3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxEmbedIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
111 from .peertube import PeerTubeIE
114 class GenericIE(InfoExtractor):
115 IE_DESC = 'Generic downloader that works on some sites'
119 # Direct link to a video
121 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
122 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
127 'upload_date': '20100513',
130 # Direct link to media delivered compressed (until Accept-Encoding is *)
132 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
133 'md5': '128c42e68b13950268b648275386fc74',
135 'id': 'FictionJunction-Parallel_Hearts',
137 'title': 'FictionJunction-Parallel_Hearts',
138 'upload_date': '20140522',
140 'expected_warnings': [
141 'URL could be a direct video link, returning it as such.'
143 'skip': 'URL invalid',
145 # Direct download with broken HEAD
147 'url': 'http://ai-radio.org:8000/radio.opus',
154 'skip_download': True, # infinite live stream
156 'expected_warnings': [
157 r'501.*Not Implemented',
161 # Direct link with incorrect MIME type
163 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
164 'md5': '4ccbebe5f36706d85221f204d7eb5913',
166 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
167 'id': '5_Lennart_Poettering_-_Systemd',
169 'title': '5_Lennart_Poettering_-_Systemd',
170 'upload_date': '20141120',
172 'expected_warnings': [
173 'URL could be a direct video link, returning it as such.'
178 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
180 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
181 'title': 'Zero Punctuation',
182 'description': 're:.*groundbreaking video review series.*'
184 'playlist_mincount': 11,
186 # RSS feed with enclosure
188 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
190 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
192 'upload_date': '20150228',
193 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
196 # RSS feed with enclosures and unsupported link URLs
198 'url': 'http://www.hellointernet.fm/podcast?format=rss',
200 'id': 'http://www.hellointernet.fm/podcast?format=rss',
201 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
202 'title': 'Hello Internet',
204 'playlist_mincount': 100,
206 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
208 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
212 'title': 'Automatics, robotics and biocybernetics',
213 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
214 'upload_date': '20130627',
215 'formats': 'mincount:16',
216 'subtitles': 'mincount:1',
219 'force_generic_extractor': True,
220 'skip_download': True,
223 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
225 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
230 'formats': 'mincount:1',
233 'skip_download': True,
236 # SMIL from https://www.restudy.dk/video/play/id/1637
238 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
242 'title': 'video_1637',
243 'formats': 'mincount:3',
246 'skip_download': True,
249 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
251 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
253 'id': 'smil-service',
255 'title': 'smil-service',
256 'formats': 'mincount:1',
259 'skip_download': True,
262 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
264 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
268 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
269 'formats': 'mincount:3',
272 'skip_download': True,
275 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
277 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
279 'id': 'mZlp2ctYIUEB',
281 'title': 'Tikibad ontruimd wegens brand',
282 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
283 'thumbnail': r're:^https?://.*\.jpg$',
287 'skip_download': True,
290 # MPD from http://dash-mse-test.appspot.com/media.html
292 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
293 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
295 'id': 'car-20120827-manifest',
297 'title': 'car-20120827-manifest',
298 'formats': 'mincount:9',
299 'upload_date': '20130904',
302 'format': 'bestvideo',
305 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
307 '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',
312 'formats': 'mincount:8',
316 'skip_download': True,
318 'skip': 'video gone',
320 # m3u8 served with Content-Type: text/plain
322 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
327 'upload_date': '20140720',
328 'formats': 'mincount:11',
332 'skip_download': True,
334 'skip': 'video gone',
338 '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',
342 'upload_date': '20130224',
343 'uploader_id': 'TheVerge',
344 'description': r're:^Chris Ziegler takes a look at the\.*',
345 'uploader': 'The Verge',
346 'title': 'First Firefox OS phones side-by-side',
349 'skip_download': False,
353 # redirect in Refresh HTTP header
354 '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',
358 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
359 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
360 'upload_date': '20150917',
361 'uploader_id': 'brtvofficial',
362 'uploader': 'Boiler Room',
365 'skip_download': False,
369 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
370 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
372 'id': '13601338388002',
374 'uploader': 'www.hodiho.fr',
375 'title': 'R\u00e9gis plante sa Jeep',
378 # bandcamp page with custom domain
380 'add_ie': ['Bandcamp'],
381 'url': 'http://bronyrock.com/track/the-pony-mash',
385 'title': 'The Pony Mash',
386 'uploader': 'M_Pallante',
388 'skip': 'There is a limit of 200 free downloads / month for the test song',
391 # embedded brightcove video
392 # it also tests brightcove videos that need to set the 'Referer'
393 # in the http requests
394 'add_ie': ['BrightcoveLegacy'],
395 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
397 'id': '2765128793001',
399 'title': 'Le cours de bourse : l’analyse technique',
400 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
401 'uploader': 'BFM BUSINESS',
404 'skip_download': True,
408 # embedded with itemprop embedURL and video id spelled as `idVideo`
409 'add_id': ['BrightcoveLegacy'],
410 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
412 'id': '5255628253001',
414 'title': 'md5:37c519b1128915607601e75a87995fc0',
415 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
416 'uploader': 'BFM BUSINESS',
417 'uploader_id': '876450612001',
418 'timestamp': 1482255315,
419 'upload_date': '20161220',
422 'skip_download': True,
426 # https://github.com/rg3/youtube-dl/issues/2253
427 'url': 'http://bcove.me/i6nfkrc3',
428 'md5': '0ba9446db037002366bab3b3eb30c88c',
430 'id': '3101154703001',
432 'title': 'Still no power',
433 'uploader': 'thestar.com',
434 '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.',
436 'add_ie': ['BrightcoveLegacy'],
437 'skip': 'video gone',
440 'url': 'http://www.championat.com/video/football/v/87/87499.html',
441 'md5': 'fb973ecf6e4a78a67453647444222983',
443 'id': '3414141473001',
445 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
446 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
447 'uploader': 'Championat',
451 # https://github.com/rg3/youtube-dl/issues/3541
452 'add_ie': ['BrightcoveLegacy'],
453 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
455 'id': '3866516442001',
457 'title': 'Leer mij vrouwen kennen: Aflevering 1',
458 'description': 'Leer mij vrouwen kennen: Aflevering 1',
459 'uploader': 'SBS Broadcasting',
461 'skip': 'Restricted to Netherlands',
463 'skip_download': True, # m3u8 download
467 # Brightcove video in <iframe>
468 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
469 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
471 'id': '5360463607001',
473 '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',
474 '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。',
475 'uploader': 'United Nations',
476 'uploader_id': '1362235914001',
477 'timestamp': 1489593889,
478 'upload_date': '20170315',
480 'add_ie': ['BrightcoveLegacy'],
483 # Brightcove with alternative playerID key
484 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
486 'id': 'nmeth.2062_SV1',
487 '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',
491 'id': '2228375078001',
493 'title': 'nmeth.2062-sv1',
494 'description': 'nmeth.2062-sv1',
495 'timestamp': 1363357591,
496 'upload_date': '20130315',
497 'uploader': 'Nature Publishing Group',
498 'uploader_id': '1964492299001',
503 # Brightcove with UUID in videoPlayer
504 'url': 'http://www8.hp.com/cn/zh/home.html',
506 'id': '5255815316001',
508 'title': 'Sprocket Video - China',
509 'description': 'Sprocket Video - China',
510 'uploader': 'HP-Video Gallery',
511 'timestamp': 1482263210,
512 'upload_date': '20161220',
513 'uploader_id': '1107601872001',
516 'skip_download': True, # m3u8 download
518 'skip': 'video rotates...weekly?',
521 # Brightcove:new type [2].
522 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
523 'md5': '2b35148fcf48da41c9fb4591650784f3',
525 'id': '5348741021001',
527 'upload_date': '20170306',
528 'uploader_id': '4191638492001',
529 'timestamp': 1488769918,
530 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
535 # Alternative brightcove <video> attributes
536 '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/',
538 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
539 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
542 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
544 'id': '5311302538001',
546 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
547 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
548 'timestamp': 1486321708,
549 'upload_date': '20170205',
550 'uploader_id': '800000640001',
552 'only_matching': True,
556 # Brightcove with UUID in videoPlayer
557 'url': 'http://www8.hp.com/cn/zh/home.html',
559 'id': '5255815316001',
561 'title': 'Sprocket Video - China',
562 'description': 'Sprocket Video - China',
563 'uploader': 'HP-Video Gallery',
564 'timestamp': 1482263210,
565 'upload_date': '20161220',
566 'uploader_id': '1107601872001',
569 'skip_download': True, # m3u8 download
574 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
575 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
577 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
579 'title': '2cc213299525360.mov', # that's what we get
582 'add_ie': ['Ooyala'],
585 # ooyala video embedded with http://player.ooyala.com/iframe.js
586 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
588 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
590 'title': '"Steve Jobs: Man in the Machine" trailer',
591 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
595 'skip_download': True,
597 'skip': 'movie expired',
599 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
601 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
603 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
605 'title': 'Steampunk Fest Comes to Honesdale',
609 'skip_download': True,
614 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
618 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
619 'upload_date': '20140225',
620 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
621 'uploader': 'Tested',
622 'uploader_id': 'testedcom',
624 # No need to test YoutubeIE here
626 'skip_download': True,
631 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
635 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
636 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
638 # HEAD requests lead to endless 301, while GET is OK
639 'expected_warnings': ['301'],
643 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
647 'title': 'Охотское море стало целиком российским',
648 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
652 'skip_download': True,
657 '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/',
661 'title': 'Дошкольное воспитание',
666 'url': 'http://www.vestifinance.ru/articles/25753',
669 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
674 'title': 'Госзаказ. День 3',
680 'title': 'Госзаказ. День 2',
686 'title': 'Госзаказ. День 1',
692 'skip_download': True,
697 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
699 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
701 'title': 'Ужастики, русский трейлер (2015)',
702 'thumbnail': r're:^https?://.*\.jpg$',
708 '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',
711 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
713 'playlist_mincount': 7,
714 # This forum does not allow <iframe> syntaxes anymore
715 # Now HTML tags are displayed as-is
716 'skip': 'No videos on this page',
720 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
721 'md5': '65fdff94098e4a607385a60c5177c638',
725 'title': 'Hidden miracles of the natural world',
726 'uploader': 'Louie Schwartzberg',
727 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
730 # nowvideo embed hidden behind percent encoding
732 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
733 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
735 'id': '06e53103ca9aa',
737 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
738 'description': 'No description',
743 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
744 'md5': '7653032cbb25bf6c80d80f217055fa43',
746 'id': '048195-004_PLUS7-F',
749 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
750 'upload_date': '20140320',
753 'skip_download': 'Requires rtmpdump'
755 'skip': 'video gone',
759 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
763 'title': 'Alcaline, le concert avec Calogero',
764 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
765 'upload_date': '20150226',
766 'timestamp': 1424989860,
771 'skip_download': True,
773 'expected_warnings': [
779 'url': 'http://www.wired.com/2014/04/honda-asimo/',
780 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
782 'id': '53501be369702d3275860000',
784 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
789 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
790 'md5': '441aeeb82eb72c422c7f14ec533999cd',
792 'id': 'k2mm4bCdJ6CQ2i7c8o2',
794 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
795 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
797 'uploader_id': 'xgditw',
798 'upload_date': '20140425',
799 'timestamp': 1398441542,
801 'add_ie': ['Dailymotion'],
805 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
809 'title': 'Care worker punches elderly dementia patient in head 11 times',
810 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
812 'add_ie': ['DailyMail'],
814 'skip_download': True,
819 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
823 'title': 'The NBL Auction 2014',
824 'uploader': 'BADMINTON England',
825 'uploader_id': 'BADMINTONEvents',
826 'upload_date': '20140603',
827 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
829 'add_ie': ['Youtube'],
831 'skip_download': True,
836 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
837 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
839 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
841 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
842 'description': 'Two valets share their love for movie star Liam Neesons.',
843 'timestamp': 1349922600,
844 'upload_date': '20121011',
847 # YouTube embed via <data-embed-url="">
849 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
853 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
854 'uploader': 'Gameloft',
855 'uploader_id': 'gameloft',
856 'upload_date': '20140828',
857 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
860 'skip_download': True,
863 # YouTube <object> embed
865 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
866 'md5': '516718101ec834f74318df76259fb3cc',
870 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
871 'upload_date': '20080526',
872 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
873 'uploader': 'Christopher Sykes',
874 'uploader_id': 'ChristopherJSykes',
876 'add_ie': ['Youtube'],
880 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
882 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
884 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
885 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
890 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
892 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
893 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
899 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
904 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
905 'md5': '9d65602bf31c6e20014319c7d07fba27',
907 'id': '5123ea6d5e5a7',
910 'uploader': 'www.handjobhub.com',
911 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
914 # Multiple brightcove videos
915 # https://github.com/rg3/youtube-dl/issues/2283
917 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
919 'id': 'always-never',
920 'title': 'Always / Never - The New Yorker',
924 'extract_flat': False,
925 'skip_download': True,
930 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
931 'md5': '96f09a37e44da40dd083e12d9a683327',
935 'title': 'Ump changes call to ball',
936 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
938 'timestamp': 1401537900,
939 'upload_date': '20140531',
940 'thumbnail': r're:^https?://.*\.jpg$',
945 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
946 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
950 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
951 'description': 'a Paywall Videos video from Remilon',
953 'uploader': 'study.com',
954 'timestamp': 1459678540,
955 'upload_date': '20160403',
956 'filesize': 24687186,
960 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
961 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
965 'title': 'Conversation about Hexagonal Rails Part 1',
966 'description': 'a Martin Fowler video from ThoughtWorks',
968 'uploader': 'thoughtworks.wistia.com',
969 'timestamp': 1401832161,
970 'upload_date': '20140603',
973 # Wistia standard embed (async)
975 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
979 'title': 'Drip Brennan Dunn Workshop',
980 'description': 'a JV Webinars video from getdrip-1',
982 'timestamp': 1463607249,
983 'upload_date': '20160518',
986 'skip_download': True,
991 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
995 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
996 'uploader': 'Sophos Security',
997 'title': 'Chet Chat 171 - Oct 29, 2014',
998 'upload_date': '20141029',
1001 # Soundcloud multiple embeds
1003 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1006 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1008 'playlist_mincount': 7,
1010 # TuneIn station embed
1012 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1017 'location': 'Paris, France',
1022 'skip_download': True,
1027 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1031 'upload_date': '20141112',
1032 'title': 'Rosetta #CometLanding webcast HL 10',
1035 # Another Livestream embed, without 'new.' in URL
1037 'url': 'https://www.freespeech.org/',
1041 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1045 'skip_download': True,
1050 'url': 'https://skiplagged.com/',
1053 'title': 'Skiplagged: The smart way to find cheap flights',
1055 'playlist_mincount': 1,
1056 'add_ie': ['Youtube'],
1060 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1064 'upload_date': '20141126',
1065 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1070 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1072 'id': '730m_DandD_1901_512k',
1074 'uploader': 'www.abc.net.au',
1075 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1078 # embedded viddler video
1080 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1084 'uploader': 'deadspin',
1085 'title': 'WALL-TO-GORTAT',
1086 'timestamp': 1422285291,
1087 'upload_date': '20150126',
1089 'add_ie': ['Viddler'],
1093 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1097 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1098 'description': 'md5:601cb790edd05908957dae8aaa866465',
1099 'upload_date': '20150220',
1101 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1105 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1107 'id': 'Mrj4DVp2zeA',
1109 'upload_date': '20150212',
1110 'uploader': 'The National Archives UK',
1111 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1112 'uploader_id': 'NationalArchives08',
1113 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1118 'url': 'http://www.suffolk.edu/sjc/live.php',
1122 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1123 'uploader': 'www.suffolk.edu',
1126 'skip_download': True,
1128 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1132 'url': 'http://www.indiedb.com/games/king-machine/videos',
1136 'title': 'king machine trailer 1',
1137 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1138 'thumbnail': r're:^https?://.*\.jpg$',
1142 # JWPlayer config passed as variable
1143 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1147 'title': 'ARIELE | Tube Cup',
1148 'uploader': 'www.txxx.com',
1152 'skip_download': True,
1157 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1158 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1162 'upload_date': '20171122',
1163 'timestamp': 1511366290,
1164 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1166 'add_ie': [JWPlatformIE.ie_key()],
1169 # Video.js embed, multiple formats
1170 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1172 'id': 'yygqldloqIk',
1174 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1175 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1176 'upload_date': '20130314',
1177 'uploader': 'PROстое3D',
1178 'uploader_id': 'PROstoe3D',
1181 'skip_download': True,
1185 # Video.js embed, single format
1186 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1190 'title': 'Step 1 - Good Foundation',
1191 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1194 'skip_download': True,
1199 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1200 'playlist_mincount': 5,
1202 'id': 'aanslagen-kopenhagen',
1203 'title': 'Aanslagen Kopenhagen',
1208 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1212 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1215 # Kaltura embed (different embed code)
1217 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1221 'upload_date': '20150127',
1222 'uploader_id': 'PremierMedia',
1224 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1227 # Kaltura embed with single quotes
1229 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1234 'timestamp': 1355743100,
1235 'upload_date': '20121217',
1236 'uploader_id': 'cplapp@learn360.com',
1238 'add_ie': ['Kaltura'],
1241 # Kaltura embedded via quoted entry_id
1242 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1246 'title': '06_matthew_brender_raj_dutt',
1247 'timestamp': 1466638791,
1248 'upload_date': '20160622',
1250 'add_ie': ['Kaltura'],
1251 'expected_warnings': [
1252 'Could not send HEAD request'
1255 'skip_download': True,
1259 # Kaltura embedded, some fileExt broken (#11480)
1260 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1264 'title': 'Our "Standard Models" of particle physics and cosmology',
1265 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1266 'timestamp': 1321158993,
1267 'upload_date': '20111113',
1268 'uploader_id': 'kps1',
1270 'add_ie': ['Kaltura'],
1273 # Kaltura iframe embed
1274 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1275 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1279 'title': 'I. M. Pei: A Centennial Celebration',
1280 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1281 'upload_date': '20170403',
1282 'uploader_id': 'batchUser',
1283 'timestamp': 1491232186,
1285 'add_ie': ['Kaltura'],
1288 # Kaltura iframe embed, more sophisticated
1289 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1293 'title': 'lecture-05sep2017',
1294 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1295 'upload_date': '20170913',
1296 'uploader_id': 'eps2',
1297 'timestamp': 1505340777,
1300 'skip_download': True,
1302 'add_ie': ['Kaltura'],
1305 # meta twitter:player
1306 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1310 'title': 'Main Twerk (Video)',
1311 'upload_date': '20171208',
1312 'uploader_id': 'sebastian.salinas@thechive.com',
1313 'timestamp': 1512713057,
1316 'skip_download': True,
1318 'add_ie': ['Kaltura'],
1320 # referrer protected EaglePlatform embed
1322 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1326 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1327 'thumbnail': r're:^https?://.*\.jpg$',
1332 'skip_download': True,
1335 # ClipYou (EaglePlatform) embed (custom URL)
1337 'url': 'http://muz-tv.ru/play/7129/',
1338 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1342 'title': "'O Sole Mio",
1343 'thumbnail': r're:^https?://.*\.jpg$',
1348 'skip_download': True,
1350 'skip': 'This video is unavailable.',
1354 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1358 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1359 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1360 'thumbnail': r're:^https?://.*\.jpg$',
1364 'skip': 'HTTP Error 404: Not Found',
1368 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1372 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1373 'thumbnail': r're:^https?://.*\.png$',
1379 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1380 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1384 'title': 'Facebook Creates "On This Day" | Crunch Report',
1385 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1386 'timestamp': 1427237531,
1387 'uploader': 'Crunch Report',
1388 'upload_date': '20150324',
1392 'skip_download': True,
1397 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1401 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1406 # Crooks and Liars embed
1408 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1412 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1413 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1414 'timestamp': 1428207000,
1415 'upload_date': '20150405',
1416 'uploader': 'Heather',
1419 # Crooks and Liars external embed
1421 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1423 'id': 'MTE3MjUtMzQ2MzA',
1425 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1426 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1427 'timestamp': 1265032391,
1428 'upload_date': '20100201',
1429 'uploader': 'Heather',
1432 # NBC Sports vplayer embed
1434 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1436 'id': 'ln7x1qSThw4k',
1438 'title': "PFT Live: New leader in the 'new-look' defense",
1439 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1440 'uploader': 'NBCU-SPORTS',
1441 'upload_date': '20140107',
1442 'timestamp': 1389118457,
1444 'skip': 'Invalid Page URL',
1448 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1449 'md5': '1aa589c675898ae6d37a17913cf68d66',
1451 'id': 'x_dtl_oa_LettermanliftPR_160608',
1453 'title': 'David Letterman: A Preview',
1454 '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.',
1455 'upload_date': '20160609',
1456 'timestamp': 1465431544,
1457 'uploader': 'NBCU-NEWS',
1462 'url': 'https://video.udn.com/news/300346',
1463 'md5': 'fd2060e988c326991037b9aff9df21a6',
1467 'title': '中一中男師變性 全校師生力挺',
1468 'thumbnail': r're:^https?://.*\.jpg$',
1472 'skip_download': True,
1474 'expected_warnings': ['Failed to parse JSON Expecting value'],
1476 # Brightcove URL in single quotes
1478 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1479 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1481 'id': '4255764656001',
1483 'title': 'SN Presents: Russell Martin, World Citizen',
1484 '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.',
1485 'uploader': 'Rogers Sportsnet',
1486 'uploader_id': '1704050871',
1487 'upload_date': '20150525',
1488 'timestamp': 1432570283,
1491 # OnionStudios embed
1493 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1497 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1498 'thumbnail': r're:^https?://.*\.jpe?g$',
1499 'uploader': 'ClickHole',
1500 'uploader_id': 'clickhole',
1505 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1507 'id': '74849a00-85a9-11e1-9660-123139220831',
1509 'title': '#whilewewatch',
1512 # AdobeTVVideo embed
1514 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1515 'md5': '43662b577c018ad707a63766462b1e87',
1519 'title': 'New experience with Acrobat DC',
1520 'description': 'New experience with Acrobat DC',
1521 'duration': 248.667,
1524 # BrightcoveInPageEmbed embed
1526 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1528 'id': '4238694884001',
1530 'title': 'Tabletop: Dread, Last Thoughts',
1531 'description': 'Tabletop: Dread, Last Thoughts',
1535 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1536 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1538 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1540 'id': '4785848093001',
1542 'title': 'The Cardinal Pell Interview',
1543 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1544 'uploader': 'GlobeCast Australia - GlobeStream',
1545 'uploader_id': '2733773828001',
1546 'upload_date': '20160304',
1547 'timestamp': 1457083087,
1551 'skip_download': True,
1555 # Brightcove embed with whitespace around attribute names
1556 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1558 'id': '3167554373001',
1560 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1561 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1562 'uploader_id': '1079349493',
1563 'upload_date': '20140207',
1564 'timestamp': 1391810548,
1567 'skip_download': True,
1570 # Another form of arte.tv embed
1572 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1573 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1575 'id': '030273-562_PLUS7-F',
1577 'title': 'ARTE Reportage - Nulle part, en France',
1578 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1579 'upload_date': '20160409',
1584 'url': 'http://www.wykop.pl/link/3088787/',
1585 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1587 'id': '874_1459135191',
1589 'title': 'Man shows poor quality of new apartment building',
1590 'description': 'The wall is like a sand pile.',
1591 'uploader': 'Lake8737',
1593 'add_ie': [LiveLeakIE.ie_key()],
1595 # Another LiveLeak embed pattern (#13336)
1597 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1599 'id': '2eb_1496309988',
1601 'title': 'Thief robs place where everyone was armed',
1602 'description': 'md5:694d73ee79e535953cf2488562288eee',
1603 'uploader': 'brazilwtf',
1605 'add_ie': [LiveLeakIE.ie_key()],
1607 # Duplicated embedded video URLs
1609 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1611 'id': '149298443_480_16c25b74_2',
1613 'title': 'vs. Blue Orange Spring Game',
1614 'uploader': 'www.hudl.com',
1617 # twitter:player:stream embed
1619 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1623 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1624 'uploader': 'www.rtl.be',
1628 'skip_download': True,
1631 # twitter:player embed
1633 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1634 'md5': 'a3e0df96369831de324f0778e126653c',
1636 'id': '4909620399001',
1638 'title': 'What Do Black Holes Sound Like?',
1639 'description': 'what do black holes sound like',
1640 'upload_date': '20160524',
1641 'uploader_id': '29913724001',
1642 'timestamp': 1464107587,
1643 'uploader': 'TheAtlantic',
1645 'add_ie': ['BrightcoveLegacy'],
1647 # Facebook <iframe> embed
1649 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1650 'md5': 'fbcde74f534176ecb015849146dd3aee',
1652 'id': '599637780109885',
1654 'title': 'Facebook video #599637780109885',
1657 # Facebook <iframe> embed, plugin video
1659 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1661 'id': '1754168231264132',
1663 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1664 'uploader': 'Tariq Ramadan (official)',
1665 'timestamp': 1496758379,
1666 'upload_date': '20170606',
1669 'skip_download': True,
1672 # Facebook API embed
1674 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1675 'md5': 'a47372ee61b39a7b90287094d447d94e',
1677 'id': '10153467542406923',
1679 'title': 'Facebook video #10153467542406923',
1682 # Wordpress "YouTube Video Importer" plugin
1684 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1685 'md5': 'd16797741b560b485194eddda8121b48',
1687 'id': 'HNTXWDXV9Is',
1689 'title': 'Blue Devils Drumline Stanford lot 2016',
1690 'upload_date': '20160627',
1691 'uploader_id': 'GENOCIDE8GENERAL10',
1692 'uploader': 'cylus cyrus',
1696 # video stored on custom kaltura server
1697 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1698 'md5': '537617d06e64dfed891fa1593c4b30cc',
1702 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1703 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1704 'uploader_id': 'videos.expansion@el-mundo.net',
1705 'upload_date': '20150429',
1706 'timestamp': 1430303472,
1708 'add_ie': ['Kaltura'],
1711 # Non-standard Vimeo embed
1712 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1713 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1717 'title': 'Understanding the web - Teaser',
1718 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1719 'upload_date': '20151214',
1720 'uploader': 'OpenClassrooms',
1721 'uploader_id': 'openclassrooms',
1723 'add_ie': ['Vimeo'],
1726 # generic vimeo embed that requires original URL passed as Referer
1727 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1728 'only_matching': True,
1731 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1732 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1734 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1736 'title': 'Big Buck Bunny',
1737 'description': 'Royalty free test video',
1738 'timestamp': 1432816365,
1739 'upload_date': '20150528',
1743 'skip_download': True,
1745 'add_ie': [ArkenaIE.ie_key()],
1748 '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/',
1752 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1755 'skip_download': True,
1757 'add_ie': [Vbox7IE.ie_key()],
1761 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1764 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1766 'playlist_mincount': 3,
1770 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1772 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1773 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1775 'playlist_mincount': 2,
1779 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1783 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1784 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1787 'skip_download': True,
1789 'add_ie': [TwentyMinutenIE.ie_key()],
1793 'url': 'https://en.support.wordpress.com/videopress/',
1797 'title': 'IMG_5786',
1798 'timestamp': 1435711927,
1799 'upload_date': '20150701',
1802 'skip_download': True,
1804 'add_ie': [VideoPressIE.ie_key()],
1808 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1810 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1812 'title': 'Магаззино: Казань 2',
1813 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1814 'uploader': 'Магаззино',
1815 'upload_date': '20170228',
1816 'uploader_id': '996642',
1819 'skip_download': True,
1821 'add_ie': [RutubeIE.ie_key()],
1824 # ThePlatform embedded with whitespaces in URLs
1825 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1826 'only_matching': True,
1829 # Senate ISVP iframe https
1830 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1831 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1833 'id': 'govtaff020316',
1835 'title': 'Integrated Senate Video Player',
1837 'add_ie': [SenateISVPIE.ie_key()],
1840 # Limelight embeds (1 channel embed + 4 media embeds)
1841 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1843 'id': 'FacilitatorTraining2017',
1844 'title': 'Facilitator Training 2017',
1846 'playlist_mincount': 5,
1849 # Limelight embed (LimelightPlayerUtil.embed)
1850 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1852 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1854 'title': '07448641',
1855 'timestamp': 1499890639,
1856 'upload_date': '20170712',
1859 'skip_download': True,
1861 'add_ie': ['LimelightMedia'],
1864 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1866 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1867 'title': 'Standoff with Walnut Creek murder suspect ends',
1868 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1870 'playlist_mincount': 4,
1873 # WashingtonPost embed
1874 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1876 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1878 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1879 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1880 'timestamp': 1455216756,
1881 'uploader': 'The Washington Post',
1882 'upload_date': '20160211',
1884 'add_ie': [WashingtonPostIE.ie_key()],
1888 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1892 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1895 'skip_download': True,
1897 'add_ie': [MediasetIE.ie_key()],
1901 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1904 'title': 'Slovenskom sa prehnala vlna silných búrok',
1906 'playlist_mincount': 5,
1907 'add_ie': [JojIE.ie_key()],
1910 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1911 'url': 'https://tvrain.ru/amp/418921/',
1912 'md5': 'cc00413936695987e8de148b67d14f1d',
1916 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1921 'url': 'http://help.vzaar.com/article/165-embedding-video',
1922 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1926 'title': 'Building A Business Online: Principal Chairs Q & A',
1930 # multiple HTML5 videos on one page
1931 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1933 'id': 'keyscenarios',
1934 'title': 'Rescue Kit 14 Free Edition - Getting started',
1936 'playlist_count': 4,
1940 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1941 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1944 'title': 'vl14062007715967',
1949 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1950 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1952 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1954 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1955 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1956 'timestamp': 1474354800,
1957 'upload_date': '20160920',
1961 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1965 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1966 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1967 'timestamp': 1516100691,
1968 'upload_date': '20180116',
1971 'skip_download': True,
1973 'add_ie': [SpringboardPlatformIE.ie_key()],
1976 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1978 'id': 'uPDB5I9wfp8',
1980 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1981 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1982 'upload_date': '20160219',
1983 'uploader': 'Pocoyo - Português (BR)',
1984 'uploader_id': 'PocoyoBrazil',
1986 'add_ie': [YoutubeIE.ie_key()],
1988 'skip_download': True,
1992 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1994 'id': 'vMDE4NzI1Mjgt690b',
1998 'add_ie': [YapFilesIE.ie_key()],
2000 'skip_download': True,
2004 # CloudflareStream embed
2005 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2007 'id': '31c9291ab41fac05471db4e73aa11717',
2009 'title': '31c9291ab41fac05471db4e73aa11717',
2011 'add_ie': [CloudflareStreamIE.ie_key()],
2013 'skip_download': True,
2018 'url': 'https://joinpeertube.org/fr/home/',
2021 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2023 'playlist_count': 2,
2026 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2027 'md5': 'b68d276de422ab07ee1d49388103f457',
2030 'title': 'Lock up and get excited',
2033 'skip': 'TODO: fix nested playlists processing in tests',
2036 # # TODO: find another test
2037 # # http://schema.org/VideoObject
2038 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2039 # 'md5': '888dcf08b7ea671381f00fab74692755',
2041 # 'id': 'nyvTSJMKId',
2043 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2044 # 'description': '#love for cats.',
2045 # 'timestamp': 1461244995,
2046 # 'upload_date': '20160421',
2049 # 'force_generic_extractor': True,
2054 def report_following_redirect(self, new_url):
2055 """Report information extraction."""
2056 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2058 def _extract_rss(self, url, video_id, doc):
2059 playlist_title = doc.find('./channel/title').text
2060 playlist_desc_el = doc.find('./channel/description')
2061 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2064 for it in doc.findall('./channel/item'):
2066 enclosure_nodes = it.findall('./enclosure')
2067 for e in enclosure_nodes:
2068 next_url = e.attrib.get('url')
2073 next_url = xpath_text(it, 'link', fatal=False)
2079 '_type': 'url_transparent',
2081 'title': it.find('title').text,
2085 '_type': 'playlist',
2087 'title': playlist_title,
2088 'description': playlist_desc,
2092 def _extract_camtasia(self, url, video_id, webpage):
2093 """ Returns None if no camtasia video can be found. """
2095 camtasia_cfg = self._search_regex(
2096 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2097 webpage, 'camtasia configuration file', default=None)
2098 if camtasia_cfg is None:
2101 title = self._html_search_meta('DC.title', webpage, fatal=True)
2103 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2104 camtasia_cfg = self._download_xml(
2105 camtasia_url, video_id,
2106 note='Downloading camtasia configuration',
2107 errnote='Failed to download camtasia configuration')
2108 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2111 for n in fileset_node.getchildren():
2112 url_n = n.find('./uri')
2117 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2118 'title': '%s - %s' % (title, n.tag),
2119 'url': compat_urlparse.urljoin(url, url_n.text),
2120 'duration': float_or_none(n.find('./duration').text),
2124 '_type': 'playlist',
2129 def _real_extract(self, url):
2130 if url.startswith('//'):
2133 'url': self.http_scheme() + url,
2136 parsed_url = compat_urlparse.urlparse(url)
2137 if not parsed_url.scheme:
2138 default_search = self._downloader.params.get('default_search')
2139 if default_search is None:
2140 default_search = 'fixup_error'
2142 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2144 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2145 return self.url_result('http://' + url)
2146 elif default_search != 'fixup_error':
2147 if default_search == 'auto_warning':
2148 if re.match(r'^(?:url|URL)$', url):
2149 raise ExtractorError(
2150 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2153 self._downloader.report_warning(
2154 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2155 return self.url_result('ytsearch:' + url)
2157 if default_search in ('error', 'fixup_error'):
2158 raise ExtractorError(
2159 '%r is not a valid URL. '
2160 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2161 % (url, url), expected=True)
2163 if ':' not in default_search:
2164 default_search += ':'
2165 return self.url_result(default_search + url)
2167 url, smuggled_data = unsmuggle_url(url)
2168 force_videoid = None
2169 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2170 if smuggled_data and 'force_videoid' in smuggled_data:
2171 force_videoid = smuggled_data['force_videoid']
2172 video_id = force_videoid
2174 video_id = self._generic_id(url)
2176 self.to_screen('%s: Requesting header' % video_id)
2178 head_req = HEADRequest(url)
2179 head_response = self._request_webpage(
2181 note=False, errnote='Could not send HEAD request to %s' % url,
2184 if head_response is not False:
2185 # Check for redirect
2186 new_url = compat_str(head_response.geturl())
2188 self.report_following_redirect(new_url)
2190 new_url = smuggle_url(
2191 new_url, {'force_videoid': force_videoid})
2192 return self.url_result(new_url)
2194 full_response = None
2195 if head_response is False:
2196 request = sanitized_Request(url)
2197 request.add_header('Accept-Encoding', '*')
2198 full_response = self._request_webpage(request, video_id)
2199 head_response = full_response
2203 'title': self._generic_title(url),
2204 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2207 # Check for direct link to a video
2208 content_type = head_response.headers.get('Content-Type', '').lower()
2209 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2211 format_id = compat_str(m.group('format_id'))
2212 if format_id.endswith('mpegurl'):
2213 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2214 elif format_id == 'f4m':
2215 formats = self._extract_f4m_formats(url, video_id)
2218 'format_id': format_id,
2220 'vcodec': 'none' if m.group('type') == 'audio' else None
2222 info_dict['direct'] = True
2223 self._sort_formats(formats)
2224 info_dict['formats'] = formats
2227 if not self._downloader.params.get('test', False) and not is_intentional:
2228 force = self._downloader.params.get('force_generic_extractor', False)
2229 self._downloader.report_warning(
2230 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2232 if not full_response:
2233 request = sanitized_Request(url)
2234 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2235 # making it impossible to download only chunk of the file (yet we need only 512kB to
2236 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2237 # that will always result in downloading the whole file that is not desirable.
2238 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2239 # to accept raw bytes and being able to download only a chunk.
2240 # It may probably better to solve this by checking Content-Type for application/octet-stream
2241 # after HEAD request finishes, but not sure if we can rely on this.
2242 request.add_header('Accept-Encoding', '*')
2243 full_response = self._request_webpage(request, video_id)
2245 first_bytes = full_response.read(512)
2247 # Is it an M3U playlist?
2248 if first_bytes.startswith(b'#EXTM3U'):
2249 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2250 self._sort_formats(info_dict['formats'])
2253 # Maybe it's a direct link to a video?
2254 # Be careful not to download the whole thing!
2255 if not is_html(first_bytes):
2256 self._downloader.report_warning(
2257 'URL could be a direct video link, returning it as such.')
2264 webpage = self._webpage_read_content(
2265 full_response, url, video_id, prefix=first_bytes)
2267 self.report_extraction(video_id)
2269 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2271 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2272 if doc.tag == 'rss':
2273 return self._extract_rss(url, video_id, doc)
2274 elif doc.tag == 'SmoothStreamingMedia':
2275 info_dict['formats'] = self._parse_ism_formats(doc, url)
2276 self._sort_formats(info_dict['formats'])
2278 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2279 smil = self._parse_smil(doc, url, video_id)
2280 self._sort_formats(smil['formats'])
2282 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2283 return self.playlist_result(
2285 doc, video_id, xspf_url=url,
2286 xspf_base_url=compat_str(full_response.geturl())),
2288 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2289 info_dict['formats'] = self._parse_mpd_formats(
2291 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2293 self._sort_formats(info_dict['formats'])
2295 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2296 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2297 self._sort_formats(info_dict['formats'])
2299 except compat_xml_parse_error:
2302 # Is it a Camtasia project?
2303 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2304 if camtasia_res is not None:
2307 # Sometimes embedded video player is hidden behind percent encoding
2308 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2309 # Unescaping the whole page allows to handle those cases in a generic way
2310 webpage = compat_urllib_parse_unquote(webpage)
2312 # it's tempting to parse this further, but you would
2313 # have to take into account all the variations like
2314 # Video Title - Site Name
2315 # Site Name | Video Title
2316 # Video Title - Tagline | Site Name
2317 # and so on and so forth; it's just not practical
2318 video_title = self._og_search_title(
2319 webpage, default=None) or self._html_search_regex(
2320 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2323 # Try to detect age limit automatically
2324 age_limit = self._rta_search(webpage)
2325 # And then there are the jokers who advertise that they use RTA,
2326 # but actually don't.
2327 AGE_LIMIT_MARKERS = [
2328 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2330 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2333 # video uploader is domain name
2334 video_uploader = self._search_regex(
2335 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2337 video_description = self._og_search_description(webpage, default=None)
2338 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2341 'title': video_title,
2342 'description': video_description,
2343 'thumbnail': video_thumbnail,
2344 'age_limit': age_limit,
2347 # Look for Brightcove Legacy Studio embeds
2348 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2352 'url': smuggle_url(bc_url, {'Referer': url}),
2353 'ie_key': 'BrightcoveLegacy'
2354 } for bc_url in bc_urls]
2357 '_type': 'playlist',
2358 'title': video_title,
2363 # Look for Brightcove New Studio embeds
2364 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2366 return self.playlist_from_matches(
2367 bc_urls, video_id, video_title,
2368 getter=lambda x: smuggle_url(x, {'referrer': url}),
2371 # Look for Nexx embeds
2372 nexx_urls = NexxIE._extract_urls(webpage)
2374 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2376 # Look for Nexx iFrame embeds
2377 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2379 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2381 # Look for ThePlatform embeds
2382 tp_urls = ThePlatformIE._extract_urls(webpage)
2384 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2386 # Look for Vessel embeds
2387 vessel_urls = VesselIE._extract_urls(webpage)
2389 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2391 # Look for embedded rtl.nl player
2392 matches = re.findall(
2393 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2396 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2398 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2400 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2402 vid_me_embed_url = self._search_regex(
2403 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2404 webpage, 'vid.me embed', default=None)
2405 if vid_me_embed_url is not None:
2406 return self.url_result(vid_me_embed_url, 'Vidme')
2408 # Look for YouTube embeds
2409 youtube_urls = YoutubeIE._extract_urls(webpage)
2411 return self.playlist_from_matches(
2412 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2414 matches = DailymotionIE._extract_urls(webpage)
2416 return self.playlist_from_matches(matches, video_id, video_title)
2418 # Look for embedded Dailymotion playlist player (#3822)
2420 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2422 playlists = re.findall(
2423 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2425 return self.playlist_from_matches(
2426 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2428 # Look for DailyMail embeds
2429 dailymail_urls = DailyMailIE._extract_urls(webpage)
2431 return self.playlist_from_matches(
2432 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2434 # Look for embedded Wistia player
2435 wistia_url = WistiaIE._extract_url(webpage)
2438 '_type': 'url_transparent',
2439 'url': self._proto_relative_url(wistia_url),
2440 'ie_key': WistiaIE.ie_key(),
2441 'uploader': video_uploader,
2444 # Look for SVT player
2445 svt_url = SVTIE._extract_url(webpage)
2447 return self.url_result(svt_url, 'SVT')
2449 # Look for Bandcamp pages with custom domain
2450 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2451 if mobj is not None:
2452 burl = unescapeHTML(mobj.group(1))
2453 # Don't set the extractor because it can be a track url or an album
2454 return self.url_result(burl)
2456 # Look for embedded Vevo player
2458 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2459 if mobj is not None:
2460 return self.url_result(mobj.group('url'))
2462 # Look for embedded Viddler player
2464 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2466 if mobj is not None:
2467 return self.url_result(mobj.group('url'))
2469 # Look for NYTimes player
2471 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2473 if mobj is not None:
2474 return self.url_result(mobj.group('url'))
2476 # Look for Libsyn player
2478 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2479 if mobj is not None:
2480 return self.url_result(mobj.group('url'))
2482 # Look for Ooyala videos
2483 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2484 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2485 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2486 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2487 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2488 if mobj is not None:
2489 embed_token = self._search_regex(
2490 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2491 webpage, 'ooyala embed token', default=None)
2492 return OoyalaIE._build_url_result(smuggle_url(
2495 'embed_token': embed_token,
2498 # Look for multiple Ooyala embeds on SBN network websites
2499 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2500 if mobj is not None:
2501 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2503 return self.playlist_from_matches(
2504 embeds, video_id, video_title,
2505 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2507 # Look for Aparat videos
2508 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2509 if mobj is not None:
2510 return self.url_result(mobj.group(1), 'Aparat')
2512 # Look for MPORA videos
2513 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2514 if mobj is not None:
2515 return self.url_result(mobj.group(1), 'Mpora')
2517 # Look for embedded NovaMov-based player
2519 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2520 (?P<url>http://(?:(?:embed|www)\.)?
2522 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2523 videoweed\.(?:es|com)|
2524 movshare\.(?:net|sx|ag)|
2525 divxstage\.(?:eu|net|ch|co|at|ag))
2526 /embed\.php.+?)\1''', webpage)
2527 if mobj is not None:
2528 return self.url_result(mobj.group('url'))
2530 # Look for embedded Facebook player
2531 facebook_urls = FacebookIE._extract_urls(webpage)
2533 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2535 # Look for embedded VK player
2536 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2537 if mobj is not None:
2538 return self.url_result(mobj.group('url'), 'VK')
2540 # Look for embedded Odnoklassniki player
2541 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2545 # Look for embedded ivi player
2546 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2547 if mobj is not None:
2548 return self.url_result(mobj.group('url'), 'Ivi')
2550 # Look for embedded Huffington Post player
2552 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2553 if mobj is not None:
2554 return self.url_result(mobj.group('url'), 'HuffPost')
2557 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2558 if mobj is not None:
2559 return self.url_result(mobj.group('url'))
2560 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2561 if mobj is not None:
2562 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2564 # Look for funnyordie embed
2565 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2567 return self.playlist_from_matches(
2568 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2570 # Look for BBC iPlayer embed
2571 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2573 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2575 # Look for embedded RUTV player
2576 rutv_url = RUTVIE._extract_url(webpage)
2578 return self.url_result(rutv_url, 'RUTV')
2580 # Look for embedded TVC player
2581 tvc_url = TVCIE._extract_url(webpage)
2583 return self.url_result(tvc_url, 'TVC')
2585 # Look for embedded SportBox player
2586 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2588 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2590 # Look for embedded XHamster player
2591 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2593 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2595 # Look for embedded TNAFlixNetwork player
2596 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2598 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2600 # Look for embedded PornHub player
2601 pornhub_urls = PornHubIE._extract_urls(webpage)
2603 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2605 # Look for embedded DrTuber player
2606 drtuber_urls = DrTuberIE._extract_urls(webpage)
2608 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2610 # Look for embedded RedTube player
2611 redtube_urls = RedTubeIE._extract_urls(webpage)
2613 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2615 # Look for embedded Tube8 player
2616 tube8_urls = Tube8IE._extract_urls(webpage)
2618 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2620 # Look for embedded Tvigle player
2622 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2623 if mobj is not None:
2624 return self.url_result(mobj.group('url'), 'Tvigle')
2626 # Look for embedded TED player
2628 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2629 if mobj is not None:
2630 return self.url_result(mobj.group('url'), 'TED')
2632 # Look for embedded Ustream videos
2633 ustream_url = UstreamIE._extract_url(webpage)
2635 return self.url_result(ustream_url, UstreamIE.ie_key())
2637 # Look for embedded arte.tv player
2639 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2641 if mobj is not None:
2642 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2644 # Look for embedded francetv player
2646 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'))
2651 # Look for embedded smotri.com player
2652 smotri_url = SmotriIE._extract_url(webpage)
2654 return self.url_result(smotri_url, 'Smotri')
2656 # Look for embedded Myvi.ru player
2657 myvi_url = MyviIE._extract_url(webpage)
2659 return self.url_result(myvi_url)
2661 # Look for embedded soundcloud player
2662 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2664 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2666 # Look for tunein player
2667 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2669 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2671 # Look for embedded mtvservices player
2672 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2674 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2676 # Look for embedded yahoo player
2678 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2680 if mobj is not None:
2681 return self.url_result(mobj.group('url'), 'Yahoo')
2683 # Look for embedded sbs.com.au player
2687 <meta\s+property="og:video"\s+content=|
2690 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2692 if mobj is not None:
2693 return self.url_result(mobj.group('url'), 'SBS')
2695 # Look for embedded Cinchcast player
2697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2699 if mobj is not None:
2700 return self.url_result(mobj.group('url'), 'Cinchcast')
2703 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2707 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2709 if mobj is not None:
2710 return self.url_result(mobj.group('url'), 'MLB')
2713 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2715 if mobj is not None:
2716 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2719 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2721 if mobj is not None:
2722 return self.url_result(mobj.group('url'), 'Livestream')
2724 # Look for Zapiks embed
2726 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2727 if mobj is not None:
2728 return self.url_result(mobj.group('url'), 'Zapiks')
2730 # Look for Kaltura embeds
2731 kaltura_url = KalturaIE._extract_url(webpage)
2733 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2735 # Look for EaglePlatform embeds
2736 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2737 if eagleplatform_url:
2738 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2740 # Look for ClipYou (uses EaglePlatform) embeds
2742 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2743 if mobj is not None:
2744 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2746 # Look for Pladform embeds
2747 pladform_url = PladformIE._extract_url(webpage)
2749 return self.url_result(pladform_url)
2751 # Look for Videomore embeds
2752 videomore_url = VideomoreIE._extract_url(webpage)
2754 return self.url_result(videomore_url)
2756 # Look for Webcaster embeds
2757 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2759 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2761 # Look for Playwire embeds
2763 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2764 if mobj is not None:
2765 return self.url_result(mobj.group('url'))
2767 # Look for 5min embeds
2769 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2770 if mobj is not None:
2771 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2773 # Look for Crooks and Liars embeds
2775 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2776 if mobj is not None:
2777 return self.url_result(mobj.group('url'))
2779 # Look for NBC Sports VPlayer embeds
2780 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2782 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2784 # Look for NBC News embeds
2785 nbc_news_embed_url = re.search(
2786 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2787 if nbc_news_embed_url:
2788 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2790 # Look for Google Drive embeds
2791 google_drive_url = GoogleDriveIE._extract_url(webpage)
2792 if google_drive_url:
2793 return self.url_result(google_drive_url, 'GoogleDrive')
2795 # Look for UDN embeds
2797 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2798 if mobj is not None:
2799 return self.url_result(
2800 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2802 # Look for Senate ISVP iframe
2803 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2805 return self.url_result(senate_isvp_url, 'SenateISVP')
2807 # Look for OnionStudios embeds
2808 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2809 if onionstudios_url:
2810 return self.url_result(onionstudios_url)
2812 # Look for ViewLift embeds
2813 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2815 return self.url_result(viewlift_url)
2817 # Look for JWPlatform embeds
2818 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2820 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2822 # Look for Digiteka embeds
2823 digiteka_url = DigitekaIE._extract_url(webpage)
2825 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2827 # Look for Arkena embeds
2828 arkena_url = ArkenaIE._extract_url(webpage)
2830 return self.url_result(arkena_url, ArkenaIE.ie_key())
2832 # Look for Piksel embeds
2833 piksel_url = PikselIE._extract_url(webpage)
2835 return self.url_result(piksel_url, PikselIE.ie_key())
2837 # Look for Limelight embeds
2838 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2840 return self.playlist_result(
2841 limelight_urls, video_id, video_title, video_description)
2843 # Look for Anvato embeds
2844 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2846 return self.playlist_result(
2847 anvato_urls, video_id, video_title, video_description)
2849 # Look for AdobeTVVideo embeds
2851 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2853 if mobj is not None:
2854 return self.url_result(
2855 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2858 # Look for Vine embeds
2860 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2862 if mobj is not None:
2863 return self.url_result(
2864 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2866 # Look for VODPlatform embeds
2868 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2870 if mobj is not None:
2871 return self.url_result(
2872 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2874 # Look for Mangomolo embeds
2876 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2878 video\?.*?\bid=(?P<video_id>\d+)|
2879 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2880 ).+?)\1''', webpage)
2881 if mobj is not None:
2883 '_type': 'url_transparent',
2884 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2885 'title': video_title,
2886 'description': video_description,
2887 'thumbnail': video_thumbnail,
2888 'uploader': video_uploader,
2890 video_id = mobj.group('video_id')
2893 'ie_key': 'MangomoloVideo',
2898 'ie_key': 'MangomoloLive',
2899 'id': mobj.group('channel_id'),
2903 # Look for Instagram embeds
2904 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2905 if instagram_embed_url is not None:
2906 return self.url_result(
2907 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2909 # Look for LiveLeak embeds
2910 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2912 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2914 # Look for 3Q SDN embeds
2915 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2918 '_type': 'url_transparent',
2919 'ie_key': ThreeQSDNIE.ie_key(),
2920 'url': self._proto_relative_url(threeqsdn_url),
2921 'title': video_title,
2922 'description': video_description,
2923 'thumbnail': video_thumbnail,
2924 'uploader': video_uploader,
2927 # Look for VBOX7 embeds
2928 vbox7_url = Vbox7IE._extract_url(webpage)
2930 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2932 # Look for DBTV embeds
2933 dbtv_urls = DBTVIE._extract_urls(webpage)
2935 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2937 # Look for Videa embeds
2938 videa_urls = VideaIE._extract_urls(webpage)
2940 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2942 # Look for 20 minuten embeds
2943 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2945 return self.playlist_from_matches(
2946 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2948 # Look for Openload embeds
2949 openload_urls = OpenloadIE._extract_urls(webpage)
2951 return self.playlist_from_matches(
2952 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2954 # Look for VideoPress embeds
2955 videopress_urls = VideoPressIE._extract_urls(webpage)
2957 return self.playlist_from_matches(
2958 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2960 # Look for Rutube embeds
2961 rutube_urls = RutubeIE._extract_urls(webpage)
2963 return self.playlist_from_matches(
2964 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2966 # Look for WashingtonPost embeds
2967 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2969 return self.playlist_from_matches(
2970 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2972 # Look for Mediaset embeds
2973 mediaset_urls = MediasetIE._extract_urls(webpage)
2975 return self.playlist_from_matches(
2976 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2978 # Look for JOJ.sk embeds
2979 joj_urls = JojIE._extract_urls(webpage)
2981 return self.playlist_from_matches(
2982 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2984 # Look for megaphone.fm embeds
2985 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2987 return self.playlist_from_matches(
2988 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2990 # Look for vzaar embeds
2991 vzaar_urls = VzaarIE._extract_urls(webpage)
2993 return self.playlist_from_matches(
2994 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2996 channel9_urls = Channel9IE._extract_urls(webpage)
2998 return self.playlist_from_matches(
2999 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3001 vshare_urls = VShareIE._extract_urls(webpage)
3003 return self.playlist_from_matches(
3004 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3006 # Look for Mediasite embeds
3007 mediasite_urls = MediasiteIE._extract_urls(webpage)
3010 self.url_result(smuggle_url(
3011 compat_urlparse.urljoin(url, mediasite_url),
3012 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3013 for mediasite_url in mediasite_urls]
3014 return self.playlist_result(entries, video_id, video_title)
3016 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3017 if springboardplatform_urls:
3018 return self.playlist_from_matches(
3019 springboardplatform_urls, video_id, video_title,
3020 ie=SpringboardPlatformIE.ie_key())
3022 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3024 return self.playlist_from_matches(
3025 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3027 vice_urls = ViceIE._extract_urls(webpage)
3029 return self.playlist_from_matches(
3030 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3032 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3034 return self.playlist_from_matches(
3035 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3037 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3038 if cloudflarestream_urls:
3039 return self.playlist_from_matches(
3040 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3042 peertube_urls = PeerTubeIE._extract_urls(webpage)
3044 return self.playlist_from_matches(
3045 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3047 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3048 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3050 if sharevideos_urls:
3051 return self.playlist_from_matches(
3052 sharevideos_urls, video_id, video_title)
3054 # Look for HTML5 media
3055 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3057 if len(entries) == 1:
3060 'title': video_title,
3063 for num, entry in enumerate(entries, start=1):
3065 'id': '%s-%s' % (video_id, num),
3066 'title': '%s (%d)' % (video_title, num),
3068 for entry in entries:
3069 self._sort_formats(entry['formats'])
3070 return self.playlist_result(entries, video_id, video_title)
3072 jwplayer_data = self._find_jwplayer_data(
3073 webpage, video_id, transform_source=js_to_json)
3075 info = self._parse_jwplayer_data(
3076 jwplayer_data, video_id, require_title=False, base_url=url)
3077 return merge_dicts(info, info_dict)
3081 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3083 if mobj is not None:
3084 sources = self._parse_json(
3085 mobj.group(1), video_id, transform_source=js_to_json,
3087 if not isinstance(sources, list):
3090 for source in sources:
3091 src = source.get('src')
3092 if not src or not isinstance(src, compat_str):
3094 src = compat_urlparse.urljoin(url, src)
3095 src_type = source.get('type')
3096 if isinstance(src_type, compat_str):
3097 src_type = src_type.lower()
3098 ext = determine_ext(src).lower()
3099 if src_type == 'video/youtube':
3100 return self.url_result(src, YoutubeIE.ie_key())
3101 if src_type == 'application/dash+xml' or ext == 'mpd':
3102 formats.extend(self._extract_mpd_formats(
3103 src, video_id, mpd_id='dash', fatal=False))
3104 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3105 formats.extend(self._extract_m3u8_formats(
3106 src, video_id, 'mp4', entry_protocol='m3u8_native',
3107 m3u8_id='hls', fatal=False))
3111 'ext': (mimetype2ext(src_type) or
3112 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3115 self._sort_formats(formats)
3116 info_dict['formats'] = formats
3119 # Looking for http://schema.org/VideoObject
3120 json_ld = self._search_json_ld(
3121 webpage, video_id, default={}, expected_type='VideoObject')
3122 if json_ld.get('url'):
3123 return merge_dicts(json_ld, info_dict)
3125 def check_video(vurl):
3126 if YoutubeIE.suitable(vurl):
3128 if RtmpIE.suitable(vurl):
3130 vpath = compat_urlparse.urlparse(vurl).path
3131 vext = determine_ext(vpath)
3132 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3134 def filter_video(urls):
3135 return list(filter(check_video, urls))
3137 # Start with something easy: JW Player in SWFObject
3138 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3140 # Look for gorilla-vid style embedding
3141 found = filter_video(re.findall(r'''(?sx)
3145 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3148 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3150 # Broaden the search a little bit
3151 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3153 # Broaden the findall a little bit: JWPlayer JS loader
3154 found = filter_video(re.findall(
3155 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3158 found = filter_video(re.findall(r'''(?xs)
3159 flowplayer\("[^"]+",\s*
3161 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3162 ["']?url["']?\s*:\s*["']([^"']+)["']
3167 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3169 # Try to find twitter cards info
3170 # twitter:player:stream should be checked before twitter:player since
3171 # it is expected to contain a raw stream (see
3172 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3173 found = filter_video(re.findall(
3174 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3176 # We look for Open Graph info:
3177 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3178 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3179 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3180 if m_video_type is not None:
3181 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3183 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3185 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3186 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3189 # Look also in Refresh HTTP header
3190 refresh_header = head_response.headers.get('Refresh')
3192 # In python 2 response HTTP headers are bytestrings
3193 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3194 refresh_header = refresh_header.decode('iso-8859-1')
3195 found = re.search(REDIRECT_REGEX, refresh_header)
3197 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3199 self.report_following_redirect(new_url)
3208 # twitter:player is a https URL to iframe player that may or may not
3209 # be supported by youtube-dl thus this is checked the very last (see
3210 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3211 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3212 if embed_url and embed_url != url:
3213 return self.url_result(embed_url)
3216 raise UnsupportedError(url)
3219 for video_url in orderedSet(found):
3220 video_url = unescapeHTML(video_url)
3221 video_url = video_url.replace('\\/', '/')
3222 video_url = compat_urlparse.urljoin(url, video_url)
3223 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3225 # Sometimes, jwplayer extraction will result in a YouTube URL
3226 if YoutubeIE.suitable(video_url):
3227 entries.append(self.url_result(video_url, 'Youtube'))
3230 # here's a fun little line of code for you:
3231 video_id = os.path.splitext(video_id)[0]
3235 'uploader': video_uploader,
3236 'title': video_title,
3237 'age_limit': age_limit,
3240 if RtmpIE.suitable(video_url):
3241 entry_info_dict.update({
3242 '_type': 'url_transparent',
3243 'ie_key': RtmpIE.ie_key(),
3246 entries.append(entry_info_dict)
3249 ext = determine_ext(video_url)
3251 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3253 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3255 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3257 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3259 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3260 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3261 # Just matching .ism/manifest is not enough to be reliably sure
3262 # whether it's actually an ISM manifest or some other streaming
3263 # manifest since there are various streaming URL formats
3264 # possible (see [1]) as well as some other shenanigans like
3265 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3267 # Thus the most reasonable way to solve this is to delegate
3268 # to generic extractor in order to look into the contents of
3269 # the manifest itself.
3270 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3271 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3272 entry_info_dict = self.url_result(
3273 smuggle_url(video_url, {'to_generic': True}),
3276 entry_info_dict['url'] = video_url
3278 if entry_info_dict.get('formats'):
3279 self._sort_formats(entry_info_dict['formats'])
3281 entries.append(entry_info_dict)
3283 if len(entries) == 1:
3286 for num, e in enumerate(entries, start=1):
3287 # 'url' results don't have a title
3288 if e.get('title') is not None:
3289 e['title'] = '%s (%d)' % (e['title'], num)
3291 '_type': 'playlist',