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
112 class GenericIE(InfoExtractor):
113 IE_DESC = 'Generic downloader that works on some sites'
117 # Direct link to a video
119 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
120 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
125 'upload_date': '20100513',
128 # Direct link to media delivered compressed (until Accept-Encoding is *)
130 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
131 'md5': '128c42e68b13950268b648275386fc74',
133 'id': 'FictionJunction-Parallel_Hearts',
135 'title': 'FictionJunction-Parallel_Hearts',
136 'upload_date': '20140522',
138 'expected_warnings': [
139 'URL could be a direct video link, returning it as such.'
141 'skip': 'URL invalid',
143 # Direct download with broken HEAD
145 'url': 'http://ai-radio.org:8000/radio.opus',
152 'skip_download': True, # infinite live stream
154 'expected_warnings': [
155 r'501.*Not Implemented',
159 # Direct link with incorrect MIME type
161 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
162 'md5': '4ccbebe5f36706d85221f204d7eb5913',
164 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
165 'id': '5_Lennart_Poettering_-_Systemd',
167 'title': '5_Lennart_Poettering_-_Systemd',
168 'upload_date': '20141120',
170 'expected_warnings': [
171 'URL could be a direct video link, returning it as such.'
176 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
178 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
179 'title': 'Zero Punctuation',
180 'description': 're:.*groundbreaking video review series.*'
182 'playlist_mincount': 11,
184 # RSS feed with enclosure
186 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
188 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
190 'upload_date': '20150228',
191 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
194 # RSS feed with enclosures and unsupported link URLs
196 'url': 'http://www.hellointernet.fm/podcast?format=rss',
198 'id': 'http://www.hellointernet.fm/podcast?format=rss',
199 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
200 'title': 'Hello Internet',
202 'playlist_mincount': 100,
204 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
206 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
210 'title': 'Automatics, robotics and biocybernetics',
211 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
212 'upload_date': '20130627',
213 'formats': 'mincount:16',
214 'subtitles': 'mincount:1',
217 'force_generic_extractor': True,
218 'skip_download': True,
221 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
223 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
228 'formats': 'mincount:1',
231 'skip_download': True,
234 # SMIL from https://www.restudy.dk/video/play/id/1637
236 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
240 'title': 'video_1637',
241 'formats': 'mincount:3',
244 'skip_download': True,
247 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
249 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
251 'id': 'smil-service',
253 'title': 'smil-service',
254 'formats': 'mincount:1',
257 'skip_download': True,
260 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
262 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
266 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
267 'formats': 'mincount:3',
270 'skip_download': True,
273 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
275 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
277 'id': 'mZlp2ctYIUEB',
279 'title': 'Tikibad ontruimd wegens brand',
280 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
281 'thumbnail': r're:^https?://.*\.jpg$',
285 'skip_download': True,
288 # MPD from http://dash-mse-test.appspot.com/media.html
290 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
291 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
293 'id': 'car-20120827-manifest',
295 'title': 'car-20120827-manifest',
296 'formats': 'mincount:9',
297 'upload_date': '20130904',
300 'format': 'bestvideo',
303 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
305 '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',
310 'formats': 'mincount:8',
314 'skip_download': True,
316 'skip': 'video gone',
318 # m3u8 served with Content-Type: text/plain
320 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
325 'upload_date': '20140720',
326 'formats': 'mincount:11',
330 'skip_download': True,
332 'skip': 'video gone',
336 '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',
340 'upload_date': '20130224',
341 'uploader_id': 'TheVerge',
342 'description': r're:^Chris Ziegler takes a look at the\.*',
343 'uploader': 'The Verge',
344 'title': 'First Firefox OS phones side-by-side',
347 'skip_download': False,
351 # redirect in Refresh HTTP header
352 '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',
356 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
357 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
358 'upload_date': '20150917',
359 'uploader_id': 'brtvofficial',
360 'uploader': 'Boiler Room',
363 'skip_download': False,
367 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
368 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
370 'id': '13601338388002',
372 'uploader': 'www.hodiho.fr',
373 'title': 'R\u00e9gis plante sa Jeep',
376 # bandcamp page with custom domain
378 'add_ie': ['Bandcamp'],
379 'url': 'http://bronyrock.com/track/the-pony-mash',
383 'title': 'The Pony Mash',
384 'uploader': 'M_Pallante',
386 'skip': 'There is a limit of 200 free downloads / month for the test song',
389 # embedded brightcove video
390 # it also tests brightcove videos that need to set the 'Referer'
391 # in the http requests
392 'add_ie': ['BrightcoveLegacy'],
393 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
395 'id': '2765128793001',
397 'title': 'Le cours de bourse : l’analyse technique',
398 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
399 'uploader': 'BFM BUSINESS',
402 'skip_download': True,
406 # embedded with itemprop embedURL and video id spelled as `idVideo`
407 'add_id': ['BrightcoveLegacy'],
408 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
410 'id': '5255628253001',
412 'title': 'md5:37c519b1128915607601e75a87995fc0',
413 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
414 'uploader': 'BFM BUSINESS',
415 'uploader_id': '876450612001',
416 'timestamp': 1482255315,
417 'upload_date': '20161220',
420 'skip_download': True,
424 # https://github.com/rg3/youtube-dl/issues/2253
425 'url': 'http://bcove.me/i6nfkrc3',
426 'md5': '0ba9446db037002366bab3b3eb30c88c',
428 'id': '3101154703001',
430 'title': 'Still no power',
431 'uploader': 'thestar.com',
432 '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.',
434 'add_ie': ['BrightcoveLegacy'],
435 'skip': 'video gone',
438 'url': 'http://www.championat.com/video/football/v/87/87499.html',
439 'md5': 'fb973ecf6e4a78a67453647444222983',
441 'id': '3414141473001',
443 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
444 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
445 'uploader': 'Championat',
449 # https://github.com/rg3/youtube-dl/issues/3541
450 'add_ie': ['BrightcoveLegacy'],
451 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
453 'id': '3866516442001',
455 'title': 'Leer mij vrouwen kennen: Aflevering 1',
456 'description': 'Leer mij vrouwen kennen: Aflevering 1',
457 'uploader': 'SBS Broadcasting',
459 'skip': 'Restricted to Netherlands',
461 'skip_download': True, # m3u8 download
465 # Brightcove video in <iframe>
466 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
467 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
469 'id': '5360463607001',
471 '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',
472 '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。',
473 'uploader': 'United Nations',
474 'uploader_id': '1362235914001',
475 'timestamp': 1489593889,
476 'upload_date': '20170315',
478 'add_ie': ['BrightcoveLegacy'],
481 # Brightcove with alternative playerID key
482 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
484 'id': 'nmeth.2062_SV1',
485 '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',
489 'id': '2228375078001',
491 'title': 'nmeth.2062-sv1',
492 'description': 'nmeth.2062-sv1',
493 'timestamp': 1363357591,
494 'upload_date': '20130315',
495 'uploader': 'Nature Publishing Group',
496 'uploader_id': '1964492299001',
501 # Brightcove with UUID in videoPlayer
502 'url': 'http://www8.hp.com/cn/zh/home.html',
504 'id': '5255815316001',
506 'title': 'Sprocket Video - China',
507 'description': 'Sprocket Video - China',
508 'uploader': 'HP-Video Gallery',
509 'timestamp': 1482263210,
510 'upload_date': '20161220',
511 'uploader_id': '1107601872001',
514 'skip_download': True, # m3u8 download
516 'skip': 'video rotates...weekly?',
519 # Brightcove:new type [2].
520 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
521 'md5': '2b35148fcf48da41c9fb4591650784f3',
523 'id': '5348741021001',
525 'upload_date': '20170306',
526 'uploader_id': '4191638492001',
527 'timestamp': 1488769918,
528 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
533 # Alternative brightcove <video> attributes
534 '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/',
536 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
537 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
540 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
542 'id': '5311302538001',
544 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
545 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
546 'timestamp': 1486321708,
547 'upload_date': '20170205',
548 'uploader_id': '800000640001',
550 'only_matching': True,
554 # Brightcove with UUID in videoPlayer
555 'url': 'http://www8.hp.com/cn/zh/home.html',
557 'id': '5255815316001',
559 'title': 'Sprocket Video - China',
560 'description': 'Sprocket Video - China',
561 'uploader': 'HP-Video Gallery',
562 'timestamp': 1482263210,
563 'upload_date': '20161220',
564 'uploader_id': '1107601872001',
567 'skip_download': True, # m3u8 download
572 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
573 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
575 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
577 'title': '2cc213299525360.mov', # that's what we get
580 'add_ie': ['Ooyala'],
583 # ooyala video embedded with http://player.ooyala.com/iframe.js
584 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
586 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
588 'title': '"Steve Jobs: Man in the Machine" trailer',
589 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
593 'skip_download': True,
595 'skip': 'movie expired',
597 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
599 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
601 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
603 'title': 'Steampunk Fest Comes to Honesdale',
607 'skip_download': True,
612 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
616 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
617 'upload_date': '20140225',
618 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
619 'uploader': 'Tested',
620 'uploader_id': 'testedcom',
622 # No need to test YoutubeIE here
624 'skip_download': True,
629 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
633 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
634 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
636 # HEAD requests lead to endless 301, while GET is OK
637 'expected_warnings': ['301'],
641 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
645 'title': 'Охотское море стало целиком российским',
646 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
650 'skip_download': True,
655 '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/',
659 'title': 'Дошкольное воспитание',
664 'url': 'http://www.vestifinance.ru/articles/25753',
667 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
672 'title': 'Госзаказ. День 3',
678 'title': 'Госзаказ. День 2',
684 'title': 'Госзаказ. День 1',
690 'skip_download': True,
695 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
697 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
699 'title': 'Ужастики, русский трейлер (2015)',
700 'thumbnail': r're:^https?://.*\.jpg$',
706 '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',
709 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
711 'playlist_mincount': 7,
712 # This forum does not allow <iframe> syntaxes anymore
713 # Now HTML tags are displayed as-is
714 'skip': 'No videos on this page',
718 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
719 'md5': '65fdff94098e4a607385a60c5177c638',
723 'title': 'Hidden miracles of the natural world',
724 'uploader': 'Louie Schwartzberg',
725 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
728 # nowvideo embed hidden behind percent encoding
730 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
731 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
733 'id': '06e53103ca9aa',
735 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
736 'description': 'No description',
741 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
742 'md5': '7653032cbb25bf6c80d80f217055fa43',
744 'id': '048195-004_PLUS7-F',
747 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
748 'upload_date': '20140320',
751 'skip_download': 'Requires rtmpdump'
753 'skip': 'video gone',
757 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
761 'title': 'Alcaline, le concert avec Calogero',
762 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
763 'upload_date': '20150226',
764 'timestamp': 1424989860,
769 'skip_download': True,
771 'expected_warnings': [
777 'url': 'http://www.wired.com/2014/04/honda-asimo/',
778 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
780 'id': '53501be369702d3275860000',
782 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
787 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
788 'md5': '441aeeb82eb72c422c7f14ec533999cd',
790 'id': 'k2mm4bCdJ6CQ2i7c8o2',
792 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
793 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
795 'uploader_id': 'xgditw',
796 'upload_date': '20140425',
797 'timestamp': 1398441542,
799 'add_ie': ['Dailymotion'],
803 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
807 'title': 'Care worker punches elderly dementia patient in head 11 times',
808 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
810 'add_ie': ['DailyMail'],
812 'skip_download': True,
817 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
821 'title': 'The NBL Auction 2014',
822 'uploader': 'BADMINTON England',
823 'uploader_id': 'BADMINTONEvents',
824 'upload_date': '20140603',
825 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
827 'add_ie': ['Youtube'],
829 'skip_download': True,
834 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
835 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
837 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
839 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
840 'description': 'Two valets share their love for movie star Liam Neesons.',
841 'timestamp': 1349922600,
842 'upload_date': '20121011',
845 # YouTube embed via <data-embed-url="">
847 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
851 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
852 'uploader': 'Gameloft',
853 'uploader_id': 'gameloft',
854 'upload_date': '20140828',
855 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
858 'skip_download': True,
861 # YouTube <object> embed
863 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
864 'md5': '516718101ec834f74318df76259fb3cc',
868 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
869 'upload_date': '20080526',
870 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
871 'uploader': 'Christopher Sykes',
872 'uploader_id': 'ChristopherJSykes',
874 'add_ie': ['Youtube'],
878 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
880 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
882 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
883 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
888 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
890 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
891 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
897 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
902 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
903 'md5': '9d65602bf31c6e20014319c7d07fba27',
905 'id': '5123ea6d5e5a7',
908 'uploader': 'www.handjobhub.com',
909 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
912 # Multiple brightcove videos
913 # https://github.com/rg3/youtube-dl/issues/2283
915 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
917 'id': 'always-never',
918 'title': 'Always / Never - The New Yorker',
922 'extract_flat': False,
923 'skip_download': True,
928 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
929 'md5': '96f09a37e44da40dd083e12d9a683327',
933 'title': 'Ump changes call to ball',
934 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
936 'timestamp': 1401537900,
937 'upload_date': '20140531',
938 'thumbnail': r're:^https?://.*\.jpg$',
943 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
944 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
948 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
949 'description': 'a Paywall Videos video from Remilon',
951 'uploader': 'study.com',
952 'timestamp': 1459678540,
953 'upload_date': '20160403',
954 'filesize': 24687186,
958 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
959 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
963 'title': 'Conversation about Hexagonal Rails Part 1',
964 'description': 'a Martin Fowler video from ThoughtWorks',
966 'uploader': 'thoughtworks.wistia.com',
967 'timestamp': 1401832161,
968 'upload_date': '20140603',
971 # Wistia standard embed (async)
973 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
977 'title': 'Drip Brennan Dunn Workshop',
978 'description': 'a JV Webinars video from getdrip-1',
980 'timestamp': 1463607249,
981 'upload_date': '20160518',
984 'skip_download': True,
989 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
993 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
994 'uploader': 'Sophos Security',
995 'title': 'Chet Chat 171 - Oct 29, 2014',
996 'upload_date': '20141029',
999 # Soundcloud multiple embeds
1001 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1004 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1006 'playlist_mincount': 7,
1008 # TuneIn station embed
1010 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1015 'location': 'Paris, France',
1020 'skip_download': True,
1025 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1029 'upload_date': '20141112',
1030 'title': 'Rosetta #CometLanding webcast HL 10',
1033 # Another Livestream embed, without 'new.' in URL
1035 'url': 'https://www.freespeech.org/',
1039 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1043 'skip_download': True,
1048 'url': 'https://skiplagged.com/',
1051 'title': 'Skiplagged: The smart way to find cheap flights',
1053 'playlist_mincount': 1,
1054 'add_ie': ['Youtube'],
1058 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1062 'upload_date': '20141126',
1063 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1068 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1070 'id': '730m_DandD_1901_512k',
1072 'uploader': 'www.abc.net.au',
1073 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1076 # embedded viddler video
1078 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1082 'uploader': 'deadspin',
1083 'title': 'WALL-TO-GORTAT',
1084 'timestamp': 1422285291,
1085 'upload_date': '20150126',
1087 'add_ie': ['Viddler'],
1091 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1095 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1096 'description': 'md5:601cb790edd05908957dae8aaa866465',
1097 'upload_date': '20150220',
1099 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1103 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1105 'id': 'Mrj4DVp2zeA',
1107 'upload_date': '20150212',
1108 'uploader': 'The National Archives UK',
1109 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1110 'uploader_id': 'NationalArchives08',
1111 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1116 'url': 'http://www.suffolk.edu/sjc/live.php',
1120 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1121 'uploader': 'www.suffolk.edu',
1124 'skip_download': True,
1126 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1130 'url': 'http://www.indiedb.com/games/king-machine/videos',
1134 'title': 'king machine trailer 1',
1135 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1136 'thumbnail': r're:^https?://.*\.jpg$',
1140 # JWPlayer config passed as variable
1141 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1145 'title': 'ARIELE | Tube Cup',
1146 'uploader': 'www.txxx.com',
1150 'skip_download': True,
1155 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1156 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1160 'upload_date': '20171122',
1161 'timestamp': 1511366290,
1162 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1164 'add_ie': [JWPlatformIE.ie_key()],
1167 # Video.js embed, multiple formats
1168 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1170 'id': 'yygqldloqIk',
1172 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1173 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1174 'upload_date': '20130314',
1175 'uploader': 'PROстое3D',
1176 'uploader_id': 'PROstoe3D',
1179 'skip_download': True,
1183 # Video.js embed, single format
1184 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1188 'title': 'Step 1 - Good Foundation',
1189 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1192 'skip_download': True,
1197 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1198 'playlist_mincount': 5,
1200 'id': 'aanslagen-kopenhagen',
1201 'title': 'Aanslagen Kopenhagen',
1206 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1210 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1213 # Kaltura embed (different embed code)
1215 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1219 'upload_date': '20150127',
1220 'uploader_id': 'PremierMedia',
1222 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1225 # Kaltura embed with single quotes
1227 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1232 'timestamp': 1355743100,
1233 'upload_date': '20121217',
1234 'uploader_id': 'cplapp@learn360.com',
1236 'add_ie': ['Kaltura'],
1239 # Kaltura embedded via quoted entry_id
1240 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1244 'title': '06_matthew_brender_raj_dutt',
1245 'timestamp': 1466638791,
1246 'upload_date': '20160622',
1248 'add_ie': ['Kaltura'],
1249 'expected_warnings': [
1250 'Could not send HEAD request'
1253 'skip_download': True,
1257 # Kaltura embedded, some fileExt broken (#11480)
1258 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1262 'title': 'Our "Standard Models" of particle physics and cosmology',
1263 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1264 'timestamp': 1321158993,
1265 'upload_date': '20111113',
1266 'uploader_id': 'kps1',
1268 'add_ie': ['Kaltura'],
1271 # Kaltura iframe embed
1272 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1273 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1277 'title': 'I. M. Pei: A Centennial Celebration',
1278 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1279 'upload_date': '20170403',
1280 'uploader_id': 'batchUser',
1281 'timestamp': 1491232186,
1283 'add_ie': ['Kaltura'],
1286 # meta twitter:player
1287 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1291 'title': 'Main Twerk (Video)',
1292 'upload_date': '20171208',
1293 'uploader_id': 'sebastian.salinas@thechive.com',
1294 'timestamp': 1512713057,
1297 'skip_download': True,
1299 'add_ie': ['Kaltura'],
1301 # referrer protected EaglePlatform embed
1303 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1307 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1308 'thumbnail': r're:^https?://.*\.jpg$',
1313 'skip_download': True,
1316 # ClipYou (EaglePlatform) embed (custom URL)
1318 'url': 'http://muz-tv.ru/play/7129/',
1319 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1323 'title': "'O Sole Mio",
1324 'thumbnail': r're:^https?://.*\.jpg$',
1329 'skip_download': True,
1331 'skip': 'This video is unavailable.',
1335 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1339 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1340 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1341 'thumbnail': r're:^https?://.*\.jpg$',
1345 'skip': 'HTTP Error 404: Not Found',
1349 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1353 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1354 'thumbnail': r're:^https?://.*\.png$',
1360 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1361 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1365 'title': 'Facebook Creates "On This Day" | Crunch Report',
1366 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1367 'timestamp': 1427237531,
1368 'uploader': 'Crunch Report',
1369 'upload_date': '20150324',
1373 'skip_download': True,
1378 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1382 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1387 # Crooks and Liars embed
1389 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1393 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1394 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1395 'timestamp': 1428207000,
1396 'upload_date': '20150405',
1397 'uploader': 'Heather',
1400 # Crooks and Liars external embed
1402 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1404 'id': 'MTE3MjUtMzQ2MzA',
1406 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1407 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1408 'timestamp': 1265032391,
1409 'upload_date': '20100201',
1410 'uploader': 'Heather',
1413 # NBC Sports vplayer embed
1415 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1417 'id': 'ln7x1qSThw4k',
1419 'title': "PFT Live: New leader in the 'new-look' defense",
1420 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1421 'uploader': 'NBCU-SPORTS',
1422 'upload_date': '20140107',
1423 'timestamp': 1389118457,
1425 'skip': 'Invalid Page URL',
1429 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1430 'md5': '1aa589c675898ae6d37a17913cf68d66',
1432 'id': 'x_dtl_oa_LettermanliftPR_160608',
1434 'title': 'David Letterman: A Preview',
1435 '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.',
1436 'upload_date': '20160609',
1437 'timestamp': 1465431544,
1438 'uploader': 'NBCU-NEWS',
1443 'url': 'https://video.udn.com/news/300346',
1444 'md5': 'fd2060e988c326991037b9aff9df21a6',
1448 'title': '中一中男師變性 全校師生力挺',
1449 'thumbnail': r're:^https?://.*\.jpg$',
1453 'skip_download': True,
1455 'expected_warnings': ['Failed to parse JSON Expecting value'],
1459 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1461 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1463 'description': 'Index/Match versus VLOOKUP.',
1464 'title': 'This is what separates the Excel masters from the wannabes',
1465 'duration': 191.933,
1469 'skip_download': True,
1472 # Brightcove URL in single quotes
1474 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1475 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1477 'id': '4255764656001',
1479 'title': 'SN Presents: Russell Martin, World Citizen',
1480 '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.',
1481 'uploader': 'Rogers Sportsnet',
1482 'uploader_id': '1704050871',
1483 'upload_date': '20150525',
1484 'timestamp': 1432570283,
1487 # OnionStudios embed
1489 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1494 'thumbnail': r're:^https?://.*\.jpe?g$',
1495 'uploader': 'ClickHole',
1496 'uploader_id': 'clickhole',
1501 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1503 'id': '74849a00-85a9-11e1-9660-123139220831',
1505 'title': '#whilewewatch',
1508 # AdobeTVVideo embed
1510 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1511 'md5': '43662b577c018ad707a63766462b1e87',
1515 'title': 'New experience with Acrobat DC',
1516 'description': 'New experience with Acrobat DC',
1517 'duration': 248.667,
1520 # BrightcoveInPageEmbed embed
1522 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1524 'id': '4238694884001',
1526 'title': 'Tabletop: Dread, Last Thoughts',
1527 'description': 'Tabletop: Dread, Last Thoughts',
1531 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1532 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1534 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1536 'id': '4785848093001',
1538 'title': 'The Cardinal Pell Interview',
1539 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1540 'uploader': 'GlobeCast Australia - GlobeStream',
1541 'uploader_id': '2733773828001',
1542 'upload_date': '20160304',
1543 'timestamp': 1457083087,
1547 'skip_download': True,
1551 # Brightcove embed with whitespace around attribute names
1552 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1554 'id': '3167554373001',
1556 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1557 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1558 'uploader_id': '1079349493',
1559 'upload_date': '20140207',
1560 'timestamp': 1391810548,
1563 'skip_download': True,
1566 # Another form of arte.tv embed
1568 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1569 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1571 'id': '030273-562_PLUS7-F',
1573 'title': 'ARTE Reportage - Nulle part, en France',
1574 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1575 'upload_date': '20160409',
1580 'url': 'http://www.wykop.pl/link/3088787/',
1581 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1583 'id': '874_1459135191',
1585 'title': 'Man shows poor quality of new apartment building',
1586 'description': 'The wall is like a sand pile.',
1587 'uploader': 'Lake8737',
1589 'add_ie': [LiveLeakIE.ie_key()],
1591 # Another LiveLeak embed pattern (#13336)
1593 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1595 'id': '2eb_1496309988',
1597 'title': 'Thief robs place where everyone was armed',
1598 'description': 'md5:694d73ee79e535953cf2488562288eee',
1599 'uploader': 'brazilwtf',
1601 'add_ie': [LiveLeakIE.ie_key()],
1603 # Duplicated embedded video URLs
1605 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1607 'id': '149298443_480_16c25b74_2',
1609 'title': 'vs. Blue Orange Spring Game',
1610 'uploader': 'www.hudl.com',
1613 # twitter:player:stream embed
1615 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1619 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1620 'uploader': 'www.rtl.be',
1624 'skip_download': True,
1627 # twitter:player embed
1629 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1630 'md5': 'a3e0df96369831de324f0778e126653c',
1632 'id': '4909620399001',
1634 'title': 'What Do Black Holes Sound Like?',
1635 'description': 'what do black holes sound like',
1636 'upload_date': '20160524',
1637 'uploader_id': '29913724001',
1638 'timestamp': 1464107587,
1639 'uploader': 'TheAtlantic',
1641 'add_ie': ['BrightcoveLegacy'],
1643 # Facebook <iframe> embed
1645 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1646 'md5': 'fbcde74f534176ecb015849146dd3aee',
1648 'id': '599637780109885',
1650 'title': 'Facebook video #599637780109885',
1653 # Facebook <iframe> embed, plugin video
1655 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1657 'id': '1754168231264132',
1659 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1660 'uploader': 'Tariq Ramadan (official)',
1661 'timestamp': 1496758379,
1662 'upload_date': '20170606',
1665 'skip_download': True,
1668 # Facebook API embed
1670 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1671 'md5': 'a47372ee61b39a7b90287094d447d94e',
1673 'id': '10153467542406923',
1675 'title': 'Facebook video #10153467542406923',
1678 # Wordpress "YouTube Video Importer" plugin
1680 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1681 'md5': 'd16797741b560b485194eddda8121b48',
1683 'id': 'HNTXWDXV9Is',
1685 'title': 'Blue Devils Drumline Stanford lot 2016',
1686 'upload_date': '20160627',
1687 'uploader_id': 'GENOCIDE8GENERAL10',
1688 'uploader': 'cylus cyrus',
1692 # video stored on custom kaltura server
1693 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1694 'md5': '537617d06e64dfed891fa1593c4b30cc',
1698 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1699 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1700 'uploader_id': 'videos.expansion@el-mundo.net',
1701 'upload_date': '20150429',
1702 'timestamp': 1430303472,
1704 'add_ie': ['Kaltura'],
1707 # Non-standard Vimeo embed
1708 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1709 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1713 'title': 'Understanding the web - Teaser',
1714 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1715 'upload_date': '20151214',
1716 'uploader': 'OpenClassrooms',
1717 'uploader_id': 'openclassrooms',
1719 'add_ie': ['Vimeo'],
1722 # generic vimeo embed that requires original URL passed as Referer
1723 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1724 'only_matching': True,
1727 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1728 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1730 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1732 'title': 'Big Buck Bunny',
1733 'description': 'Royalty free test video',
1734 'timestamp': 1432816365,
1735 'upload_date': '20150528',
1739 'skip_download': True,
1741 'add_ie': [ArkenaIE.ie_key()],
1744 '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/',
1748 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1751 'skip_download': True,
1753 'add_ie': [Vbox7IE.ie_key()],
1757 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1760 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1762 'playlist_mincount': 3,
1766 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1768 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1769 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1771 'playlist_mincount': 2,
1775 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1779 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1780 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1783 'skip_download': True,
1785 'add_ie': [TwentyMinutenIE.ie_key()],
1789 'url': 'https://en.support.wordpress.com/videopress/',
1793 'title': 'IMG_5786',
1794 'timestamp': 1435711927,
1795 'upload_date': '20150701',
1798 'skip_download': True,
1800 'add_ie': [VideoPressIE.ie_key()],
1804 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1806 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1808 'title': 'Магаззино: Казань 2',
1809 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1810 'uploader': 'Магаззино',
1811 'upload_date': '20170228',
1812 'uploader_id': '996642',
1815 'skip_download': True,
1817 'add_ie': [RutubeIE.ie_key()],
1820 # ThePlatform embedded with whitespaces in URLs
1821 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1822 'only_matching': True,
1825 # Senate ISVP iframe https
1826 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1827 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1829 'id': 'govtaff020316',
1831 'title': 'Integrated Senate Video Player',
1833 'add_ie': [SenateISVPIE.ie_key()],
1836 # Limelight embeds (1 channel embed + 4 media embeds)
1837 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1839 'id': 'FacilitatorTraining2017',
1840 'title': 'Facilitator Training 2017',
1842 'playlist_mincount': 5,
1845 # Limelight embed (LimelightPlayerUtil.embed)
1846 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1848 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1850 'title': '07448641',
1851 'timestamp': 1499890639,
1852 'upload_date': '20170712',
1855 'skip_download': True,
1857 'add_ie': ['LimelightMedia'],
1860 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1862 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1863 'title': 'Standoff with Walnut Creek murder suspect ends',
1864 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1866 'playlist_mincount': 4,
1869 # WashingtonPost embed
1870 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1872 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1874 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1875 '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.',
1876 'timestamp': 1455216756,
1877 'uploader': 'The Washington Post',
1878 'upload_date': '20160211',
1880 'add_ie': [WashingtonPostIE.ie_key()],
1884 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1888 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1891 'skip_download': True,
1893 'add_ie': [MediasetIE.ie_key()],
1897 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1899 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1900 'title': 'Slovenskom sa prehnala vlna silných búrok',
1902 'playlist_mincount': 5,
1903 'add_ie': [JojIE.ie_key()],
1906 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1907 'url': 'https://tvrain.ru/amp/418921/',
1908 'md5': 'cc00413936695987e8de148b67d14f1d',
1912 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1917 'url': 'http://help.vzaar.com/article/165-embedding-video',
1918 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1922 'title': 'Building A Business Online: Principal Chairs Q & A',
1926 # multiple HTML5 videos on one page
1927 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1929 'id': 'keyscenarios',
1930 'title': 'Rescue Kit 14 Free Edition - Getting started',
1932 'playlist_count': 4,
1936 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1937 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1940 'title': 'vl14062007715967',
1945 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1946 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1948 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1950 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1951 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1952 'timestamp': 1474354800,
1953 'upload_date': '20160920',
1957 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1961 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1962 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1963 'timestamp': 1516100691,
1964 'upload_date': '20180116',
1967 'skip_download': True,
1969 'add_ie': [SpringboardPlatformIE.ie_key()],
1972 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1974 'id': 'uPDB5I9wfp8',
1976 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1977 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1978 'upload_date': '20160219',
1979 'uploader': 'Pocoyo - Português (BR)',
1980 'uploader_id': 'PocoyoBrazil',
1982 'add_ie': [YoutubeIE.ie_key()],
1984 'skip_download': True,
1988 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1990 'id': 'vMDE4NzI1Mjgt690b',
1994 'add_ie': [YapFilesIE.ie_key()],
1996 'skip_download': True,
2000 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2001 'md5': 'b68d276de422ab07ee1d49388103f457',
2004 'title': 'Lock up and get excited',
2007 'skip': 'TODO: fix nested playlists processing in tests',
2010 # # TODO: find another test
2011 # # http://schema.org/VideoObject
2012 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2013 # 'md5': '888dcf08b7ea671381f00fab74692755',
2015 # 'id': 'nyvTSJMKId',
2017 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2018 # 'description': '#love for cats.',
2019 # 'timestamp': 1461244995,
2020 # 'upload_date': '20160421',
2023 # 'force_generic_extractor': True,
2028 def report_following_redirect(self, new_url):
2029 """Report information extraction."""
2030 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2032 def _extract_rss(self, url, video_id, doc):
2033 playlist_title = doc.find('./channel/title').text
2034 playlist_desc_el = doc.find('./channel/description')
2035 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2038 for it in doc.findall('./channel/item'):
2040 enclosure_nodes = it.findall('./enclosure')
2041 for e in enclosure_nodes:
2042 next_url = e.attrib.get('url')
2047 next_url = xpath_text(it, 'link', fatal=False)
2053 '_type': 'url_transparent',
2055 'title': it.find('title').text,
2059 '_type': 'playlist',
2061 'title': playlist_title,
2062 'description': playlist_desc,
2066 def _extract_camtasia(self, url, video_id, webpage):
2067 """ Returns None if no camtasia video can be found. """
2069 camtasia_cfg = self._search_regex(
2070 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2071 webpage, 'camtasia configuration file', default=None)
2072 if camtasia_cfg is None:
2075 title = self._html_search_meta('DC.title', webpage, fatal=True)
2077 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2078 camtasia_cfg = self._download_xml(
2079 camtasia_url, video_id,
2080 note='Downloading camtasia configuration',
2081 errnote='Failed to download camtasia configuration')
2082 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2085 for n in fileset_node.getchildren():
2086 url_n = n.find('./uri')
2091 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2092 'title': '%s - %s' % (title, n.tag),
2093 'url': compat_urlparse.urljoin(url, url_n.text),
2094 'duration': float_or_none(n.find('./duration').text),
2098 '_type': 'playlist',
2103 def _real_extract(self, url):
2104 if url.startswith('//'):
2107 'url': self.http_scheme() + url,
2110 parsed_url = compat_urlparse.urlparse(url)
2111 if not parsed_url.scheme:
2112 default_search = self._downloader.params.get('default_search')
2113 if default_search is None:
2114 default_search = 'fixup_error'
2116 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2118 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2119 return self.url_result('http://' + url)
2120 elif default_search != 'fixup_error':
2121 if default_search == 'auto_warning':
2122 if re.match(r'^(?:url|URL)$', url):
2123 raise ExtractorError(
2124 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2127 self._downloader.report_warning(
2128 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2129 return self.url_result('ytsearch:' + url)
2131 if default_search in ('error', 'fixup_error'):
2132 raise ExtractorError(
2133 '%r is not a valid URL. '
2134 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2135 % (url, url), expected=True)
2137 if ':' not in default_search:
2138 default_search += ':'
2139 return self.url_result(default_search + url)
2141 url, smuggled_data = unsmuggle_url(url)
2142 force_videoid = None
2143 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2144 if smuggled_data and 'force_videoid' in smuggled_data:
2145 force_videoid = smuggled_data['force_videoid']
2146 video_id = force_videoid
2148 video_id = self._generic_id(url)
2150 self.to_screen('%s: Requesting header' % video_id)
2152 head_req = HEADRequest(url)
2153 head_response = self._request_webpage(
2155 note=False, errnote='Could not send HEAD request to %s' % url,
2158 if head_response is not False:
2159 # Check for redirect
2160 new_url = compat_str(head_response.geturl())
2162 self.report_following_redirect(new_url)
2164 new_url = smuggle_url(
2165 new_url, {'force_videoid': force_videoid})
2166 return self.url_result(new_url)
2168 full_response = None
2169 if head_response is False:
2170 request = sanitized_Request(url)
2171 request.add_header('Accept-Encoding', '*')
2172 full_response = self._request_webpage(request, video_id)
2173 head_response = full_response
2177 'title': self._generic_title(url),
2178 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2181 # Check for direct link to a video
2182 content_type = head_response.headers.get('Content-Type', '').lower()
2183 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2185 format_id = compat_str(m.group('format_id'))
2186 if format_id.endswith('mpegurl'):
2187 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2188 elif format_id == 'f4m':
2189 formats = self._extract_f4m_formats(url, video_id)
2192 'format_id': format_id,
2194 'vcodec': 'none' if m.group('type') == 'audio' else None
2196 info_dict['direct'] = True
2197 self._sort_formats(formats)
2198 info_dict['formats'] = formats
2201 if not self._downloader.params.get('test', False) and not is_intentional:
2202 force = self._downloader.params.get('force_generic_extractor', False)
2203 self._downloader.report_warning(
2204 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2206 if not full_response:
2207 request = sanitized_Request(url)
2208 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2209 # making it impossible to download only chunk of the file (yet we need only 512kB to
2210 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2211 # that will always result in downloading the whole file that is not desirable.
2212 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2213 # to accept raw bytes and being able to download only a chunk.
2214 # It may probably better to solve this by checking Content-Type for application/octet-stream
2215 # after HEAD request finishes, but not sure if we can rely on this.
2216 request.add_header('Accept-Encoding', '*')
2217 full_response = self._request_webpage(request, video_id)
2219 first_bytes = full_response.read(512)
2221 # Is it an M3U playlist?
2222 if first_bytes.startswith(b'#EXTM3U'):
2223 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2224 self._sort_formats(info_dict['formats'])
2227 # Maybe it's a direct link to a video?
2228 # Be careful not to download the whole thing!
2229 if not is_html(first_bytes):
2230 self._downloader.report_warning(
2231 'URL could be a direct video link, returning it as such.')
2238 webpage = self._webpage_read_content(
2239 full_response, url, video_id, prefix=first_bytes)
2241 self.report_extraction(video_id)
2243 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2245 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2246 if doc.tag == 'rss':
2247 return self._extract_rss(url, video_id, doc)
2248 elif doc.tag == 'SmoothStreamingMedia':
2249 info_dict['formats'] = self._parse_ism_formats(doc, url)
2250 self._sort_formats(info_dict['formats'])
2252 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2253 smil = self._parse_smil(doc, url, video_id)
2254 self._sort_formats(smil['formats'])
2256 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2257 return self.playlist_result(
2259 doc, video_id, xspf_url=url,
2260 xspf_base_url=compat_str(full_response.geturl())),
2262 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2263 info_dict['formats'] = self._parse_mpd_formats(
2265 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2267 self._sort_formats(info_dict['formats'])
2269 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2270 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2271 self._sort_formats(info_dict['formats'])
2273 except compat_xml_parse_error:
2276 # Is it a Camtasia project?
2277 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2278 if camtasia_res is not None:
2281 # Sometimes embedded video player is hidden behind percent encoding
2282 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2283 # Unescaping the whole page allows to handle those cases in a generic way
2284 webpage = compat_urllib_parse_unquote(webpage)
2286 # it's tempting to parse this further, but you would
2287 # have to take into account all the variations like
2288 # Video Title - Site Name
2289 # Site Name | Video Title
2290 # Video Title - Tagline | Site Name
2291 # and so on and so forth; it's just not practical
2292 video_title = self._og_search_title(
2293 webpage, default=None) or self._html_search_regex(
2294 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2297 # Try to detect age limit automatically
2298 age_limit = self._rta_search(webpage)
2299 # And then there are the jokers who advertise that they use RTA,
2300 # but actually don't.
2301 AGE_LIMIT_MARKERS = [
2302 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2304 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2307 # video uploader is domain name
2308 video_uploader = self._search_regex(
2309 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2311 video_description = self._og_search_description(webpage, default=None)
2312 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2315 'title': video_title,
2316 'description': video_description,
2317 'thumbnail': video_thumbnail,
2318 'age_limit': age_limit,
2321 # Look for Brightcove Legacy Studio embeds
2322 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2326 'url': smuggle_url(bc_url, {'Referer': url}),
2327 'ie_key': 'BrightcoveLegacy'
2328 } for bc_url in bc_urls]
2331 '_type': 'playlist',
2332 'title': video_title,
2337 # Look for Brightcove New Studio embeds
2338 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2340 return self.playlist_from_matches(
2341 bc_urls, video_id, video_title,
2342 getter=lambda x: smuggle_url(x, {'referrer': url}),
2345 # Look for Nexx embeds
2346 nexx_urls = NexxIE._extract_urls(webpage)
2348 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2350 # Look for Nexx iFrame embeds
2351 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2353 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2355 # Look for ThePlatform embeds
2356 tp_urls = ThePlatformIE._extract_urls(webpage)
2358 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2360 # Look for Vessel embeds
2361 vessel_urls = VesselIE._extract_urls(webpage)
2363 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2365 # Look for embedded rtl.nl player
2366 matches = re.findall(
2367 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2370 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2372 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2374 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2376 vid_me_embed_url = self._search_regex(
2377 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2378 webpage, 'vid.me embed', default=None)
2379 if vid_me_embed_url is not None:
2380 return self.url_result(vid_me_embed_url, 'Vidme')
2382 # Look for YouTube embeds
2383 youtube_urls = YoutubeIE._extract_urls(webpage)
2385 return self.playlist_from_matches(
2386 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2388 matches = DailymotionIE._extract_urls(webpage)
2390 return self.playlist_from_matches(matches, video_id, video_title)
2392 # Look for embedded Dailymotion playlist player (#3822)
2394 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2396 playlists = re.findall(
2397 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2399 return self.playlist_from_matches(
2400 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2402 # Look for DailyMail embeds
2403 dailymail_urls = DailyMailIE._extract_urls(webpage)
2405 return self.playlist_from_matches(
2406 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2408 # Look for embedded Wistia player
2409 wistia_url = WistiaIE._extract_url(webpage)
2412 '_type': 'url_transparent',
2413 'url': self._proto_relative_url(wistia_url),
2414 'ie_key': WistiaIE.ie_key(),
2415 'uploader': video_uploader,
2418 # Look for SVT player
2419 svt_url = SVTIE._extract_url(webpage)
2421 return self.url_result(svt_url, 'SVT')
2423 # Look for Bandcamp pages with custom domain
2424 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2425 if mobj is not None:
2426 burl = unescapeHTML(mobj.group(1))
2427 # Don't set the extractor because it can be a track url or an album
2428 return self.url_result(burl)
2430 # Look for embedded Vevo player
2432 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2433 if mobj is not None:
2434 return self.url_result(mobj.group('url'))
2436 # Look for embedded Viddler player
2438 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2440 if mobj is not None:
2441 return self.url_result(mobj.group('url'))
2443 # Look for NYTimes player
2445 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2447 if mobj is not None:
2448 return self.url_result(mobj.group('url'))
2450 # Look for Libsyn player
2452 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2453 if mobj is not None:
2454 return self.url_result(mobj.group('url'))
2456 # Look for Ooyala videos
2457 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2458 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2459 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2460 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2461 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2462 if mobj is not None:
2463 embed_token = self._search_regex(
2464 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2465 webpage, 'ooyala embed token', default=None)
2466 return OoyalaIE._build_url_result(smuggle_url(
2469 'embed_token': embed_token,
2472 # Look for multiple Ooyala embeds on SBN network websites
2473 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2474 if mobj is not None:
2475 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2477 return self.playlist_from_matches(
2478 embeds, video_id, video_title,
2479 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2481 # Look for Aparat videos
2482 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2483 if mobj is not None:
2484 return self.url_result(mobj.group(1), 'Aparat')
2486 # Look for MPORA videos
2487 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2488 if mobj is not None:
2489 return self.url_result(mobj.group(1), 'Mpora')
2491 # Look for embedded NovaMov-based player
2493 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2494 (?P<url>http://(?:(?:embed|www)\.)?
2496 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2497 videoweed\.(?:es|com)|
2498 movshare\.(?:net|sx|ag)|
2499 divxstage\.(?:eu|net|ch|co|at|ag))
2500 /embed\.php.+?)\1''', webpage)
2501 if mobj is not None:
2502 return self.url_result(mobj.group('url'))
2504 # Look for embedded Facebook player
2505 facebook_urls = FacebookIE._extract_urls(webpage)
2507 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2509 # Look for embedded VK player
2510 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2511 if mobj is not None:
2512 return self.url_result(mobj.group('url'), 'VK')
2514 # Look for embedded Odnoklassniki player
2515 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2516 if mobj is not None:
2517 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2519 # Look for embedded ivi player
2520 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2521 if mobj is not None:
2522 return self.url_result(mobj.group('url'), 'Ivi')
2524 # Look for embedded Huffington Post player
2526 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2527 if mobj is not None:
2528 return self.url_result(mobj.group('url'), 'HuffPost')
2531 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'))
2534 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2535 if mobj is not None:
2536 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2538 # Look for funnyordie embed
2539 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2541 return self.playlist_from_matches(
2542 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2544 # Look for BBC iPlayer embed
2545 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2547 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2549 # Look for embedded RUTV player
2550 rutv_url = RUTVIE._extract_url(webpage)
2552 return self.url_result(rutv_url, 'RUTV')
2554 # Look for embedded TVC player
2555 tvc_url = TVCIE._extract_url(webpage)
2557 return self.url_result(tvc_url, 'TVC')
2559 # Look for embedded SportBox player
2560 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2562 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2564 # Look for embedded XHamster player
2565 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2567 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2569 # Look for embedded TNAFlixNetwork player
2570 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2572 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2574 # Look for embedded PornHub player
2575 pornhub_urls = PornHubIE._extract_urls(webpage)
2577 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2579 # Look for embedded DrTuber player
2580 drtuber_urls = DrTuberIE._extract_urls(webpage)
2582 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2584 # Look for embedded RedTube player
2585 redtube_urls = RedTubeIE._extract_urls(webpage)
2587 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2589 # Look for embedded Tube8 player
2590 tube8_urls = Tube8IE._extract_urls(webpage)
2592 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2594 # Look for embedded Tvigle player
2596 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2597 if mobj is not None:
2598 return self.url_result(mobj.group('url'), 'Tvigle')
2600 # Look for embedded TED player
2602 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'), 'TED')
2606 # Look for embedded Ustream videos
2607 ustream_url = UstreamIE._extract_url(webpage)
2609 return self.url_result(ustream_url, UstreamIE.ie_key())
2611 # Look for embedded arte.tv player
2613 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2615 if mobj is not None:
2616 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2618 # Look for embedded francetv player
2620 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2622 if mobj is not None:
2623 return self.url_result(mobj.group('url'))
2625 # Look for embedded smotri.com player
2626 smotri_url = SmotriIE._extract_url(webpage)
2628 return self.url_result(smotri_url, 'Smotri')
2630 # Look for embedded Myvi.ru player
2631 myvi_url = MyviIE._extract_url(webpage)
2633 return self.url_result(myvi_url)
2635 # Look for embedded soundcloud player
2636 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2638 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2640 # Look for tunein player
2641 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2643 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2645 # Look for embedded mtvservices player
2646 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2648 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2650 # Look for embedded yahoo player
2652 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2654 if mobj is not None:
2655 return self.url_result(mobj.group('url'), 'Yahoo')
2657 # Look for embedded sbs.com.au player
2661 <meta\s+property="og:video"\s+content=|
2664 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2666 if mobj is not None:
2667 return self.url_result(mobj.group('url'), 'SBS')
2669 # Look for embedded Cinchcast player
2671 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2673 if mobj is not None:
2674 return self.url_result(mobj.group('url'), 'Cinchcast')
2677 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2681 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2683 if mobj is not None:
2684 return self.url_result(mobj.group('url'), 'MLB')
2687 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2689 if mobj is not None:
2690 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2693 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2695 if mobj is not None:
2696 return self.url_result(mobj.group('url'), 'Livestream')
2698 # Look for Zapiks embed
2700 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2701 if mobj is not None:
2702 return self.url_result(mobj.group('url'), 'Zapiks')
2704 # Look for Kaltura embeds
2705 kaltura_url = KalturaIE._extract_url(webpage)
2707 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2709 # Look for EaglePlatform embeds
2710 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2711 if eagleplatform_url:
2712 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2714 # Look for ClipYou (uses EaglePlatform) embeds
2716 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2717 if mobj is not None:
2718 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2720 # Look for Pladform embeds
2721 pladform_url = PladformIE._extract_url(webpage)
2723 return self.url_result(pladform_url)
2725 # Look for Videomore embeds
2726 videomore_url = VideomoreIE._extract_url(webpage)
2728 return self.url_result(videomore_url)
2730 # Look for Webcaster embeds
2731 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2733 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2735 # Look for Playwire embeds
2737 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2738 if mobj is not None:
2739 return self.url_result(mobj.group('url'))
2741 # Look for 5min embeds
2743 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2744 if mobj is not None:
2745 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2747 # Look for Crooks and Liars embeds
2749 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2750 if mobj is not None:
2751 return self.url_result(mobj.group('url'))
2753 # Look for NBC Sports VPlayer embeds
2754 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2756 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2758 # Look for NBC News embeds
2759 nbc_news_embed_url = re.search(
2760 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2761 if nbc_news_embed_url:
2762 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2764 # Look for Google Drive embeds
2765 google_drive_url = GoogleDriveIE._extract_url(webpage)
2766 if google_drive_url:
2767 return self.url_result(google_drive_url, 'GoogleDrive')
2769 # Look for UDN embeds
2771 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2772 if mobj is not None:
2773 return self.url_result(
2774 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2776 # Look for Senate ISVP iframe
2777 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2779 return self.url_result(senate_isvp_url, 'SenateISVP')
2781 # Look for OnionStudios embeds
2782 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2783 if onionstudios_url:
2784 return self.url_result(onionstudios_url)
2786 # Look for ViewLift embeds
2787 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2789 return self.url_result(viewlift_url)
2791 # Look for JWPlatform embeds
2792 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2794 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2796 # Look for Digiteka embeds
2797 digiteka_url = DigitekaIE._extract_url(webpage)
2799 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2801 # Look for Arkena embeds
2802 arkena_url = ArkenaIE._extract_url(webpage)
2804 return self.url_result(arkena_url, ArkenaIE.ie_key())
2806 # Look for Piksel embeds
2807 piksel_url = PikselIE._extract_url(webpage)
2809 return self.url_result(piksel_url, PikselIE.ie_key())
2811 # Look for Limelight embeds
2812 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2814 return self.playlist_result(
2815 limelight_urls, video_id, video_title, video_description)
2817 # Look for Anvato embeds
2818 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2820 return self.playlist_result(
2821 anvato_urls, video_id, video_title, video_description)
2823 # Look for AdobeTVVideo embeds
2825 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2827 if mobj is not None:
2828 return self.url_result(
2829 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2832 # Look for Vine embeds
2834 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2836 if mobj is not None:
2837 return self.url_result(
2838 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2840 # Look for VODPlatform embeds
2842 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2844 if mobj is not None:
2845 return self.url_result(
2846 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2848 # Look for Mangomolo embeds
2850 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2852 video\?.*?\bid=(?P<video_id>\d+)|
2853 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2854 ).+?)\1''', webpage)
2855 if mobj is not None:
2857 '_type': 'url_transparent',
2858 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2859 'title': video_title,
2860 'description': video_description,
2861 'thumbnail': video_thumbnail,
2862 'uploader': video_uploader,
2864 video_id = mobj.group('video_id')
2867 'ie_key': 'MangomoloVideo',
2872 'ie_key': 'MangomoloLive',
2873 'id': mobj.group('channel_id'),
2877 # Look for Instagram embeds
2878 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2879 if instagram_embed_url is not None:
2880 return self.url_result(
2881 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2883 # Look for LiveLeak embeds
2884 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2886 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2888 # Look for 3Q SDN embeds
2889 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2892 '_type': 'url_transparent',
2893 'ie_key': ThreeQSDNIE.ie_key(),
2894 'url': self._proto_relative_url(threeqsdn_url),
2895 'title': video_title,
2896 'description': video_description,
2897 'thumbnail': video_thumbnail,
2898 'uploader': video_uploader,
2901 # Look for VBOX7 embeds
2902 vbox7_url = Vbox7IE._extract_url(webpage)
2904 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2906 # Look for DBTV embeds
2907 dbtv_urls = DBTVIE._extract_urls(webpage)
2909 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2911 # Look for Videa embeds
2912 videa_urls = VideaIE._extract_urls(webpage)
2914 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2916 # Look for 20 minuten embeds
2917 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2919 return self.playlist_from_matches(
2920 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2922 # Look for Openload embeds
2923 openload_urls = OpenloadIE._extract_urls(webpage)
2925 return self.playlist_from_matches(
2926 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2928 # Look for VideoPress embeds
2929 videopress_urls = VideoPressIE._extract_urls(webpage)
2931 return self.playlist_from_matches(
2932 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2934 # Look for Rutube embeds
2935 rutube_urls = RutubeIE._extract_urls(webpage)
2937 return self.playlist_from_matches(
2938 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2940 # Look for WashingtonPost embeds
2941 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2943 return self.playlist_from_matches(
2944 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2946 # Look for Mediaset embeds
2947 mediaset_urls = MediasetIE._extract_urls(webpage)
2949 return self.playlist_from_matches(
2950 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2952 # Look for JOJ.sk embeds
2953 joj_urls = JojIE._extract_urls(webpage)
2955 return self.playlist_from_matches(
2956 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2958 # Look for megaphone.fm embeds
2959 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2961 return self.playlist_from_matches(
2962 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2964 # Look for vzaar embeds
2965 vzaar_urls = VzaarIE._extract_urls(webpage)
2967 return self.playlist_from_matches(
2968 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2970 channel9_urls = Channel9IE._extract_urls(webpage)
2972 return self.playlist_from_matches(
2973 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2975 vshare_urls = VShareIE._extract_urls(webpage)
2977 return self.playlist_from_matches(
2978 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2980 # Look for Mediasite embeds
2981 mediasite_urls = MediasiteIE._extract_urls(webpage)
2984 self.url_result(smuggle_url(
2985 compat_urlparse.urljoin(url, mediasite_url),
2986 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2987 for mediasite_url in mediasite_urls]
2988 return self.playlist_result(entries, video_id, video_title)
2990 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2991 if springboardplatform_urls:
2992 return self.playlist_from_matches(
2993 springboardplatform_urls, video_id, video_title,
2994 ie=SpringboardPlatformIE.ie_key())
2996 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2998 return self.playlist_from_matches(
2999 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3001 vice_urls = ViceIE._extract_urls(webpage)
3003 return self.playlist_from_matches(
3004 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3006 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3008 return self.playlist_from_matches(
3009 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3011 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3012 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3014 if sharevideos_urls:
3015 return self.playlist_from_matches(
3016 sharevideos_urls, video_id, video_title)
3018 # Look for HTML5 media
3019 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3021 if len(entries) == 1:
3024 'title': video_title,
3027 for num, entry in enumerate(entries, start=1):
3029 'id': '%s-%s' % (video_id, num),
3030 'title': '%s (%d)' % (video_title, num),
3032 for entry in entries:
3033 self._sort_formats(entry['formats'])
3034 return self.playlist_result(entries, video_id, video_title)
3036 jwplayer_data = self._find_jwplayer_data(
3037 webpage, video_id, transform_source=js_to_json)
3039 info = self._parse_jwplayer_data(
3040 jwplayer_data, video_id, require_title=False, base_url=url)
3041 return merge_dicts(info, info_dict)
3045 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3047 if mobj is not None:
3048 sources = self._parse_json(
3049 mobj.group(1), video_id, transform_source=js_to_json,
3051 if not isinstance(sources, list):
3054 for source in sources:
3055 src = source.get('src')
3056 if not src or not isinstance(src, compat_str):
3058 src = compat_urlparse.urljoin(url, src)
3059 src_type = source.get('type')
3060 if isinstance(src_type, compat_str):
3061 src_type = src_type.lower()
3062 ext = determine_ext(src).lower()
3063 if src_type == 'video/youtube':
3064 return self.url_result(src, YoutubeIE.ie_key())
3065 if src_type == 'application/dash+xml' or ext == 'mpd':
3066 formats.extend(self._extract_mpd_formats(
3067 src, video_id, mpd_id='dash', fatal=False))
3068 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3069 formats.extend(self._extract_m3u8_formats(
3070 src, video_id, 'mp4', entry_protocol='m3u8_native',
3071 m3u8_id='hls', fatal=False))
3075 'ext': (mimetype2ext(src_type) or
3076 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3079 self._sort_formats(formats)
3080 info_dict['formats'] = formats
3083 # Looking for http://schema.org/VideoObject
3084 json_ld = self._search_json_ld(
3085 webpage, video_id, default={}, expected_type='VideoObject')
3086 if json_ld.get('url'):
3087 return merge_dicts(json_ld, info_dict)
3089 def check_video(vurl):
3090 if YoutubeIE.suitable(vurl):
3092 if RtmpIE.suitable(vurl):
3094 vpath = compat_urlparse.urlparse(vurl).path
3095 vext = determine_ext(vpath)
3096 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3098 def filter_video(urls):
3099 return list(filter(check_video, urls))
3101 # Start with something easy: JW Player in SWFObject
3102 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3104 # Look for gorilla-vid style embedding
3105 found = filter_video(re.findall(r'''(?sx)
3109 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3112 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3114 # Broaden the search a little bit
3115 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3117 # Broaden the findall a little bit: JWPlayer JS loader
3118 found = filter_video(re.findall(
3119 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3122 found = filter_video(re.findall(r'''(?xs)
3123 flowplayer\("[^"]+",\s*
3125 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3126 ["']?url["']?\s*:\s*["']([^"']+)["']
3131 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3133 # Try to find twitter cards info
3134 # twitter:player:stream should be checked before twitter:player since
3135 # it is expected to contain a raw stream (see
3136 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3137 found = filter_video(re.findall(
3138 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3140 # We look for Open Graph info:
3141 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3142 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3143 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3144 if m_video_type is not None:
3145 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3147 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3149 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3150 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3153 # Look also in Refresh HTTP header
3154 refresh_header = head_response.headers.get('Refresh')
3156 # In python 2 response HTTP headers are bytestrings
3157 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3158 refresh_header = refresh_header.decode('iso-8859-1')
3159 found = re.search(REDIRECT_REGEX, refresh_header)
3161 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3163 self.report_following_redirect(new_url)
3172 # twitter:player is a https URL to iframe player that may or may not
3173 # be supported by youtube-dl thus this is checked the very last (see
3174 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3175 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3176 if embed_url and embed_url != url:
3177 return self.url_result(embed_url)
3180 raise UnsupportedError(url)
3183 for video_url in orderedSet(found):
3184 video_url = unescapeHTML(video_url)
3185 video_url = video_url.replace('\\/', '/')
3186 video_url = compat_urlparse.urljoin(url, video_url)
3187 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3189 # Sometimes, jwplayer extraction will result in a YouTube URL
3190 if YoutubeIE.suitable(video_url):
3191 entries.append(self.url_result(video_url, 'Youtube'))
3194 # here's a fun little line of code for you:
3195 video_id = os.path.splitext(video_id)[0]
3199 'uploader': video_uploader,
3200 'title': video_title,
3201 'age_limit': age_limit,
3204 if RtmpIE.suitable(video_url):
3205 entry_info_dict.update({
3206 '_type': 'url_transparent',
3207 'ie_key': RtmpIE.ie_key(),
3210 entries.append(entry_info_dict)
3213 ext = determine_ext(video_url)
3215 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3217 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3219 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3221 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3223 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3224 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3225 # Just matching .ism/manifest is not enough to be reliably sure
3226 # whether it's actually an ISM manifest or some other streaming
3227 # manifest since there are various streaming URL formats
3228 # possible (see [1]) as well as some other shenanigans like
3229 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3231 # Thus the most reasonable way to solve this is to delegate
3232 # to generic extractor in order to look into the contents of
3233 # the manifest itself.
3234 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3235 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3236 entry_info_dict = self.url_result(
3237 smuggle_url(video_url, {'to_generic': True}),
3240 entry_info_dict['url'] = video_url
3242 if entry_info_dict.get('formats'):
3243 self._sort_formats(entry_info_dict['formats'])
3245 entries.append(entry_info_dict)
3247 if len(entries) == 1:
3250 for num, e in enumerate(entries, start=1):
3251 # 'url' results don't have a title
3252 if e.get('title') is not None:
3253 e['title'] = '%s (%d)' % (e['title'], num)
3255 '_type': 'playlist',