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 SportBoxIE
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 .mofosex
import MofosexEmbedIE
64 from .spankwire
import SpankwireIE
65 from .youporn
import YouPornIE
66 from .vimeo
import VimeoIE
67 from .dailymotion
import DailymotionIE
68 from .dailymail
import DailyMailIE
69 from .onionstudios
import OnionStudiosIE
70 from .viewlift
import ViewLiftEmbedIE
71 from .mtv
import MTVServicesEmbeddedIE
72 from .pladform
import PladformIE
73 from .videomore
import VideomoreIE
74 from .webcaster
import WebcasterFeedIE
75 from .googledrive
import GoogleDriveIE
76 from .jwplatform
import JWPlatformIE
77 from .digiteka
import DigitekaIE
78 from .arkena
import ArkenaIE
79 from .instagram
import InstagramIE
80 from .liveleak
import LiveLeakIE
81 from .threeqsdn
import ThreeQSDNIE
82 from .theplatform
import ThePlatformIE
83 from .kaltura
import KalturaIE
84 from .eagleplatform
import EaglePlatformIE
85 from .facebook
import FacebookIE
86 from .soundcloud
import SoundcloudEmbedIE
87 from .tunein
import TuneInBaseIE
88 from .vbox7
import Vbox7IE
89 from .dbtv
import DBTVIE
90 from .piksel
import PikselIE
91 from .videa
import VideaIE
92 from .twentymin
import TwentyMinutenIE
93 from .ustream
import UstreamIE
94 from .videopress
import VideoPressIE
95 from .rutube
import RutubeIE
96 from .limelight
import LimelightBaseIE
97 from .anvato
import AnvatoIE
98 from .washingtonpost
import WashingtonPostIE
99 from .wistia
import WistiaIE
100 from .mediaset
import MediasetIE
101 from .joj
import JojIE
102 from .megaphone
import MegaphoneIE
103 from .vzaar
import VzaarIE
104 from .channel9
import Channel9IE
105 from .vshare
import VShareIE
106 from .mediasite
import MediasiteIE
107 from .springboardplatform
import SpringboardPlatformIE
108 from .yapfiles
import YapFilesIE
109 from .vice
import ViceIE
110 from .xfileshare
import XFileShareIE
111 from .cloudflarestream
import CloudflareStreamIE
112 from .peertube
import PeerTubeIE
113 from .teachable
import TeachableIE
114 from .indavideo
import IndavideoEmbedIE
115 from .apa
import APAIE
116 from .foxnews
import FoxNewsIE
117 from .viqeo
import ViqeoIE
118 from .expressen
import ExpressenIE
119 from .zype
import ZypeIE
120 from .odnoklassniki
import OdnoklassnikiIE
121 from .kinja
import KinjaEmbedIE
122 from .rcs
import RCSEmbedsIE
125 class GenericIE(InfoExtractor
):
126 IE_DESC
= 'Generic downloader that works on some sites'
130 # Direct link to a video
132 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
133 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
138 'upload_date': '20100513',
141 # Direct link to media delivered compressed (until Accept-Encoding is *)
143 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
144 'md5': '128c42e68b13950268b648275386fc74',
146 'id': 'FictionJunction-Parallel_Hearts',
148 'title': 'FictionJunction-Parallel_Hearts',
149 'upload_date': '20140522',
151 'expected_warnings': [
152 'URL could be a direct video link, returning it as such.'
154 'skip': 'URL invalid',
156 # Direct download with broken HEAD
158 'url': 'http://ai-radio.org:8000/radio.opus',
165 'skip_download': True, # infinite live stream
167 'expected_warnings': [
168 r
'501.*Not Implemented',
172 # Direct link with incorrect MIME type
174 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
175 'md5': '4ccbebe5f36706d85221f204d7eb5913',
177 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
178 'id': '5_Lennart_Poettering_-_Systemd',
180 'title': '5_Lennart_Poettering_-_Systemd',
181 'upload_date': '20141120',
183 'expected_warnings': [
184 'URL could be a direct video link, returning it as such.'
189 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
191 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
192 'title': 'Zero Punctuation',
193 'description': 're:.*groundbreaking video review series.*'
195 'playlist_mincount': 11,
197 # RSS feed with enclosure
199 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
201 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
203 'upload_date': '20150228',
204 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
207 # RSS feed with enclosures and unsupported link URLs
209 'url': 'http://www.hellointernet.fm/podcast?format=rss',
211 'id': 'http://www.hellointernet.fm/podcast?format=rss',
212 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
213 'title': 'Hello Internet',
215 'playlist_mincount': 100,
217 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
219 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
223 'title': 'Automatics, robotics and biocybernetics',
224 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
225 'upload_date': '20130627',
226 'formats': 'mincount:16',
227 'subtitles': 'mincount:1',
230 'force_generic_extractor': True,
231 'skip_download': True,
234 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
236 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
241 'formats': 'mincount:1',
244 'skip_download': True,
247 # SMIL from https://www.restudy.dk/video/play/id/1637
249 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
253 'title': 'video_1637',
254 'formats': 'mincount:3',
257 'skip_download': True,
260 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
262 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
264 'id': 'smil-service',
266 'title': 'smil-service',
267 'formats': 'mincount:1',
270 'skip_download': True,
273 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
275 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
279 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
280 'formats': 'mincount:3',
283 'skip_download': True,
286 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
288 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
290 'id': 'mZlp2ctYIUEB',
292 'title': 'Tikibad ontruimd wegens brand',
293 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
294 'thumbnail': r
're:^https?://.*\.jpg$',
298 'skip_download': True,
301 # MPD from http://dash-mse-test.appspot.com/media.html
303 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
304 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
306 'id': 'car-20120827-manifest',
308 'title': 'car-20120827-manifest',
309 'formats': 'mincount:9',
310 'upload_date': '20130904',
313 'format': 'bestvideo',
316 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
318 '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',
323 'formats': 'mincount:8',
327 'skip_download': True,
329 'skip': 'video gone',
331 # m3u8 served with Content-Type: text/plain
333 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
338 'upload_date': '20140720',
339 'formats': 'mincount:11',
343 'skip_download': True,
345 'skip': 'video gone',
349 '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',
353 'upload_date': '20130224',
354 'uploader_id': 'TheVerge',
355 'description': r
're:^Chris Ziegler takes a look at the\.*',
356 'uploader': 'The Verge',
357 'title': 'First Firefox OS phones side-by-side',
360 'skip_download': False,
364 # redirect in Refresh HTTP header
365 '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',
369 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
370 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
371 'upload_date': '20150917',
372 'uploader_id': 'brtvofficial',
373 'uploader': 'Boiler Room',
376 'skip_download': False,
380 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
381 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
383 'id': '13601338388002',
385 'uploader': 'www.hodiho.fr',
386 'title': 'R\u00e9gis plante sa Jeep',
389 # bandcamp page with custom domain
391 'add_ie': ['Bandcamp'],
392 'url': 'http://bronyrock.com/track/the-pony-mash',
396 'title': 'The Pony Mash',
397 'uploader': 'M_Pallante',
399 'skip': 'There is a limit of 200 free downloads / month for the test song',
402 # embedded brightcove video
403 # it also tests brightcove videos that need to set the 'Referer'
404 # in the http requests
405 'add_ie': ['BrightcoveLegacy'],
406 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
408 'id': '2765128793001',
410 'title': 'Le cours de bourse : l’analyse technique',
411 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
412 'uploader': 'BFM BUSINESS',
415 'skip_download': True,
419 # embedded with itemprop embedURL and video id spelled as `idVideo`
420 'add_id': ['BrightcoveLegacy'],
421 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
423 'id': '5255628253001',
425 'title': 'md5:37c519b1128915607601e75a87995fc0',
426 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
427 'uploader': 'BFM BUSINESS',
428 'uploader_id': '876450612001',
429 'timestamp': 1482255315,
430 'upload_date': '20161220',
433 'skip_download': True,
437 # https://github.com/ytdl-org/youtube-dl/issues/2253
438 'url': 'http://bcove.me/i6nfkrc3',
439 'md5': '0ba9446db037002366bab3b3eb30c88c',
441 'id': '3101154703001',
443 'title': 'Still no power',
444 'uploader': 'thestar.com',
445 '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.',
447 'add_ie': ['BrightcoveLegacy'],
448 'skip': 'video gone',
451 'url': 'http://www.championat.com/video/football/v/87/87499.html',
452 'md5': 'fb973ecf6e4a78a67453647444222983',
454 'id': '3414141473001',
456 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
457 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
458 'uploader': 'Championat',
462 # https://github.com/ytdl-org/youtube-dl/issues/3541
463 'add_ie': ['BrightcoveLegacy'],
464 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
466 'id': '3866516442001',
468 'title': 'Leer mij vrouwen kennen: Aflevering 1',
469 'description': 'Leer mij vrouwen kennen: Aflevering 1',
470 'uploader': 'SBS Broadcasting',
472 'skip': 'Restricted to Netherlands',
474 'skip_download': True, # m3u8 download
478 # Brightcove video in <iframe>
479 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
480 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
482 'id': '5360463607001',
484 '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',
485 '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。',
486 'uploader': 'United Nations',
487 'uploader_id': '1362235914001',
488 'timestamp': 1489593889,
489 'upload_date': '20170315',
491 'add_ie': ['BrightcoveLegacy'],
494 # Brightcove with alternative playerID key
495 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
497 'id': 'nmeth.2062_SV1',
498 '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',
502 'id': '2228375078001',
504 'title': 'nmeth.2062-sv1',
505 'description': 'nmeth.2062-sv1',
506 'timestamp': 1363357591,
507 'upload_date': '20130315',
508 'uploader': 'Nature Publishing Group',
509 'uploader_id': '1964492299001',
514 # Brightcove with UUID in videoPlayer
515 'url': 'http://www8.hp.com/cn/zh/home.html',
517 'id': '5255815316001',
519 'title': 'Sprocket Video - China',
520 'description': 'Sprocket Video - China',
521 'uploader': 'HP-Video Gallery',
522 'timestamp': 1482263210,
523 'upload_date': '20161220',
524 'uploader_id': '1107601872001',
527 'skip_download': True, # m3u8 download
529 'skip': 'video rotates...weekly?',
532 # Brightcove:new type [2].
533 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
534 'md5': '2b35148fcf48da41c9fb4591650784f3',
536 'id': '5348741021001',
538 'upload_date': '20170306',
539 'uploader_id': '4191638492001',
540 'timestamp': 1488769918,
541 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
546 # Alternative brightcove <video> attributes
547 '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/',
549 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
550 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
553 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
555 'id': '5311302538001',
557 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
558 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
559 'timestamp': 1486321708,
560 'upload_date': '20170205',
561 'uploader_id': '800000640001',
563 'only_matching': True,
567 # Brightcove with UUID in videoPlayer
568 'url': 'http://www8.hp.com/cn/zh/home.html',
570 'id': '5255815316001',
572 'title': 'Sprocket Video - China',
573 'description': 'Sprocket Video - China',
574 'uploader': 'HP-Video Gallery',
575 'timestamp': 1482263210,
576 'upload_date': '20161220',
577 'uploader_id': '1107601872001',
580 'skip_download': True, # m3u8 download
585 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
586 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
588 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
590 'title': '2cc213299525360.mov', # that's what we get
593 'add_ie': ['Ooyala'],
596 # ooyala video embedded with http://player.ooyala.com/iframe.js
597 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
599 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
601 'title': '"Steve Jobs: Man in the Machine" trailer',
602 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
606 'skip_download': True,
608 'skip': 'movie expired',
610 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
612 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
614 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
616 'title': 'Steampunk Fest Comes to Honesdale',
620 'skip_download': True,
625 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
629 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
630 'upload_date': '20140225',
631 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
632 'uploader': 'Tested',
633 'uploader_id': 'testedcom',
635 # No need to test YoutubeIE here
637 'skip_download': True,
642 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
646 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
647 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
649 # HEAD requests lead to endless 301, while GET is OK
650 'expected_warnings': ['301'],
654 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
658 'title': 'Охотское море стало целиком российским',
659 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
663 'skip_download': True,
668 '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/',
672 'title': 'Дошкольное воспитание',
677 'url': 'http://www.vestifinance.ru/articles/25753',
680 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
685 'title': 'Госзаказ. День 3',
691 'title': 'Госзаказ. День 2',
697 'title': 'Госзаказ. День 1',
703 'skip_download': True,
708 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
710 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
712 'title': 'Ужастики, русский трейлер (2015)',
713 'thumbnail': r
're:^https?://.*\.jpg$',
719 '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',
722 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
724 'playlist_mincount': 7,
725 # This forum does not allow <iframe> syntaxes anymore
726 # Now HTML tags are displayed as-is
727 'skip': 'No videos on this page',
731 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
732 'md5': '65fdff94098e4a607385a60c5177c638',
736 'title': 'Hidden miracles of the natural world',
737 'uploader': 'Louie Schwartzberg',
738 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
741 # nowvideo embed hidden behind percent encoding
743 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
744 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
746 'id': '06e53103ca9aa',
748 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
749 'description': 'No description',
754 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
755 'md5': '7653032cbb25bf6c80d80f217055fa43',
757 'id': '048195-004_PLUS7-F',
760 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
761 'upload_date': '20140320',
764 'skip_download': 'Requires rtmpdump'
766 'skip': 'video gone',
770 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
774 'title': 'Alcaline, le concert avec Calogero',
775 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
776 'upload_date': '20150226',
777 'timestamp': 1424989860,
782 'skip_download': True,
784 'expected_warnings': [
790 'url': 'http://www.wired.com/2014/04/honda-asimo/',
791 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
793 'id': '53501be369702d3275860000',
795 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
800 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
801 'md5': '441aeeb82eb72c422c7f14ec533999cd',
803 'id': 'k2mm4bCdJ6CQ2i7c8o2',
805 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
806 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
808 'uploader_id': 'xgditw',
809 'upload_date': '20140425',
810 'timestamp': 1398441542,
812 'add_ie': ['Dailymotion'],
816 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
820 'title': 'Care worker punches elderly dementia patient in head 11 times',
821 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
823 'add_ie': ['DailyMail'],
825 'skip_download': True,
830 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
834 'title': 'The NBL Auction 2014',
835 'uploader': 'BADMINTON England',
836 'uploader_id': 'BADMINTONEvents',
837 'upload_date': '20140603',
838 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
840 'add_ie': ['Youtube'],
842 'skip_download': True,
847 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
848 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
850 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
852 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
853 'description': 'Two valets share their love for movie star Liam Neesons.',
854 'timestamp': 1349922600,
855 'upload_date': '20121011',
858 # YouTube embed via <data-embed-url="">
860 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
864 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
865 'uploader': 'Gameloft',
866 'uploader_id': 'gameloft',
867 'upload_date': '20140828',
868 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
871 'skip_download': True,
874 # YouTube <object> embed
876 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
877 'md5': '516718101ec834f74318df76259fb3cc',
881 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
882 'upload_date': '20080526',
883 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
884 'uploader': 'Christopher Sykes',
885 'uploader_id': 'ChristopherJSykes',
887 'add_ie': ['Youtube'],
891 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
893 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
895 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
896 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
901 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
903 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
904 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
910 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
915 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
916 'md5': '9d65602bf31c6e20014319c7d07fba27',
918 'id': '5123ea6d5e5a7',
921 'uploader': 'www.handjobhub.com',
922 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
925 # Multiple brightcove videos
926 # https://github.com/ytdl-org/youtube-dl/issues/2283
928 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
930 'id': 'always-never',
931 'title': 'Always / Never - The New Yorker',
935 'extract_flat': False,
936 'skip_download': True,
941 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
942 'md5': '96f09a37e44da40dd083e12d9a683327',
946 'title': 'Ump changes call to ball',
947 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
949 'timestamp': 1401537900,
950 'upload_date': '20140531',
951 'thumbnail': r
're:^https?://.*\.jpg$',
956 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
957 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
961 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
962 'description': 'a Paywall Videos video from Remilon',
964 'uploader': 'study.com',
965 'timestamp': 1459678540,
966 'upload_date': '20160403',
967 'filesize': 24687186,
971 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
972 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
976 'title': 'Conversation about Hexagonal Rails Part 1',
977 'description': 'a Martin Fowler video from ThoughtWorks',
979 'uploader': 'thoughtworks.wistia.com',
980 'timestamp': 1401832161,
981 'upload_date': '20140603',
984 # Wistia standard embed (async)
986 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
990 'title': 'Drip Brennan Dunn Workshop',
991 'description': 'a JV Webinars video from getdrip-1',
993 'timestamp': 1463607249,
994 'upload_date': '20160518',
997 'skip_download': True,
1002 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1006 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1007 'uploader': 'Sophos Security',
1008 'title': 'Chet Chat 171 - Oct 29, 2014',
1009 'upload_date': '20141029',
1012 # Soundcloud multiple embeds
1014 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1017 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1019 'playlist_mincount': 7,
1021 # TuneIn station embed
1023 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1028 'location': 'Paris, France',
1033 'skip_download': True,
1038 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1042 'upload_date': '20141112',
1043 'title': 'Rosetta #CometLanding webcast HL 10',
1046 # Another Livestream embed, without 'new.' in URL
1048 'url': 'https://www.freespeech.org/',
1052 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1056 'skip_download': True,
1061 'url': 'https://skiplagged.com/',
1064 'title': 'Skiplagged: The smart way to find cheap flights',
1066 'playlist_mincount': 1,
1067 'add_ie': ['Youtube'],
1071 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1075 'upload_date': '20141126',
1076 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1081 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1083 'id': '730m_DandD_1901_512k',
1085 'uploader': 'www.abc.net.au',
1086 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1089 # embedded viddler video
1091 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1095 'uploader': 'deadspin',
1096 'title': 'WALL-TO-GORTAT',
1097 'timestamp': 1422285291,
1098 'upload_date': '20150126',
1100 'add_ie': ['Viddler'],
1104 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1108 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1109 'description': 'md5:601cb790edd05908957dae8aaa866465',
1110 'upload_date': '20150220',
1112 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1116 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1118 'id': 'Mrj4DVp2zeA',
1120 'upload_date': '20150212',
1121 'uploader': 'The National Archives UK',
1122 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1123 'uploader_id': 'NationalArchives08',
1124 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1129 'url': 'http://www.suffolk.edu/sjc/live.php',
1133 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1134 'uploader': 'www.suffolk.edu',
1137 'skip_download': True,
1139 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1143 'url': 'http://www.indiedb.com/games/king-machine/videos',
1147 'title': 'king machine trailer 1',
1148 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1149 'thumbnail': r
're:^https?://.*\.jpg$',
1153 # JWPlayer config passed as variable
1154 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1158 'title': 'ARIELE | Tube Cup',
1159 'uploader': 'www.txxx.com',
1163 'skip_download': True,
1168 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1169 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1173 'upload_date': '20171122',
1174 'timestamp': 1511366290,
1175 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1177 'add_ie': [JWPlatformIE
.ie_key()],
1180 # Video.js embed, multiple formats
1181 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1183 'id': 'yygqldloqIk',
1185 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1186 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1187 'upload_date': '20130314',
1188 'uploader': 'PROстое3D',
1189 'uploader_id': 'PROstoe3D',
1192 'skip_download': True,
1196 # Video.js embed, single format
1197 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1201 'title': 'Step 1 - Good Foundation',
1202 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1205 'skip_download': True,
1210 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1211 'playlist_mincount': 5,
1213 'id': 'aanslagen-kopenhagen',
1214 'title': 'Aanslagen Kopenhagen',
1219 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1223 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1226 # Kaltura embed (different embed code)
1228 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1232 'upload_date': '20150127',
1233 'uploader_id': 'PremierMedia',
1235 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1238 # Kaltura embed with single quotes
1240 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1245 'timestamp': 1355743100,
1246 'upload_date': '20121217',
1247 'uploader_id': 'cplapp@learn360.com',
1249 'add_ie': ['Kaltura'],
1252 # Kaltura embedded via quoted entry_id
1253 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1257 'title': '06_matthew_brender_raj_dutt',
1258 'timestamp': 1466638791,
1259 'upload_date': '20160622',
1261 'add_ie': ['Kaltura'],
1262 'expected_warnings': [
1263 'Could not send HEAD request'
1266 'skip_download': True,
1270 # Kaltura embedded, some fileExt broken (#11480)
1271 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1275 'title': 'Our "Standard Models" of particle physics and cosmology',
1276 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1277 'timestamp': 1321158993,
1278 'upload_date': '20111113',
1279 'uploader_id': 'kps1',
1281 'add_ie': ['Kaltura'],
1284 # Kaltura iframe embed
1285 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1286 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1290 'title': 'I. M. Pei: A Centennial Celebration',
1291 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1292 'upload_date': '20170403',
1293 'uploader_id': 'batchUser',
1294 'timestamp': 1491232186,
1296 'add_ie': ['Kaltura'],
1299 # Kaltura iframe embed, more sophisticated
1300 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1304 'title': 'lecture-05sep2017',
1305 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1306 'upload_date': '20170913',
1307 'uploader_id': 'eps2',
1308 'timestamp': 1505340777,
1311 'skip_download': True,
1313 'add_ie': ['Kaltura'],
1316 # meta twitter:player
1317 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1321 'title': 'Main Twerk (Video)',
1322 'upload_date': '20171208',
1323 'uploader_id': 'sebastian.salinas@thechive.com',
1324 'timestamp': 1512713057,
1327 'skip_download': True,
1329 'add_ie': ['Kaltura'],
1331 # referrer protected EaglePlatform embed
1333 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1337 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1338 'thumbnail': r
're:^https?://.*\.jpg$',
1343 'skip_download': True,
1346 # ClipYou (EaglePlatform) embed (custom URL)
1348 'url': 'http://muz-tv.ru/play/7129/',
1349 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1353 'title': "'O Sole Mio",
1354 'thumbnail': r
're:^https?://.*\.jpg$',
1359 'skip_download': True,
1361 'skip': 'This video is unavailable.',
1365 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1369 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1370 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1371 'thumbnail': r
're:^https?://.*\.jpg$',
1375 'skip': 'HTTP Error 404: Not Found',
1379 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1383 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1384 'thumbnail': r
're:^https?://.*\.png$',
1390 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1391 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1395 'title': 'Facebook Creates "On This Day" | Crunch Report',
1396 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1397 'timestamp': 1427237531,
1398 'uploader': 'Crunch Report',
1399 'upload_date': '20150324',
1403 'skip_download': True,
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,
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 'description': 'Migrated from OnionStudios',
1499 'thumbnail': r
're:^https?://.*\.jpe?g$',
1500 'uploader': 'clickhole',
1501 'upload_date': '20150527',
1502 'timestamp': 1432744860,
1507 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1509 'id': '74849a00-85a9-11e1-9660-123139220831',
1511 'title': '#whilewewatch',
1514 # AdobeTVVideo embed
1516 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1517 'md5': '43662b577c018ad707a63766462b1e87',
1521 'title': 'New experience with Acrobat DC',
1522 'description': 'New experience with Acrobat DC',
1523 'duration': 248.667,
1526 # BrightcoveInPageEmbed embed
1528 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1530 'id': '4238694884001',
1532 'title': 'Tabletop: Dread, Last Thoughts',
1533 'description': 'Tabletop: Dread, Last Thoughts',
1537 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1538 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1540 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1542 'id': '4785848093001',
1544 'title': 'The Cardinal Pell Interview',
1545 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1546 'uploader': 'GlobeCast Australia - GlobeStream',
1547 'uploader_id': '2733773828001',
1548 'upload_date': '20160304',
1549 'timestamp': 1457083087,
1553 'skip_download': True,
1557 # Brightcove embed with whitespace around attribute names
1558 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1560 'id': '3167554373001',
1562 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1563 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1564 'uploader_id': '1079349493',
1565 'upload_date': '20140207',
1566 'timestamp': 1391810548,
1569 'skip_download': True,
1572 # Another form of arte.tv embed
1574 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1575 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1577 'id': '030273-562_PLUS7-F',
1579 'title': 'ARTE Reportage - Nulle part, en France',
1580 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1581 'upload_date': '20160409',
1586 'url': 'http://www.wykop.pl/link/3088787/',
1587 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1589 'id': '874_1459135191',
1591 'title': 'Man shows poor quality of new apartment building',
1592 'description': 'The wall is like a sand pile.',
1593 'uploader': 'Lake8737',
1595 'add_ie': [LiveLeakIE
.ie_key()],
1597 # Another LiveLeak embed pattern (#13336)
1599 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1601 'id': '2eb_1496309988',
1603 'title': 'Thief robs place where everyone was armed',
1604 'description': 'md5:694d73ee79e535953cf2488562288eee',
1605 'uploader': 'brazilwtf',
1607 'add_ie': [LiveLeakIE
.ie_key()],
1609 # Duplicated embedded video URLs
1611 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1613 'id': '149298443_480_16c25b74_2',
1615 'title': 'vs. Blue Orange Spring Game',
1616 'uploader': 'www.hudl.com',
1619 # twitter:player:stream embed
1621 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1625 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1626 'uploader': 'www.rtl.be',
1630 'skip_download': True,
1633 # twitter:player embed
1635 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1636 'md5': 'a3e0df96369831de324f0778e126653c',
1638 'id': '4909620399001',
1640 'title': 'What Do Black Holes Sound Like?',
1641 'description': 'what do black holes sound like',
1642 'upload_date': '20160524',
1643 'uploader_id': '29913724001',
1644 'timestamp': 1464107587,
1645 'uploader': 'TheAtlantic',
1647 'add_ie': ['BrightcoveLegacy'],
1649 # Facebook <iframe> embed
1651 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1652 'md5': 'fbcde74f534176ecb015849146dd3aee',
1654 'id': '599637780109885',
1656 'title': 'Facebook video #599637780109885',
1659 # Facebook <iframe> embed, plugin video
1661 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1663 'id': '1754168231264132',
1665 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1666 'uploader': 'Tariq Ramadan (official)',
1667 'timestamp': 1496758379,
1668 'upload_date': '20170606',
1671 'skip_download': True,
1674 # Facebook API embed
1676 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1677 'md5': 'a47372ee61b39a7b90287094d447d94e',
1679 'id': '10153467542406923',
1681 'title': 'Facebook video #10153467542406923',
1684 # Wordpress "YouTube Video Importer" plugin
1686 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1687 'md5': 'd16797741b560b485194eddda8121b48',
1689 'id': 'HNTXWDXV9Is',
1691 'title': 'Blue Devils Drumline Stanford lot 2016',
1692 'upload_date': '20160627',
1693 'uploader_id': 'GENOCIDE8GENERAL10',
1694 'uploader': 'cylus cyrus',
1698 # video stored on custom kaltura server
1699 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1700 'md5': '537617d06e64dfed891fa1593c4b30cc',
1704 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1705 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1706 'uploader_id': 'videos.expansion@el-mundo.net',
1707 'upload_date': '20150429',
1708 'timestamp': 1430303472,
1710 'add_ie': ['Kaltura'],
1713 # multiple kaltura embeds, nsfw
1714 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1716 'id': 'kamila-avec-video-jaime-sadomie',
1717 'title': "Kamila avec vídeo “J'aime sadomie”",
1719 'playlist_count': 8,
1722 # Non-standard Vimeo embed
1723 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1724 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1728 'title': 'Understanding the web - Teaser',
1729 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1730 'upload_date': '20151214',
1731 'uploader': 'OpenClassrooms',
1732 'uploader_id': 'openclassrooms',
1734 'add_ie': ['Vimeo'],
1737 # generic vimeo embed that requires original URL passed as Referer
1738 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1739 'only_matching': True,
1742 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1743 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1745 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1747 'title': 'Big Buck Bunny',
1748 'description': 'Royalty free test video',
1749 'timestamp': 1432816365,
1750 'upload_date': '20150528',
1754 'skip_download': True,
1756 'add_ie': [ArkenaIE
.ie_key()],
1759 '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/',
1763 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1766 'skip_download': True,
1768 'add_ie': [Vbox7IE
.ie_key()],
1772 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1775 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1777 'playlist_mincount': 3,
1781 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1783 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1784 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1786 'playlist_mincount': 2,
1790 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1794 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1795 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1798 'skip_download': True,
1800 'add_ie': [TwentyMinutenIE
.ie_key()],
1804 'url': 'https://en.support.wordpress.com/videopress/',
1808 'title': 'IMG_5786',
1809 'timestamp': 1435711927,
1810 'upload_date': '20150701',
1813 'skip_download': True,
1815 'add_ie': [VideoPressIE
.ie_key()],
1819 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1821 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1823 'title': 'Магаззино: Казань 2',
1824 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1825 'uploader': 'Магаззино',
1826 'upload_date': '20170228',
1827 'uploader_id': '996642',
1830 'skip_download': True,
1832 'add_ie': [RutubeIE
.ie_key()],
1835 # ThePlatform embedded with whitespaces in URLs
1836 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1837 'only_matching': True,
1840 # Senate ISVP iframe https
1841 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1842 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1844 'id': 'govtaff020316',
1846 'title': 'Integrated Senate Video Player',
1848 'add_ie': [SenateISVPIE
.ie_key()],
1851 # Limelight embeds (1 channel embed + 4 media embeds)
1852 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1854 'id': 'FacilitatorTraining2017',
1855 'title': 'Facilitator Training 2017',
1857 'playlist_mincount': 5,
1860 # Limelight embed (LimelightPlayerUtil.embed)
1861 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1863 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1865 'title': '07448641',
1866 'timestamp': 1499890639,
1867 'upload_date': '20170712',
1870 'skip_download': True,
1872 'add_ie': ['LimelightMedia'],
1875 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1877 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1878 'title': 'Standoff with Walnut Creek murder suspect ends',
1879 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1881 'playlist_mincount': 4,
1884 # WashingtonPost embed
1885 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1887 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1889 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1890 '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.',
1891 'timestamp': 1455216756,
1892 'uploader': 'The Washington Post',
1893 'upload_date': '20160211',
1895 'add_ie': [WashingtonPostIE
.ie_key()],
1899 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1903 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1906 'skip_download': True,
1908 'add_ie': [MediasetIE
.ie_key()],
1912 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1914 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1915 'title': 'Slovenskom sa prehnala vlna silných búrok',
1917 'playlist_mincount': 5,
1918 'add_ie': [JojIE
.ie_key()],
1921 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1922 'url': 'https://tvrain.ru/amp/418921/',
1923 'md5': 'cc00413936695987e8de148b67d14f1d',
1927 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1932 'url': 'http://help.vzaar.com/article/165-embedding-video',
1933 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1937 'title': 'Building A Business Online: Principal Chairs Q & A',
1941 # multiple HTML5 videos on one page
1942 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1944 'id': 'keyscenarios',
1945 'title': 'Rescue Kit 14 Free Edition - Getting started',
1947 'playlist_count': 4,
1951 'url': 'https://youtube-dlc-demo.neocities.org/vshare.html',
1952 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1955 'title': 'vl14062007715967',
1960 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1961 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1963 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1965 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1966 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1967 'timestamp': 1474354800,
1968 'upload_date': '20160920',
1972 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1976 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1977 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1978 'timestamp': 1516100691,
1979 'upload_date': '20180116',
1982 'skip_download': True,
1984 'add_ie': [SpringboardPlatformIE
.ie_key()],
1987 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1989 'id': 'uPDB5I9wfp8',
1991 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1992 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1993 'upload_date': '20160219',
1994 'uploader': 'Pocoyo - Português (BR)',
1995 'uploader_id': 'PocoyoBrazil',
1997 'add_ie': [YoutubeIE
.ie_key()],
1999 'skip_download': True,
2003 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2005 'id': 'vMDE4NzI1Mjgt690b',
2009 'add_ie': [YapFilesIE
.ie_key()],
2011 'skip_download': True,
2015 # CloudflareStream embed
2016 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2018 'id': '31c9291ab41fac05471db4e73aa11717',
2020 'title': '31c9291ab41fac05471db4e73aa11717',
2022 'add_ie': [CloudflareStreamIE
.ie_key()],
2024 'skip_download': True,
2029 'url': 'https://joinpeertube.org/fr/home/',
2032 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2034 'playlist_count': 2,
2038 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2042 'title': 'Így kell otthon hamburgert sütni',
2043 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2044 'timestamp': 1426330212,
2045 'upload_date': '20150314',
2046 'uploader': 'StreetKitchen',
2047 'uploader_id': '546363',
2049 'add_ie': [IndavideoEmbedIE
.ie_key()],
2051 'skip_download': True,
2055 # APA embed via JWPlatform embed
2056 'url': 'http://www.vol.at/blue-man-group/5593454',
2060 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2061 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2062 'thumbnail': r
're:^https?://.*\.jpg$',
2064 'timestamp': 1519211149,
2065 'upload_date': '20180221',
2068 'skip_download': True,
2072 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2073 'md5': 'b68d276de422ab07ee1d49388103f457',
2076 'title': 'Lock up and get excited',
2079 'skip': 'TODO: fix nested playlists processing in tests',
2083 'url': 'https://viqeo.tv/',
2086 'title': 'All-new video platform',
2088 'playlist_count': 6,
2091 # Squarespace video embed, 2019-08-28
2092 'url': 'http://ootboxford.com',
2094 'id': 'Tc7b_JGdZfw',
2095 'title': 'Out of the Blue, at Childish Things 10',
2097 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2098 'uploader_id': 'helendouglashouse',
2099 'uploader': 'Helen & Douglas House',
2100 'upload_date': '20140328',
2103 'skip_download': True,
2108 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2110 'id': '5b400b834b32992a310622b9',
2112 'title': 'Smoky Barbecue Favorites',
2113 'thumbnail': r
're:^https?://.*\.jpe?g',
2114 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2115 'upload_date': '20170909',
2116 'timestamp': 1504915200,
2118 'add_ie': [ZypeIE
.ie_key()],
2120 'skip_download': True,
2125 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2129 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2130 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2131 'thumbnail': r
're:^https?://.*\.jpg$',
2134 'skip_download': True,
2136 'expected_warnings': ['Failed to download MPD manifest'],
2139 # DailyMotion embed with DM.player
2140 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2142 'id': 'k6aKkGHd9FJs4mtJN39',
2144 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2145 'description': 'This video is private.',
2146 'uploader_id': 'x1jf30l',
2147 'uploader': 'beIN SPORTS USA',
2148 'upload_date': '20190528',
2149 'timestamp': 1559062971,
2152 'skip_download': True,
2156 # # TODO: find another test
2157 # # http://schema.org/VideoObject
2158 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2159 # 'md5': '888dcf08b7ea671381f00fab74692755',
2161 # 'id': 'nyvTSJMKId',
2163 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2164 # 'description': '#love for cats.',
2165 # 'timestamp': 1461244995,
2166 # 'upload_date': '20160421',
2169 # 'force_generic_extractor': True,
2174 def report_following_redirect(self
, new_url
):
2175 """Report information extraction."""
2176 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
2178 def _extract_rss(self
, url
, video_id
, doc
):
2179 playlist_title
= doc
.find('./channel/title').text
2180 playlist_desc_el
= doc
.find('./channel/description')
2181 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
2184 for it
in doc
.findall('./channel/item'):
2186 enclosure_nodes
= it
.findall('./enclosure')
2187 for e
in enclosure_nodes
:
2188 next_url
= e
.attrib
.get('url')
2193 next_url
= xpath_text(it
, 'link', fatal
=False)
2199 '_type': 'url_transparent',
2201 'title': it
.find('title').text
,
2205 '_type': 'playlist',
2207 'title': playlist_title
,
2208 'description': playlist_desc
,
2212 def _extract_camtasia(self
, url
, video_id
, webpage
):
2213 """ Returns None if no camtasia video can be found. """
2215 camtasia_cfg
= self
._search
_regex
(
2216 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2217 webpage
, 'camtasia configuration file', default
=None)
2218 if camtasia_cfg
is None:
2221 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
2223 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
2224 camtasia_cfg
= self
._download
_xml
(
2225 camtasia_url
, video_id
,
2226 note
='Downloading camtasia configuration',
2227 errnote
='Failed to download camtasia configuration')
2228 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
2231 for n
in fileset_node
.getchildren():
2232 url_n
= n
.find('./uri')
2237 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
2238 'title': '%s - %s' % (title
, n
.tag
),
2239 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
2240 'duration': float_or_none(n
.find('./duration').text
),
2244 '_type': 'playlist',
2249 def _real_extract(self
, url
):
2250 if url
.startswith('//'):
2251 return self
.url_result(self
.http_scheme() + url
)
2253 parsed_url
= compat_urlparse
.urlparse(url
)
2254 if not parsed_url
.scheme
:
2255 default_search
= self
._downloader
.params
.get('default_search')
2256 if default_search
is None:
2257 default_search
= 'fixup_error'
2259 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
2260 if re
.match(r
'^[^\s/]+\.[^\s/]+/', url
):
2261 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
2262 return self
.url_result('http://' + url
)
2263 elif default_search
!= 'fixup_error':
2264 if default_search
== 'auto_warning':
2265 if re
.match(r
'^(?:url|URL)$', url
):
2266 raise ExtractorError(
2267 'Invalid URL: %r . Call youtube-dlc like this: youtube-dlc -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
2270 self
._downloader
.report_warning(
2271 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
2272 return self
.url_result('ytsearch:' + url
)
2274 if default_search
in ('error', 'fixup_error'):
2275 raise ExtractorError(
2276 '%r is not a valid URL. '
2277 'Set --default-search "ytsearch" (or run youtube-dlc "ytsearch:%s" ) to search YouTube'
2278 % (url
, url
), expected
=True)
2280 if ':' not in default_search
:
2281 default_search
+= ':'
2282 return self
.url_result(default_search
+ url
)
2284 url
, smuggled_data
= unsmuggle_url(url
)
2285 force_videoid
= None
2286 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
2287 if smuggled_data
and 'force_videoid' in smuggled_data
:
2288 force_videoid
= smuggled_data
['force_videoid']
2289 video_id
= force_videoid
2291 video_id
= self
._generic
_id
(url
)
2293 self
.to_screen('%s: Requesting header' % video_id
)
2295 head_req
= HEADRequest(url
)
2296 head_response
= self
._request
_webpage
(
2298 note
=False, errnote
='Could not send HEAD request to %s' % url
,
2301 if head_response
is not False:
2302 # Check for redirect
2303 new_url
= head_response
.geturl()
2305 self
.report_following_redirect(new_url
)
2307 new_url
= smuggle_url(
2308 new_url
, {'force_videoid': force_videoid}
)
2309 return self
.url_result(new_url
)
2311 full_response
= None
2312 if head_response
is False:
2313 request
= sanitized_Request(url
)
2314 request
.add_header('Accept-Encoding', '*')
2315 full_response
= self
._request
_webpage
(request
, video_id
)
2316 head_response
= full_response
2320 'title': self
._generic
_title
(url
),
2321 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
2324 # Check for direct link to a video
2325 content_type
= head_response
.headers
.get('Content-Type', '').lower()
2326 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
2328 format_id
= compat_str(m
.group('format_id'))
2329 if format_id
.endswith('mpegurl'):
2330 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2331 elif format_id
== 'f4m':
2332 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
2335 'format_id': format_id
,
2337 'vcodec': 'none' if m
.group('type') == 'audio' else None
2339 info_dict
['direct'] = True
2340 self
._sort
_formats
(formats
)
2341 info_dict
['formats'] = formats
2344 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
2345 force
= self
._downloader
.params
.get('force_generic_extractor', False)
2346 self
._downloader
.report_warning(
2347 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
2349 if not full_response
:
2350 request
= sanitized_Request(url
)
2351 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2352 # making it impossible to download only chunk of the file (yet we need only 512kB to
2353 # test whether it's HTML or not). According to youtube-dlc default Accept-Encoding
2354 # that will always result in downloading the whole file that is not desirable.
2355 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2356 # to accept raw bytes and being able to download only a chunk.
2357 # It may probably better to solve this by checking Content-Type for application/octet-stream
2358 # after HEAD request finishes, but not sure if we can rely on this.
2359 request
.add_header('Accept-Encoding', '*')
2360 full_response
= self
._request
_webpage
(request
, video_id
)
2362 first_bytes
= full_response
.read(512)
2364 # Is it an M3U playlist?
2365 if first_bytes
.startswith(b
'#EXTM3U'):
2366 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2367 self
._sort
_formats
(info_dict
['formats'])
2370 # Maybe it's a direct link to a video?
2371 # Be careful not to download the whole thing!
2372 if not is_html(first_bytes
):
2373 self
._downloader
.report_warning(
2374 'URL could be a direct video link, returning it as such.')
2381 webpage
= self
._webpage
_read
_content
(
2382 full_response
, url
, video_id
, prefix
=first_bytes
)
2384 self
.report_extraction(video_id
)
2386 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2388 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
2389 if doc
.tag
== 'rss':
2390 return self
._extract
_rss
(url
, video_id
, doc
)
2391 elif doc
.tag
== 'SmoothStreamingMedia':
2392 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
2393 self
._sort
_formats
(info_dict
['formats'])
2395 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
2396 smil
= self
._parse
_smil
(doc
, url
, video_id
)
2397 self
._sort
_formats
(smil
['formats'])
2399 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
2400 return self
.playlist_result(
2402 doc
, video_id
, xspf_url
=url
,
2403 xspf_base_url
=full_response
.geturl()),
2405 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
2406 info_dict
['formats'] = self
._parse
_mpd
_formats
(
2408 mpd_base_url
=full_response
.geturl().rpartition('/')[0],
2410 self
._sort
_formats
(info_dict
['formats'])
2412 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
2413 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
2414 self
._sort
_formats
(info_dict
['formats'])
2416 except compat_xml_parse_error
:
2419 # Is it a Camtasia project?
2420 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
2421 if camtasia_res
is not None:
2424 # Sometimes embedded video player is hidden behind percent encoding
2425 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2426 # Unescaping the whole page allows to handle those cases in a generic way
2427 webpage
= compat_urllib_parse_unquote(webpage
)
2429 # Unescape squarespace embeds to be detected by generic extractor,
2430 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2432 r
'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2433 lambda x
: unescapeHTML(x
.group(0)), webpage
)
2435 # it's tempting to parse this further, but you would
2436 # have to take into account all the variations like
2437 # Video Title - Site Name
2438 # Site Name | Video Title
2439 # Video Title - Tagline | Site Name
2440 # and so on and so forth; it's just not practical
2441 video_title
= self
._og
_search
_title
(
2442 webpage
, default
=None) or self
._html
_search
_regex
(
2443 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
2446 # Try to detect age limit automatically
2447 age_limit
= self
._rta
_search
(webpage
)
2448 # And then there are the jokers who advertise that they use RTA,
2449 # but actually don't.
2450 AGE_LIMIT_MARKERS
= [
2451 r
'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2453 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
2456 # video uploader is domain name
2457 video_uploader
= self
._search
_regex
(
2458 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
2460 video_description
= self
._og
_search
_description
(webpage
, default
=None)
2461 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
2464 'title': video_title
,
2465 'description': video_description
,
2466 'thumbnail': video_thumbnail
,
2467 'age_limit': age_limit
,
2470 # Look for Brightcove Legacy Studio embeds
2471 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
2475 'url': smuggle_url(bc_url
, {'Referer': url}
),
2476 'ie_key': 'BrightcoveLegacy'
2477 } for bc_url
in bc_urls
]
2480 '_type': 'playlist',
2481 'title': video_title
,
2486 # Look for Brightcove New Studio embeds
2487 bc_urls
= BrightcoveNewIE
._extract
_urls
(self
, webpage
)
2489 return self
.playlist_from_matches(
2490 bc_urls
, video_id
, video_title
,
2491 getter
=lambda x
: smuggle_url(x
, {'referrer': url}
),
2494 # Look for Nexx embeds
2495 nexx_urls
= NexxIE
._extract
_urls
(webpage
)
2497 return self
.playlist_from_matches(nexx_urls
, video_id
, video_title
, ie
=NexxIE
.ie_key())
2499 # Look for Nexx iFrame embeds
2500 nexx_embed_urls
= NexxEmbedIE
._extract
_urls
(webpage
)
2502 return self
.playlist_from_matches(nexx_embed_urls
, video_id
, video_title
, ie
=NexxEmbedIE
.ie_key())
2504 # Look for ThePlatform embeds
2505 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
2507 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
2509 # Look for embedded rtl.nl player
2510 matches
= re
.findall(
2511 r
'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2514 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
2516 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
2518 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
2520 vid_me_embed_url
= self
._search
_regex
(
2521 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2522 webpage, 'vid.me embed', default=None)
2523 if vid_me_embed_url is not None:
2524 return self.url_result(vid_me_embed_url, 'Vidme')
2526 # Look for YouTube embeds
2527 youtube_urls = YoutubeIE._extract_urls(webpage)
2529 return self.playlist_from_matches(
2530 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2532 matches = DailymotionIE._extract_urls(webpage)
2534 return self.playlist_from_matches(matches, video_id, video_title)
2536 # Look for embedded Dailymotion playlist player (#3822)
2538 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}
/widget
/jukebox
\?.+?
)\
1', webpage)
2540 playlists = re.findall(
2541 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
2543 return self.playlist_from_matches(
2544 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
2546 # Look for DailyMail embeds
2547 dailymail_urls = DailyMailIE._extract_urls(webpage)
2549 return self.playlist_from_matches(
2550 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2552 # Look for Teachable embeds, must be before Wistia
2553 teachable_url = TeachableIE._extract_url(webpage, url)
2555 return self.url_result(teachable_url)
2557 # Look for embedded Wistia player
2558 wistia_urls = WistiaIE._extract_urls(webpage)
2560 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2561 for entry in playlist['entries
']:
2563 '_type
': 'url_transparent
',
2564 'uploader
': video_uploader,
2568 # Look for SVT player
2569 svt_url = SVTIE._extract_url(webpage)
2571 return self.url_result(svt_url, 'SVT
')
2573 # Look for Bandcamp pages with custom domain
2574 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
2575 if mobj is not None:
2576 burl = unescapeHTML(mobj.group(1))
2577 # Don't
set the extractor because it can be a track url
or an album
2578 return self
.url_result(burl
)
2580 # Look for embedded Vevo player
2582 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group('url
'))
2586 # Look for embedded Viddler player
2588 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2590 if mobj is not None:
2591 return self.url_result(mobj.group('url'))
2593 # Look for NYTimes player
2595 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
2597 if mobj is not None:
2598 return self.url_result(mobj.group('url
'))
2600 # Look for Libsyn player
2602 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'))
2606 # Look for Ooyala videos
2607 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2608 or re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage)
2609 or re.search(r'OO\
.Player\
.create\
.apply\
(\s
*OO\
.Player\s
*,\s
*op\
(\s
*\
[\s
*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage)
2610 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P
<ec
>.{32}
)[\'"]\)', webpage)
2611 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage))
2612 if mobj is not None:
2613 embed_token = self._search_regex(
2614 r'embedToken[\'"]?\s
*:\s
*[\'"]([^\'"]+)',
2615 webpage, 'ooyala embed token
', default=None)
2616 return OoyalaIE._build_url_result(smuggle_url(
2619 'embed_token
': embed_token,
2622 # Look for multiple Ooyala embeds on SBN network websites
2623 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
2624 if mobj is not None:
2625 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2627 return self.playlist_from_matches(
2628 embeds, video_id, video_title,
2629 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
2631 # Look for Aparat videos
2632 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2633 if mobj is not None:
2634 return self.url_result(mobj.group(1), 'Aparat')
2636 # Look for MPORA videos
2637 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
2638 if mobj is not None:
2639 return self.url_result(mobj.group(1), 'Mpora
')
2641 # Look for embedded Facebook player
2642 facebook_urls = FacebookIE._extract_urls(webpage)
2644 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2646 # Look for embedded VK player
2647 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'), 'VK')
2651 # Look for embedded Odnoklassniki player
2652 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2653 if odnoklassniki_url:
2654 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2656 # Look for embedded ivi player
2657 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
2658 if mobj is not None:
2659 return self.url_result(mobj.group('url
'), 'Ivi
')
2661 # Look for embedded Huffington Post player
2663 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2664 if mobj is not None:
2665 return self.url_result(mobj.group('url'), 'HuffPost')
2668 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
2669 if mobj is not None:
2670 return self.url_result(mobj.group('url'))
2671 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
2672 if mobj is not None:
2673 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2675 # Look for funnyordie embed
2676 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
2678 return self.playlist_from_matches(
2679 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie
')
2681 # Look for BBC iPlayer embed
2682 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
2684 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk
')
2686 # Look for embedded RUTV player
2687 rutv_url = RUTVIE._extract_url(webpage)
2689 return self.url_result(rutv_url, 'RUTV
')
2691 # Look for embedded TVC player
2692 tvc_url = TVCIE._extract_url(webpage)
2694 return self.url_result(tvc_url, 'TVC
')
2696 # Look for embedded SportBox player
2697 sportbox_urls = SportBoxIE._extract_urls(webpage)
2699 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2701 # Look for embedded XHamster player
2702 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2704 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed
')
2706 # Look for embedded TNAFlixNetwork player
2707 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2709 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2711 # Look for embedded PornHub player
2712 pornhub_urls = PornHubIE._extract_urls(webpage)
2714 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2716 # Look for embedded DrTuber player
2717 drtuber_urls = DrTuberIE._extract_urls(webpage)
2719 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2721 # Look for embedded RedTube player
2722 redtube_urls = RedTubeIE._extract_urls(webpage)
2724 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2726 # Look for embedded Tube8 player
2727 tube8_urls = Tube8IE._extract_urls(webpage)
2729 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2731 # Look for embedded Mofosex player
2732 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2734 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2736 # Look for embedded Spankwire player
2737 spankwire_urls = SpankwireIE._extract_urls(webpage)
2739 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2741 # Look for embedded YouPorn player
2742 youporn_urls = YouPornIE._extract_urls(webpage)
2744 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2746 # Look for embedded Tvigle player
2748 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2749 if mobj is not None:
2750 return self.url_result(mobj.group('url'), 'Tvigle')
2752 # Look for embedded TED player
2754 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
2755 if mobj is not None:
2756 return self.url_result(mobj.group('url
'), 'TED
')
2758 # Look for embedded Ustream videos
2759 ustream_url = UstreamIE._extract_url(webpage)
2761 return self.url_result(ustream_url, UstreamIE.ie_key())
2763 # Look for embedded arte.tv player
2765 r'<(?
:script|iframe
) [^
>]*?src
="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2767 if mobj is not None:
2768 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2770 # Look for embedded francetv player
2772 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
://)?embed\
.francetv\
.fr
/\?ue
=.+?
)\
1',
2774 if mobj is not None:
2775 return self.url_result(mobj.group('url
'))
2777 # Look for embedded smotri.com player
2778 smotri_url = SmotriIE._extract_url(webpage)
2780 return self.url_result(smotri_url, 'Smotri
')
2782 # Look for embedded Myvi.ru player
2783 myvi_url = MyviIE._extract_url(webpage)
2785 return self.url_result(myvi_url)
2787 # Look for embedded soundcloud player
2788 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2790 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2792 # Look for tunein player
2793 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2795 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2797 # Look for embedded mtvservices player
2798 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2800 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded
')
2802 # Look for embedded yahoo player
2804 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2806 if mobj is not None:
2807 return self.url_result(mobj.group('url'), 'Yahoo')
2809 # Look for embedded sbs.com.au player
2813 <meta\s+property="og
:video
"\s+content=|
2816 (["\'])(?P
<url
>https?
://(?
:www\
.)?sbs\
.com\
.au
/ondemand
/video
/.+?
)\
1''',
2818 if mobj is not None:
2819 return self.url_result(mobj.group('url'), 'SBS')
2821 # Look for embedded Cinchcast player
2823 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2825 if mobj is not None:
2826 return self.url_result(mobj.group('url'), 'Cinchcast')
2829 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2833 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2835 if mobj is not None:
2836 return self.url_result(mobj.group('url'), 'MLB')
2839 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2841 if mobj is not None:
2842 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2845 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2847 if mobj is not None:
2848 return self.url_result(mobj.group('url'), 'Livestream')
2850 # Look for Zapiks embed
2852 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2853 if mobj is not None:
2854 return self.url_result(mobj.group('url'), 'Zapiks')
2856 # Look for Kaltura embeds
2857 kaltura_urls = KalturaIE._extract_urls(webpage)
2859 return self.playlist_from_matches(
2860 kaltura_urls, video_id, video_title,
2861 getter=lambda x: smuggle_url(x, {'source_url': url}),
2862 ie=KalturaIE.ie_key())
2864 # Look for EaglePlatform embeds
2865 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2866 if eagleplatform_url:
2867 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2869 # Look for ClipYou (uses EaglePlatform) embeds
2871 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2872 if mobj is not None:
2873 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2875 # Look for Pladform embeds
2876 pladform_url = PladformIE._extract_url(webpage)
2878 return self.url_result(pladform_url)
2880 # Look for Videomore embeds
2881 videomore_url = VideomoreIE._extract_url(webpage)
2883 return self.url_result(videomore_url)
2885 # Look for Webcaster embeds
2886 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2888 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2890 # Look for Playwire embeds
2892 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2893 if mobj is not None:
2894 return self.url_result(mobj.group('url'))
2896 # Look for 5min embeds
2898 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2899 if mobj is not None:
2900 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2902 # Look for Crooks and Liars embeds
2904 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2905 if mobj is not None:
2906 return self.url_result(mobj.group('url'))
2908 # Look for NBC Sports VPlayer embeds
2909 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2911 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2913 # Look for NBC News embeds
2914 nbc_news_embed_url = re.search(
2915 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2916 if nbc_news_embed_url:
2917 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2919 # Look for Google Drive embeds
2920 google_drive_url = GoogleDriveIE._extract_url(webpage)
2921 if google_drive_url:
2922 return self.url_result(google_drive_url, 'GoogleDrive')
2924 # Look for UDN embeds
2926 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2927 if mobj is not None:
2928 return self.url_result(
2929 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2931 # Look for Senate ISVP iframe
2932 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2934 return self.url_result(senate_isvp_url, 'SenateISVP')
2936 # Look for Kinja embeds
2937 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2938 if kinja_embed_urls:
2939 return self.playlist_from_matches(
2940 kinja_embed_urls, video_id, video_title)
2942 # Look for OnionStudios embeds
2943 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2944 if onionstudios_url:
2945 return self.url_result(onionstudios_url)
2947 # Look for ViewLift embeds
2948 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2950 return self.url_result(viewlift_url)
2952 # Look for JWPlatform embeds
2953 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2955 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2957 # Look for Digiteka embeds
2958 digiteka_url = DigitekaIE._extract_url(webpage)
2960 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2962 # Look for Arkena embeds
2963 arkena_url = ArkenaIE._extract_url(webpage)
2965 return self.url_result(arkena_url, ArkenaIE.ie_key())
2967 # Look for Piksel embeds
2968 piksel_url = PikselIE._extract_url(webpage)
2970 return self.url_result(piksel_url, PikselIE.ie_key())
2972 # Look for Limelight embeds
2973 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2975 return self.playlist_result(
2976 limelight_urls, video_id, video_title, video_description)
2978 # Look for Anvato embeds
2979 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2981 return self.playlist_result(
2982 anvato_urls, video_id, video_title, video_description)
2984 # Look for AdobeTVVideo embeds
2986 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2988 if mobj is not None:
2989 return self.url_result(
2990 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2993 # Look for Vine embeds
2995 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2997 if mobj is not None:
2998 return self.url_result(
2999 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3001 # Look for VODPlatform embeds
3003 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3005 if mobj is not None:
3006 return self.url_result(
3007 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3009 # Look for Mangomolo embeds
3011 r'''(?x
)<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//
3013 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3014 player\.mangomolo\.com/v1
3017 video\?.*?\bid=(?P<video_id>\d+)|
3018 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3019 ).+?)\1''', webpage)
3020 if mobj is not None:
3022 '_type': 'url_transparent',
3023 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3024 'title': video_title,
3025 'description': video_description,
3026 'thumbnail': video_thumbnail,
3027 'uploader': video_uploader,
3029 video_id = mobj.group('video_id')
3032 'ie_key': 'MangomoloVideo',
3037 'ie_key': 'MangomoloLive',
3038 'id': mobj.group('channel_id'),
3042 # Look for Instagram embeds
3043 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3044 if instagram_embed_url is not None:
3045 return self.url_result(
3046 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3048 # Look for LiveLeak embeds
3049 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3051 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3053 # Look for 3Q SDN embeds
3054 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3057 '_type': 'url_transparent',
3058 'ie_key': ThreeQSDNIE.ie_key(),
3059 'url': self._proto_relative_url(threeqsdn_url),
3060 'title': video_title,
3061 'description': video_description,
3062 'thumbnail': video_thumbnail,
3063 'uploader': video_uploader,
3066 # Look for VBOX7 embeds
3067 vbox7_url = Vbox7IE._extract_url(webpage)
3069 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3071 # Look for DBTV embeds
3072 dbtv_urls = DBTVIE._extract_urls(webpage)
3074 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3076 # Look for Videa embeds
3077 videa_urls = VideaIE._extract_urls(webpage)
3079 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3081 # Look for 20 minuten embeds
3082 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3084 return self.playlist_from_matches(
3085 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3087 # Look for VideoPress embeds
3088 videopress_urls = VideoPressIE._extract_urls(webpage)
3090 return self.playlist_from_matches(
3091 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3093 # Look for Rutube embeds
3094 rutube_urls = RutubeIE._extract_urls(webpage)
3096 return self.playlist_from_matches(
3097 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3099 # Look for WashingtonPost embeds
3100 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3102 return self.playlist_from_matches(
3103 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3105 # Look for Mediaset embeds
3106 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3108 return self.playlist_from_matches(
3109 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3111 # Look for JOJ.sk embeds
3112 joj_urls = JojIE._extract_urls(webpage)
3114 return self.playlist_from_matches(
3115 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3117 # Look for megaphone.fm embeds
3118 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3120 return self.playlist_from_matches(
3121 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3123 # Look for vzaar embeds
3124 vzaar_urls = VzaarIE._extract_urls(webpage)
3126 return self.playlist_from_matches(
3127 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3129 channel9_urls = Channel9IE._extract_urls(webpage)
3131 return self.playlist_from_matches(
3132 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3134 vshare_urls = VShareIE._extract_urls(webpage)
3136 return self.playlist_from_matches(
3137 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3139 # Look for Mediasite embeds
3140 mediasite_urls = MediasiteIE._extract_urls(webpage)
3143 self.url_result(smuggle_url(
3144 compat_urlparse.urljoin(url, mediasite_url),
3145 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3146 for mediasite_url in mediasite_urls]
3147 return self.playlist_result(entries, video_id, video_title)
3149 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3150 if springboardplatform_urls:
3151 return self.playlist_from_matches(
3152 springboardplatform_urls, video_id, video_title,
3153 ie=SpringboardPlatformIE.ie_key())
3155 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3157 return self.playlist_from_matches(
3158 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3160 vice_urls = ViceIE._extract_urls(webpage)
3162 return self.playlist_from_matches(
3163 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3165 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3167 return self.playlist_from_matches(
3168 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3170 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3171 if cloudflarestream_urls:
3172 return self.playlist_from_matches(
3173 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3175 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3177 return self.playlist_from_matches(
3178 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3180 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3182 return self.playlist_from_matches(
3183 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3185 apa_urls = APAIE._extract_urls(webpage)
3187 return self.playlist_from_matches(
3188 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3190 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3192 return self.playlist_from_matches(
3193 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3195 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3196 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.share
-videos\
.se
/auto
/embed
/\d
+\?.*?
\buid
=\d
+.*?
)\
1',
3198 if sharevideos_urls:
3199 return self.playlist_from_matches(
3200 sharevideos_urls, video_id, video_title)
3202 viqeo_urls = ViqeoIE._extract_urls(webpage)
3204 return self.playlist_from_matches(
3205 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3207 expressen_urls = ExpressenIE._extract_urls(webpage)
3209 return self.playlist_from_matches(
3210 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3212 zype_urls = ZypeIE._extract_urls(webpage)
3214 return self.playlist_from_matches(
3215 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3217 # Look for RCS media group embeds
3218 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3220 return self.playlist_from_matches(
3221 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3223 # Look for HTML5 media
3224 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls
')
3226 if len(entries) == 1:
3229 'title
': video_title,
3232 for num, entry in enumerate(entries, start=1):
3234 'id': '%s-%s' % (video_id, num),
3235 'title
': '%s (%d)' % (video_title, num),
3237 for entry in entries:
3238 self._sort_formats(entry['formats
'])
3239 return self.playlist_result(entries, video_id, video_title)
3241 jwplayer_data = self._find_jwplayer_data(
3242 webpage, video_id, transform_source=js_to_json)
3245 info = self._parse_jwplayer_data(
3246 jwplayer_data, video_id, require_title=False, base_url=url)
3247 return merge_dicts(info, info_dict)
3248 except ExtractorError:
3249 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3254 r'(?s
)\bvideojs\s
*\
(.+?\
.src\s
*\
(\s
*((?
:\
[.+?\
]|{.+?}
))\s
*\
)\s
*;',
3256 if mobj is not None:
3257 sources = self._parse_json(
3258 mobj.group(1), video_id, transform_source=js_to_json,
3260 if not isinstance(sources, list):
3263 for source in sources:
3264 src = source.get('src
')
3265 if not src or not isinstance(src, compat_str):
3267 src = compat_urlparse.urljoin(url, src)
3268 src_type = source.get('type')
3269 if isinstance(src_type, compat_str):
3270 src_type = src_type.lower()
3271 ext = determine_ext(src).lower()
3272 if src_type == 'video
/youtube
':
3273 return self.url_result(src, YoutubeIE.ie_key())
3274 if src_type == 'application
/dash
+xml
' or ext == 'mpd
':
3275 formats.extend(self._extract_mpd_formats(
3276 src, video_id, mpd_id='dash
', fatal=False))
3277 elif src_type == 'application
/x
-mpegurl
' or ext == 'm3u8
':
3278 formats.extend(self._extract_m3u8_formats(
3279 src, video_id, 'mp4
', entry_protocol='m3u8_native
',
3280 m3u8_id='hls
', fatal=False))
3284 'ext
': (mimetype2ext(src_type)
3285 or ext if ext in KNOWN_EXTENSIONS else 'mp4
'),
3288 self._sort_formats(formats)
3289 info_dict['formats
'] = formats
3292 # Looking for http://schema.org/VideoObject
3293 json_ld = self._search_json_ld(
3294 webpage, video_id, default={}, expected_type='VideoObject
')
3295 if json_ld.get('url
'):
3296 return merge_dicts(json_ld, info_dict)
3298 def check_video(vurl):
3299 if YoutubeIE.suitable(vurl):
3301 if RtmpIE.suitable(vurl):
3303 vpath = compat_urlparse.urlparse(vurl).path
3304 vext = determine_ext(vpath)
3305 return '.' in vpath and vext not in ('swf
', 'png
', 'jpg
', 'srt
', 'sbv
', 'sub
', 'vtt
', 'ttml
', 'js
', 'xml
')
3307 def filter_video(urls):
3308 return list(filter(check_video, urls))
3310 # Start with something easy: JW Player in SWFObject
3311 found = filter_video(re.findall(r'flashvars
: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3313 # Look for gorilla-vid style embedding
3314 found = filter_video(re.findall(r'''(?sx)
3318 jwplayer\s*\(\s*["'][^
'"]+["']\s
*\
)\s
*\
.setup
3321 ['"]?file['"]?\s*:\s*["\'](.*?
)["\']''', webpage))
3323 # Broaden the search a little bit
3324 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3326 # Broaden the findall a little bit: JWPlayer JS loader
3327 found = filter_video(re.findall(
3328 r'[^A
-Za
-z0
-9]?
(?
:file|video_url
)["\']?:\s*["\'](http(?
![^
\'"]+\.[0-9]+[\'"])[^
\'"]+)["\']', webpage))
3331 found = filter_video(re.findall(r'''(?xs)
3332 flowplayer\("[^"]+",\s*
3334 \s*\{[^}]+? ["']?clip
["']?\s*:\s*\{\s*
3335 ["']?url["']?\s
*:\s
*["']([^"']+)["']
3340 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3342 # Try to find twitter cards info
3343 # twitter:player:stream should be checked before twitter:player since
3344 # it is expected to contain a raw stream (see
3345 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3346 found = filter_video(re.findall(
3347 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3349 # We look for Open Graph info:
3350 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3351 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3352 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3353 if m_video_type is not None:
3354 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3356 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3358 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3359 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3362 # Look also in Refresh HTTP header
3363 refresh_header = head_response.headers.get('Refresh')
3365 # In python 2 response HTTP headers are bytestrings
3366 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3367 refresh_header = refresh_header.decode('iso-8859-1')
3368 found = re.search(REDIRECT_REGEX, refresh_header)
3370 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3372 self.report_following_redirect(new_url)
3381 # twitter:player is a https URL to iframe player that may or may not
3382 # be supported by youtube-dlc thus this is checked the very last (see
3383 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3384 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3385 if embed_url and embed_url != url:
3386 return self.url_result(embed_url)
3389 raise UnsupportedError(url)
3392 for video_url in orderedSet(found):
3393 video_url = unescapeHTML(video_url)
3394 video_url = video_url.replace('\\/', '/')
3395 video_url = compat_urlparse.urljoin(url, video_url)
3396 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3398 # Sometimes, jwplayer extraction will result in a YouTube URL
3399 if YoutubeIE.suitable(video_url):
3400 entries.append(self.url_result(video_url, 'Youtube'))
3403 # here's a fun little line of code for you:
3404 video_id = os.path.splitext(video_id)[0]
3408 'uploader': video_uploader,
3409 'title': video_title,
3410 'age_limit': age_limit,
3413 if RtmpIE.suitable(video_url):
3414 entry_info_dict.update({
3415 '_type': 'url_transparent',
3416 'ie_key': RtmpIE.ie_key(),
3419 entries.append(entry_info_dict)
3422 ext = determine_ext(video_url)
3424 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3426 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3428 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3430 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3432 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3433 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3434 # Just matching .ism/manifest is not enough to be reliably sure
3435 # whether it's actually an ISM manifest or some other streaming
3436 # manifest since there are various streaming URL formats
3437 # possible (see [1]) as well as some other shenanigans like
3438 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3440 # Thus the most reasonable way to solve this is to delegate
3441 # to generic extractor in order to look into the contents of
3442 # the manifest itself.
3443 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3444 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3445 entry_info_dict = self.url_result(
3446 smuggle_url(video_url, {'to_generic': True}),
3449 entry_info_dict['url'] = video_url
3451 if entry_info_dict.get('formats'):
3452 self._sort_formats(entry_info_dict['formats'])
3454 entries.append(entry_info_dict)
3456 if len(entries) == 1:
3459 for num, e in enumerate(entries, start=1):
3460 # 'url' results don't have a title
3461 if e.get('title') is not None:
3462 e['title'] = '%s (%d)' % (e['title'], num)
3464 '_type': 'playlist',