]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/generic.py
[test/download] Fallback test to `bv`
[yt-dlp.git] / yt_dlp / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 int_or_none,
24 is_html,
25 js_to_json,
26 KNOWN_EXTENSIONS,
27 merge_dicts,
28 mimetype2ext,
29 orderedSet,
30 parse_duration,
31 sanitized_Request,
32 smuggle_url,
33 unescapeHTML,
34 unified_timestamp,
35 unsmuggle_url,
36 UnsupportedError,
37 url_or_none,
38 xpath_attr,
39 xpath_text,
40 xpath_with_ns,
41 )
42 from .commonprotocols import RtmpIE
43 from .brightcove import (
44 BrightcoveLegacyIE,
45 BrightcoveNewIE,
46 )
47 from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50 )
51 from .nbc import NBCSportsVPlayerIE
52 from .ooyala import OoyalaIE
53 from .rutv import RUTVIE
54 from .tvc import TVCIE
55 from .sportbox import SportBoxIE
56 from .myvi import MyviIE
57 from .condenast import CondeNastIE
58 from .udn import UDNEmbedIE
59 from .senateisvp import SenateISVPIE
60 from .svt import SVTIE
61 from .pornhub import PornHubIE
62 from .xhamster import XHamsterEmbedIE
63 from .tnaflix import TNAFlixNetworkEmbedIE
64 from .drtuber import DrTuberIE
65 from .redtube import RedTubeIE
66 from .tube8 import Tube8IE
67 from .mofosex import MofosexEmbedIE
68 from .spankwire import SpankwireIE
69 from .youporn import YouPornIE
70 from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73 )
74 from .dailymotion import DailymotionIE
75 from .dailymail import DailyMailIE
76 from .onionstudios import OnionStudiosIE
77 from .viewlift import ViewLiftEmbedIE
78 from .mtv import MTVServicesEmbeddedIE
79 from .pladform import PladformIE
80 from .videomore import VideomoreIE
81 from .webcaster import WebcasterFeedIE
82 from .googledrive import GoogleDriveIE
83 from .jwplatform import JWPlatformIE
84 from .digiteka import DigitekaIE
85 from .arkena import ArkenaIE
86 from .instagram import InstagramIE
87 from .threeqsdn import ThreeQSDNIE
88 from .theplatform import ThePlatformIE
89 from .kaltura import KalturaIE
90 from .eagleplatform import EaglePlatformIE
91 from .facebook import FacebookIE
92 from .soundcloud import SoundcloudEmbedIE
93 from .tunein import TuneInBaseIE
94 from .vbox7 import Vbox7IE
95 from .dbtv import DBTVIE
96 from .piksel import PikselIE
97 from .videa import VideaIE
98 from .twentymin import TwentyMinutenIE
99 from .ustream import UstreamIE
100 from .arte import ArteTVEmbedIE
101 from .videopress import VideoPressIE
102 from .rutube import RutubeIE
103 from .limelight import LimelightBaseIE
104 from .anvato import AnvatoIE
105 from .washingtonpost import WashingtonPostIE
106 from .wistia import WistiaIE
107 from .mediaset import MediasetIE
108 from .joj import JojIE
109 from .megaphone import MegaphoneIE
110 from .vzaar import VzaarIE
111 from .channel9 import Channel9IE
112 from .vshare import VShareIE
113 from .mediasite import MediasiteIE
114 from .springboardplatform import SpringboardPlatformIE
115 from .yapfiles import YapFilesIE
116 from .vice import ViceIE
117 from .xfileshare import XFileShareIE
118 from .cloudflarestream import CloudflareStreamIE
119 from .peertube import PeerTubeIE
120 from .teachable import TeachableIE
121 from .indavideo import IndavideoEmbedIE
122 from .apa import APAIE
123 from .foxnews import FoxNewsIE
124 from .viqeo import ViqeoIE
125 from .expressen import ExpressenIE
126 from .zype import ZypeIE
127 from .odnoklassniki import OdnoklassnikiIE
128 from .vk import VKIE
129 from .kinja import KinjaEmbedIE
130 from .gedidigital import GediDigitalIE
131 from .rcs import RCSEmbedsIE
132 from .bitchute import BitChuteIE
133 from .rumble import RumbleEmbedIE
134 from .arcpublishing import ArcPublishingIE
135 from .medialaan import MedialaanIE
136 from .simplecast import SimplecastIE
137 from .wimtv import WimTVIE
138
139
140 class GenericIE(InfoExtractor):
141 IE_DESC = 'Generic downloader that works on some sites'
142 _VALID_URL = r'.*'
143 IE_NAME = 'generic'
144 _TESTS = [
145 # Direct link to a video
146 {
147 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
148 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
149 'info_dict': {
150 'id': 'trailer',
151 'ext': 'mp4',
152 'title': 'trailer',
153 'upload_date': '20100513',
154 }
155 },
156 # Direct link to media delivered compressed (until Accept-Encoding is *)
157 {
158 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
159 'md5': '128c42e68b13950268b648275386fc74',
160 'info_dict': {
161 'id': 'FictionJunction-Parallel_Hearts',
162 'ext': 'flac',
163 'title': 'FictionJunction-Parallel_Hearts',
164 'upload_date': '20140522',
165 },
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
168 ],
169 'skip': 'URL invalid',
170 },
171 # Direct download with broken HEAD
172 {
173 'url': 'http://ai-radio.org:8000/radio.opus',
174 'info_dict': {
175 'id': 'radio',
176 'ext': 'opus',
177 'title': 'radio',
178 },
179 'params': {
180 'skip_download': True, # infinite live stream
181 },
182 'expected_warnings': [
183 r'501.*Not Implemented',
184 r'400.*Bad Request',
185 ],
186 },
187 # Direct link with incorrect MIME type
188 {
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'md5': '4ccbebe5f36706d85221f204d7eb5913',
191 'info_dict': {
192 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
193 'id': '5_Lennart_Poettering_-_Systemd',
194 'ext': 'webm',
195 'title': '5_Lennart_Poettering_-_Systemd',
196 'upload_date': '20141120',
197 },
198 'expected_warnings': [
199 'URL could be a direct video link, returning it as such.'
200 ]
201 },
202 # RSS feed
203 {
204 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
205 'info_dict': {
206 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'title': 'Zero Punctuation',
208 'description': 're:.*groundbreaking video review series.*'
209 },
210 'playlist_mincount': 11,
211 },
212 # RSS feed with enclosure
213 {
214 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
215 'info_dict': {
216 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
217 'title': 'MSNBC Rachel Maddow (video)',
218 'description': 're:.*her unique approach to storytelling.*',
219 },
220 'playlist': [{
221 'info_dict': {
222 'ext': 'mov',
223 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
224 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
225 'description': 're:.*her unique approach to storytelling.*',
226 'upload_date': '20201204',
227 },
228 }],
229 },
230 # RSS feed with item with description and thumbnails
231 {
232 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'info_dict': {
234 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'title': 're:.*100% Hydrogen.*',
236 'description': 're:.*In this episode.*',
237 },
238 'playlist': [{
239 'info_dict': {
240 'ext': 'm4a',
241 'id': 'c1c879525ce2cb640b344507e682c36d',
242 'title': 're:Hydrogen!',
243 'description': 're:.*In this episode we are going.*',
244 'timestamp': 1567977776,
245 'upload_date': '20190908',
246 'duration': 459,
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'episode_number': 1,
249 'season_number': 1,
250 'age_limit': 0,
251 },
252 }],
253 'params': {
254 'skip_download': True,
255 },
256 },
257 # RSS feed with enclosures and unsupported link URLs
258 {
259 'url': 'http://www.hellointernet.fm/podcast?format=rss',
260 'info_dict': {
261 'id': 'http://www.hellointernet.fm/podcast?format=rss',
262 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
263 'title': 'Hello Internet',
264 },
265 'playlist_mincount': 100,
266 },
267 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
268 {
269 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
270 'info_dict': {
271 'id': 'smil',
272 'ext': 'mp4',
273 'title': 'Automatics, robotics and biocybernetics',
274 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
275 'upload_date': '20130627',
276 'formats': 'mincount:16',
277 'subtitles': 'mincount:1',
278 },
279 'params': {
280 'force_generic_extractor': True,
281 'skip_download': True,
282 },
283 },
284 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
285 {
286 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
287 'info_dict': {
288 'id': 'hds',
289 'ext': 'flv',
290 'title': 'hds',
291 'formats': 'mincount:1',
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # SMIL from https://www.restudy.dk/video/play/id/1637
298 {
299 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
300 'info_dict': {
301 'id': 'video_1637',
302 'ext': 'flv',
303 'title': 'video_1637',
304 'formats': 'mincount:3',
305 },
306 'params': {
307 'skip_download': True,
308 },
309 },
310 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
311 {
312 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
313 'info_dict': {
314 'id': 'smil-service',
315 'ext': 'flv',
316 'title': 'smil-service',
317 'formats': 'mincount:1',
318 },
319 'params': {
320 'skip_download': True,
321 },
322 },
323 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
324 {
325 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
326 'info_dict': {
327 'id': '4719370',
328 'ext': 'mp4',
329 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
330 'formats': 'mincount:3',
331 },
332 'params': {
333 'skip_download': True,
334 },
335 },
336 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
337 {
338 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
339 'info_dict': {
340 'id': 'mZlp2ctYIUEB',
341 'ext': 'mp4',
342 'title': 'Tikibad ontruimd wegens brand',
343 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
344 'thumbnail': r're:^https?://.*\.jpg$',
345 'duration': 33,
346 },
347 'params': {
348 'skip_download': True,
349 },
350 },
351 # MPD from http://dash-mse-test.appspot.com/media.html
352 {
353 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
354 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
355 'info_dict': {
356 'id': 'car-20120827-manifest',
357 'ext': 'mp4',
358 'title': 'car-20120827-manifest',
359 'formats': 'mincount:9',
360 'upload_date': '20130904',
361 },
362 },
363 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
364 {
365 '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',
366 'info_dict': {
367 'id': 'content',
368 'ext': 'mp4',
369 'title': 'content',
370 'formats': 'mincount:8',
371 },
372 'params': {
373 # m3u8 downloads
374 'skip_download': True,
375 },
376 'skip': 'video gone',
377 },
378 # m3u8 served with Content-Type: text/plain
379 {
380 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
381 'info_dict': {
382 'id': 'index',
383 'ext': 'mp4',
384 'title': 'index',
385 'upload_date': '20140720',
386 'formats': 'mincount:11',
387 },
388 'params': {
389 # m3u8 downloads
390 'skip_download': True,
391 },
392 'skip': 'video gone',
393 },
394 # google redirect
395 {
396 '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',
397 'info_dict': {
398 'id': 'cmQHVoWB5FY',
399 'ext': 'mp4',
400 'upload_date': '20130224',
401 'uploader_id': 'TheVerge',
402 'description': r're:^Chris Ziegler takes a look at the\.*',
403 'uploader': 'The Verge',
404 'title': 'First Firefox OS phones side-by-side',
405 },
406 'params': {
407 'skip_download': False,
408 }
409 },
410 {
411 # redirect in Refresh HTTP header
412 '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',
413 'info_dict': {
414 'id': 'pO8h3EaFRdo',
415 'ext': 'mp4',
416 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
417 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
418 'upload_date': '20150917',
419 'uploader_id': 'brtvofficial',
420 'uploader': 'Boiler Room',
421 },
422 'params': {
423 'skip_download': False,
424 },
425 },
426 {
427 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
428 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
429 'info_dict': {
430 'id': '13601338388002',
431 'ext': 'mp4',
432 'uploader': 'www.hodiho.fr',
433 'title': 'R\u00e9gis plante sa Jeep',
434 }
435 },
436 # bandcamp page with custom domain
437 {
438 'add_ie': ['Bandcamp'],
439 'url': 'http://bronyrock.com/track/the-pony-mash',
440 'info_dict': {
441 'id': '3235767654',
442 'ext': 'mp3',
443 'title': 'The Pony Mash',
444 'uploader': 'M_Pallante',
445 },
446 'skip': 'There is a limit of 200 free downloads / month for the test song',
447 },
448 {
449 # embedded brightcove video
450 # it also tests brightcove videos that need to set the 'Referer'
451 # in the http requests
452 'add_ie': ['BrightcoveLegacy'],
453 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
454 'info_dict': {
455 'id': '2765128793001',
456 'ext': 'mp4',
457 'title': 'Le cours de bourse : l’analyse technique',
458 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
459 'uploader': 'BFM BUSINESS',
460 },
461 'params': {
462 'skip_download': True,
463 },
464 },
465 {
466 # embedded with itemprop embedURL and video id spelled as `idVideo`
467 'add_id': ['BrightcoveLegacy'],
468 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
469 'info_dict': {
470 'id': '5255628253001',
471 'ext': 'mp4',
472 'title': 'md5:37c519b1128915607601e75a87995fc0',
473 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
474 'uploader': 'BFM BUSINESS',
475 'uploader_id': '876450612001',
476 'timestamp': 1482255315,
477 'upload_date': '20161220',
478 },
479 'params': {
480 'skip_download': True,
481 },
482 },
483 {
484 # https://github.com/ytdl-org/youtube-dl/issues/2253
485 'url': 'http://bcove.me/i6nfkrc3',
486 'md5': '0ba9446db037002366bab3b3eb30c88c',
487 'info_dict': {
488 'id': '3101154703001',
489 'ext': 'mp4',
490 'title': 'Still no power',
491 'uploader': 'thestar.com',
492 '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.',
493 },
494 'add_ie': ['BrightcoveLegacy'],
495 'skip': 'video gone',
496 },
497 {
498 'url': 'http://www.championat.com/video/football/v/87/87499.html',
499 'md5': 'fb973ecf6e4a78a67453647444222983',
500 'info_dict': {
501 'id': '3414141473001',
502 'ext': 'mp4',
503 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
504 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
505 'uploader': 'Championat',
506 },
507 },
508 {
509 # https://github.com/ytdl-org/youtube-dl/issues/3541
510 'add_ie': ['BrightcoveLegacy'],
511 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
512 'info_dict': {
513 'id': '3866516442001',
514 'ext': 'mp4',
515 'title': 'Leer mij vrouwen kennen: Aflevering 1',
516 'description': 'Leer mij vrouwen kennen: Aflevering 1',
517 'uploader': 'SBS Broadcasting',
518 },
519 'skip': 'Restricted to Netherlands',
520 'params': {
521 'skip_download': True, # m3u8 download
522 },
523 },
524 {
525 # Brightcove video in <iframe>
526 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
527 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
528 'info_dict': {
529 'id': '5360463607001',
530 'ext': 'mp4',
531 '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',
532 '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。',
533 'uploader': 'United Nations',
534 'uploader_id': '1362235914001',
535 'timestamp': 1489593889,
536 'upload_date': '20170315',
537 },
538 'add_ie': ['BrightcoveLegacy'],
539 },
540 {
541 # Brightcove with alternative playerID key
542 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
543 'info_dict': {
544 'id': 'nmeth.2062_SV1',
545 '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',
546 },
547 'playlist': [{
548 'info_dict': {
549 'id': '2228375078001',
550 'ext': 'mp4',
551 'title': 'nmeth.2062-sv1',
552 'description': 'nmeth.2062-sv1',
553 'timestamp': 1363357591,
554 'upload_date': '20130315',
555 'uploader': 'Nature Publishing Group',
556 'uploader_id': '1964492299001',
557 },
558 }],
559 },
560 {
561 # Brightcove with UUID in videoPlayer
562 'url': 'http://www8.hp.com/cn/zh/home.html',
563 'info_dict': {
564 'id': '5255815316001',
565 'ext': 'mp4',
566 'title': 'Sprocket Video - China',
567 'description': 'Sprocket Video - China',
568 'uploader': 'HP-Video Gallery',
569 'timestamp': 1482263210,
570 'upload_date': '20161220',
571 'uploader_id': '1107601872001',
572 },
573 'params': {
574 'skip_download': True, # m3u8 download
575 },
576 'skip': 'video rotates...weekly?',
577 },
578 {
579 # Brightcove:new type [2].
580 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
581 'md5': '2b35148fcf48da41c9fb4591650784f3',
582 'info_dict': {
583 'id': '5348741021001',
584 'ext': 'mp4',
585 'upload_date': '20170306',
586 'uploader_id': '4191638492001',
587 'timestamp': 1488769918,
588 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
589
590 },
591 },
592 {
593 # Alternative brightcove <video> attributes
594 '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/',
595 'info_dict': {
596 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
597 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
598 },
599 'playlist': [{
600 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
601 'info_dict': {
602 'id': '5311302538001',
603 'ext': 'mp4',
604 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
605 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
606 'timestamp': 1486321708,
607 'upload_date': '20170205',
608 'uploader_id': '800000640001',
609 },
610 'only_matching': True,
611 }],
612 },
613 {
614 # Brightcove with UUID in videoPlayer
615 'url': 'http://www8.hp.com/cn/zh/home.html',
616 'info_dict': {
617 'id': '5255815316001',
618 'ext': 'mp4',
619 'title': 'Sprocket Video - China',
620 'description': 'Sprocket Video - China',
621 'uploader': 'HP-Video Gallery',
622 'timestamp': 1482263210,
623 'upload_date': '20161220',
624 'uploader_id': '1107601872001',
625 },
626 'params': {
627 'skip_download': True, # m3u8 download
628 },
629 },
630 # ooyala video
631 {
632 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
633 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
634 'info_dict': {
635 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
636 'ext': 'mp4',
637 'title': '2cc213299525360.mov', # that's what we get
638 'duration': 238.231,
639 },
640 'add_ie': ['Ooyala'],
641 },
642 {
643 # ooyala video embedded with http://player.ooyala.com/iframe.js
644 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
645 'info_dict': {
646 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
647 'ext': 'mp4',
648 'title': '"Steve Jobs: Man in the Machine" trailer',
649 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
650 'duration': 135.427,
651 },
652 'params': {
653 'skip_download': True,
654 },
655 'skip': 'movie expired',
656 },
657 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
658 {
659 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
660 'info_dict': {
661 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
662 'ext': 'mp4',
663 'title': 'Steampunk Fest Comes to Honesdale',
664 'duration': 43.276,
665 },
666 'params': {
667 'skip_download': True,
668 }
669 },
670 # embed.ly video
671 {
672 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
673 'info_dict': {
674 'id': '9ODmcdjQcHQ',
675 'ext': 'mp4',
676 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
677 'upload_date': '20140225',
678 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
679 'uploader': 'Tested',
680 'uploader_id': 'testedcom',
681 },
682 # No need to test YoutubeIE here
683 'params': {
684 'skip_download': True,
685 },
686 },
687 # funnyordie embed
688 {
689 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
690 'info_dict': {
691 'id': '18e820ec3f',
692 'ext': 'mp4',
693 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
694 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
695 },
696 # HEAD requests lead to endless 301, while GET is OK
697 'expected_warnings': ['301'],
698 },
699 # RUTV embed
700 {
701 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
702 'info_dict': {
703 'id': '776940',
704 'ext': 'mp4',
705 'title': 'Охотское море стало целиком российским',
706 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
707 },
708 'params': {
709 # m3u8 download
710 'skip_download': True,
711 },
712 },
713 # TVC embed
714 {
715 '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/',
716 'info_dict': {
717 'id': '55304',
718 'ext': 'mp4',
719 'title': 'Дошкольное воспитание',
720 },
721 },
722 # SportBox embed
723 {
724 'url': 'http://www.vestifinance.ru/articles/25753',
725 'info_dict': {
726 'id': '25753',
727 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
728 },
729 'playlist': [{
730 'info_dict': {
731 'id': '370908',
732 'title': 'Госзаказ. День 3',
733 'ext': 'mp4',
734 }
735 }, {
736 'info_dict': {
737 'id': '370905',
738 'title': 'Госзаказ. День 2',
739 'ext': 'mp4',
740 }
741 }, {
742 'info_dict': {
743 'id': '370902',
744 'title': 'Госзаказ. День 1',
745 'ext': 'mp4',
746 }
747 }],
748 'params': {
749 # m3u8 download
750 'skip_download': True,
751 },
752 },
753 # Myvi.ru embed
754 {
755 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
756 'info_dict': {
757 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
758 'ext': 'mp4',
759 'title': 'Ужастики, русский трейлер (2015)',
760 'thumbnail': r're:^https?://.*\.jpg$',
761 'duration': 153,
762 }
763 },
764 # XHamster embed
765 {
766 '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',
767 'info_dict': {
768 'id': 'showthread',
769 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
770 },
771 'playlist_mincount': 7,
772 # This forum does not allow <iframe> syntaxes anymore
773 # Now HTML tags are displayed as-is
774 'skip': 'No videos on this page',
775 },
776 # Embedded TED video
777 {
778 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
779 'md5': '65fdff94098e4a607385a60c5177c638',
780 'info_dict': {
781 'id': '1969',
782 'ext': 'mp4',
783 'title': 'Hidden miracles of the natural world',
784 'uploader': 'Louie Schwartzberg',
785 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
786 }
787 },
788 # nowvideo embed hidden behind percent encoding
789 {
790 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
791 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
792 'info_dict': {
793 'id': '06e53103ca9aa',
794 'ext': 'flv',
795 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
796 'description': 'No description',
797 },
798 },
799 # arte embed
800 {
801 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
802 'md5': '7653032cbb25bf6c80d80f217055fa43',
803 'info_dict': {
804 'id': '048195-004_PLUS7-F',
805 'ext': 'flv',
806 'title': 'X:enius',
807 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
808 'upload_date': '20140320',
809 },
810 'params': {
811 'skip_download': 'Requires rtmpdump'
812 },
813 'skip': 'video gone',
814 },
815 # francetv embed
816 {
817 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
818 'info_dict': {
819 'id': 'EV_30231',
820 'ext': 'mp4',
821 'title': 'Alcaline, le concert avec Calogero',
822 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
823 'upload_date': '20150226',
824 'timestamp': 1424989860,
825 'duration': 5400,
826 },
827 'params': {
828 # m3u8 downloads
829 'skip_download': True,
830 },
831 'expected_warnings': [
832 'Forbidden'
833 ]
834 },
835 # Condé Nast embed
836 {
837 'url': 'http://www.wired.com/2014/04/honda-asimo/',
838 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
839 'info_dict': {
840 'id': '53501be369702d3275860000',
841 'ext': 'mp4',
842 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
843 }
844 },
845 # Dailymotion embed
846 {
847 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
848 'md5': '441aeeb82eb72c422c7f14ec533999cd',
849 'info_dict': {
850 'id': 'k2mm4bCdJ6CQ2i7c8o2',
851 'ext': 'mp4',
852 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
853 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
854 'uploader': 'Spi0n',
855 'uploader_id': 'xgditw',
856 'upload_date': '20140425',
857 'timestamp': 1398441542,
858 },
859 'add_ie': ['Dailymotion'],
860 },
861 # DailyMail embed
862 {
863 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
864 'info_dict': {
865 'id': '1495629',
866 'ext': 'mp4',
867 'title': 'Care worker punches elderly dementia patient in head 11 times',
868 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
869 },
870 'add_ie': ['DailyMail'],
871 'params': {
872 'skip_download': True,
873 },
874 },
875 # YouTube embed
876 {
877 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
878 'info_dict': {
879 'id': 'FXRb4ykk4S0',
880 'ext': 'mp4',
881 'title': 'The NBL Auction 2014',
882 'uploader': 'BADMINTON England',
883 'uploader_id': 'BADMINTONEvents',
884 'upload_date': '20140603',
885 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
886 },
887 'add_ie': ['Youtube'],
888 'params': {
889 'skip_download': True,
890 }
891 },
892 # MTVServices embed
893 {
894 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
895 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
896 'info_dict': {
897 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
898 'ext': 'mp4',
899 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
900 'description': 'Two valets share their love for movie star Liam Neesons.',
901 'timestamp': 1349922600,
902 'upload_date': '20121011',
903 },
904 },
905 # YouTube embed via <data-embed-url="">
906 {
907 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
908 'info_dict': {
909 'id': '4vAffPZIT44',
910 'ext': 'mp4',
911 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
912 'uploader': 'Gameloft',
913 'uploader_id': 'gameloft',
914 'upload_date': '20140828',
915 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
916 },
917 'params': {
918 'skip_download': True,
919 }
920 },
921 # YouTube <object> embed
922 {
923 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
924 'md5': '516718101ec834f74318df76259fb3cc',
925 'info_dict': {
926 'id': 'msN87y-iEx0',
927 'ext': 'webm',
928 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
929 'upload_date': '20080526',
930 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
931 'uploader': 'Christopher Sykes',
932 'uploader_id': 'ChristopherJSykes',
933 },
934 'add_ie': ['Youtube'],
935 },
936 # Camtasia studio
937 {
938 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
939 'playlist': [{
940 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
941 'info_dict': {
942 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
943 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
944 'ext': 'flv',
945 'duration': 2235.90,
946 }
947 }, {
948 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
949 'info_dict': {
950 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
951 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
952 'ext': 'flv',
953 'duration': 2235.93,
954 }
955 }],
956 'info_dict': {
957 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
958 }
959 },
960 # Flowplayer
961 {
962 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
963 'md5': '9d65602bf31c6e20014319c7d07fba27',
964 'info_dict': {
965 'id': '5123ea6d5e5a7',
966 'ext': 'mp4',
967 'age_limit': 18,
968 'uploader': 'www.handjobhub.com',
969 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
970 }
971 },
972 # Multiple brightcove videos
973 # https://github.com/ytdl-org/youtube-dl/issues/2283
974 {
975 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
976 'info_dict': {
977 'id': 'always-never',
978 'title': 'Always / Never - The New Yorker',
979 },
980 'playlist_count': 3,
981 'params': {
982 'extract_flat': False,
983 'skip_download': True,
984 }
985 },
986 # MLB embed
987 {
988 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
989 'md5': '96f09a37e44da40dd083e12d9a683327',
990 'info_dict': {
991 'id': '33322633',
992 'ext': 'mp4',
993 'title': 'Ump changes call to ball',
994 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
995 'duration': 48,
996 'timestamp': 1401537900,
997 'upload_date': '20140531',
998 'thumbnail': r're:^https?://.*\.jpg$',
999 },
1000 },
1001 # Wistia embed
1002 {
1003 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1004 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1005 'info_dict': {
1006 'id': '6e2wtrbdaf',
1007 'ext': 'mov',
1008 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1009 'description': 'a Paywall Videos video from Remilon',
1010 'duration': 644.072,
1011 'uploader': 'study.com',
1012 'timestamp': 1459678540,
1013 'upload_date': '20160403',
1014 'filesize': 24687186,
1015 },
1016 },
1017 {
1018 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1019 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1020 'info_dict': {
1021 'id': 'uxjb0lwrcz',
1022 'ext': 'mp4',
1023 'title': 'Conversation about Hexagonal Rails Part 1',
1024 'description': 'a Martin Fowler video from ThoughtWorks',
1025 'duration': 1715.0,
1026 'uploader': 'thoughtworks.wistia.com',
1027 'timestamp': 1401832161,
1028 'upload_date': '20140603',
1029 },
1030 },
1031 # Wistia standard embed (async)
1032 {
1033 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1034 'info_dict': {
1035 'id': '807fafadvk',
1036 'ext': 'mp4',
1037 'title': 'Drip Brennan Dunn Workshop',
1038 'description': 'a JV Webinars video from getdrip-1',
1039 'duration': 4986.95,
1040 'timestamp': 1463607249,
1041 'upload_date': '20160518',
1042 },
1043 'params': {
1044 'skip_download': True,
1045 }
1046 },
1047 # Soundcloud embed
1048 {
1049 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1050 'info_dict': {
1051 'id': '174391317',
1052 'ext': 'mp3',
1053 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1054 'uploader': 'Sophos Security',
1055 'title': 'Chet Chat 171 - Oct 29, 2014',
1056 'upload_date': '20141029',
1057 }
1058 },
1059 # Soundcloud multiple embeds
1060 {
1061 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1062 'info_dict': {
1063 'id': '52809',
1064 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1065 },
1066 'playlist_mincount': 7,
1067 },
1068 # TuneIn station embed
1069 {
1070 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1071 'info_dict': {
1072 'id': '204146',
1073 'ext': 'mp3',
1074 'title': 'CNRV',
1075 'location': 'Paris, France',
1076 'is_live': True,
1077 },
1078 'params': {
1079 # Live stream
1080 'skip_download': True,
1081 },
1082 },
1083 # Livestream embed
1084 {
1085 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1086 'info_dict': {
1087 'id': '67864563',
1088 'ext': 'flv',
1089 'upload_date': '20141112',
1090 'title': 'Rosetta #CometLanding webcast HL 10',
1091 }
1092 },
1093 # Another Livestream embed, without 'new.' in URL
1094 {
1095 'url': 'https://www.freespeech.org/',
1096 'info_dict': {
1097 'id': '123537347',
1098 'ext': 'mp4',
1099 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1100 },
1101 'params': {
1102 # Live stream
1103 'skip_download': True,
1104 },
1105 },
1106 # LazyYT
1107 {
1108 'url': 'https://skiplagged.com/',
1109 'info_dict': {
1110 'id': 'skiplagged',
1111 'title': 'Skiplagged: The smart way to find cheap flights',
1112 },
1113 'playlist_mincount': 1,
1114 'add_ie': ['Youtube'],
1115 },
1116 # Cinchcast embed
1117 {
1118 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1119 'info_dict': {
1120 'id': '7141703',
1121 'ext': 'mp3',
1122 'upload_date': '20141126',
1123 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1124 }
1125 },
1126 # Cinerama player
1127 {
1128 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1129 'info_dict': {
1130 'id': '730m_DandD_1901_512k',
1131 'ext': 'mp4',
1132 'uploader': 'www.abc.net.au',
1133 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1134 }
1135 },
1136 # embedded viddler video
1137 {
1138 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1139 'info_dict': {
1140 'id': '4d03aad9',
1141 'ext': 'mp4',
1142 'uploader': 'deadspin',
1143 'title': 'WALL-TO-GORTAT',
1144 'timestamp': 1422285291,
1145 'upload_date': '20150126',
1146 },
1147 'add_ie': ['Viddler'],
1148 },
1149 # Libsyn embed
1150 {
1151 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1152 'info_dict': {
1153 'id': '3377616',
1154 'ext': 'mp3',
1155 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1156 'description': 'md5:601cb790edd05908957dae8aaa866465',
1157 'upload_date': '20150220',
1158 },
1159 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1160 },
1161 # jwplayer YouTube
1162 {
1163 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1164 'info_dict': {
1165 'id': 'Mrj4DVp2zeA',
1166 'ext': 'mp4',
1167 'upload_date': '20150212',
1168 'uploader': 'The National Archives UK',
1169 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1170 'uploader_id': 'NationalArchives08',
1171 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1172 },
1173 },
1174 # jwplayer rtmp
1175 {
1176 'url': 'http://www.suffolk.edu/sjc/live.php',
1177 'info_dict': {
1178 'id': 'live',
1179 'ext': 'flv',
1180 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1181 'uploader': 'www.suffolk.edu',
1182 },
1183 'params': {
1184 'skip_download': True,
1185 },
1186 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1187 },
1188 # jwplayer with only the json URL
1189 {
1190 'url': 'https://www.hollywoodreporter.com/news/general-news/dunkirk-team-reveals-what-christopher-nolan-said-oscar-win-meet-your-oscar-winner-1092454',
1191 'info_dict': {
1192 'id': 'TljWkvWH',
1193 'ext': 'mp4',
1194 'upload_date': '20180306',
1195 'title': 'md5:91eb1862f6526415214f62c00b453936',
1196 'description': 'md5:73048ae50ae953da10549d1d2fe9b3aa',
1197 'timestamp': 1520367225,
1198 },
1199 'params': {
1200 'skip_download': True,
1201 },
1202 },
1203 # Complex jwplayer
1204 {
1205 'url': 'http://www.indiedb.com/games/king-machine/videos',
1206 'info_dict': {
1207 'id': 'videos',
1208 'ext': 'mp4',
1209 'title': 'king machine trailer 1',
1210 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1211 'thumbnail': r're:^https?://.*\.jpg$',
1212 },
1213 },
1214 {
1215 # JWPlayer config passed as variable
1216 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1217 'info_dict': {
1218 'id': '3326530_hq',
1219 'ext': 'mp4',
1220 'title': 'ARIELE | Tube Cup',
1221 'uploader': 'www.txxx.com',
1222 'age_limit': 18,
1223 },
1224 'params': {
1225 'skip_download': True,
1226 }
1227 },
1228 {
1229 # JWPlatform iframe
1230 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
1231 'info_dict': {
1232 'id': 'AG26UQXM',
1233 'ext': 'mp4',
1234 'upload_date': '20160719',
1235 'timestamp': 468923808,
1236 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
1237 },
1238 'add_ie': [JWPlatformIE.ie_key()],
1239 },
1240 {
1241 # Video.js embed, multiple formats
1242 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1243 'info_dict': {
1244 'id': 'yygqldloqIk',
1245 'ext': 'mp4',
1246 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1247 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1248 'upload_date': '20130314',
1249 'uploader': 'PROстое3D',
1250 'uploader_id': 'PROstoe3D',
1251 },
1252 'params': {
1253 'skip_download': True,
1254 },
1255 },
1256 {
1257 # Video.js embed, single format
1258 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1259 'info_dict': {
1260 'id': 'watch',
1261 'ext': 'mp4',
1262 'title': 'Step 1 - Good Foundation',
1263 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1264 },
1265 'params': {
1266 'skip_download': True,
1267 },
1268 },
1269 # rtl.nl embed
1270 {
1271 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1272 'playlist_mincount': 5,
1273 'info_dict': {
1274 'id': 'aanslagen-kopenhagen',
1275 'title': 'Aanslagen Kopenhagen',
1276 }
1277 },
1278 # Zapiks embed
1279 {
1280 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1281 'info_dict': {
1282 'id': '118046',
1283 'ext': 'mp4',
1284 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1285 }
1286 },
1287 # Kaltura embed (different embed code)
1288 {
1289 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1290 'info_dict': {
1291 'id': '1_a52wc67y',
1292 'ext': 'flv',
1293 'upload_date': '20150127',
1294 'uploader_id': 'PremierMedia',
1295 'timestamp': int,
1296 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1297 },
1298 },
1299 # Kaltura embed with single quotes
1300 {
1301 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1302 'info_dict': {
1303 'id': '0_izeg5utt',
1304 'ext': 'mp4',
1305 'title': '35871',
1306 'timestamp': 1355743100,
1307 'upload_date': '20121217',
1308 'uploader_id': 'cplapp@learn360.com',
1309 },
1310 'add_ie': ['Kaltura'],
1311 },
1312 {
1313 # Kaltura embedded via quoted entry_id
1314 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1315 'info_dict': {
1316 'id': '0_utuok90b',
1317 'ext': 'mp4',
1318 'title': '06_matthew_brender_raj_dutt',
1319 'timestamp': 1466638791,
1320 'upload_date': '20160622',
1321 },
1322 'add_ie': ['Kaltura'],
1323 'expected_warnings': [
1324 'Could not send HEAD request'
1325 ],
1326 'params': {
1327 'skip_download': True,
1328 }
1329 },
1330 {
1331 # Kaltura embedded, some fileExt broken (#11480)
1332 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1333 'info_dict': {
1334 'id': '1_sgtvehim',
1335 'ext': 'mp4',
1336 'title': 'Our "Standard Models" of particle physics and cosmology',
1337 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1338 'timestamp': 1321158993,
1339 'upload_date': '20111113',
1340 'uploader_id': 'kps1',
1341 },
1342 'add_ie': ['Kaltura'],
1343 },
1344 {
1345 # Kaltura iframe embed
1346 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1347 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1348 'info_dict': {
1349 'id': '0_f2cfbpwy',
1350 'ext': 'mp4',
1351 'title': 'I. M. Pei: A Centennial Celebration',
1352 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1353 'upload_date': '20170403',
1354 'uploader_id': 'batchUser',
1355 'timestamp': 1491232186,
1356 },
1357 'add_ie': ['Kaltura'],
1358 },
1359 {
1360 # Kaltura iframe embed, more sophisticated
1361 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1362 'info_dict': {
1363 'id': '1_9gzouybz',
1364 'ext': 'mp4',
1365 'title': 'lecture-05sep2017',
1366 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1367 'upload_date': '20170913',
1368 'uploader_id': 'eps2',
1369 'timestamp': 1505340777,
1370 },
1371 'params': {
1372 'skip_download': True,
1373 },
1374 'add_ie': ['Kaltura'],
1375 },
1376 {
1377 # meta twitter:player
1378 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1379 'info_dict': {
1380 'id': '0_01b42zps',
1381 'ext': 'mp4',
1382 'title': 'Main Twerk (Video)',
1383 'upload_date': '20171208',
1384 'uploader_id': 'sebastian.salinas@thechive.com',
1385 'timestamp': 1512713057,
1386 },
1387 'params': {
1388 'skip_download': True,
1389 },
1390 'add_ie': ['Kaltura'],
1391 },
1392 # referrer protected EaglePlatform embed
1393 {
1394 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1395 'info_dict': {
1396 'id': '582306',
1397 'ext': 'mp4',
1398 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1399 'thumbnail': r're:^https?://.*\.jpg$',
1400 'duration': 3382,
1401 'view_count': int,
1402 },
1403 'params': {
1404 'skip_download': True,
1405 },
1406 },
1407 # ClipYou (EaglePlatform) embed (custom URL)
1408 {
1409 'url': 'http://muz-tv.ru/play/7129/',
1410 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1411 'info_dict': {
1412 'id': '12820',
1413 'ext': 'mp4',
1414 'title': "'O Sole Mio",
1415 'thumbnail': r're:^https?://.*\.jpg$',
1416 'duration': 216,
1417 'view_count': int,
1418 },
1419 'params': {
1420 'skip_download': True,
1421 },
1422 'skip': 'This video is unavailable.',
1423 },
1424 # Pladform embed
1425 {
1426 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1427 'info_dict': {
1428 'id': '100183293',
1429 'ext': 'mp4',
1430 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1431 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1432 'thumbnail': r're:^https?://.*\.jpg$',
1433 'duration': 694,
1434 'age_limit': 0,
1435 },
1436 'skip': 'HTTP Error 404: Not Found',
1437 },
1438 # Playwire embed
1439 {
1440 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1441 'info_dict': {
1442 'id': '3519514',
1443 'ext': 'mp4',
1444 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1445 'thumbnail': r're:^https?://.*\.png$',
1446 'duration': 45.115,
1447 },
1448 },
1449 # 5min embed
1450 {
1451 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1452 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1453 'info_dict': {
1454 'id': '518726732',
1455 'ext': 'mp4',
1456 'title': 'Facebook Creates "On This Day" | Crunch Report',
1457 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1458 'timestamp': 1427237531,
1459 'uploader': 'Crunch Report',
1460 'upload_date': '20150324',
1461 },
1462 'params': {
1463 # m3u8 download
1464 'skip_download': True,
1465 },
1466 },
1467 # Crooks and Liars embed
1468 {
1469 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1470 'info_dict': {
1471 'id': '8RUoRhRi',
1472 'ext': 'mp4',
1473 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1474 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1475 'timestamp': 1428207000,
1476 'upload_date': '20150405',
1477 'uploader': 'Heather',
1478 },
1479 },
1480 # Crooks and Liars external embed
1481 {
1482 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1483 'info_dict': {
1484 'id': 'MTE3MjUtMzQ2MzA',
1485 'ext': 'mp4',
1486 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1487 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1488 'timestamp': 1265032391,
1489 'upload_date': '20100201',
1490 'uploader': 'Heather',
1491 },
1492 },
1493 # NBC Sports vplayer embed
1494 {
1495 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1496 'info_dict': {
1497 'id': 'ln7x1qSThw4k',
1498 'ext': 'flv',
1499 'title': "PFT Live: New leader in the 'new-look' defense",
1500 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1501 'uploader': 'NBCU-SPORTS',
1502 'upload_date': '20140107',
1503 'timestamp': 1389118457,
1504 },
1505 'skip': 'Invalid Page URL',
1506 },
1507 # NBC News embed
1508 {
1509 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1510 'md5': '1aa589c675898ae6d37a17913cf68d66',
1511 'info_dict': {
1512 'id': 'x_dtl_oa_LettermanliftPR_160608',
1513 'ext': 'mp4',
1514 'title': 'David Letterman: A Preview',
1515 '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.',
1516 'upload_date': '20160609',
1517 'timestamp': 1465431544,
1518 'uploader': 'NBCU-NEWS',
1519 },
1520 },
1521 # UDN embed
1522 {
1523 'url': 'https://video.udn.com/news/300346',
1524 'md5': 'fd2060e988c326991037b9aff9df21a6',
1525 'info_dict': {
1526 'id': '300346',
1527 'ext': 'mp4',
1528 'title': '中一中男師變性 全校師生力挺',
1529 'thumbnail': r're:^https?://.*\.jpg$',
1530 },
1531 'params': {
1532 # m3u8 download
1533 'skip_download': True,
1534 },
1535 'expected_warnings': ['Failed to parse JSON Expecting value'],
1536 },
1537 # Brightcove URL in single quotes
1538 {
1539 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1540 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1541 'info_dict': {
1542 'id': '4255764656001',
1543 'ext': 'mp4',
1544 'title': 'SN Presents: Russell Martin, World Citizen',
1545 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1546 'uploader': 'Rogers Sportsnet',
1547 'uploader_id': '1704050871',
1548 'upload_date': '20150525',
1549 'timestamp': 1432570283,
1550 },
1551 },
1552 # Kinja embed
1553 {
1554 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1555 'info_dict': {
1556 'id': '106351',
1557 'ext': 'mp4',
1558 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1559 'description': 'Migrated from OnionStudios',
1560 'thumbnail': r're:^https?://.*\.jpe?g$',
1561 'uploader': 'clickhole',
1562 'upload_date': '20150527',
1563 'timestamp': 1432744860,
1564 }
1565 },
1566 # SnagFilms embed
1567 {
1568 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1569 'info_dict': {
1570 'id': '74849a00-85a9-11e1-9660-123139220831',
1571 'ext': 'mp4',
1572 'title': '#whilewewatch',
1573 }
1574 },
1575 # AdobeTVVideo embed
1576 {
1577 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1578 'md5': '43662b577c018ad707a63766462b1e87',
1579 'info_dict': {
1580 'id': '2456',
1581 'ext': 'mp4',
1582 'title': 'New experience with Acrobat DC',
1583 'description': 'New experience with Acrobat DC',
1584 'duration': 248.667,
1585 },
1586 },
1587 # BrightcoveInPageEmbed embed
1588 {
1589 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1590 'info_dict': {
1591 'id': '4238694884001',
1592 'ext': 'flv',
1593 'title': 'Tabletop: Dread, Last Thoughts',
1594 'description': 'Tabletop: Dread, Last Thoughts',
1595 'duration': 51690,
1596 },
1597 },
1598 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1599 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1600 {
1601 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1602 'info_dict': {
1603 'id': '4785848093001',
1604 'ext': 'mp4',
1605 'title': 'The Cardinal Pell Interview',
1606 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1607 'uploader': 'GlobeCast Australia - GlobeStream',
1608 'uploader_id': '2733773828001',
1609 'upload_date': '20160304',
1610 'timestamp': 1457083087,
1611 },
1612 'params': {
1613 # m3u8 downloads
1614 'skip_download': True,
1615 },
1616 },
1617 {
1618 # Brightcove embed with whitespace around attribute names
1619 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1620 'info_dict': {
1621 'id': '3167554373001',
1622 'ext': 'mp4',
1623 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1624 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1625 'uploader_id': '1079349493',
1626 'upload_date': '20140207',
1627 'timestamp': 1391810548,
1628 },
1629 'params': {
1630 'skip_download': True,
1631 },
1632 },
1633 # Another form of arte.tv embed
1634 {
1635 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1636 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1637 'info_dict': {
1638 'id': '030273-562_PLUS7-F',
1639 'ext': 'mp4',
1640 'title': 'ARTE Reportage - Nulle part, en France',
1641 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1642 'upload_date': '20160409',
1643 },
1644 },
1645 # Duplicated embedded video URLs
1646 {
1647 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1648 'info_dict': {
1649 'id': '149298443_480_16c25b74_2',
1650 'ext': 'mp4',
1651 'title': 'vs. Blue Orange Spring Game',
1652 'uploader': 'www.hudl.com',
1653 },
1654 },
1655 # twitter:player:stream embed
1656 {
1657 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1658 'info_dict': {
1659 'id': 'master',
1660 'ext': 'mp4',
1661 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1662 'uploader': 'www.rtl.be',
1663 },
1664 'params': {
1665 # m3u8 downloads
1666 'skip_download': True,
1667 },
1668 },
1669 # twitter:player embed
1670 {
1671 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1672 'md5': 'a3e0df96369831de324f0778e126653c',
1673 'info_dict': {
1674 'id': '4909620399001',
1675 'ext': 'mp4',
1676 'title': 'What Do Black Holes Sound Like?',
1677 'description': 'what do black holes sound like',
1678 'upload_date': '20160524',
1679 'uploader_id': '29913724001',
1680 'timestamp': 1464107587,
1681 'uploader': 'TheAtlantic',
1682 },
1683 'add_ie': ['BrightcoveLegacy'],
1684 },
1685 # Facebook <iframe> embed
1686 {
1687 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1688 'md5': 'fbcde74f534176ecb015849146dd3aee',
1689 'info_dict': {
1690 'id': '599637780109885',
1691 'ext': 'mp4',
1692 'title': 'Facebook video #599637780109885',
1693 },
1694 },
1695 # Facebook <iframe> embed, plugin video
1696 {
1697 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1698 'info_dict': {
1699 'id': '1754168231264132',
1700 'ext': 'mp4',
1701 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1702 'uploader': 'Tariq Ramadan (official)',
1703 'timestamp': 1496758379,
1704 'upload_date': '20170606',
1705 },
1706 'params': {
1707 'skip_download': True,
1708 },
1709 },
1710 # Facebook API embed
1711 {
1712 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1713 'md5': 'a47372ee61b39a7b90287094d447d94e',
1714 'info_dict': {
1715 'id': '10153467542406923',
1716 'ext': 'mp4',
1717 'title': 'Facebook video #10153467542406923',
1718 },
1719 },
1720 # Wordpress "YouTube Video Importer" plugin
1721 {
1722 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1723 'md5': 'd16797741b560b485194eddda8121b48',
1724 'info_dict': {
1725 'id': 'HNTXWDXV9Is',
1726 'ext': 'mp4',
1727 'title': 'Blue Devils Drumline Stanford lot 2016',
1728 'upload_date': '20160627',
1729 'uploader_id': 'GENOCIDE8GENERAL10',
1730 'uploader': 'cylus cyrus',
1731 },
1732 },
1733 {
1734 # video stored on custom kaltura server
1735 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1736 'md5': '537617d06e64dfed891fa1593c4b30cc',
1737 'info_dict': {
1738 'id': '0_1iotm5bh',
1739 'ext': 'mp4',
1740 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1741 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1742 'uploader_id': 'videos.expansion@el-mundo.net',
1743 'upload_date': '20150429',
1744 'timestamp': 1430303472,
1745 },
1746 'add_ie': ['Kaltura'],
1747 },
1748 {
1749 # multiple kaltura embeds, nsfw
1750 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1751 'info_dict': {
1752 'id': 'kamila-avec-video-jaime-sadomie',
1753 'title': "Kamila avec vídeo “J'aime sadomie”",
1754 },
1755 'playlist_count': 8,
1756 },
1757 {
1758 # Non-standard Vimeo embed
1759 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1760 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1761 'info_dict': {
1762 'id': '148867247',
1763 'ext': 'mp4',
1764 'title': 'Understanding the web - Teaser',
1765 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1766 'upload_date': '20151214',
1767 'uploader': 'OpenClassrooms',
1768 'uploader_id': 'openclassrooms',
1769 },
1770 'add_ie': ['Vimeo'],
1771 },
1772 {
1773 # generic vimeo embed that requires original URL passed as Referer
1774 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1775 'only_matching': True,
1776 },
1777 {
1778 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1779 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1780 'info_dict': {
1781 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1782 'ext': 'mp4',
1783 'title': 'Big Buck Bunny',
1784 'description': 'Royalty free test video',
1785 'timestamp': 1432816365,
1786 'upload_date': '20150528',
1787 'is_live': False,
1788 },
1789 'params': {
1790 'skip_download': True,
1791 },
1792 'add_ie': [ArkenaIE.ie_key()],
1793 },
1794 {
1795 '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/',
1796 'info_dict': {
1797 'id': '1c7141f46c',
1798 'ext': 'mp4',
1799 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1800 },
1801 'params': {
1802 'skip_download': True,
1803 },
1804 'add_ie': [Vbox7IE.ie_key()],
1805 },
1806 {
1807 # DBTV embeds
1808 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1809 'info_dict': {
1810 'id': '43254897',
1811 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1812 },
1813 'playlist_mincount': 3,
1814 },
1815 {
1816 # Videa embeds
1817 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1818 'info_dict': {
1819 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1820 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1821 },
1822 'playlist_mincount': 2,
1823 },
1824 {
1825 # 20 minuten embed
1826 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1827 'info_dict': {
1828 'id': '523629',
1829 'ext': 'mp4',
1830 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1831 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1832 },
1833 'params': {
1834 'skip_download': True,
1835 },
1836 'add_ie': [TwentyMinutenIE.ie_key()],
1837 },
1838 {
1839 # VideoPress embed
1840 'url': 'https://en.support.wordpress.com/videopress/',
1841 'info_dict': {
1842 'id': 'OcobLTqC',
1843 'ext': 'm4v',
1844 'title': 'IMG_5786',
1845 'timestamp': 1435711927,
1846 'upload_date': '20150701',
1847 },
1848 'params': {
1849 'skip_download': True,
1850 },
1851 'add_ie': [VideoPressIE.ie_key()],
1852 },
1853 {
1854 # Rutube embed
1855 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1856 'info_dict': {
1857 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1858 'ext': 'flv',
1859 'title': 'Магаззино: Казань 2',
1860 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1861 'uploader': 'Магаззино',
1862 'upload_date': '20170228',
1863 'uploader_id': '996642',
1864 },
1865 'params': {
1866 'skip_download': True,
1867 },
1868 'add_ie': [RutubeIE.ie_key()],
1869 },
1870 {
1871 # ThePlatform embedded with whitespaces in URLs
1872 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1873 'only_matching': True,
1874 },
1875 {
1876 # Senate ISVP iframe https
1877 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1878 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1879 'info_dict': {
1880 'id': 'govtaff020316',
1881 'ext': 'mp4',
1882 'title': 'Integrated Senate Video Player',
1883 },
1884 'add_ie': [SenateISVPIE.ie_key()],
1885 },
1886 {
1887 # Limelight embeds (1 channel embed + 4 media embeds)
1888 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1889 'info_dict': {
1890 'id': 'FacilitatorTraining2017',
1891 'title': 'Facilitator Training 2017',
1892 },
1893 'playlist_mincount': 5,
1894 },
1895 {
1896 # Limelight embed (LimelightPlayerUtil.embed)
1897 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1898 'info_dict': {
1899 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1900 'ext': 'mp4',
1901 'title': '07448641',
1902 'timestamp': 1499890639,
1903 'upload_date': '20170712',
1904 },
1905 'params': {
1906 'skip_download': True,
1907 },
1908 'add_ie': ['LimelightMedia'],
1909 },
1910 {
1911 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1912 'info_dict': {
1913 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1914 'title': 'Standoff with Walnut Creek murder suspect ends',
1915 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1916 },
1917 'playlist_mincount': 4,
1918 },
1919 {
1920 # WashingtonPost embed
1921 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1922 'info_dict': {
1923 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1924 'ext': 'mp4',
1925 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1926 '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.',
1927 'timestamp': 1455216756,
1928 'uploader': 'The Washington Post',
1929 'upload_date': '20160211',
1930 },
1931 'add_ie': [WashingtonPostIE.ie_key()],
1932 },
1933 {
1934 # Mediaset embed
1935 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1936 'info_dict': {
1937 'id': '720642',
1938 'ext': 'mp4',
1939 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1940 },
1941 'params': {
1942 'skip_download': True,
1943 },
1944 'add_ie': [MediasetIE.ie_key()],
1945 },
1946 {
1947 # JOJ.sk embeds
1948 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1949 'info_dict': {
1950 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1951 'title': 'Slovenskom sa prehnala vlna silných búrok',
1952 },
1953 'playlist_mincount': 5,
1954 'add_ie': [JojIE.ie_key()],
1955 },
1956 {
1957 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1958 'url': 'https://tvrain.ru/amp/418921/',
1959 'md5': 'cc00413936695987e8de148b67d14f1d',
1960 'info_dict': {
1961 'id': '418921',
1962 'ext': 'mp4',
1963 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1964 },
1965 },
1966 {
1967 # vzaar embed
1968 'url': 'http://help.vzaar.com/article/165-embedding-video',
1969 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1970 'info_dict': {
1971 'id': '8707641',
1972 'ext': 'mp4',
1973 'title': 'Building A Business Online: Principal Chairs Q & A',
1974 },
1975 },
1976 {
1977 # multiple HTML5 videos on one page
1978 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1979 'info_dict': {
1980 'id': 'keyscenarios',
1981 'title': 'Rescue Kit 14 Free Edition - Getting started',
1982 },
1983 'playlist_count': 4,
1984 },
1985 {
1986 # vshare embed
1987 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1988 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1989 'info_dict': {
1990 'id': '0f64ce6',
1991 'title': 'vl14062007715967',
1992 'ext': 'mp4',
1993 }
1994 },
1995 {
1996 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1997 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1998 'info_dict': {
1999 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2000 'ext': 'mp4',
2001 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2002 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2003 'timestamp': 1474354800,
2004 'upload_date': '20160920',
2005 }
2006 },
2007 {
2008 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2009 'info_dict': {
2010 'id': '1731611',
2011 'ext': 'mp4',
2012 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2013 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2014 'timestamp': 1516100691,
2015 'upload_date': '20180116',
2016 },
2017 'params': {
2018 'skip_download': True,
2019 },
2020 'add_ie': [SpringboardPlatformIE.ie_key()],
2021 },
2022 {
2023 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2024 'info_dict': {
2025 'id': 'vMDE4NzI1Mjgt690b',
2026 'ext': 'mp4',
2027 'title': 'Котята',
2028 },
2029 'add_ie': [YapFilesIE.ie_key()],
2030 'params': {
2031 'skip_download': True,
2032 },
2033 },
2034 {
2035 # CloudflareStream embed
2036 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2037 'info_dict': {
2038 'id': '31c9291ab41fac05471db4e73aa11717',
2039 'ext': 'mp4',
2040 'title': '31c9291ab41fac05471db4e73aa11717',
2041 },
2042 'add_ie': [CloudflareStreamIE.ie_key()],
2043 'params': {
2044 'skip_download': True,
2045 },
2046 },
2047 {
2048 # PeerTube embed
2049 'url': 'https://joinpeertube.org/fr/home/',
2050 'info_dict': {
2051 'id': 'home',
2052 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2053 },
2054 'playlist_count': 2,
2055 },
2056 {
2057 # Indavideo embed
2058 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2059 'info_dict': {
2060 'id': '1693903',
2061 'ext': 'mp4',
2062 'title': 'Így kell otthon hamburgert sütni',
2063 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2064 'timestamp': 1426330212,
2065 'upload_date': '20150314',
2066 'uploader': 'StreetKitchen',
2067 'uploader_id': '546363',
2068 },
2069 'add_ie': [IndavideoEmbedIE.ie_key()],
2070 'params': {
2071 'skip_download': True,
2072 },
2073 },
2074 {
2075 # APA embed via JWPlatform embed
2076 'url': 'http://www.vol.at/blue-man-group/5593454',
2077 'info_dict': {
2078 'id': 'jjv85FdZ',
2079 'ext': 'mp4',
2080 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2081 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2082 'thumbnail': r're:^https?://.*\.jpg$',
2083 'duration': 254,
2084 'timestamp': 1519211149,
2085 'upload_date': '20180221',
2086 },
2087 'params': {
2088 'skip_download': True,
2089 },
2090 },
2091 {
2092 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2093 'md5': 'b68d276de422ab07ee1d49388103f457',
2094 'info_dict': {
2095 'id': '83645793',
2096 'title': 'Lock up and get excited',
2097 'ext': 'mp4'
2098 },
2099 'skip': 'TODO: fix nested playlists processing in tests',
2100 },
2101 {
2102 # Viqeo embeds
2103 'url': 'https://viqeo.tv/',
2104 'info_dict': {
2105 'id': 'viqeo',
2106 'title': 'All-new video platform',
2107 },
2108 'playlist_count': 6,
2109 },
2110 {
2111 # Squarespace video embed, 2019-08-28
2112 'url': 'http://ootboxford.com',
2113 'info_dict': {
2114 'id': 'Tc7b_JGdZfw',
2115 'title': 'Out of the Blue, at Childish Things 10',
2116 'ext': 'mp4',
2117 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2118 'uploader_id': 'helendouglashouse',
2119 'uploader': 'Helen & Douglas House',
2120 'upload_date': '20140328',
2121 },
2122 'params': {
2123 'skip_download': True,
2124 },
2125 },
2126 # {
2127 # # Zype embed
2128 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2129 # 'info_dict': {
2130 # 'id': '5b400b834b32992a310622b9',
2131 # 'ext': 'mp4',
2132 # 'title': 'Smoky Barbecue Favorites',
2133 # 'thumbnail': r're:^https?://.*\.jpe?g',
2134 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2135 # 'upload_date': '20170909',
2136 # 'timestamp': 1504915200,
2137 # },
2138 # 'add_ie': [ZypeIE.ie_key()],
2139 # 'params': {
2140 # 'skip_download': True,
2141 # },
2142 # },
2143 {
2144 # videojs embed
2145 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2146 'info_dict': {
2147 'id': 'shell',
2148 'ext': 'mp4',
2149 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2150 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2151 'thumbnail': r're:^https?://.*\.jpg$',
2152 },
2153 'params': {
2154 'skip_download': True,
2155 },
2156 'expected_warnings': ['Failed to download MPD manifest'],
2157 },
2158 {
2159 # DailyMotion embed with DM.player
2160 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2161 'info_dict': {
2162 'id': 'k6aKkGHd9FJs4mtJN39',
2163 'ext': 'mp4',
2164 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2165 'description': 'This video is private.',
2166 'uploader_id': 'x1jf30l',
2167 'uploader': 'beIN SPORTS USA',
2168 'upload_date': '20190528',
2169 'timestamp': 1559062971,
2170 },
2171 'params': {
2172 'skip_download': True,
2173 },
2174 },
2175 # {
2176 # # TODO: find another test
2177 # # http://schema.org/VideoObject
2178 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2179 # 'md5': '888dcf08b7ea671381f00fab74692755',
2180 # 'info_dict': {
2181 # 'id': 'nyvTSJMKId',
2182 # 'ext': 'mp4',
2183 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2184 # 'description': '#love for cats.',
2185 # 'timestamp': 1461244995,
2186 # 'upload_date': '20160421',
2187 # },
2188 # 'params': {
2189 # 'force_generic_extractor': True,
2190 # },
2191 # },
2192 {
2193 # VHX Embed
2194 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2195 'info_dict': {
2196 'id': '858208',
2197 'ext': 'mp4',
2198 'title': 'Untitled',
2199 'uploader_id': 'user80538407',
2200 'uploader': 'OTT Videos',
2201 },
2202 },
2203 {
2204 # ArcPublishing PoWa video player
2205 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2206 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2207 'info_dict': {
2208 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2209 'ext': 'mp4',
2210 'title': 'Senate candidates wave to voters on Anchorage streets',
2211 'description': 'md5:91f51a6511f090617353dc720318b20e',
2212 'timestamp': 1604378735,
2213 'upload_date': '20201103',
2214 'duration': 1581,
2215 },
2216 },
2217 {
2218 # MyChannels SDK embed
2219 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2220 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2221 'md5': '90c0699c37006ef18e198c032d81739c',
2222 'info_dict': {
2223 'id': '194165',
2224 'ext': 'mp4',
2225 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2226 'timestamp': 1611740340,
2227 'upload_date': '20210127',
2228 'duration': 159,
2229 },
2230 },
2231 {
2232 # Simplecast player embed
2233 'url': 'https://www.bio.org/podcast',
2234 'info_dict': {
2235 'id': 'podcast',
2236 'title': 'I AM BIO Podcast | BIO',
2237 },
2238 'playlist_mincount': 52,
2239 },
2240 {
2241 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2242 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2243 'only_matching': True,
2244 }, {
2245 # WimTv embed player
2246 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2247 'info_dict': {
2248 'id': 'wearefmi-pt-2-2021',
2249 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2250 },
2251 'playlist_count': 1,
2252 }, {
2253 # KVS Player
2254 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2255 'info_dict': {
2256 'id': '105',
2257 'display_id': 'kelis-4th-of-july',
2258 'ext': 'mp4',
2259 'title': 'Kelis - 4th Of July',
2260 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2261 },
2262 'params': {
2263 'skip_download': True,
2264 },
2265 }, {
2266 # KVS Player
2267 'url': 'https://www.kvs-demo.com/embed/105/',
2268 'info_dict': {
2269 'id': '105',
2270 'display_id': 'kelis-4th-of-july',
2271 'ext': 'mp4',
2272 'title': 'Kelis - 4th Of July / Embed Player',
2273 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2274 },
2275 'params': {
2276 'skip_download': True,
2277 },
2278 }, {
2279 # KVS Player
2280 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2281 'md5': '3397979512c682f6b85b3b04989df224',
2282 'info_dict': {
2283 'id': '2400174',
2284 'display_id': 'french-boy-pantsed',
2285 'ext': 'mp4',
2286 'title': 'French Boy Pantsed - ThisVid.com',
2287 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2288 }
2289 }, {
2290 # KVS Player
2291 'url': 'https://thisvid.com/embed/2400174/',
2292 'md5': '3397979512c682f6b85b3b04989df224',
2293 'info_dict': {
2294 'id': '2400174',
2295 'display_id': 'french-boy-pantsed',
2296 'ext': 'mp4',
2297 'title': 'French Boy Pantsed - ThisVid.com',
2298 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2299 }
2300 }, {
2301 # KVS Player
2302 'url': 'https://youix.com/video/leningrad-zoj/',
2303 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2304 'info_dict': {
2305 'id': '18485',
2306 'display_id': 'leningrad-zoj',
2307 'ext': 'mp4',
2308 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2309 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2310 }
2311 }, {
2312 # KVS Player
2313 'url': 'https://youix.com/embed/18485',
2314 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2315 'info_dict': {
2316 'id': '18485',
2317 'display_id': 'leningrad-zoj',
2318 'ext': 'mp4',
2319 'title': 'Ленинград - ЗОЖ',
2320 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2321 }
2322 }, {
2323 # KVS Player
2324 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2325 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2326 'info_dict': {
2327 'id': '21217',
2328 'display_id': '40-nochey-40-nights-2016',
2329 'ext': 'mp4',
2330 'title': '40 ночей (2016) - BogMedia.org',
2331 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2332 }
2333 },
2334 ]
2335
2336 def report_following_redirect(self, new_url):
2337 """Report information extraction."""
2338 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2339
2340 def _extract_rss(self, url, video_id, doc):
2341 playlist_title = doc.find('./channel/title').text
2342 playlist_desc_el = doc.find('./channel/description')
2343 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2344
2345 NS_MAP = {
2346 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2347 }
2348
2349 entries = []
2350 for it in doc.findall('./channel/item'):
2351 next_url = None
2352 enclosure_nodes = it.findall('./enclosure')
2353 for e in enclosure_nodes:
2354 next_url = e.attrib.get('url')
2355 if next_url:
2356 break
2357
2358 if not next_url:
2359 next_url = xpath_text(it, 'link', fatal=False)
2360
2361 if not next_url:
2362 continue
2363
2364 def itunes(key):
2365 return xpath_text(
2366 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2367 default=None)
2368
2369 duration = itunes('duration')
2370 explicit = (itunes('explicit') or '').lower()
2371 if explicit in ('true', 'yes'):
2372 age_limit = 18
2373 elif explicit in ('false', 'no'):
2374 age_limit = 0
2375 else:
2376 age_limit = None
2377
2378 entries.append({
2379 '_type': 'url_transparent',
2380 'url': next_url,
2381 'title': it.find('title').text,
2382 'description': xpath_text(it, 'description', default=None),
2383 'timestamp': unified_timestamp(
2384 xpath_text(it, 'pubDate', default=None)),
2385 'duration': int_or_none(duration) or parse_duration(duration),
2386 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2387 'episode': itunes('title'),
2388 'episode_number': int_or_none(itunes('episode')),
2389 'season_number': int_or_none(itunes('season')),
2390 'age_limit': age_limit,
2391 })
2392
2393 return {
2394 '_type': 'playlist',
2395 'id': url,
2396 'title': playlist_title,
2397 'description': playlist_desc,
2398 'entries': entries,
2399 }
2400
2401 def _extract_camtasia(self, url, video_id, webpage):
2402 """ Returns None if no camtasia video can be found. """
2403
2404 camtasia_cfg = self._search_regex(
2405 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2406 webpage, 'camtasia configuration file', default=None)
2407 if camtasia_cfg is None:
2408 return None
2409
2410 title = self._html_search_meta('DC.title', webpage, fatal=True)
2411
2412 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2413 camtasia_cfg = self._download_xml(
2414 camtasia_url, video_id,
2415 note='Downloading camtasia configuration',
2416 errnote='Failed to download camtasia configuration')
2417 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2418
2419 entries = []
2420 for n in fileset_node.getchildren():
2421 url_n = n.find('./uri')
2422 if url_n is None:
2423 continue
2424
2425 entries.append({
2426 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2427 'title': '%s - %s' % (title, n.tag),
2428 'url': compat_urlparse.urljoin(url, url_n.text),
2429 'duration': float_or_none(n.find('./duration').text),
2430 })
2431
2432 return {
2433 '_type': 'playlist',
2434 'entries': entries,
2435 'title': title,
2436 }
2437
2438 def _kvs_getrealurl(self, video_url, license_code):
2439 if not video_url.startswith('function/0/'):
2440 return video_url # not obfuscated
2441
2442 url_path, _, url_query = video_url.partition('?')
2443 urlparts = url_path.split('/')[2:]
2444 license = self._kvs_getlicensetoken(license_code)
2445 newmagic = urlparts[5][:32]
2446
2447 for o in range(len(newmagic) - 1, -1, -1):
2448 new = ''
2449 l = (o + sum([int(n) for n in license[o:]])) % 32
2450
2451 for i in range(0, len(newmagic)):
2452 if i == o:
2453 new += newmagic[l]
2454 elif i == l:
2455 new += newmagic[o]
2456 else:
2457 new += newmagic[i]
2458 newmagic = new
2459
2460 urlparts[5] = newmagic + urlparts[5][32:]
2461 return '/'.join(urlparts) + '?' + url_query
2462
2463 def _kvs_getlicensetoken(self, license):
2464 modlicense = license.replace('$', '').replace('0', '1')
2465 center = int(len(modlicense) / 2)
2466 fronthalf = int(modlicense[:center + 1])
2467 backhalf = int(modlicense[center:])
2468
2469 modlicense = str(4 * abs(fronthalf - backhalf))
2470 retval = ''
2471 for o in range(0, center + 1):
2472 for i in range(1, 5):
2473 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2474 return retval
2475
2476 def _real_extract(self, url):
2477 if url.startswith('//'):
2478 return self.url_result(self.http_scheme() + url)
2479
2480 parsed_url = compat_urlparse.urlparse(url)
2481 if not parsed_url.scheme:
2482 default_search = self.get_param('default_search')
2483 if default_search is None:
2484 default_search = 'fixup_error'
2485
2486 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2487 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2488 self.report_warning('The url doesn\'t specify the protocol, trying with http')
2489 return self.url_result('http://' + url)
2490 elif default_search != 'fixup_error':
2491 if default_search == 'auto_warning':
2492 if re.match(r'^(?:url|URL)$', url):
2493 raise ExtractorError(
2494 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2495 expected=True)
2496 else:
2497 self.report_warning(
2498 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2499 return self.url_result('ytsearch:' + url)
2500
2501 if default_search in ('error', 'fixup_error'):
2502 raise ExtractorError(
2503 '%r is not a valid URL. '
2504 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
2505 % (url, url), expected=True)
2506 else:
2507 if ':' not in default_search:
2508 default_search += ':'
2509 return self.url_result(default_search + url)
2510
2511 url, smuggled_data = unsmuggle_url(url)
2512 force_videoid = None
2513 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2514 if smuggled_data and 'force_videoid' in smuggled_data:
2515 force_videoid = smuggled_data['force_videoid']
2516 video_id = force_videoid
2517 else:
2518 video_id = self._generic_id(url)
2519
2520 self.to_screen('%s: Requesting header' % video_id)
2521
2522 head_req = HEADRequest(url)
2523 head_response = self._request_webpage(
2524 head_req, video_id,
2525 note=False, errnote='Could not send HEAD request to %s' % url,
2526 fatal=False)
2527
2528 if head_response is not False:
2529 # Check for redirect
2530 new_url = head_response.geturl()
2531 if url != new_url:
2532 self.report_following_redirect(new_url)
2533 if force_videoid:
2534 new_url = smuggle_url(
2535 new_url, {'force_videoid': force_videoid})
2536 return self.url_result(new_url)
2537
2538 full_response = None
2539 if head_response is False:
2540 request = sanitized_Request(url)
2541 request.add_header('Accept-Encoding', '*')
2542 full_response = self._request_webpage(request, video_id)
2543 head_response = full_response
2544
2545 info_dict = {
2546 'id': video_id,
2547 'title': self._generic_title(url),
2548 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2549 }
2550
2551 # Check for direct link to a video
2552 content_type = head_response.headers.get('Content-Type', '').lower()
2553 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2554 if m:
2555 format_id = compat_str(m.group('format_id'))
2556 subtitles = {}
2557 if format_id.endswith('mpegurl'):
2558 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2559 elif format_id == 'f4m':
2560 formats = self._extract_f4m_formats(url, video_id)
2561 else:
2562 formats = [{
2563 'format_id': format_id,
2564 'url': url,
2565 'vcodec': 'none' if m.group('type') == 'audio' else None
2566 }]
2567 info_dict['direct'] = True
2568 self._sort_formats(formats)
2569 info_dict['formats'] = formats
2570 info_dict['subtitles'] = subtitles
2571 return info_dict
2572
2573 if not self.get_param('test', False) and not is_intentional:
2574 force = self.get_param('force_generic_extractor', False)
2575 self.report_warning(
2576 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2577
2578 if not full_response:
2579 request = sanitized_Request(url)
2580 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2581 # making it impossible to download only chunk of the file (yet we need only 512kB to
2582 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
2583 # that will always result in downloading the whole file that is not desirable.
2584 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2585 # to accept raw bytes and being able to download only a chunk.
2586 # It may probably better to solve this by checking Content-Type for application/octet-stream
2587 # after HEAD request finishes, but not sure if we can rely on this.
2588 request.add_header('Accept-Encoding', '*')
2589 full_response = self._request_webpage(request, video_id)
2590
2591 first_bytes = full_response.read(512)
2592
2593 # Is it an M3U playlist?
2594 if first_bytes.startswith(b'#EXTM3U'):
2595 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2596 self._sort_formats(info_dict['formats'])
2597 return info_dict
2598
2599 # Maybe it's a direct link to a video?
2600 # Be careful not to download the whole thing!
2601 if not is_html(first_bytes):
2602 self.report_warning(
2603 'URL could be a direct video link, returning it as such.')
2604 info_dict.update({
2605 'direct': True,
2606 'url': url,
2607 })
2608 return info_dict
2609
2610 webpage = self._webpage_read_content(
2611 full_response, url, video_id, prefix=first_bytes)
2612
2613 if '<title>DPG Media Privacy Gate</title>' in webpage:
2614 webpage = self._download_webpage(url, video_id)
2615
2616 self.report_extraction(video_id)
2617
2618 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2619 try:
2620 try:
2621 doc = compat_etree_fromstring(webpage)
2622 except compat_xml_parse_error:
2623 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2624 if doc.tag == 'rss':
2625 return self._extract_rss(url, video_id, doc)
2626 elif doc.tag == 'SmoothStreamingMedia':
2627 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
2628 self._sort_formats(info_dict['formats'])
2629 return info_dict
2630 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2631 smil = self._parse_smil(doc, url, video_id)
2632 self._sort_formats(smil['formats'])
2633 return smil
2634 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2635 return self.playlist_result(
2636 self._parse_xspf(
2637 doc, video_id, xspf_url=url,
2638 xspf_base_url=full_response.geturl()),
2639 video_id)
2640 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2641 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
2642 doc,
2643 mpd_base_url=full_response.geturl().rpartition('/')[0],
2644 mpd_url=url)
2645 self._sort_formats(info_dict['formats'])
2646 return info_dict
2647 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2648 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2649 self._sort_formats(info_dict['formats'])
2650 return info_dict
2651 except compat_xml_parse_error:
2652 pass
2653
2654 # Is it a Camtasia project?
2655 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2656 if camtasia_res is not None:
2657 return camtasia_res
2658
2659 # Sometimes embedded video player is hidden behind percent encoding
2660 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2661 # Unescaping the whole page allows to handle those cases in a generic way
2662 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2663 # There probably should be a second run of generic extractor on unescaped webpage.
2664 # webpage = compat_urllib_parse_unquote(webpage)
2665
2666 # Unescape squarespace embeds to be detected by generic extractor,
2667 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2668 webpage = re.sub(
2669 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2670 lambda x: unescapeHTML(x.group(0)), webpage)
2671
2672 # it's tempting to parse this further, but you would
2673 # have to take into account all the variations like
2674 # Video Title - Site Name
2675 # Site Name | Video Title
2676 # Video Title - Tagline | Site Name
2677 # and so on and so forth; it's just not practical
2678 video_title = self._og_search_title(
2679 webpage, default=None) or self._html_search_regex(
2680 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2681 default='video')
2682
2683 # Try to detect age limit automatically
2684 age_limit = self._rta_search(webpage)
2685 # And then there are the jokers who advertise that they use RTA,
2686 # but actually don't.
2687 AGE_LIMIT_MARKERS = [
2688 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2689 ]
2690 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2691 age_limit = 18
2692
2693 # video uploader is domain name
2694 video_uploader = self._search_regex(
2695 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2696
2697 video_description = self._og_search_description(webpage, default=None)
2698 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2699
2700 info_dict.update({
2701 'title': video_title,
2702 'description': video_description,
2703 'thumbnail': video_thumbnail,
2704 'age_limit': age_limit,
2705 })
2706
2707 # Look for Brightcove Legacy Studio embeds
2708 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2709 if bc_urls:
2710 entries = [{
2711 '_type': 'url',
2712 'url': smuggle_url(bc_url, {'Referer': url}),
2713 'ie_key': 'BrightcoveLegacy'
2714 } for bc_url in bc_urls]
2715
2716 return {
2717 '_type': 'playlist',
2718 'title': video_title,
2719 'id': video_id,
2720 'entries': entries,
2721 }
2722
2723 # Look for Brightcove New Studio embeds
2724 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2725 if bc_urls:
2726 return self.playlist_from_matches(
2727 bc_urls, video_id, video_title,
2728 getter=lambda x: smuggle_url(x, {'referrer': url}),
2729 ie='BrightcoveNew')
2730
2731 # Look for Nexx embeds
2732 nexx_urls = NexxIE._extract_urls(webpage)
2733 if nexx_urls:
2734 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2735
2736 # Look for Nexx iFrame embeds
2737 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2738 if nexx_embed_urls:
2739 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2740
2741 # Look for ThePlatform embeds
2742 tp_urls = ThePlatformIE._extract_urls(webpage)
2743 if tp_urls:
2744 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2745
2746 arc_urls = ArcPublishingIE._extract_urls(webpage)
2747 if arc_urls:
2748 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2749
2750 mychannels_urls = MedialaanIE._extract_urls(webpage)
2751 if mychannels_urls:
2752 return self.playlist_from_matches(
2753 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2754
2755 # Look for embedded rtl.nl player
2756 matches = re.findall(
2757 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2758 webpage)
2759 if matches:
2760 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2761
2762 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2763 if vimeo_urls:
2764 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2765
2766 vhx_url = VHXEmbedIE._extract_url(webpage)
2767 if vhx_url:
2768 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2769
2770 # Invidious Instances
2771 # https://github.com/yt-dlp/yt-dlp/issues/195
2772 # https://github.com/iv-org/invidious/pull/1730
2773 youtube_url = self._search_regex(
2774 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2775 webpage, 'youtube link', default=None)
2776 if youtube_url:
2777 return self.url_result(youtube_url, YoutubeIE.ie_key())
2778
2779 # Look for YouTube embeds
2780 youtube_urls = YoutubeIE._extract_urls(webpage)
2781 if youtube_urls:
2782 return self.playlist_from_matches(
2783 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2784
2785 matches = DailymotionIE._extract_urls(webpage)
2786 if matches:
2787 return self.playlist_from_matches(matches, video_id, video_title)
2788
2789 # Look for embedded Dailymotion playlist player (#3822)
2790 m = re.search(
2791 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2792 if m:
2793 playlists = re.findall(
2794 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2795 if playlists:
2796 return self.playlist_from_matches(
2797 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2798
2799 # Look for DailyMail embeds
2800 dailymail_urls = DailyMailIE._extract_urls(webpage)
2801 if dailymail_urls:
2802 return self.playlist_from_matches(
2803 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2804
2805 # Look for Teachable embeds, must be before Wistia
2806 teachable_url = TeachableIE._extract_url(webpage, url)
2807 if teachable_url:
2808 return self.url_result(teachable_url)
2809
2810 # Look for embedded Wistia player
2811 wistia_urls = WistiaIE._extract_urls(webpage)
2812 if wistia_urls:
2813 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2814 for entry in playlist['entries']:
2815 entry.update({
2816 '_type': 'url_transparent',
2817 'uploader': video_uploader,
2818 })
2819 return playlist
2820
2821 # Look for SVT player
2822 svt_url = SVTIE._extract_url(webpage)
2823 if svt_url:
2824 return self.url_result(svt_url, 'SVT')
2825
2826 # Look for Bandcamp pages with custom domain
2827 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2828 if mobj is not None:
2829 burl = unescapeHTML(mobj.group(1))
2830 # Don't set the extractor because it can be a track url or an album
2831 return self.url_result(burl)
2832
2833 # Look for embedded Vevo player
2834 mobj = re.search(
2835 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2836 if mobj is not None:
2837 return self.url_result(mobj.group('url'))
2838
2839 # Look for embedded Viddler player
2840 mobj = re.search(
2841 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2842 webpage)
2843 if mobj is not None:
2844 return self.url_result(mobj.group('url'))
2845
2846 # Look for NYTimes player
2847 mobj = re.search(
2848 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2849 webpage)
2850 if mobj is not None:
2851 return self.url_result(mobj.group('url'))
2852
2853 # Look for Libsyn player
2854 mobj = re.search(
2855 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2856 if mobj is not None:
2857 return self.url_result(mobj.group('url'))
2858
2859 # Look for Ooyala videos
2860 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2861 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2862 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2863 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2864 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2865 if mobj is not None:
2866 embed_token = self._search_regex(
2867 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2868 webpage, 'ooyala embed token', default=None)
2869 return OoyalaIE._build_url_result(smuggle_url(
2870 mobj.group('ec'), {
2871 'domain': url,
2872 'embed_token': embed_token,
2873 }))
2874
2875 # Look for multiple Ooyala embeds on SBN network websites
2876 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2877 if mobj is not None:
2878 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2879 if embeds:
2880 return self.playlist_from_matches(
2881 embeds, video_id, video_title,
2882 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2883
2884 # Look for Aparat videos
2885 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2886 if mobj is not None:
2887 return self.url_result(mobj.group(1), 'Aparat')
2888
2889 # Look for MPORA videos
2890 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2891 if mobj is not None:
2892 return self.url_result(mobj.group(1), 'Mpora')
2893
2894 # Look for embedded Facebook player
2895 facebook_urls = FacebookIE._extract_urls(webpage)
2896 if facebook_urls:
2897 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2898
2899 # Look for embedded VK player
2900 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2901 if mobj is not None:
2902 return self.url_result(mobj.group('url'), 'VK')
2903
2904 # Look for embedded Odnoklassniki player
2905 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2906 if odnoklassniki_url:
2907 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2908
2909 # Look for sibnet embedded player
2910 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2911 if sibnet_urls:
2912 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2913
2914 # Look for embedded ivi player
2915 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2916 if mobj is not None:
2917 return self.url_result(mobj.group('url'), 'Ivi')
2918
2919 # Look for embedded Huffington Post player
2920 mobj = re.search(
2921 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2922 if mobj is not None:
2923 return self.url_result(mobj.group('url'), 'HuffPost')
2924
2925 # Look for embed.ly
2926 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2927 if mobj is not None:
2928 return self.url_result(mobj.group('url'))
2929 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2930 if mobj is not None:
2931 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2932
2933 # Look for funnyordie embed
2934 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2935 if matches:
2936 return self.playlist_from_matches(
2937 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2938
2939 # Look for Simplecast embeds
2940 simplecast_urls = SimplecastIE._extract_urls(webpage)
2941 if simplecast_urls:
2942 return self.playlist_from_matches(
2943 simplecast_urls, video_id, video_title)
2944
2945 # Look for BBC iPlayer embed
2946 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2947 if matches:
2948 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2949
2950 # Look for embedded RUTV player
2951 rutv_url = RUTVIE._extract_url(webpage)
2952 if rutv_url:
2953 return self.url_result(rutv_url, 'RUTV')
2954
2955 # Look for embedded TVC player
2956 tvc_url = TVCIE._extract_url(webpage)
2957 if tvc_url:
2958 return self.url_result(tvc_url, 'TVC')
2959
2960 # Look for embedded SportBox player
2961 sportbox_urls = SportBoxIE._extract_urls(webpage)
2962 if sportbox_urls:
2963 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2964
2965 # Look for embedded XHamster player
2966 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2967 if xhamster_urls:
2968 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2969
2970 # Look for embedded TNAFlixNetwork player
2971 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2972 if tnaflix_urls:
2973 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2974
2975 # Look for embedded PornHub player
2976 pornhub_urls = PornHubIE._extract_urls(webpage)
2977 if pornhub_urls:
2978 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2979
2980 # Look for embedded DrTuber player
2981 drtuber_urls = DrTuberIE._extract_urls(webpage)
2982 if drtuber_urls:
2983 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2984
2985 # Look for embedded RedTube player
2986 redtube_urls = RedTubeIE._extract_urls(webpage)
2987 if redtube_urls:
2988 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2989
2990 # Look for embedded Tube8 player
2991 tube8_urls = Tube8IE._extract_urls(webpage)
2992 if tube8_urls:
2993 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2994
2995 # Look for embedded Mofosex player
2996 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2997 if mofosex_urls:
2998 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2999
3000 # Look for embedded Spankwire player
3001 spankwire_urls = SpankwireIE._extract_urls(webpage)
3002 if spankwire_urls:
3003 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3004
3005 # Look for embedded YouPorn player
3006 youporn_urls = YouPornIE._extract_urls(webpage)
3007 if youporn_urls:
3008 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3009
3010 # Look for embedded Tvigle player
3011 mobj = re.search(
3012 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3013 if mobj is not None:
3014 return self.url_result(mobj.group('url'), 'Tvigle')
3015
3016 # Look for embedded TED player
3017 mobj = re.search(
3018 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
3019 if mobj is not None:
3020 return self.url_result(mobj.group('url'), 'TED')
3021
3022 # Look for embedded Ustream videos
3023 ustream_url = UstreamIE._extract_url(webpage)
3024 if ustream_url:
3025 return self.url_result(ustream_url, UstreamIE.ie_key())
3026
3027 # Look for embedded arte.tv player
3028 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3029 if arte_urls:
3030 return self.playlist_from_matches(arte_urls, video_id, video_title)
3031
3032 # Look for embedded francetv player
3033 mobj = re.search(
3034 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3035 webpage)
3036 if mobj is not None:
3037 return self.url_result(mobj.group('url'))
3038
3039 # Look for embedded Myvi.ru player
3040 myvi_url = MyviIE._extract_url(webpage)
3041 if myvi_url:
3042 return self.url_result(myvi_url)
3043
3044 # Look for embedded soundcloud player
3045 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3046 if soundcloud_urls:
3047 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3048
3049 # Look for tunein player
3050 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3051 if tunein_urls:
3052 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3053
3054 # Look for embedded mtvservices player
3055 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3056 if mtvservices_url:
3057 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3058
3059 # Look for embedded yahoo player
3060 mobj = re.search(
3061 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3062 webpage)
3063 if mobj is not None:
3064 return self.url_result(mobj.group('url'), 'Yahoo')
3065
3066 # Look for embedded sbs.com.au player
3067 mobj = re.search(
3068 r'''(?x)
3069 (?:
3070 <meta\s+property="og:video"\s+content=|
3071 <iframe[^>]+?src=
3072 )
3073 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3074 webpage)
3075 if mobj is not None:
3076 return self.url_result(mobj.group('url'), 'SBS')
3077
3078 # Look for embedded Cinchcast player
3079 mobj = re.search(
3080 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3081 webpage)
3082 if mobj is not None:
3083 return self.url_result(mobj.group('url'), 'Cinchcast')
3084
3085 mobj = re.search(
3086 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
3087 webpage)
3088 if not mobj:
3089 mobj = re.search(
3090 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3091 webpage)
3092 if mobj is not None:
3093 return self.url_result(mobj.group('url'), 'MLB')
3094
3095 mobj = re.search(
3096 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3097 webpage)
3098 if mobj is not None:
3099 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3100
3101 mobj = re.search(
3102 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
3103 webpage)
3104 if mobj is not None:
3105 return self.url_result(mobj.group('url'), 'Livestream')
3106
3107 # Look for Zapiks embed
3108 mobj = re.search(
3109 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3110 if mobj is not None:
3111 return self.url_result(mobj.group('url'), 'Zapiks')
3112
3113 # Look for Kaltura embeds
3114 kaltura_urls = KalturaIE._extract_urls(webpage)
3115 if kaltura_urls:
3116 return self.playlist_from_matches(
3117 kaltura_urls, video_id, video_title,
3118 getter=lambda x: smuggle_url(x, {'source_url': url}),
3119 ie=KalturaIE.ie_key())
3120
3121 # Look for EaglePlatform embeds
3122 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3123 if eagleplatform_url:
3124 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3125
3126 # Look for ClipYou (uses EaglePlatform) embeds
3127 mobj = re.search(
3128 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3129 if mobj is not None:
3130 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3131
3132 # Look for Pladform embeds
3133 pladform_url = PladformIE._extract_url(webpage)
3134 if pladform_url:
3135 return self.url_result(pladform_url)
3136
3137 # Look for Videomore embeds
3138 videomore_url = VideomoreIE._extract_url(webpage)
3139 if videomore_url:
3140 return self.url_result(videomore_url)
3141
3142 # Look for Webcaster embeds
3143 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3144 if webcaster_url:
3145 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3146
3147 # Look for Playwire embeds
3148 mobj = re.search(
3149 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3150 if mobj is not None:
3151 return self.url_result(mobj.group('url'))
3152
3153 # Look for 5min embeds
3154 mobj = re.search(
3155 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3156 if mobj is not None:
3157 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3158
3159 # Look for Crooks and Liars embeds
3160 mobj = re.search(
3161 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3162 if mobj is not None:
3163 return self.url_result(mobj.group('url'))
3164
3165 # Look for NBC Sports VPlayer embeds
3166 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3167 if nbc_sports_url:
3168 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3169
3170 # Look for NBC News embeds
3171 nbc_news_embed_url = re.search(
3172 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3173 if nbc_news_embed_url:
3174 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3175
3176 # Look for Google Drive embeds
3177 google_drive_url = GoogleDriveIE._extract_url(webpage)
3178 if google_drive_url:
3179 return self.url_result(google_drive_url, 'GoogleDrive')
3180
3181 # Look for UDN embeds
3182 mobj = re.search(
3183 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3184 if mobj is not None:
3185 return self.url_result(
3186 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3187
3188 # Look for Senate ISVP iframe
3189 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3190 if senate_isvp_url:
3191 return self.url_result(senate_isvp_url, 'SenateISVP')
3192
3193 # Look for Kinja embeds
3194 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3195 if kinja_embed_urls:
3196 return self.playlist_from_matches(
3197 kinja_embed_urls, video_id, video_title)
3198
3199 # Look for OnionStudios embeds
3200 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3201 if onionstudios_url:
3202 return self.url_result(onionstudios_url)
3203
3204 # Look for ViewLift embeds
3205 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3206 if viewlift_url:
3207 return self.url_result(viewlift_url)
3208
3209 # Look for JWPlatform embeds
3210 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3211 if jwplatform_urls:
3212 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3213
3214 # Look for Digiteka embeds
3215 digiteka_url = DigitekaIE._extract_url(webpage)
3216 if digiteka_url:
3217 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3218
3219 # Look for Arkena embeds
3220 arkena_url = ArkenaIE._extract_url(webpage)
3221 if arkena_url:
3222 return self.url_result(arkena_url, ArkenaIE.ie_key())
3223
3224 # Look for Piksel embeds
3225 piksel_url = PikselIE._extract_url(webpage)
3226 if piksel_url:
3227 return self.url_result(piksel_url, PikselIE.ie_key())
3228
3229 # Look for Limelight embeds
3230 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3231 if limelight_urls:
3232 return self.playlist_result(
3233 limelight_urls, video_id, video_title, video_description)
3234
3235 # Look for Anvato embeds
3236 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3237 if anvato_urls:
3238 return self.playlist_result(
3239 anvato_urls, video_id, video_title, video_description)
3240
3241 # Look for AdobeTVVideo embeds
3242 mobj = re.search(
3243 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3244 webpage)
3245 if mobj is not None:
3246 return self.url_result(
3247 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3248 'AdobeTVVideo')
3249
3250 # Look for Vine embeds
3251 mobj = re.search(
3252 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3253 webpage)
3254 if mobj is not None:
3255 return self.url_result(
3256 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3257
3258 # Look for VODPlatform embeds
3259 mobj = re.search(
3260 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3261 webpage)
3262 if mobj is not None:
3263 return self.url_result(
3264 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3265
3266 # Look for Mangomolo embeds
3267 mobj = re.search(
3268 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3269 (?:
3270 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3271 player\.mangomolo\.com/v1
3272 )/
3273 (?:
3274 video\?.*?\bid=(?P<video_id>\d+)|
3275 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3276 ).+?)\1''', webpage)
3277 if mobj is not None:
3278 info = {
3279 '_type': 'url_transparent',
3280 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3281 'title': video_title,
3282 'description': video_description,
3283 'thumbnail': video_thumbnail,
3284 'uploader': video_uploader,
3285 }
3286 video_id = mobj.group('video_id')
3287 if video_id:
3288 info.update({
3289 'ie_key': 'MangomoloVideo',
3290 'id': video_id,
3291 })
3292 else:
3293 info.update({
3294 'ie_key': 'MangomoloLive',
3295 'id': mobj.group('channel_id'),
3296 })
3297 return info
3298
3299 # Look for Instagram embeds
3300 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3301 if instagram_embed_url is not None:
3302 return self.url_result(
3303 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3304
3305 # Look for 3Q SDN embeds
3306 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3307 if threeqsdn_url:
3308 return {
3309 '_type': 'url_transparent',
3310 'ie_key': ThreeQSDNIE.ie_key(),
3311 'url': self._proto_relative_url(threeqsdn_url),
3312 'title': video_title,
3313 'description': video_description,
3314 'thumbnail': video_thumbnail,
3315 'uploader': video_uploader,
3316 }
3317
3318 # Look for VBOX7 embeds
3319 vbox7_url = Vbox7IE._extract_url(webpage)
3320 if vbox7_url:
3321 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3322
3323 # Look for DBTV embeds
3324 dbtv_urls = DBTVIE._extract_urls(webpage)
3325 if dbtv_urls:
3326 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3327
3328 # Look for Videa embeds
3329 videa_urls = VideaIE._extract_urls(webpage)
3330 if videa_urls:
3331 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3332
3333 # Look for 20 minuten embeds
3334 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3335 if twentymin_urls:
3336 return self.playlist_from_matches(
3337 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3338
3339 # Look for VideoPress embeds
3340 videopress_urls = VideoPressIE._extract_urls(webpage)
3341 if videopress_urls:
3342 return self.playlist_from_matches(
3343 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3344
3345 # Look for Rutube embeds
3346 rutube_urls = RutubeIE._extract_urls(webpage)
3347 if rutube_urls:
3348 return self.playlist_from_matches(
3349 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3350
3351 # Look for WashingtonPost embeds
3352 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3353 if wapo_urls:
3354 return self.playlist_from_matches(
3355 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3356
3357 # Look for Mediaset embeds
3358 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3359 if mediaset_urls:
3360 return self.playlist_from_matches(
3361 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3362
3363 # Look for JOJ.sk embeds
3364 joj_urls = JojIE._extract_urls(webpage)
3365 if joj_urls:
3366 return self.playlist_from_matches(
3367 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3368
3369 # Look for megaphone.fm embeds
3370 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3371 if mpfn_urls:
3372 return self.playlist_from_matches(
3373 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3374
3375 # Look for vzaar embeds
3376 vzaar_urls = VzaarIE._extract_urls(webpage)
3377 if vzaar_urls:
3378 return self.playlist_from_matches(
3379 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3380
3381 channel9_urls = Channel9IE._extract_urls(webpage)
3382 if channel9_urls:
3383 return self.playlist_from_matches(
3384 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3385
3386 vshare_urls = VShareIE._extract_urls(webpage)
3387 if vshare_urls:
3388 return self.playlist_from_matches(
3389 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3390
3391 # Look for Mediasite embeds
3392 mediasite_urls = MediasiteIE._extract_urls(webpage)
3393 if mediasite_urls:
3394 entries = [
3395 self.url_result(smuggle_url(
3396 compat_urlparse.urljoin(url, mediasite_url),
3397 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3398 for mediasite_url in mediasite_urls]
3399 return self.playlist_result(entries, video_id, video_title)
3400
3401 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3402 if springboardplatform_urls:
3403 return self.playlist_from_matches(
3404 springboardplatform_urls, video_id, video_title,
3405 ie=SpringboardPlatformIE.ie_key())
3406
3407 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3408 if yapfiles_urls:
3409 return self.playlist_from_matches(
3410 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3411
3412 vice_urls = ViceIE._extract_urls(webpage)
3413 if vice_urls:
3414 return self.playlist_from_matches(
3415 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3416
3417 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3418 if xfileshare_urls:
3419 return self.playlist_from_matches(
3420 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3421
3422 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3423 if cloudflarestream_urls:
3424 return self.playlist_from_matches(
3425 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3426
3427 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3428 if peertube_urls:
3429 return self.playlist_from_matches(
3430 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3431
3432 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3433 if indavideo_urls:
3434 return self.playlist_from_matches(
3435 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3436
3437 apa_urls = APAIE._extract_urls(webpage)
3438 if apa_urls:
3439 return self.playlist_from_matches(
3440 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3441
3442 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3443 if foxnews_urls:
3444 return self.playlist_from_matches(
3445 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3446
3447 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3448 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3449 webpage)]
3450 if sharevideos_urls:
3451 return self.playlist_from_matches(
3452 sharevideos_urls, video_id, video_title)
3453
3454 viqeo_urls = ViqeoIE._extract_urls(webpage)
3455 if viqeo_urls:
3456 return self.playlist_from_matches(
3457 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3458
3459 expressen_urls = ExpressenIE._extract_urls(webpage)
3460 if expressen_urls:
3461 return self.playlist_from_matches(
3462 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3463
3464 zype_urls = ZypeIE._extract_urls(webpage)
3465 if zype_urls:
3466 return self.playlist_from_matches(
3467 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3468
3469 gedi_urls = GediDigitalIE._extract_urls(webpage)
3470 if gedi_urls:
3471 return self.playlist_from_matches(
3472 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
3473
3474 # Look for RCS media group embeds
3475 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3476 if rcs_urls:
3477 return self.playlist_from_matches(
3478 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3479
3480 wimtv_urls = WimTVIE._extract_urls(webpage)
3481 if wimtv_urls:
3482 return self.playlist_from_matches(
3483 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3484
3485 bitchute_urls = BitChuteIE._extract_urls(webpage)
3486 if bitchute_urls:
3487 return self.playlist_from_matches(
3488 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3489
3490 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3491 if len(rumble_urls) == 1:
3492 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3493 if rumble_urls:
3494 return self.playlist_from_matches(
3495 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3496
3497 # Look for HTML5 media
3498 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3499 if entries:
3500 if len(entries) == 1:
3501 entries[0].update({
3502 'id': video_id,
3503 'title': video_title,
3504 })
3505 else:
3506 for num, entry in enumerate(entries, start=1):
3507 entry.update({
3508 'id': '%s-%s' % (video_id, num),
3509 'title': '%s (%d)' % (video_title, num),
3510 })
3511 for entry in entries:
3512 self._sort_formats(entry['formats'])
3513 return self.playlist_result(entries, video_id, video_title)
3514
3515 jwplayer_data = self._find_jwplayer_data(
3516 webpage, video_id, transform_source=js_to_json)
3517 if jwplayer_data:
3518 if isinstance(jwplayer_data.get('playlist'), str):
3519 return {
3520 **info_dict,
3521 '_type': 'url',
3522 'ie_key': JWPlatformIE.ie_key(),
3523 'url': jwplayer_data['playlist'],
3524 }
3525 try:
3526 info = self._parse_jwplayer_data(
3527 jwplayer_data, video_id, require_title=False, base_url=url)
3528 return merge_dicts(info, info_dict)
3529 except ExtractorError:
3530 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3531 pass
3532
3533 # Video.js embed
3534 mobj = re.search(
3535 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3536 webpage)
3537 if mobj is not None:
3538 sources = self._parse_json(
3539 mobj.group(1), video_id, transform_source=js_to_json,
3540 fatal=False) or []
3541 if not isinstance(sources, list):
3542 sources = [sources]
3543 formats = []
3544 subtitles = {}
3545 for source in sources:
3546 src = source.get('src')
3547 if not src or not isinstance(src, compat_str):
3548 continue
3549 src = compat_urlparse.urljoin(url, src)
3550 src_type = source.get('type')
3551 if isinstance(src_type, compat_str):
3552 src_type = src_type.lower()
3553 ext = determine_ext(src).lower()
3554 if src_type == 'video/youtube':
3555 return self.url_result(src, YoutubeIE.ie_key())
3556 if src_type == 'application/dash+xml' or ext == 'mpd':
3557 fmts, subs = self._extract_mpd_formats_and_subtitles(
3558 src, video_id, mpd_id='dash', fatal=False)
3559 formats.extend(fmts)
3560 self._merge_subtitles(subs, target=subtitles)
3561 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3562 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3563 src, video_id, 'mp4', entry_protocol='m3u8_native',
3564 m3u8_id='hls', fatal=False)
3565 formats.extend(fmts)
3566 self._merge_subtitles(subs, target=subtitles)
3567 else:
3568 formats.append({
3569 'url': src,
3570 'ext': (mimetype2ext(src_type)
3571 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3572 'http_headers': {
3573 'Referer': full_response.geturl(),
3574 },
3575 })
3576 if formats or subtitles:
3577 self._sort_formats(formats)
3578 info_dict['formats'] = formats
3579 info_dict['subtitles'] = subtitles
3580 return info_dict
3581
3582 # Looking for http://schema.org/VideoObject
3583 json_ld = self._search_json_ld(webpage, video_id, default={})
3584 if json_ld.get('url'):
3585 return merge_dicts(json_ld, info_dict)
3586
3587 def check_video(vurl):
3588 if YoutubeIE.suitable(vurl):
3589 return True
3590 if RtmpIE.suitable(vurl):
3591 return True
3592 vpath = compat_urlparse.urlparse(vurl).path
3593 vext = determine_ext(vpath)
3594 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3595
3596 def filter_video(urls):
3597 return list(filter(check_video, urls))
3598
3599 # Start with something easy: JW Player in SWFObject
3600 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3601 if not found:
3602 # Look for gorilla-vid style embedding
3603 found = filter_video(re.findall(r'''(?sx)
3604 (?:
3605 jw_plugins|
3606 JWPlayerOptions|
3607 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3608 )
3609 .*?
3610 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3611 if not found:
3612 # Look for generic KVS player
3613 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3614 if found:
3615 if found.group('maj_ver') not in ['4', '5']:
3616 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3617 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3618 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3619
3620 # extract the part after the last / as the display_id from the
3621 # canonical URL.
3622 display_id = self._search_regex(
3623 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3624 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3625 webpage, 'display_id', fatal=False
3626 )
3627 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3628
3629 thumbnail = flashvars['preview_url']
3630 if thumbnail.startswith('//'):
3631 protocol, _, _ = url.partition('/')
3632 thumbnail = protocol + thumbnail
3633
3634 formats = []
3635 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3636 if key in flashvars and '/get_file/' in flashvars[key]:
3637 next_format = {
3638 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3639 'format_id': flashvars.get(key + '_text', key),
3640 'ext': 'mp4',
3641 }
3642 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3643 if height:
3644 next_format['height'] = int(height.group(1))
3645 else:
3646 next_format['quality'] = 1
3647 formats.append(next_format)
3648 self._sort_formats(formats)
3649
3650 return {
3651 'id': flashvars['video_id'],
3652 'display_id': display_id,
3653 'title': title,
3654 'thumbnail': thumbnail,
3655 'formats': formats,
3656 }
3657 if not found:
3658 # Broaden the search a little bit
3659 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3660 if not found:
3661 # Broaden the findall a little bit: JWPlayer JS loader
3662 found = filter_video(re.findall(
3663 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3664 if not found:
3665 # Flow player
3666 found = filter_video(re.findall(r'''(?xs)
3667 flowplayer\("[^"]+",\s*
3668 \{[^}]+?\}\s*,
3669 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3670 ["']?url["']?\s*:\s*["']([^"']+)["']
3671 ''', webpage))
3672 if not found:
3673 # Cinerama player
3674 found = re.findall(
3675 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3676 if not found:
3677 # Try to find twitter cards info
3678 # twitter:player:stream should be checked before twitter:player since
3679 # it is expected to contain a raw stream (see
3680 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3681 found = filter_video(re.findall(
3682 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3683 if not found:
3684 # We look for Open Graph info:
3685 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3686 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3687 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3688 if m_video_type is not None:
3689 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3690 if not found:
3691 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3692 found = re.search(
3693 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3694 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3695 webpage)
3696 if not found:
3697 # Look also in Refresh HTTP header
3698 refresh_header = head_response.headers.get('Refresh')
3699 if refresh_header:
3700 # In python 2 response HTTP headers are bytestrings
3701 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3702 refresh_header = refresh_header.decode('iso-8859-1')
3703 found = re.search(REDIRECT_REGEX, refresh_header)
3704 if found:
3705 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3706 if new_url != url:
3707 self.report_following_redirect(new_url)
3708 return {
3709 '_type': 'url',
3710 'url': new_url,
3711 }
3712 else:
3713 found = None
3714
3715 if not found:
3716 # twitter:player is a https URL to iframe player that may or may not
3717 # be supported by yt-dlp thus this is checked the very last (see
3718 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3719 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3720 if embed_url and embed_url != url:
3721 return self.url_result(embed_url)
3722
3723 if not found:
3724 raise UnsupportedError(url)
3725
3726 entries = []
3727 for video_url in orderedSet(found):
3728 video_url = unescapeHTML(video_url)
3729 video_url = video_url.replace('\\/', '/')
3730 video_url = compat_urlparse.urljoin(url, video_url)
3731 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3732
3733 # Sometimes, jwplayer extraction will result in a YouTube URL
3734 if YoutubeIE.suitable(video_url):
3735 entries.append(self.url_result(video_url, 'Youtube'))
3736 continue
3737
3738 # here's a fun little line of code for you:
3739 video_id = os.path.splitext(video_id)[0]
3740
3741 entry_info_dict = {
3742 'id': video_id,
3743 'uploader': video_uploader,
3744 'title': video_title,
3745 'age_limit': age_limit,
3746 }
3747
3748 if RtmpIE.suitable(video_url):
3749 entry_info_dict.update({
3750 '_type': 'url_transparent',
3751 'ie_key': RtmpIE.ie_key(),
3752 'url': video_url,
3753 })
3754 entries.append(entry_info_dict)
3755 continue
3756
3757 ext = determine_ext(video_url)
3758 if ext == 'smil':
3759 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
3760 elif ext == 'xspf':
3761 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3762 elif ext == 'm3u8':
3763 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
3764 elif ext == 'mpd':
3765 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3766 elif ext == 'f4m':
3767 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3768 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3769 # Just matching .ism/manifest is not enough to be reliably sure
3770 # whether it's actually an ISM manifest or some other streaming
3771 # manifest since there are various streaming URL formats
3772 # possible (see [1]) as well as some other shenanigans like
3773 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3774 # so on.
3775 # Thus the most reasonable way to solve this is to delegate
3776 # to generic extractor in order to look into the contents of
3777 # the manifest itself.
3778 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3779 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3780 entry_info_dict = self.url_result(
3781 smuggle_url(video_url, {'to_generic': True}),
3782 GenericIE.ie_key())
3783 else:
3784 entry_info_dict['url'] = video_url
3785
3786 if entry_info_dict.get('formats'):
3787 self._sort_formats(entry_info_dict['formats'])
3788
3789 entries.append(entry_info_dict)
3790
3791 if len(entries) == 1:
3792 return entries[0]
3793 else:
3794 for num, e in enumerate(entries, start=1):
3795 # 'url' results don't have a title
3796 if e.get('title') is not None:
3797 e['title'] = '%s (%d)' % (e['title'], num)
3798 return {
3799 '_type': 'playlist',
3800 'entries': entries,
3801 }