2816 'uploader': video_uploader,
2817 'title': video_title,
2818 'age_limit': age_limit,
2821 if RtmpIE.suitable(video_url):
2822 entry_info_dict.update({
2823 '_type': 'url_transparent',
2824 'ie_key': RtmpIE.ie_key(),
2827 entries.append(entry_info_dict)
2830 ext = determine_ext(video_url)
2832 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2834 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2836 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2838 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2840 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2841 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2842 # Just matching .ism/manifest is not enough to be reliably sure
2843 # whether it's actually an ISM manifest or some other streaming
2844 # manifest since there are various streaming URL formats
2845 # possible (see [1]) as well as some other shenanigans like
2846 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2848 # Thus the most reasonable way to solve this is to delegate
2849 # to generic extractor in order to look into the contents of
2850 # the manifest itself.
2851 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2852 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2853 entry_info_dict = self.url_result(
2854 smuggle_url(video_url, {'to_generic': True}),
2857 entry_info_dict['url'] = video_url
2859 if entry_info_dict.get('formats'):
2860 self._sort_formats(entry_info_dict['formats'])
2862 entries.append(entry_info_dict)
2864 if len(entries) == 1:
2867 for num, e in enumerate(entries, start=1):
2868 # 'url' results don't have a title
2869 if e.get('title') is not None:
2870 e['title'] = '%s (%d)' % (e['title'], num)
2872 '_type': 'playlist',