]> jfr.im git - yt-dlp.git/blame_incremental - yt_dlp/extractor/generic.py
[Stripchat] Add extractor (#1668)
[yt-dlp.git] / yt_dlp / extractor / generic.py
... / ...
CommitLineData
1# coding: utf-8
2
3from __future__ import unicode_literals
4
5import os
6import re
7import sys
8
9from .common import InfoExtractor
10from .youtube import YoutubeIE
11from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17)
18from ..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)
42from .commonprotocols import RtmpIE
43from .brightcove import (
44 BrightcoveLegacyIE,
45 BrightcoveNewIE,
46)
47from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50)
51from .nbc import NBCSportsVPlayerIE
52from .ooyala import OoyalaIE
53from .rutv import RUTVIE
54from .tvc import TVCIE
55from .sportbox import SportBoxIE
56from .myvi import MyviIE
57from .condenast import CondeNastIE
58from .udn import UDNEmbedIE
59from .senateisvp import SenateISVPIE
60from .svt import SVTIE
61from .pornhub import PornHubIE
62from .xhamster import XHamsterEmbedIE
63from .tnaflix import TNAFlixNetworkEmbedIE
64from .drtuber import DrTuberIE
65from .redtube import RedTubeIE
66from .tube8 import Tube8IE
67from .mofosex import MofosexEmbedIE
68from .spankwire import SpankwireIE
69from .youporn import YouPornIE
70from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73)
74from .dailymotion import DailymotionIE
75from .dailymail import DailyMailIE
76from .onionstudios import OnionStudiosIE
77from .viewlift import ViewLiftEmbedIE
78from .mtv import MTVServicesEmbeddedIE
79from .pladform import PladformIE
80from .videomore import VideomoreIE
81from .webcaster import WebcasterFeedIE
82from .googledrive import GoogleDriveIE
83from .jwplatform import JWPlatformIE
84from .digiteka import DigitekaIE
85from .arkena import ArkenaIE
86from .instagram import InstagramIE
87from .threeqsdn import ThreeQSDNIE
88from .theplatform import ThePlatformIE
89from .kaltura import KalturaIE
90from .eagleplatform import EaglePlatformIE
91from .facebook import FacebookIE
92from .soundcloud import SoundcloudEmbedIE
93from .tunein import TuneInBaseIE
94from .vbox7 import Vbox7IE
95from .dbtv import DBTVIE
96from .piksel import PikselIE
97from .videa import VideaIE
98from .twentymin import TwentyMinutenIE
99from .ustream import UstreamIE
100from .arte import ArteTVEmbedIE
101from .videopress import VideoPressIE
102from .rutube import RutubeIE
103from .limelight import LimelightBaseIE
104from .anvato import AnvatoIE
105from .washingtonpost import WashingtonPostIE
106from .wistia import WistiaIE
107from .mediaset import MediasetIE
108from .joj import JojIE
109from .megaphone import MegaphoneIE
110from .vzaar import VzaarIE
111from .channel9 import Channel9IE
112from .vshare import VShareIE
113from .mediasite import MediasiteIE
114from .springboardplatform import SpringboardPlatformIE
115from .yapfiles import YapFilesIE
116from .vice import ViceIE
117from .xfileshare import XFileShareIE
118from .cloudflarestream import CloudflareStreamIE
119from .peertube import PeerTubeIE
120from .teachable import TeachableIE
121from .indavideo import IndavideoEmbedIE
122from .apa import APAIE
123from .foxnews import FoxNewsIE
124from .viqeo import ViqeoIE
125from .expressen import ExpressenIE
126from .zype import ZypeIE
127from .odnoklassniki import OdnoklassnikiIE
128from .vk import VKIE
129from .kinja import KinjaEmbedIE
130from .gedidigital import GediDigitalIE
131from .rcs import RCSEmbedsIE
132from .bitchute import BitChuteIE
133from .rumble import RumbleEmbedIE
134from .arcpublishing import ArcPublishingIE
135from .medialaan import MedialaanIE
136from .simplecast import SimplecastIE
137from .wimtv import WimTVIE
138from .tvp import TVPEmbedIE
139from .blogger import BloggerIE
140
141
142class GenericIE(InfoExtractor):
143 IE_DESC = 'Generic downloader that works on some sites'
144 _VALID_URL = r'.*'
145 IE_NAME = 'generic'
146 _TESTS = [
147 # Direct link to a video
148 {
149 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
150 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
151 'info_dict': {
152 'id': 'trailer',
153 'ext': 'mp4',
154 'title': 'trailer',
155 'upload_date': '20100513',
156 }
157 },
158 # Direct link to media delivered compressed (until Accept-Encoding is *)
159 {
160 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
161 'md5': '128c42e68b13950268b648275386fc74',
162 'info_dict': {
163 'id': 'FictionJunction-Parallel_Hearts',
164 'ext': 'flac',
165 'title': 'FictionJunction-Parallel_Hearts',
166 'upload_date': '20140522',
167 },
168 'expected_warnings': [
169 'URL could be a direct video link, returning it as such.'
170 ],
171 'skip': 'URL invalid',
172 },
173 # Direct download with broken HEAD
174 {
175 'url': 'http://ai-radio.org:8000/radio.opus',
176 'info_dict': {
177 'id': 'radio',
178 'ext': 'opus',
179 'title': 'radio',
180 },
181 'params': {
182 'skip_download': True, # infinite live stream
183 },
184 'expected_warnings': [
185 r'501.*Not Implemented',
186 r'400.*Bad Request',
187 ],
188 },
189 # Direct link with incorrect MIME type
190 {
191 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
192 'md5': '4ccbebe5f36706d85221f204d7eb5913',
193 'info_dict': {
194 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
195 'id': '5_Lennart_Poettering_-_Systemd',
196 'ext': 'webm',
197 'title': '5_Lennart_Poettering_-_Systemd',
198 'upload_date': '20141120',
199 },
200 'expected_warnings': [
201 'URL could be a direct video link, returning it as such.'
202 ]
203 },
204 # RSS feed
205 {
206 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'info_dict': {
208 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
209 'title': 'Zero Punctuation',
210 'description': 're:.*groundbreaking video review series.*'
211 },
212 'playlist_mincount': 11,
213 },
214 # RSS feed with enclosure
215 {
216 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
217 'info_dict': {
218 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
219 'title': 'MSNBC Rachel Maddow (video)',
220 'description': 're:.*her unique approach to storytelling.*',
221 },
222 'playlist': [{
223 'info_dict': {
224 'ext': 'mov',
225 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
226 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
227 'description': 're:.*her unique approach to storytelling.*',
228 'upload_date': '20201204',
229 },
230 }],
231 },
232 # RSS feed with item with description and thumbnails
233 {
234 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'info_dict': {
236 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
237 'title': 're:.*100% Hydrogen.*',
238 'description': 're:.*In this episode.*',
239 },
240 'playlist': [{
241 'info_dict': {
242 'ext': 'm4a',
243 'id': 'c1c879525ce2cb640b344507e682c36d',
244 'title': 're:Hydrogen!',
245 'description': 're:.*In this episode we are going.*',
246 'timestamp': 1567977776,
247 'upload_date': '20190908',
248 'duration': 459,
249 'thumbnail': r're:^https?://.*\.jpg$',
250 'episode_number': 1,
251 'season_number': 1,
252 'age_limit': 0,
253 },
254 }],
255 'params': {
256 'skip_download': True,
257 },
258 },
259 # RSS feed with enclosures and unsupported link URLs
260 {
261 'url': 'http://www.hellointernet.fm/podcast?format=rss',
262 'info_dict': {
263 'id': 'http://www.hellointernet.fm/podcast?format=rss',
264 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
265 'title': 'Hello Internet',
266 },
267 'playlist_mincount': 100,
268 },
269 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
270 {
271 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
272 'info_dict': {
273 'id': 'smil',
274 'ext': 'mp4',
275 'title': 'Automatics, robotics and biocybernetics',
276 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
277 'upload_date': '20130627',
278 'formats': 'mincount:16',
279 'subtitles': 'mincount:1',
280 },
281 'params': {
282 'force_generic_extractor': True,
283 'skip_download': True,
284 },
285 },
286 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
287 {
288 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
289 'info_dict': {
290 'id': 'hds',
291 'ext': 'flv',
292 'title': 'hds',
293 'formats': 'mincount:1',
294 },
295 'params': {
296 'skip_download': True,
297 },
298 },
299 # SMIL from https://www.restudy.dk/video/play/id/1637
300 {
301 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
302 'info_dict': {
303 'id': 'video_1637',
304 'ext': 'flv',
305 'title': 'video_1637',
306 'formats': 'mincount:3',
307 },
308 'params': {
309 'skip_download': True,
310 },
311 },
312 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
313 {
314 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
315 'info_dict': {
316 'id': 'smil-service',
317 'ext': 'flv',
318 'title': 'smil-service',
319 'formats': 'mincount:1',
320 },
321 'params': {
322 'skip_download': True,
323 },
324 },
325 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
326 {
327 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
328 'info_dict': {
329 'id': '4719370',
330 'ext': 'mp4',
331 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
332 'formats': 'mincount:3',
333 },
334 'params': {
335 'skip_download': True,
336 },
337 },
338 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
339 {
340 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
341 'info_dict': {
342 'id': 'mZlp2ctYIUEB',
343 'ext': 'mp4',
344 'title': 'Tikibad ontruimd wegens brand',
345 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
346 'thumbnail': r're:^https?://.*\.jpg$',
347 'duration': 33,
348 },
349 'params': {
350 'skip_download': True,
351 },
352 },
353 # MPD from http://dash-mse-test.appspot.com/media.html
354 {
355 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
356 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
357 'info_dict': {
358 'id': 'car-20120827-manifest',
359 'ext': 'mp4',
360 'title': 'car-20120827-manifest',
361 'formats': 'mincount:9',
362 'upload_date': '20130904',
363 },
364 },
365 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
366 {
367 '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',
368 'info_dict': {
369 'id': 'content',
370 'ext': 'mp4',
371 'title': 'content',
372 'formats': 'mincount:8',
373 },
374 'params': {
375 # m3u8 downloads
376 'skip_download': True,
377 },
378 'skip': 'video gone',
379 },
380 # m3u8 served with Content-Type: text/plain
381 {
382 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
383 'info_dict': {
384 'id': 'index',
385 'ext': 'mp4',
386 'title': 'index',
387 'upload_date': '20140720',
388 'formats': 'mincount:11',
389 },
390 'params': {
391 # m3u8 downloads
392 'skip_download': True,
393 },
394 'skip': 'video gone',
395 },
396 # google redirect
397 {
398 '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',
399 'info_dict': {
400 'id': 'cmQHVoWB5FY',
401 'ext': 'mp4',
402 'upload_date': '20130224',
403 'uploader_id': 'TheVerge',
404 'description': r're:^Chris Ziegler takes a look at the\.*',
405 'uploader': 'The Verge',
406 'title': 'First Firefox OS phones side-by-side',
407 },
408 'params': {
409 'skip_download': False,
410 }
411 },
412 {
413 # redirect in Refresh HTTP header
414 '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',
415 'info_dict': {
416 'id': 'pO8h3EaFRdo',
417 'ext': 'mp4',
418 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
419 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
420 'upload_date': '20150917',
421 'uploader_id': 'brtvofficial',
422 'uploader': 'Boiler Room',
423 },
424 'params': {
425 'skip_download': False,
426 },
427 },
428 {
429 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
430 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
431 'info_dict': {
432 'id': '13601338388002',
433 'ext': 'mp4',
434 'uploader': 'www.hodiho.fr',
435 'title': 'R\u00e9gis plante sa Jeep',
436 }
437 },
438 # bandcamp page with custom domain
439 {
440 'add_ie': ['Bandcamp'],
441 'url': 'http://bronyrock.com/track/the-pony-mash',
442 'info_dict': {
443 'id': '3235767654',
444 'ext': 'mp3',
445 'title': 'The Pony Mash',
446 'uploader': 'M_Pallante',
447 },
448 'skip': 'There is a limit of 200 free downloads / month for the test song',
449 },
450 {
451 # embedded brightcove video
452 # it also tests brightcove videos that need to set the 'Referer'
453 # in the http requests
454 'add_ie': ['BrightcoveLegacy'],
455 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
456 'info_dict': {
457 'id': '2765128793001',
458 'ext': 'mp4',
459 'title': 'Le cours de bourse : l’analyse technique',
460 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
461 'uploader': 'BFM BUSINESS',
462 },
463 'params': {
464 'skip_download': True,
465 },
466 },
467 {
468 # embedded with itemprop embedURL and video id spelled as `idVideo`
469 'add_id': ['BrightcoveLegacy'],
470 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
471 'info_dict': {
472 'id': '5255628253001',
473 'ext': 'mp4',
474 'title': 'md5:37c519b1128915607601e75a87995fc0',
475 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
476 'uploader': 'BFM BUSINESS',
477 'uploader_id': '876450612001',
478 'timestamp': 1482255315,
479 'upload_date': '20161220',
480 },
481 'params': {
482 'skip_download': True,
483 },
484 },
485 {
486 # https://github.com/ytdl-org/youtube-dl/issues/2253
487 'url': 'http://bcove.me/i6nfkrc3',
488 'md5': '0ba9446db037002366bab3b3eb30c88c',
489 'info_dict': {
490 'id': '3101154703001',
491 'ext': 'mp4',
492 'title': 'Still no power',
493 'uploader': 'thestar.com',
494 '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.',
495 },
496 'add_ie': ['BrightcoveLegacy'],
497 'skip': 'video gone',
498 },
499 {
500 'url': 'http://www.championat.com/video/football/v/87/87499.html',
501 'md5': 'fb973ecf6e4a78a67453647444222983',
502 'info_dict': {
503 'id': '3414141473001',
504 'ext': 'mp4',
505 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
506 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
507 'uploader': 'Championat',
508 },
509 },
510 {
511 # https://github.com/ytdl-org/youtube-dl/issues/3541
512 'add_ie': ['BrightcoveLegacy'],
513 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
514 'info_dict': {
515 'id': '3866516442001',
516 'ext': 'mp4',
517 'title': 'Leer mij vrouwen kennen: Aflevering 1',
518 'description': 'Leer mij vrouwen kennen: Aflevering 1',
519 'uploader': 'SBS Broadcasting',
520 },
521 'skip': 'Restricted to Netherlands',
522 'params': {
523 'skip_download': True, # m3u8 download
524 },
525 },
526 {
527 # Brightcove video in <iframe>
528 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
529 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
530 'info_dict': {
531 'id': '5360463607001',
532 'ext': 'mp4',
533 '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',
534 '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。',
535 'uploader': 'United Nations',
536 'uploader_id': '1362235914001',
537 'timestamp': 1489593889,
538 'upload_date': '20170315',
539 },
540 'add_ie': ['BrightcoveLegacy'],
541 },
542 {
543 # Brightcove with alternative playerID key
544 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
545 'info_dict': {
546 'id': 'nmeth.2062_SV1',
547 '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',
548 },
549 'playlist': [{
550 'info_dict': {
551 'id': '2228375078001',
552 'ext': 'mp4',
553 'title': 'nmeth.2062-sv1',
554 'description': 'nmeth.2062-sv1',
555 'timestamp': 1363357591,
556 'upload_date': '20130315',
557 'uploader': 'Nature Publishing Group',
558 'uploader_id': '1964492299001',
559 },
560 }],
561 },
562 {
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'info_dict': {
566 'id': '5255815316001',
567 'ext': 'mp4',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
574 },
575 'params': {
576 'skip_download': True, # m3u8 download
577 },
578 'skip': 'video rotates...weekly?',
579 },
580 {
581 # Brightcove:new type [2].
582 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
583 'md5': '2b35148fcf48da41c9fb4591650784f3',
584 'info_dict': {
585 'id': '5348741021001',
586 'ext': 'mp4',
587 'upload_date': '20170306',
588 'uploader_id': '4191638492001',
589 'timestamp': 1488769918,
590 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
591
592 },
593 },
594 {
595 # Alternative brightcove <video> attributes
596 '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/',
597 'info_dict': {
598 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
599 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
600 },
601 'playlist': [{
602 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
603 'info_dict': {
604 'id': '5311302538001',
605 'ext': 'mp4',
606 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
607 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
608 'timestamp': 1486321708,
609 'upload_date': '20170205',
610 'uploader_id': '800000640001',
611 },
612 'only_matching': True,
613 }],
614 },
615 {
616 # Brightcove with UUID in videoPlayer
617 'url': 'http://www8.hp.com/cn/zh/home.html',
618 'info_dict': {
619 'id': '5255815316001',
620 'ext': 'mp4',
621 'title': 'Sprocket Video - China',
622 'description': 'Sprocket Video - China',
623 'uploader': 'HP-Video Gallery',
624 'timestamp': 1482263210,
625 'upload_date': '20161220',
626 'uploader_id': '1107601872001',
627 },
628 'params': {
629 'skip_download': True, # m3u8 download
630 },
631 },
632 # ooyala video
633 {
634 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
635 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
636 'info_dict': {
637 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
638 'ext': 'mp4',
639 'title': '2cc213299525360.mov', # that's what we get
640 'duration': 238.231,
641 },
642 'add_ie': ['Ooyala'],
643 },
644 {
645 # ooyala video embedded with http://player.ooyala.com/iframe.js
646 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
647 'info_dict': {
648 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
649 'ext': 'mp4',
650 'title': '"Steve Jobs: Man in the Machine" trailer',
651 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
652 'duration': 135.427,
653 },
654 'params': {
655 'skip_download': True,
656 },
657 'skip': 'movie expired',
658 },
659 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
660 {
661 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
662 'info_dict': {
663 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
664 'ext': 'mp4',
665 'title': 'Steampunk Fest Comes to Honesdale',
666 'duration': 43.276,
667 },
668 'params': {
669 'skip_download': True,
670 }
671 },
672 # embed.ly video
673 {
674 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
675 'info_dict': {
676 'id': '9ODmcdjQcHQ',
677 'ext': 'mp4',
678 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
679 'upload_date': '20140225',
680 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
681 'uploader': 'Tested',
682 'uploader_id': 'testedcom',
683 },
684 # No need to test YoutubeIE here
685 'params': {
686 'skip_download': True,
687 },
688 },
689 # funnyordie embed
690 {
691 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
692 'info_dict': {
693 'id': '18e820ec3f',
694 'ext': 'mp4',
695 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
696 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
697 },
698 # HEAD requests lead to endless 301, while GET is OK
699 'expected_warnings': ['301'],
700 },
701 # RUTV embed
702 {
703 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
704 'info_dict': {
705 'id': '776940',
706 'ext': 'mp4',
707 'title': 'Охотское море стало целиком российским',
708 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
709 },
710 'params': {
711 # m3u8 download
712 'skip_download': True,
713 },
714 },
715 # TVC embed
716 {
717 '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/',
718 'info_dict': {
719 'id': '55304',
720 'ext': 'mp4',
721 'title': 'Дошкольное воспитание',
722 },
723 },
724 # SportBox embed
725 {
726 'url': 'http://www.vestifinance.ru/articles/25753',
727 'info_dict': {
728 'id': '25753',
729 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
730 },
731 'playlist': [{
732 'info_dict': {
733 'id': '370908',
734 'title': 'Госзаказ. День 3',
735 'ext': 'mp4',
736 }
737 }, {
738 'info_dict': {
739 'id': '370905',
740 'title': 'Госзаказ. День 2',
741 'ext': 'mp4',
742 }
743 }, {
744 'info_dict': {
745 'id': '370902',
746 'title': 'Госзаказ. День 1',
747 'ext': 'mp4',
748 }
749 }],
750 'params': {
751 # m3u8 download
752 'skip_download': True,
753 },
754 },
755 # Myvi.ru embed
756 {
757 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
758 'info_dict': {
759 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
760 'ext': 'mp4',
761 'title': 'Ужастики, русский трейлер (2015)',
762 'thumbnail': r're:^https?://.*\.jpg$',
763 'duration': 153,
764 }
765 },
766 # XHamster embed
767 {
768 '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',
769 'info_dict': {
770 'id': 'showthread',
771 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
772 },
773 'playlist_mincount': 7,
774 # This forum does not allow <iframe> syntaxes anymore
775 # Now HTML tags are displayed as-is
776 'skip': 'No videos on this page',
777 },
778 # Embedded TED video
779 {
780 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
781 'md5': '65fdff94098e4a607385a60c5177c638',
782 'info_dict': {
783 'id': '1969',
784 'ext': 'mp4',
785 'title': 'Hidden miracles of the natural world',
786 'uploader': 'Louie Schwartzberg',
787 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
788 }
789 },
790 # nowvideo embed hidden behind percent encoding
791 {
792 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
793 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
794 'info_dict': {
795 'id': '06e53103ca9aa',
796 'ext': 'flv',
797 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
798 'description': 'No description',
799 },
800 },
801 # arte embed
802 {
803 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
804 'md5': '7653032cbb25bf6c80d80f217055fa43',
805 'info_dict': {
806 'id': '048195-004_PLUS7-F',
807 'ext': 'flv',
808 'title': 'X:enius',
809 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
810 'upload_date': '20140320',
811 },
812 'params': {
813 'skip_download': 'Requires rtmpdump'
814 },
815 'skip': 'video gone',
816 },
817 # francetv embed
818 {
819 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
820 'info_dict': {
821 'id': 'EV_30231',
822 'ext': 'mp4',
823 'title': 'Alcaline, le concert avec Calogero',
824 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
825 'upload_date': '20150226',
826 'timestamp': 1424989860,
827 'duration': 5400,
828 },
829 'params': {
830 # m3u8 downloads
831 'skip_download': True,
832 },
833 'expected_warnings': [
834 'Forbidden'
835 ]
836 },
837 # Condé Nast embed
838 {
839 'url': 'http://www.wired.com/2014/04/honda-asimo/',
840 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
841 'info_dict': {
842 'id': '53501be369702d3275860000',
843 'ext': 'mp4',
844 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
845 }
846 },
847 # Dailymotion embed
848 {
849 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
850 'md5': '441aeeb82eb72c422c7f14ec533999cd',
851 'info_dict': {
852 'id': 'k2mm4bCdJ6CQ2i7c8o2',
853 'ext': 'mp4',
854 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
855 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
856 'uploader': 'Spi0n',
857 'uploader_id': 'xgditw',
858 'upload_date': '20140425',
859 'timestamp': 1398441542,
860 },
861 'add_ie': ['Dailymotion'],
862 },
863 # DailyMail embed
864 {
865 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
866 'info_dict': {
867 'id': '1495629',
868 'ext': 'mp4',
869 'title': 'Care worker punches elderly dementia patient in head 11 times',
870 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
871 },
872 'add_ie': ['DailyMail'],
873 'params': {
874 'skip_download': True,
875 },
876 },
877 # YouTube embed
878 {
879 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
880 'info_dict': {
881 'id': 'FXRb4ykk4S0',
882 'ext': 'mp4',
883 'title': 'The NBL Auction 2014',
884 'uploader': 'BADMINTON England',
885 'uploader_id': 'BADMINTONEvents',
886 'upload_date': '20140603',
887 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
888 },
889 'add_ie': ['Youtube'],
890 'params': {
891 'skip_download': True,
892 }
893 },
894 # MTVServices embed
895 {
896 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
897 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
898 'info_dict': {
899 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
900 'ext': 'mp4',
901 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
902 'description': 'Two valets share their love for movie star Liam Neesons.',
903 'timestamp': 1349922600,
904 'upload_date': '20121011',
905 },
906 },
907 # YouTube embed via <data-embed-url="">
908 {
909 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
910 'info_dict': {
911 'id': '4vAffPZIT44',
912 'ext': 'mp4',
913 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
914 'uploader': 'Gameloft',
915 'uploader_id': 'gameloft',
916 'upload_date': '20140828',
917 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
918 },
919 'params': {
920 'skip_download': True,
921 }
922 },
923 # YouTube <object> embed
924 {
925 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
926 'md5': '516718101ec834f74318df76259fb3cc',
927 'info_dict': {
928 'id': 'msN87y-iEx0',
929 'ext': 'webm',
930 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
931 'upload_date': '20080526',
932 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
933 'uploader': 'Christopher Sykes',
934 'uploader_id': 'ChristopherJSykes',
935 },
936 'add_ie': ['Youtube'],
937 },
938 # Camtasia studio
939 {
940 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
941 'playlist': [{
942 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
943 'info_dict': {
944 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
945 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
946 'ext': 'flv',
947 'duration': 2235.90,
948 }
949 }, {
950 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
951 'info_dict': {
952 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
953 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
954 'ext': 'flv',
955 'duration': 2235.93,
956 }
957 }],
958 'info_dict': {
959 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
960 }
961 },
962 # Flowplayer
963 {
964 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
965 'md5': '9d65602bf31c6e20014319c7d07fba27',
966 'info_dict': {
967 'id': '5123ea6d5e5a7',
968 'ext': 'mp4',
969 'age_limit': 18,
970 'uploader': 'www.handjobhub.com',
971 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
972 }
973 },
974 # Multiple brightcove videos
975 # https://github.com/ytdl-org/youtube-dl/issues/2283
976 {
977 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
978 'info_dict': {
979 'id': 'always-never',
980 'title': 'Always / Never - The New Yorker',
981 },
982 'playlist_count': 3,
983 'params': {
984 'extract_flat': False,
985 'skip_download': True,
986 }
987 },
988 # MLB embed
989 {
990 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
991 'md5': '96f09a37e44da40dd083e12d9a683327',
992 'info_dict': {
993 'id': '33322633',
994 'ext': 'mp4',
995 'title': 'Ump changes call to ball',
996 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
997 'duration': 48,
998 'timestamp': 1401537900,
999 'upload_date': '20140531',
1000 'thumbnail': r're:^https?://.*\.jpg$',
1001 },
1002 },
1003 # Wistia embed
1004 {
1005 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1006 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1007 'info_dict': {
1008 'id': '6e2wtrbdaf',
1009 'ext': 'mov',
1010 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1011 'description': 'a Paywall Videos video from Remilon',
1012 'duration': 644.072,
1013 'uploader': 'study.com',
1014 'timestamp': 1459678540,
1015 'upload_date': '20160403',
1016 'filesize': 24687186,
1017 },
1018 },
1019 {
1020 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1021 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1022 'info_dict': {
1023 'id': 'uxjb0lwrcz',
1024 'ext': 'mp4',
1025 'title': 'Conversation about Hexagonal Rails Part 1',
1026 'description': 'a Martin Fowler video from ThoughtWorks',
1027 'duration': 1715.0,
1028 'uploader': 'thoughtworks.wistia.com',
1029 'timestamp': 1401832161,
1030 'upload_date': '20140603',
1031 },
1032 },
1033 # Wistia standard embed (async)
1034 {
1035 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1036 'info_dict': {
1037 'id': '807fafadvk',
1038 'ext': 'mp4',
1039 'title': 'Drip Brennan Dunn Workshop',
1040 'description': 'a JV Webinars video from getdrip-1',
1041 'duration': 4986.95,
1042 'timestamp': 1463607249,
1043 'upload_date': '20160518',
1044 },
1045 'params': {
1046 'skip_download': True,
1047 }
1048 },
1049 # Soundcloud embed
1050 {
1051 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1052 'info_dict': {
1053 'id': '174391317',
1054 'ext': 'mp3',
1055 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1056 'uploader': 'Sophos Security',
1057 'title': 'Chet Chat 171 - Oct 29, 2014',
1058 'upload_date': '20141029',
1059 }
1060 },
1061 # Soundcloud multiple embeds
1062 {
1063 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1064 'info_dict': {
1065 'id': '52809',
1066 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1067 },
1068 'playlist_mincount': 7,
1069 },
1070 # TuneIn station embed
1071 {
1072 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1073 'info_dict': {
1074 'id': '204146',
1075 'ext': 'mp3',
1076 'title': 'CNRV',
1077 'location': 'Paris, France',
1078 'is_live': True,
1079 },
1080 'params': {
1081 # Live stream
1082 'skip_download': True,
1083 },
1084 },
1085 # Livestream embed
1086 {
1087 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1088 'info_dict': {
1089 'id': '67864563',
1090 'ext': 'flv',
1091 'upload_date': '20141112',
1092 'title': 'Rosetta #CometLanding webcast HL 10',
1093 }
1094 },
1095 # Another Livestream embed, without 'new.' in URL
1096 {
1097 'url': 'https://www.freespeech.org/',
1098 'info_dict': {
1099 'id': '123537347',
1100 'ext': 'mp4',
1101 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1102 },
1103 'params': {
1104 # Live stream
1105 'skip_download': True,
1106 },
1107 },
1108 # LazyYT
1109 {
1110 'url': 'https://skiplagged.com/',
1111 'info_dict': {
1112 'id': 'skiplagged',
1113 'title': 'Skiplagged: The smart way to find cheap flights',
1114 },
1115 'playlist_mincount': 1,
1116 'add_ie': ['Youtube'],
1117 },
1118 # Cinchcast embed
1119 {
1120 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1121 'info_dict': {
1122 'id': '7141703',
1123 'ext': 'mp3',
1124 'upload_date': '20141126',
1125 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1126 }
1127 },
1128 # Cinerama player
1129 {
1130 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1131 'info_dict': {
1132 'id': '730m_DandD_1901_512k',
1133 'ext': 'mp4',
1134 'uploader': 'www.abc.net.au',
1135 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1136 }
1137 },
1138 # embedded viddler video
1139 {
1140 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1141 'info_dict': {
1142 'id': '4d03aad9',
1143 'ext': 'mp4',
1144 'uploader': 'deadspin',
1145 'title': 'WALL-TO-GORTAT',
1146 'timestamp': 1422285291,
1147 'upload_date': '20150126',
1148 },
1149 'add_ie': ['Viddler'],
1150 },
1151 # Libsyn embed
1152 {
1153 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1154 'info_dict': {
1155 'id': '3377616',
1156 'ext': 'mp3',
1157 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1158 'description': 'md5:601cb790edd05908957dae8aaa866465',
1159 'upload_date': '20150220',
1160 },
1161 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1162 },
1163 # jwplayer YouTube
1164 {
1165 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1166 'info_dict': {
1167 'id': 'Mrj4DVp2zeA',
1168 'ext': 'mp4',
1169 'upload_date': '20150212',
1170 'uploader': 'The National Archives UK',
1171 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1172 'uploader_id': 'NationalArchives08',
1173 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1174 },
1175 },
1176 # jwplayer rtmp
1177 {
1178 'url': 'http://www.suffolk.edu/sjc/live.php',
1179 'info_dict': {
1180 'id': 'live',
1181 'ext': 'flv',
1182 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1183 'uploader': 'www.suffolk.edu',
1184 },
1185 'params': {
1186 'skip_download': True,
1187 },
1188 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1189 },
1190 # jwplayer with only the json URL
1191 {
1192 'url': 'https://www.hollywoodreporter.com/news/general-news/dunkirk-team-reveals-what-christopher-nolan-said-oscar-win-meet-your-oscar-winner-1092454',
1193 'info_dict': {
1194 'id': 'TljWkvWH',
1195 'ext': 'mp4',
1196 'upload_date': '20180306',
1197 'title': 'md5:91eb1862f6526415214f62c00b453936',
1198 'description': 'md5:73048ae50ae953da10549d1d2fe9b3aa',
1199 'timestamp': 1520367225,
1200 },
1201 'params': {
1202 'skip_download': True,
1203 },
1204 },
1205 # Complex jwplayer
1206 {
1207 'url': 'http://www.indiedb.com/games/king-machine/videos',
1208 'info_dict': {
1209 'id': 'videos',
1210 'ext': 'mp4',
1211 'title': 'king machine trailer 1',
1212 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1213 'thumbnail': r're:^https?://.*\.jpg$',
1214 },
1215 },
1216 {
1217 # JWPlayer config passed as variable
1218 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1219 'info_dict': {
1220 'id': '3326530_hq',
1221 'ext': 'mp4',
1222 'title': 'ARIELE | Tube Cup',
1223 'uploader': 'www.txxx.com',
1224 'age_limit': 18,
1225 },
1226 'params': {
1227 'skip_download': True,
1228 }
1229 },
1230 {
1231 # JWPlatform iframe
1232 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
1233 'info_dict': {
1234 'id': 'AG26UQXM',
1235 'ext': 'mp4',
1236 'upload_date': '20160719',
1237 'timestamp': 468923808,
1238 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
1239 },
1240 'add_ie': [JWPlatformIE.ie_key()],
1241 },
1242 {
1243 # Video.js embed, multiple formats
1244 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1245 'info_dict': {
1246 'id': 'yygqldloqIk',
1247 'ext': 'mp4',
1248 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1249 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1250 'upload_date': '20130314',
1251 'uploader': 'PROстое3D',
1252 'uploader_id': 'PROstoe3D',
1253 },
1254 'params': {
1255 'skip_download': True,
1256 },
1257 },
1258 {
1259 # Video.js embed, single format
1260 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1261 'info_dict': {
1262 'id': 'watch',
1263 'ext': 'mp4',
1264 'title': 'Step 1 - Good Foundation',
1265 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1266 },
1267 'params': {
1268 'skip_download': True,
1269 },
1270 },
1271 # rtl.nl embed
1272 {
1273 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1274 'playlist_mincount': 5,
1275 'info_dict': {
1276 'id': 'aanslagen-kopenhagen',
1277 'title': 'Aanslagen Kopenhagen',
1278 }
1279 },
1280 # Zapiks embed
1281 {
1282 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1283 'info_dict': {
1284 'id': '118046',
1285 'ext': 'mp4',
1286 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1287 }
1288 },
1289 # Kaltura embed (different embed code)
1290 {
1291 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1292 'info_dict': {
1293 'id': '1_a52wc67y',
1294 'ext': 'flv',
1295 'upload_date': '20150127',
1296 'uploader_id': 'PremierMedia',
1297 'timestamp': int,
1298 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1299 },
1300 },
1301 # Kaltura embed with single quotes
1302 {
1303 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1304 'info_dict': {
1305 'id': '0_izeg5utt',
1306 'ext': 'mp4',
1307 'title': '35871',
1308 'timestamp': 1355743100,
1309 'upload_date': '20121217',
1310 'uploader_id': 'cplapp@learn360.com',
1311 },
1312 'add_ie': ['Kaltura'],
1313 },
1314 {
1315 # Kaltura embedded via quoted entry_id
1316 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1317 'info_dict': {
1318 'id': '0_utuok90b',
1319 'ext': 'mp4',
1320 'title': '06_matthew_brender_raj_dutt',
1321 'timestamp': 1466638791,
1322 'upload_date': '20160622',
1323 },
1324 'add_ie': ['Kaltura'],
1325 'expected_warnings': [
1326 'Could not send HEAD request'
1327 ],
1328 'params': {
1329 'skip_download': True,
1330 }
1331 },
1332 {
1333 # Kaltura embedded, some fileExt broken (#11480)
1334 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1335 'info_dict': {
1336 'id': '1_sgtvehim',
1337 'ext': 'mp4',
1338 'title': 'Our "Standard Models" of particle physics and cosmology',
1339 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1340 'timestamp': 1321158993,
1341 'upload_date': '20111113',
1342 'uploader_id': 'kps1',
1343 },
1344 'add_ie': ['Kaltura'],
1345 },
1346 {
1347 # Kaltura iframe embed
1348 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1349 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1350 'info_dict': {
1351 'id': '0_f2cfbpwy',
1352 'ext': 'mp4',
1353 'title': 'I. M. Pei: A Centennial Celebration',
1354 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1355 'upload_date': '20170403',
1356 'uploader_id': 'batchUser',
1357 'timestamp': 1491232186,
1358 },
1359 'add_ie': ['Kaltura'],
1360 },
1361 {
1362 # Kaltura iframe embed, more sophisticated
1363 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1364 'info_dict': {
1365 'id': '1_9gzouybz',
1366 'ext': 'mp4',
1367 'title': 'lecture-05sep2017',
1368 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1369 'upload_date': '20170913',
1370 'uploader_id': 'eps2',
1371 'timestamp': 1505340777,
1372 },
1373 'params': {
1374 'skip_download': True,
1375 },
1376 'add_ie': ['Kaltura'],
1377 },
1378 {
1379 # meta twitter:player
1380 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1381 'info_dict': {
1382 'id': '0_01b42zps',
1383 'ext': 'mp4',
1384 'title': 'Main Twerk (Video)',
1385 'upload_date': '20171208',
1386 'uploader_id': 'sebastian.salinas@thechive.com',
1387 'timestamp': 1512713057,
1388 },
1389 'params': {
1390 'skip_download': True,
1391 },
1392 'add_ie': ['Kaltura'],
1393 },
1394 # referrer protected EaglePlatform embed
1395 {
1396 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1397 'info_dict': {
1398 'id': '582306',
1399 'ext': 'mp4',
1400 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1401 'thumbnail': r're:^https?://.*\.jpg$',
1402 'duration': 3382,
1403 'view_count': int,
1404 },
1405 'params': {
1406 'skip_download': True,
1407 },
1408 },
1409 # ClipYou (EaglePlatform) embed (custom URL)
1410 {
1411 'url': 'http://muz-tv.ru/play/7129/',
1412 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1413 'info_dict': {
1414 'id': '12820',
1415 'ext': 'mp4',
1416 'title': "'O Sole Mio",
1417 'thumbnail': r're:^https?://.*\.jpg$',
1418 'duration': 216,
1419 'view_count': int,
1420 },
1421 'params': {
1422 'skip_download': True,
1423 },
1424 'skip': 'This video is unavailable.',
1425 },
1426 # Pladform embed
1427 {
1428 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1429 'info_dict': {
1430 'id': '100183293',
1431 'ext': 'mp4',
1432 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1433 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1434 'thumbnail': r're:^https?://.*\.jpg$',
1435 'duration': 694,
1436 'age_limit': 0,
1437 },
1438 'skip': 'HTTP Error 404: Not Found',
1439 },
1440 # Playwire embed
1441 {
1442 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1443 'info_dict': {
1444 'id': '3519514',
1445 'ext': 'mp4',
1446 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1447 'thumbnail': r're:^https?://.*\.png$',
1448 'duration': 45.115,
1449 },
1450 },
1451 # 5min embed
1452 {
1453 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1454 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1455 'info_dict': {
1456 'id': '518726732',
1457 'ext': 'mp4',
1458 'title': 'Facebook Creates "On This Day" | Crunch Report',
1459 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1460 'timestamp': 1427237531,
1461 'uploader': 'Crunch Report',
1462 'upload_date': '20150324',
1463 },
1464 'params': {
1465 # m3u8 download
1466 'skip_download': True,
1467 },
1468 },
1469 # Crooks and Liars embed
1470 {
1471 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1472 'info_dict': {
1473 'id': '8RUoRhRi',
1474 'ext': 'mp4',
1475 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1476 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1477 'timestamp': 1428207000,
1478 'upload_date': '20150405',
1479 'uploader': 'Heather',
1480 },
1481 },
1482 # Crooks and Liars external embed
1483 {
1484 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1485 'info_dict': {
1486 'id': 'MTE3MjUtMzQ2MzA',
1487 'ext': 'mp4',
1488 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1489 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1490 'timestamp': 1265032391,
1491 'upload_date': '20100201',
1492 'uploader': 'Heather',
1493 },
1494 },
1495 # NBC Sports vplayer embed
1496 {
1497 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1498 'info_dict': {
1499 'id': 'ln7x1qSThw4k',
1500 'ext': 'flv',
1501 'title': "PFT Live: New leader in the 'new-look' defense",
1502 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1503 'uploader': 'NBCU-SPORTS',
1504 'upload_date': '20140107',
1505 'timestamp': 1389118457,
1506 },
1507 'skip': 'Invalid Page URL',
1508 },
1509 # NBC News embed
1510 {
1511 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1512 'md5': '1aa589c675898ae6d37a17913cf68d66',
1513 'info_dict': {
1514 'id': 'x_dtl_oa_LettermanliftPR_160608',
1515 'ext': 'mp4',
1516 'title': 'David Letterman: A Preview',
1517 '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.',
1518 'upload_date': '20160609',
1519 'timestamp': 1465431544,
1520 'uploader': 'NBCU-NEWS',
1521 },
1522 },
1523 # UDN embed
1524 {
1525 'url': 'https://video.udn.com/news/300346',
1526 'md5': 'fd2060e988c326991037b9aff9df21a6',
1527 'info_dict': {
1528 'id': '300346',
1529 'ext': 'mp4',
1530 'title': '中一中男師變性 全校師生力挺',
1531 'thumbnail': r're:^https?://.*\.jpg$',
1532 },
1533 'params': {
1534 # m3u8 download
1535 'skip_download': True,
1536 },
1537 'expected_warnings': ['Failed to parse JSON Expecting value'],
1538 },
1539 # Brightcove URL in single quotes
1540 {
1541 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1542 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1543 'info_dict': {
1544 'id': '4255764656001',
1545 'ext': 'mp4',
1546 'title': 'SN Presents: Russell Martin, World Citizen',
1547 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1548 'uploader': 'Rogers Sportsnet',
1549 'uploader_id': '1704050871',
1550 'upload_date': '20150525',
1551 'timestamp': 1432570283,
1552 },
1553 },
1554 # Kinja embed
1555 {
1556 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1557 'info_dict': {
1558 'id': '106351',
1559 'ext': 'mp4',
1560 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1561 'description': 'Migrated from OnionStudios',
1562 'thumbnail': r're:^https?://.*\.jpe?g$',
1563 'uploader': 'clickhole',
1564 'upload_date': '20150527',
1565 'timestamp': 1432744860,
1566 }
1567 },
1568 # SnagFilms embed
1569 {
1570 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1571 'info_dict': {
1572 'id': '74849a00-85a9-11e1-9660-123139220831',
1573 'ext': 'mp4',
1574 'title': '#whilewewatch',
1575 }
1576 },
1577 # AdobeTVVideo embed
1578 {
1579 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1580 'md5': '43662b577c018ad707a63766462b1e87',
1581 'info_dict': {
1582 'id': '2456',
1583 'ext': 'mp4',
1584 'title': 'New experience with Acrobat DC',
1585 'description': 'New experience with Acrobat DC',
1586 'duration': 248.667,
1587 },
1588 },
1589 # BrightcoveInPageEmbed embed
1590 {
1591 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1592 'info_dict': {
1593 'id': '4238694884001',
1594 'ext': 'flv',
1595 'title': 'Tabletop: Dread, Last Thoughts',
1596 'description': 'Tabletop: Dread, Last Thoughts',
1597 'duration': 51690,
1598 },
1599 },
1600 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1601 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1602 {
1603 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1604 'info_dict': {
1605 'id': '4785848093001',
1606 'ext': 'mp4',
1607 'title': 'The Cardinal Pell Interview',
1608 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1609 'uploader': 'GlobeCast Australia - GlobeStream',
1610 'uploader_id': '2733773828001',
1611 'upload_date': '20160304',
1612 'timestamp': 1457083087,
1613 },
1614 'params': {
1615 # m3u8 downloads
1616 'skip_download': True,
1617 },
1618 },
1619 {
1620 # Brightcove embed with whitespace around attribute names
1621 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1622 'info_dict': {
1623 'id': '3167554373001',
1624 'ext': 'mp4',
1625 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1626 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1627 'uploader_id': '1079349493',
1628 'upload_date': '20140207',
1629 'timestamp': 1391810548,
1630 },
1631 'params': {
1632 'skip_download': True,
1633 },
1634 },
1635 # Another form of arte.tv embed
1636 {
1637 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1638 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1639 'info_dict': {
1640 'id': '030273-562_PLUS7-F',
1641 'ext': 'mp4',
1642 'title': 'ARTE Reportage - Nulle part, en France',
1643 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1644 'upload_date': '20160409',
1645 },
1646 },
1647 # Duplicated embedded video URLs
1648 {
1649 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1650 'info_dict': {
1651 'id': '149298443_480_16c25b74_2',
1652 'ext': 'mp4',
1653 'title': 'vs. Blue Orange Spring Game',
1654 'uploader': 'www.hudl.com',
1655 },
1656 },
1657 # twitter:player:stream embed
1658 {
1659 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1660 'info_dict': {
1661 'id': 'master',
1662 'ext': 'mp4',
1663 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1664 'uploader': 'www.rtl.be',
1665 },
1666 'params': {
1667 # m3u8 downloads
1668 'skip_download': True,
1669 },
1670 },
1671 # twitter:player embed
1672 {
1673 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1674 'md5': 'a3e0df96369831de324f0778e126653c',
1675 'info_dict': {
1676 'id': '4909620399001',
1677 'ext': 'mp4',
1678 'title': 'What Do Black Holes Sound Like?',
1679 'description': 'what do black holes sound like',
1680 'upload_date': '20160524',
1681 'uploader_id': '29913724001',
1682 'timestamp': 1464107587,
1683 'uploader': 'TheAtlantic',
1684 },
1685 'add_ie': ['BrightcoveLegacy'],
1686 },
1687 # Facebook <iframe> embed
1688 {
1689 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1690 'md5': 'fbcde74f534176ecb015849146dd3aee',
1691 'info_dict': {
1692 'id': '599637780109885',
1693 'ext': 'mp4',
1694 'title': 'Facebook video #599637780109885',
1695 },
1696 },
1697 # Facebook <iframe> embed, plugin video
1698 {
1699 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1700 'info_dict': {
1701 'id': '1754168231264132',
1702 'ext': 'mp4',
1703 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1704 'uploader': 'Tariq Ramadan (official)',
1705 'timestamp': 1496758379,
1706 'upload_date': '20170606',
1707 },
1708 'params': {
1709 'skip_download': True,
1710 },
1711 },
1712 # Facebook API embed
1713 {
1714 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1715 'md5': 'a47372ee61b39a7b90287094d447d94e',
1716 'info_dict': {
1717 'id': '10153467542406923',
1718 'ext': 'mp4',
1719 'title': 'Facebook video #10153467542406923',
1720 },
1721 },
1722 # Wordpress "YouTube Video Importer" plugin
1723 {
1724 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1725 'md5': 'd16797741b560b485194eddda8121b48',
1726 'info_dict': {
1727 'id': 'HNTXWDXV9Is',
1728 'ext': 'mp4',
1729 'title': 'Blue Devils Drumline Stanford lot 2016',
1730 'upload_date': '20160627',
1731 'uploader_id': 'GENOCIDE8GENERAL10',
1732 'uploader': 'cylus cyrus',
1733 },
1734 },
1735 {
1736 # video stored on custom kaltura server
1737 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1738 'md5': '537617d06e64dfed891fa1593c4b30cc',
1739 'info_dict': {
1740 'id': '0_1iotm5bh',
1741 'ext': 'mp4',
1742 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1743 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1744 'uploader_id': 'videos.expansion@el-mundo.net',
1745 'upload_date': '20150429',
1746 'timestamp': 1430303472,
1747 },
1748 'add_ie': ['Kaltura'],
1749 },
1750 {
1751 # multiple kaltura embeds, nsfw
1752 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1753 'info_dict': {
1754 'id': 'kamila-avec-video-jaime-sadomie',
1755 'title': "Kamila avec vídeo “J'aime sadomie”",
1756 },
1757 'playlist_count': 8,
1758 },
1759 {
1760 # Non-standard Vimeo embed
1761 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1762 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1763 'info_dict': {
1764 'id': '148867247',
1765 'ext': 'mp4',
1766 'title': 'Understanding the web - Teaser',
1767 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1768 'upload_date': '20151214',
1769 'uploader': 'OpenClassrooms',
1770 'uploader_id': 'openclassrooms',
1771 },
1772 'add_ie': ['Vimeo'],
1773 },
1774 {
1775 # generic vimeo embed that requires original URL passed as Referer
1776 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1777 'only_matching': True,
1778 },
1779 {
1780 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1781 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1782 'info_dict': {
1783 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1784 'ext': 'mp4',
1785 'title': 'Big Buck Bunny',
1786 'description': 'Royalty free test video',
1787 'timestamp': 1432816365,
1788 'upload_date': '20150528',
1789 'is_live': False,
1790 },
1791 'params': {
1792 'skip_download': True,
1793 },
1794 'add_ie': [ArkenaIE.ie_key()],
1795 },
1796 {
1797 '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/',
1798 'info_dict': {
1799 'id': '1c7141f46c',
1800 'ext': 'mp4',
1801 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1802 },
1803 'params': {
1804 'skip_download': True,
1805 },
1806 'add_ie': [Vbox7IE.ie_key()],
1807 },
1808 {
1809 # DBTV embeds
1810 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1811 'info_dict': {
1812 'id': '43254897',
1813 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1814 },
1815 'playlist_mincount': 3,
1816 },
1817 {
1818 # Videa embeds
1819 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1820 'info_dict': {
1821 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1822 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1823 },
1824 'playlist_mincount': 2,
1825 },
1826 {
1827 # 20 minuten embed
1828 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1829 'info_dict': {
1830 'id': '523629',
1831 'ext': 'mp4',
1832 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1833 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1834 },
1835 'params': {
1836 'skip_download': True,
1837 },
1838 'add_ie': [TwentyMinutenIE.ie_key()],
1839 },
1840 {
1841 # VideoPress embed
1842 'url': 'https://en.support.wordpress.com/videopress/',
1843 'info_dict': {
1844 'id': 'OcobLTqC',
1845 'ext': 'm4v',
1846 'title': 'IMG_5786',
1847 'timestamp': 1435711927,
1848 'upload_date': '20150701',
1849 },
1850 'params': {
1851 'skip_download': True,
1852 },
1853 'add_ie': [VideoPressIE.ie_key()],
1854 },
1855 {
1856 # Rutube embed
1857 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1858 'info_dict': {
1859 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1860 'ext': 'flv',
1861 'title': 'Магаззино: Казань 2',
1862 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1863 'uploader': 'Магаззино',
1864 'upload_date': '20170228',
1865 'uploader_id': '996642',
1866 },
1867 'params': {
1868 'skip_download': True,
1869 },
1870 'add_ie': [RutubeIE.ie_key()],
1871 },
1872 {
1873 # ThePlatform embedded with whitespaces in URLs
1874 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1875 'only_matching': True,
1876 },
1877 {
1878 # Senate ISVP iframe https
1879 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1880 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1881 'info_dict': {
1882 'id': 'govtaff020316',
1883 'ext': 'mp4',
1884 'title': 'Integrated Senate Video Player',
1885 },
1886 'add_ie': [SenateISVPIE.ie_key()],
1887 },
1888 {
1889 # Limelight embeds (1 channel embed + 4 media embeds)
1890 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1891 'info_dict': {
1892 'id': 'FacilitatorTraining2017',
1893 'title': 'Facilitator Training 2017',
1894 },
1895 'playlist_mincount': 5,
1896 },
1897 {
1898 # Limelight embed (LimelightPlayerUtil.embed)
1899 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1900 'info_dict': {
1901 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1902 'ext': 'mp4',
1903 'title': '07448641',
1904 'timestamp': 1499890639,
1905 'upload_date': '20170712',
1906 },
1907 'params': {
1908 'skip_download': True,
1909 },
1910 'add_ie': ['LimelightMedia'],
1911 },
1912 {
1913 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1914 'info_dict': {
1915 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1916 'title': 'Standoff with Walnut Creek murder suspect ends',
1917 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1918 },
1919 'playlist_mincount': 4,
1920 },
1921 {
1922 # WashingtonPost embed
1923 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1924 'info_dict': {
1925 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1926 'ext': 'mp4',
1927 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1928 '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.',
1929 'timestamp': 1455216756,
1930 'uploader': 'The Washington Post',
1931 'upload_date': '20160211',
1932 },
1933 'add_ie': [WashingtonPostIE.ie_key()],
1934 },
1935 {
1936 # Mediaset embed
1937 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1938 'info_dict': {
1939 'id': '720642',
1940 'ext': 'mp4',
1941 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1942 },
1943 'params': {
1944 'skip_download': True,
1945 },
1946 'add_ie': [MediasetIE.ie_key()],
1947 },
1948 {
1949 # JOJ.sk embeds
1950 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1951 'info_dict': {
1952 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1953 'title': 'Slovenskom sa prehnala vlna silných búrok',
1954 },
1955 'playlist_mincount': 5,
1956 'add_ie': [JojIE.ie_key()],
1957 },
1958 {
1959 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1960 'url': 'https://tvrain.ru/amp/418921/',
1961 'md5': 'cc00413936695987e8de148b67d14f1d',
1962 'info_dict': {
1963 'id': '418921',
1964 'ext': 'mp4',
1965 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1966 },
1967 },
1968 {
1969 # vzaar embed
1970 'url': 'http://help.vzaar.com/article/165-embedding-video',
1971 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1972 'info_dict': {
1973 'id': '8707641',
1974 'ext': 'mp4',
1975 'title': 'Building A Business Online: Principal Chairs Q & A',
1976 },
1977 },
1978 {
1979 # multiple HTML5 videos on one page
1980 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1981 'info_dict': {
1982 'id': 'keyscenarios',
1983 'title': 'Rescue Kit 14 Free Edition - Getting started',
1984 },
1985 'playlist_count': 4,
1986 },
1987 {
1988 # vshare embed
1989 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1990 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1991 'info_dict': {
1992 'id': '0f64ce6',
1993 'title': 'vl14062007715967',
1994 'ext': 'mp4',
1995 }
1996 },
1997 {
1998 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1999 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2000 'info_dict': {
2001 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2002 'ext': 'mp4',
2003 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2004 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2005 'timestamp': 1474354800,
2006 'upload_date': '20160920',
2007 }
2008 },
2009 {
2010 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2011 'info_dict': {
2012 'id': '1731611',
2013 'ext': 'mp4',
2014 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2015 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2016 'timestamp': 1516100691,
2017 'upload_date': '20180116',
2018 },
2019 'params': {
2020 'skip_download': True,
2021 },
2022 'add_ie': [SpringboardPlatformIE.ie_key()],
2023 },
2024 {
2025 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2026 'info_dict': {
2027 'id': 'vMDE4NzI1Mjgt690b',
2028 'ext': 'mp4',
2029 'title': 'Котята',
2030 },
2031 'add_ie': [YapFilesIE.ie_key()],
2032 'params': {
2033 'skip_download': True,
2034 },
2035 },
2036 {
2037 # CloudflareStream embed
2038 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2039 'info_dict': {
2040 'id': '31c9291ab41fac05471db4e73aa11717',
2041 'ext': 'mp4',
2042 'title': '31c9291ab41fac05471db4e73aa11717',
2043 },
2044 'add_ie': [CloudflareStreamIE.ie_key()],
2045 'params': {
2046 'skip_download': True,
2047 },
2048 },
2049 {
2050 # PeerTube embed
2051 'url': 'https://joinpeertube.org/fr/home/',
2052 'info_dict': {
2053 'id': 'home',
2054 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2055 },
2056 'playlist_count': 2,
2057 },
2058 {
2059 # Indavideo embed
2060 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2061 'info_dict': {
2062 'id': '1693903',
2063 'ext': 'mp4',
2064 'title': 'Így kell otthon hamburgert sütni',
2065 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2066 'timestamp': 1426330212,
2067 'upload_date': '20150314',
2068 'uploader': 'StreetKitchen',
2069 'uploader_id': '546363',
2070 },
2071 'add_ie': [IndavideoEmbedIE.ie_key()],
2072 'params': {
2073 'skip_download': True,
2074 },
2075 },
2076 {
2077 # APA embed via JWPlatform embed
2078 'url': 'http://www.vol.at/blue-man-group/5593454',
2079 'info_dict': {
2080 'id': 'jjv85FdZ',
2081 'ext': 'mp4',
2082 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2083 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2084 'thumbnail': r're:^https?://.*\.jpg$',
2085 'duration': 254,
2086 'timestamp': 1519211149,
2087 'upload_date': '20180221',
2088 },
2089 'params': {
2090 'skip_download': True,
2091 },
2092 },
2093 {
2094 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2095 'md5': 'b68d276de422ab07ee1d49388103f457',
2096 'info_dict': {
2097 'id': '83645793',
2098 'title': 'Lock up and get excited',
2099 'ext': 'mp4'
2100 },
2101 'skip': 'TODO: fix nested playlists processing in tests',
2102 },
2103 {
2104 # Viqeo embeds
2105 'url': 'https://viqeo.tv/',
2106 'info_dict': {
2107 'id': 'viqeo',
2108 'title': 'All-new video platform',
2109 },
2110 'playlist_count': 6,
2111 },
2112 {
2113 # Squarespace video embed, 2019-08-28
2114 'url': 'http://ootboxford.com',
2115 'info_dict': {
2116 'id': 'Tc7b_JGdZfw',
2117 'title': 'Out of the Blue, at Childish Things 10',
2118 'ext': 'mp4',
2119 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2120 'uploader_id': 'helendouglashouse',
2121 'uploader': 'Helen & Douglas House',
2122 'upload_date': '20140328',
2123 },
2124 'params': {
2125 'skip_download': True,
2126 },
2127 },
2128 # {
2129 # # Zype embed
2130 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2131 # 'info_dict': {
2132 # 'id': '5b400b834b32992a310622b9',
2133 # 'ext': 'mp4',
2134 # 'title': 'Smoky Barbecue Favorites',
2135 # 'thumbnail': r're:^https?://.*\.jpe?g',
2136 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2137 # 'upload_date': '20170909',
2138 # 'timestamp': 1504915200,
2139 # },
2140 # 'add_ie': [ZypeIE.ie_key()],
2141 # 'params': {
2142 # 'skip_download': True,
2143 # },
2144 # },
2145 {
2146 # videojs embed
2147 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2148 'info_dict': {
2149 'id': 'shell',
2150 'ext': 'mp4',
2151 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2152 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2153 'thumbnail': r're:^https?://.*\.jpg$',
2154 },
2155 'params': {
2156 'skip_download': True,
2157 },
2158 'expected_warnings': ['Failed to download MPD manifest'],
2159 },
2160 {
2161 # DailyMotion embed with DM.player
2162 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2163 'info_dict': {
2164 'id': 'k6aKkGHd9FJs4mtJN39',
2165 'ext': 'mp4',
2166 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2167 'description': 'This video is private.',
2168 'uploader_id': 'x1jf30l',
2169 'uploader': 'beIN SPORTS USA',
2170 'upload_date': '20190528',
2171 'timestamp': 1559062971,
2172 },
2173 'params': {
2174 'skip_download': True,
2175 },
2176 },
2177 {
2178 # blogger embed
2179 'url': 'https://blog.tomeuvizoso.net/2019/01/a-panfrost-milestone.html',
2180 'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
2181 'info_dict': {
2182 'id': 'BLOGGER-video-3c740e3a49197e16-796',
2183 'ext': 'mp4',
2184 'title': 'Blogger',
2185 'thumbnail': r're:^https?://.*',
2186 },
2187 },
2188 # {
2189 # # TODO: find another test
2190 # # http://schema.org/VideoObject
2191 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2192 # 'md5': '888dcf08b7ea671381f00fab74692755',
2193 # 'info_dict': {
2194 # 'id': 'nyvTSJMKId',
2195 # 'ext': 'mp4',
2196 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2197 # 'description': '#love for cats.',
2198 # 'timestamp': 1461244995,
2199 # 'upload_date': '20160421',
2200 # },
2201 # 'params': {
2202 # 'force_generic_extractor': True,
2203 # },
2204 # },
2205 {
2206 # VHX Embed
2207 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2208 'info_dict': {
2209 'id': '858208',
2210 'ext': 'mp4',
2211 'title': 'Untitled',
2212 'uploader_id': 'user80538407',
2213 'uploader': 'OTT Videos',
2214 },
2215 },
2216 {
2217 # ArcPublishing PoWa video player
2218 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2219 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2220 'info_dict': {
2221 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2222 'ext': 'mp4',
2223 'title': 'Senate candidates wave to voters on Anchorage streets',
2224 'description': 'md5:91f51a6511f090617353dc720318b20e',
2225 'timestamp': 1604378735,
2226 'upload_date': '20201103',
2227 'duration': 1581,
2228 },
2229 },
2230 {
2231 # MyChannels SDK embed
2232 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2233 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2234 'md5': '90c0699c37006ef18e198c032d81739c',
2235 'info_dict': {
2236 'id': '194165',
2237 'ext': 'mp4',
2238 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2239 'timestamp': 1611740340,
2240 'upload_date': '20210127',
2241 'duration': 159,
2242 },
2243 },
2244 {
2245 # Simplecast player embed
2246 'url': 'https://www.bio.org/podcast',
2247 'info_dict': {
2248 'id': 'podcast',
2249 'title': 'I AM BIO Podcast | BIO',
2250 },
2251 'playlist_mincount': 52,
2252 },
2253 {
2254 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2255 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2256 'only_matching': True,
2257 }, {
2258 # WimTv embed player
2259 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2260 'info_dict': {
2261 'id': 'wearefmi-pt-2-2021',
2262 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2263 },
2264 'playlist_count': 1,
2265 }, {
2266 # KVS Player
2267 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2268 'info_dict': {
2269 'id': '105',
2270 'display_id': 'kelis-4th-of-july',
2271 'ext': 'mp4',
2272 'title': 'Kelis - 4th Of July',
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://www.kvs-demo.com/embed/105/',
2281 'info_dict': {
2282 'id': '105',
2283 'display_id': 'kelis-4th-of-july',
2284 'ext': 'mp4',
2285 'title': 'Kelis - 4th Of July / Embed Player',
2286 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2287 },
2288 'params': {
2289 'skip_download': True,
2290 },
2291 }, {
2292 # KVS Player
2293 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2294 'md5': '3397979512c682f6b85b3b04989df224',
2295 'info_dict': {
2296 'id': '2400174',
2297 'display_id': 'french-boy-pantsed',
2298 'ext': 'mp4',
2299 'title': 'French Boy Pantsed - ThisVid.com',
2300 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2301 }
2302 }, {
2303 # KVS Player
2304 'url': 'https://thisvid.com/embed/2400174/',
2305 'md5': '3397979512c682f6b85b3b04989df224',
2306 'info_dict': {
2307 'id': '2400174',
2308 'display_id': 'french-boy-pantsed',
2309 'ext': 'mp4',
2310 'title': 'French Boy Pantsed - ThisVid.com',
2311 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2312 }
2313 }, {
2314 # KVS Player
2315 'url': 'https://youix.com/video/leningrad-zoj/',
2316 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2317 'info_dict': {
2318 'id': '18485',
2319 'display_id': 'leningrad-zoj',
2320 'ext': 'mp4',
2321 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2322 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2323 }
2324 }, {
2325 # KVS Player
2326 'url': 'https://youix.com/embed/18485',
2327 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2328 'info_dict': {
2329 'id': '18485',
2330 'display_id': 'leningrad-zoj',
2331 'ext': 'mp4',
2332 'title': 'Ленинград - ЗОЖ',
2333 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2334 }
2335 }, {
2336 # KVS Player
2337 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2338 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2339 'info_dict': {
2340 'id': '21217',
2341 'display_id': '40-nochey-40-nights-2016',
2342 'ext': 'mp4',
2343 'title': '40 ночей (2016) - BogMedia.org',
2344 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2345 }
2346 },
2347 ]
2348
2349 def report_following_redirect(self, new_url):
2350 """Report information extraction."""
2351 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2352
2353 def report_detected(self, name):
2354 self._downloader.write_debug(f'Identified a {name}')
2355
2356 def _extract_rss(self, url, video_id, doc):
2357 playlist_title = doc.find('./channel/title').text
2358 playlist_desc_el = doc.find('./channel/description')
2359 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2360
2361 NS_MAP = {
2362 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2363 }
2364
2365 entries = []
2366 for it in doc.findall('./channel/item'):
2367 next_url = None
2368 enclosure_nodes = it.findall('./enclosure')
2369 for e in enclosure_nodes:
2370 next_url = e.attrib.get('url')
2371 if next_url:
2372 break
2373
2374 if not next_url:
2375 next_url = xpath_text(it, 'link', fatal=False)
2376
2377 if not next_url:
2378 continue
2379
2380 def itunes(key):
2381 return xpath_text(
2382 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2383 default=None)
2384
2385 duration = itunes('duration')
2386 explicit = (itunes('explicit') or '').lower()
2387 if explicit in ('true', 'yes'):
2388 age_limit = 18
2389 elif explicit in ('false', 'no'):
2390 age_limit = 0
2391 else:
2392 age_limit = None
2393
2394 entries.append({
2395 '_type': 'url_transparent',
2396 'url': next_url,
2397 'title': it.find('title').text,
2398 'description': xpath_text(it, 'description', default=None),
2399 'timestamp': unified_timestamp(
2400 xpath_text(it, 'pubDate', default=None)),
2401 'duration': int_or_none(duration) or parse_duration(duration),
2402 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2403 'episode': itunes('title'),
2404 'episode_number': int_or_none(itunes('episode')),
2405 'season_number': int_or_none(itunes('season')),
2406 'age_limit': age_limit,
2407 })
2408
2409 return {
2410 '_type': 'playlist',
2411 'id': url,
2412 'title': playlist_title,
2413 'description': playlist_desc,
2414 'entries': entries,
2415 }
2416
2417 def _extract_camtasia(self, url, video_id, webpage):
2418 """ Returns None if no camtasia video can be found. """
2419
2420 camtasia_cfg = self._search_regex(
2421 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2422 webpage, 'camtasia configuration file', default=None)
2423 if camtasia_cfg is None:
2424 return None
2425
2426 title = self._html_search_meta('DC.title', webpage, fatal=True)
2427
2428 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2429 camtasia_cfg = self._download_xml(
2430 camtasia_url, video_id,
2431 note='Downloading camtasia configuration',
2432 errnote='Failed to download camtasia configuration')
2433 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2434
2435 entries = []
2436 for n in fileset_node.getchildren():
2437 url_n = n.find('./uri')
2438 if url_n is None:
2439 continue
2440
2441 entries.append({
2442 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2443 'title': '%s - %s' % (title, n.tag),
2444 'url': compat_urlparse.urljoin(url, url_n.text),
2445 'duration': float_or_none(n.find('./duration').text),
2446 })
2447
2448 return {
2449 '_type': 'playlist',
2450 'entries': entries,
2451 'title': title,
2452 }
2453
2454 def _kvs_getrealurl(self, video_url, license_code):
2455 if not video_url.startswith('function/0/'):
2456 return video_url # not obfuscated
2457
2458 url_path, _, url_query = video_url.partition('?')
2459 urlparts = url_path.split('/')[2:]
2460 license = self._kvs_getlicensetoken(license_code)
2461 newmagic = urlparts[5][:32]
2462
2463 for o in range(len(newmagic) - 1, -1, -1):
2464 new = ''
2465 l = (o + sum([int(n) for n in license[o:]])) % 32
2466
2467 for i in range(0, len(newmagic)):
2468 if i == o:
2469 new += newmagic[l]
2470 elif i == l:
2471 new += newmagic[o]
2472 else:
2473 new += newmagic[i]
2474 newmagic = new
2475
2476 urlparts[5] = newmagic + urlparts[5][32:]
2477 return '/'.join(urlparts) + '?' + url_query
2478
2479 def _kvs_getlicensetoken(self, license):
2480 modlicense = license.replace('$', '').replace('0', '1')
2481 center = int(len(modlicense) / 2)
2482 fronthalf = int(modlicense[:center + 1])
2483 backhalf = int(modlicense[center:])
2484
2485 modlicense = str(4 * abs(fronthalf - backhalf))
2486 retval = ''
2487 for o in range(0, center + 1):
2488 for i in range(1, 5):
2489 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2490 return retval
2491
2492 def _real_extract(self, url):
2493 if url.startswith('//'):
2494 return self.url_result(self.http_scheme() + url)
2495
2496 parsed_url = compat_urlparse.urlparse(url)
2497 if not parsed_url.scheme:
2498 default_search = self.get_param('default_search')
2499 if default_search is None:
2500 default_search = 'fixup_error'
2501
2502 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2503 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2504 self.report_warning('The url doesn\'t specify the protocol, trying with http')
2505 return self.url_result('http://' + url)
2506 elif default_search != 'fixup_error':
2507 if default_search == 'auto_warning':
2508 if re.match(r'^(?:url|URL)$', url):
2509 raise ExtractorError(
2510 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2511 expected=True)
2512 else:
2513 self.report_warning(
2514 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2515 return self.url_result('ytsearch:' + url)
2516
2517 if default_search in ('error', 'fixup_error'):
2518 raise ExtractorError(
2519 '%r is not a valid URL. '
2520 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
2521 % (url, url), expected=True)
2522 else:
2523 if ':' not in default_search:
2524 default_search += ':'
2525 return self.url_result(default_search + url)
2526
2527 url, smuggled_data = unsmuggle_url(url)
2528 force_videoid = None
2529 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2530 if smuggled_data and 'force_videoid' in smuggled_data:
2531 force_videoid = smuggled_data['force_videoid']
2532 video_id = force_videoid
2533 else:
2534 video_id = self._generic_id(url)
2535
2536 self.to_screen('%s: Requesting header' % video_id)
2537
2538 head_req = HEADRequest(url)
2539 head_response = self._request_webpage(
2540 head_req, video_id,
2541 note=False, errnote='Could not send HEAD request to %s' % url,
2542 fatal=False)
2543
2544 if head_response is not False:
2545 # Check for redirect
2546 new_url = head_response.geturl()
2547 if url != new_url:
2548 self.report_following_redirect(new_url)
2549 if force_videoid:
2550 new_url = smuggle_url(
2551 new_url, {'force_videoid': force_videoid})
2552 return self.url_result(new_url)
2553
2554 full_response = None
2555 if head_response is False:
2556 request = sanitized_Request(url)
2557 request.add_header('Accept-Encoding', '*')
2558 full_response = self._request_webpage(request, video_id)
2559 head_response = full_response
2560
2561 info_dict = {
2562 'id': video_id,
2563 'title': self._generic_title(url),
2564 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2565 }
2566
2567 # Check for direct link to a video
2568 content_type = head_response.headers.get('Content-Type', '').lower()
2569 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2570 if m:
2571 self.report_detected('direct video link')
2572 format_id = compat_str(m.group('format_id'))
2573 subtitles = {}
2574 if format_id.endswith('mpegurl'):
2575 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2576 elif format_id == 'f4m':
2577 formats = self._extract_f4m_formats(url, video_id)
2578 else:
2579 formats = [{
2580 'format_id': format_id,
2581 'url': url,
2582 'vcodec': 'none' if m.group('type') == 'audio' else None
2583 }]
2584 info_dict['direct'] = True
2585 self._sort_formats(formats)
2586 info_dict['formats'] = formats
2587 info_dict['subtitles'] = subtitles
2588 return info_dict
2589
2590 if not self.get_param('test', False) and not is_intentional:
2591 force = self.get_param('force_generic_extractor', False)
2592 self.report_warning(
2593 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2594
2595 if not full_response:
2596 request = sanitized_Request(url)
2597 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2598 # making it impossible to download only chunk of the file (yet we need only 512kB to
2599 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
2600 # that will always result in downloading the whole file that is not desirable.
2601 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2602 # to accept raw bytes and being able to download only a chunk.
2603 # It may probably better to solve this by checking Content-Type for application/octet-stream
2604 # after HEAD request finishes, but not sure if we can rely on this.
2605 request.add_header('Accept-Encoding', '*')
2606 full_response = self._request_webpage(request, video_id)
2607
2608 first_bytes = full_response.read(512)
2609
2610 # Is it an M3U playlist?
2611 if first_bytes.startswith(b'#EXTM3U'):
2612 self.report_detected('M3U playlist')
2613 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2614 self._sort_formats(info_dict['formats'])
2615 return info_dict
2616
2617 # Maybe it's a direct link to a video?
2618 # Be careful not to download the whole thing!
2619 if not is_html(first_bytes):
2620 self.report_warning(
2621 'URL could be a direct video link, returning it as such.')
2622 info_dict.update({
2623 'direct': True,
2624 'url': url,
2625 })
2626 return info_dict
2627
2628 webpage = self._webpage_read_content(
2629 full_response, url, video_id, prefix=first_bytes)
2630
2631 if '<title>DPG Media Privacy Gate</title>' in webpage:
2632 webpage = self._download_webpage(url, video_id)
2633
2634 self.report_extraction(video_id)
2635
2636 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2637 try:
2638 try:
2639 doc = compat_etree_fromstring(webpage)
2640 except compat_xml_parse_error:
2641 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2642 if doc.tag == 'rss':
2643 self.report_detected('RSS feed')
2644 return self._extract_rss(url, video_id, doc)
2645 elif doc.tag == 'SmoothStreamingMedia':
2646 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
2647 self.report_detected('ISM manifest')
2648 self._sort_formats(info_dict['formats'])
2649 return info_dict
2650 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2651 smil = self._parse_smil(doc, url, video_id)
2652 self.report_detected('SMIL file')
2653 self._sort_formats(smil['formats'])
2654 return smil
2655 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2656 self.report_detected('XSPF playlist')
2657 return self.playlist_result(
2658 self._parse_xspf(
2659 doc, video_id, xspf_url=url,
2660 xspf_base_url=full_response.geturl()),
2661 video_id)
2662 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2663 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
2664 doc,
2665 mpd_base_url=full_response.geturl().rpartition('/')[0],
2666 mpd_url=url)
2667 self.report_detected('DASH manifest')
2668 self._sort_formats(info_dict['formats'])
2669 return info_dict
2670 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2671 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2672 self.report_detected('F4M manifest')
2673 self._sort_formats(info_dict['formats'])
2674 return info_dict
2675 except compat_xml_parse_error:
2676 pass
2677
2678 # Is it a Camtasia project?
2679 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2680 if camtasia_res is not None:
2681 self.report_detected('Camtasia video')
2682 return camtasia_res
2683
2684 # Sometimes embedded video player is hidden behind percent encoding
2685 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2686 # Unescaping the whole page allows to handle those cases in a generic way
2687 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2688 # There probably should be a second run of generic extractor on unescaped webpage.
2689 # webpage = compat_urllib_parse_unquote(webpage)
2690
2691 # Unescape squarespace embeds to be detected by generic extractor,
2692 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2693 webpage = re.sub(
2694 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2695 lambda x: unescapeHTML(x.group(0)), webpage)
2696
2697 # it's tempting to parse this further, but you would
2698 # have to take into account all the variations like
2699 # Video Title - Site Name
2700 # Site Name | Video Title
2701 # Video Title - Tagline | Site Name
2702 # and so on and so forth; it's just not practical
2703 video_title = self._og_search_title(
2704 webpage, default=None) or self._html_search_regex(
2705 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2706 default='video')
2707
2708 # Try to detect age limit automatically
2709 age_limit = self._rta_search(webpage)
2710 # And then there are the jokers who advertise that they use RTA,
2711 # but actually don't.
2712 AGE_LIMIT_MARKERS = [
2713 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2714 ]
2715 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2716 age_limit = 18
2717
2718 # video uploader is domain name
2719 video_uploader = self._search_regex(
2720 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2721
2722 video_description = self._og_search_description(webpage, default=None)
2723 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2724
2725 info_dict.update({
2726 'title': video_title,
2727 'description': video_description,
2728 'thumbnail': video_thumbnail,
2729 'age_limit': age_limit,
2730 })
2731
2732 self._downloader.write_debug('Looking for video embeds')
2733
2734 # Look for Brightcove Legacy Studio embeds
2735 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2736 if bc_urls:
2737 entries = [{
2738 '_type': 'url',
2739 'url': smuggle_url(bc_url, {'Referer': url}),
2740 'ie_key': 'BrightcoveLegacy'
2741 } for bc_url in bc_urls]
2742
2743 return {
2744 '_type': 'playlist',
2745 'title': video_title,
2746 'id': video_id,
2747 'entries': entries,
2748 }
2749
2750 # Look for Brightcove New Studio embeds
2751 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2752 if bc_urls:
2753 return self.playlist_from_matches(
2754 bc_urls, video_id, video_title,
2755 getter=lambda x: smuggle_url(x, {'referrer': url}),
2756 ie='BrightcoveNew')
2757
2758 # Look for Nexx embeds
2759 nexx_urls = NexxIE._extract_urls(webpage)
2760 if nexx_urls:
2761 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2762
2763 # Look for Nexx iFrame embeds
2764 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2765 if nexx_embed_urls:
2766 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2767
2768 # Look for ThePlatform embeds
2769 tp_urls = ThePlatformIE._extract_urls(webpage)
2770 if tp_urls:
2771 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2772
2773 arc_urls = ArcPublishingIE._extract_urls(webpage)
2774 if arc_urls:
2775 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2776
2777 mychannels_urls = MedialaanIE._extract_urls(webpage)
2778 if mychannels_urls:
2779 return self.playlist_from_matches(
2780 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2781
2782 # Look for embedded rtl.nl player
2783 matches = re.findall(
2784 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2785 webpage)
2786 if matches:
2787 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2788
2789 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2790 if vimeo_urls:
2791 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2792
2793 vhx_url = VHXEmbedIE._extract_url(webpage)
2794 if vhx_url:
2795 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2796
2797 # Invidious Instances
2798 # https://github.com/yt-dlp/yt-dlp/issues/195
2799 # https://github.com/iv-org/invidious/pull/1730
2800 youtube_url = self._search_regex(
2801 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2802 webpage, 'youtube link', default=None)
2803 if youtube_url:
2804 return self.url_result(youtube_url, YoutubeIE.ie_key())
2805
2806 # Look for YouTube embeds
2807 youtube_urls = YoutubeIE._extract_urls(webpage)
2808 if youtube_urls:
2809 return self.playlist_from_matches(
2810 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2811
2812 matches = DailymotionIE._extract_urls(webpage)
2813 if matches:
2814 return self.playlist_from_matches(matches, video_id, video_title)
2815
2816 # Look for embedded Dailymotion playlist player (#3822)
2817 m = re.search(
2818 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2819 if m:
2820 playlists = re.findall(
2821 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2822 if playlists:
2823 return self.playlist_from_matches(
2824 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2825
2826 # Look for DailyMail embeds
2827 dailymail_urls = DailyMailIE._extract_urls(webpage)
2828 if dailymail_urls:
2829 return self.playlist_from_matches(
2830 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2831
2832 # Look for Teachable embeds, must be before Wistia
2833 teachable_url = TeachableIE._extract_url(webpage, url)
2834 if teachable_url:
2835 return self.url_result(teachable_url)
2836
2837 # Look for embedded Wistia player
2838 wistia_urls = WistiaIE._extract_urls(webpage)
2839 if wistia_urls:
2840 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2841 for entry in playlist['entries']:
2842 entry.update({
2843 '_type': 'url_transparent',
2844 'uploader': video_uploader,
2845 })
2846 return playlist
2847
2848 # Look for SVT player
2849 svt_url = SVTIE._extract_url(webpage)
2850 if svt_url:
2851 return self.url_result(svt_url, 'SVT')
2852
2853 # Look for Bandcamp pages with custom domain
2854 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2855 if mobj is not None:
2856 burl = unescapeHTML(mobj.group(1))
2857 # Don't set the extractor because it can be a track url or an album
2858 return self.url_result(burl)
2859
2860 # Look for embedded Vevo player
2861 mobj = re.search(
2862 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2863 if mobj is not None:
2864 return self.url_result(mobj.group('url'))
2865
2866 # Look for embedded Viddler player
2867 mobj = re.search(
2868 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2869 webpage)
2870 if mobj is not None:
2871 return self.url_result(mobj.group('url'))
2872
2873 # Look for NYTimes player
2874 mobj = re.search(
2875 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2876 webpage)
2877 if mobj is not None:
2878 return self.url_result(mobj.group('url'))
2879
2880 # Look for Libsyn player
2881 mobj = re.search(
2882 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2883 if mobj is not None:
2884 return self.url_result(mobj.group('url'))
2885
2886 # Look for Ooyala videos
2887 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2888 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2889 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2890 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2891 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2892 if mobj is not None:
2893 embed_token = self._search_regex(
2894 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2895 webpage, 'ooyala embed token', default=None)
2896 return OoyalaIE._build_url_result(smuggle_url(
2897 mobj.group('ec'), {
2898 'domain': url,
2899 'embed_token': embed_token,
2900 }))
2901
2902 # Look for multiple Ooyala embeds on SBN network websites
2903 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2904 if mobj is not None:
2905 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2906 if embeds:
2907 return self.playlist_from_matches(
2908 embeds, video_id, video_title,
2909 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2910
2911 # Look for Aparat videos
2912 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2913 if mobj is not None:
2914 return self.url_result(mobj.group(1), 'Aparat')
2915
2916 # Look for MPORA videos
2917 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2918 if mobj is not None:
2919 return self.url_result(mobj.group(1), 'Mpora')
2920
2921 # Look for embedded Facebook player
2922 facebook_urls = FacebookIE._extract_urls(webpage)
2923 if facebook_urls:
2924 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2925
2926 # Look for embedded VK player
2927 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2928 if mobj is not None:
2929 return self.url_result(mobj.group('url'), 'VK')
2930
2931 # Look for embedded Odnoklassniki player
2932 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2933 if odnoklassniki_url:
2934 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2935
2936 # Look for sibnet embedded player
2937 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2938 if sibnet_urls:
2939 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2940
2941 # Look for embedded ivi player
2942 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2943 if mobj is not None:
2944 return self.url_result(mobj.group('url'), 'Ivi')
2945
2946 # Look for embedded Huffington Post player
2947 mobj = re.search(
2948 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2949 if mobj is not None:
2950 return self.url_result(mobj.group('url'), 'HuffPost')
2951
2952 # Look for embed.ly
2953 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2954 if mobj is not None:
2955 return self.url_result(mobj.group('url'))
2956 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2957 if mobj is not None:
2958 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2959
2960 # Look for funnyordie embed
2961 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2962 if matches:
2963 return self.playlist_from_matches(
2964 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2965
2966 # Look for Simplecast embeds
2967 simplecast_urls = SimplecastIE._extract_urls(webpage)
2968 if simplecast_urls:
2969 return self.playlist_from_matches(
2970 simplecast_urls, video_id, video_title)
2971
2972 # Look for BBC iPlayer embed
2973 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2974 if matches:
2975 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2976
2977 # Look for embedded RUTV player
2978 rutv_url = RUTVIE._extract_url(webpage)
2979 if rutv_url:
2980 return self.url_result(rutv_url, 'RUTV')
2981
2982 # Look for embedded TVC player
2983 tvc_url = TVCIE._extract_url(webpage)
2984 if tvc_url:
2985 return self.url_result(tvc_url, 'TVC')
2986
2987 # Look for embedded SportBox player
2988 sportbox_urls = SportBoxIE._extract_urls(webpage)
2989 if sportbox_urls:
2990 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2991
2992 # Look for embedded XHamster player
2993 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2994 if xhamster_urls:
2995 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2996
2997 # Look for embedded TNAFlixNetwork player
2998 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2999 if tnaflix_urls:
3000 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
3001
3002 # Look for embedded PornHub player
3003 pornhub_urls = PornHubIE._extract_urls(webpage)
3004 if pornhub_urls:
3005 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
3006
3007 # Look for embedded DrTuber player
3008 drtuber_urls = DrTuberIE._extract_urls(webpage)
3009 if drtuber_urls:
3010 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
3011
3012 # Look for embedded RedTube player
3013 redtube_urls = RedTubeIE._extract_urls(webpage)
3014 if redtube_urls:
3015 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
3016
3017 # Look for embedded Tube8 player
3018 tube8_urls = Tube8IE._extract_urls(webpage)
3019 if tube8_urls:
3020 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
3021
3022 # Look for embedded Mofosex player
3023 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3024 if mofosex_urls:
3025 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3026
3027 # Look for embedded Spankwire player
3028 spankwire_urls = SpankwireIE._extract_urls(webpage)
3029 if spankwire_urls:
3030 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3031
3032 # Look for embedded YouPorn player
3033 youporn_urls = YouPornIE._extract_urls(webpage)
3034 if youporn_urls:
3035 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3036
3037 # Look for embedded Tvigle player
3038 mobj = re.search(
3039 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3040 if mobj is not None:
3041 return self.url_result(mobj.group('url'), 'Tvigle')
3042
3043 # Look for embedded TED player
3044 mobj = re.search(
3045 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
3046 if mobj is not None:
3047 return self.url_result(mobj.group('url'), 'TED')
3048
3049 # Look for embedded Ustream videos
3050 ustream_url = UstreamIE._extract_url(webpage)
3051 if ustream_url:
3052 return self.url_result(ustream_url, UstreamIE.ie_key())
3053
3054 # Look for embedded arte.tv player
3055 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3056 if arte_urls:
3057 return self.playlist_from_matches(arte_urls, video_id, video_title)
3058
3059 # Look for embedded francetv player
3060 mobj = re.search(
3061 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3062 webpage)
3063 if mobj is not None:
3064 return self.url_result(mobj.group('url'))
3065
3066 # Look for embedded Myvi.ru player
3067 myvi_url = MyviIE._extract_url(webpage)
3068 if myvi_url:
3069 return self.url_result(myvi_url)
3070
3071 # Look for embedded soundcloud player
3072 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3073 if soundcloud_urls:
3074 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3075
3076 # Look for tunein player
3077 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3078 if tunein_urls:
3079 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3080
3081 # Look for embedded mtvservices player
3082 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3083 if mtvservices_url:
3084 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3085
3086 # Look for embedded yahoo player
3087 mobj = re.search(
3088 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3089 webpage)
3090 if mobj is not None:
3091 return self.url_result(mobj.group('url'), 'Yahoo')
3092
3093 # Look for embedded sbs.com.au player
3094 mobj = re.search(
3095 r'''(?x)
3096 (?:
3097 <meta\s+property="og:video"\s+content=|
3098 <iframe[^>]+?src=
3099 )
3100 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3101 webpage)
3102 if mobj is not None:
3103 return self.url_result(mobj.group('url'), 'SBS')
3104
3105 # Look for embedded Cinchcast player
3106 mobj = re.search(
3107 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3108 webpage)
3109 if mobj is not None:
3110 return self.url_result(mobj.group('url'), 'Cinchcast')
3111
3112 mobj = re.search(
3113 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
3114 webpage)
3115 if not mobj:
3116 mobj = re.search(
3117 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3118 webpage)
3119 if mobj is not None:
3120 return self.url_result(mobj.group('url'), 'MLB')
3121
3122 mobj = re.search(
3123 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3124 webpage)
3125 if mobj is not None:
3126 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3127
3128 mobj = re.search(
3129 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
3130 webpage)
3131 if mobj is not None:
3132 return self.url_result(mobj.group('url'), 'Livestream')
3133
3134 # Look for Zapiks embed
3135 mobj = re.search(
3136 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3137 if mobj is not None:
3138 return self.url_result(mobj.group('url'), 'Zapiks')
3139
3140 # Look for Kaltura embeds
3141 kaltura_urls = KalturaIE._extract_urls(webpage)
3142 if kaltura_urls:
3143 return self.playlist_from_matches(
3144 kaltura_urls, video_id, video_title,
3145 getter=lambda x: smuggle_url(x, {'source_url': url}),
3146 ie=KalturaIE.ie_key())
3147
3148 # Look for EaglePlatform embeds
3149 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3150 if eagleplatform_url:
3151 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3152
3153 # Look for ClipYou (uses EaglePlatform) embeds
3154 mobj = re.search(
3155 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3156 if mobj is not None:
3157 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3158
3159 # Look for Pladform embeds
3160 pladform_url = PladformIE._extract_url(webpage)
3161 if pladform_url:
3162 return self.url_result(pladform_url)
3163
3164 # Look for Videomore embeds
3165 videomore_url = VideomoreIE._extract_url(webpage)
3166 if videomore_url:
3167 return self.url_result(videomore_url)
3168
3169 # Look for Webcaster embeds
3170 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3171 if webcaster_url:
3172 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3173
3174 # Look for Playwire embeds
3175 mobj = re.search(
3176 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3177 if mobj is not None:
3178 return self.url_result(mobj.group('url'))
3179
3180 # Look for 5min embeds
3181 mobj = re.search(
3182 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3183 if mobj is not None:
3184 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3185
3186 # Look for Crooks and Liars embeds
3187 mobj = re.search(
3188 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3189 if mobj is not None:
3190 return self.url_result(mobj.group('url'))
3191
3192 # Look for NBC Sports VPlayer embeds
3193 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3194 if nbc_sports_url:
3195 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3196
3197 # Look for NBC News embeds
3198 nbc_news_embed_url = re.search(
3199 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3200 if nbc_news_embed_url:
3201 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3202
3203 # Look for Google Drive embeds
3204 google_drive_url = GoogleDriveIE._extract_url(webpage)
3205 if google_drive_url:
3206 return self.url_result(google_drive_url, 'GoogleDrive')
3207
3208 # Look for UDN embeds
3209 mobj = re.search(
3210 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3211 if mobj is not None:
3212 return self.url_result(
3213 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3214
3215 # Look for Senate ISVP iframe
3216 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3217 if senate_isvp_url:
3218 return self.url_result(senate_isvp_url, 'SenateISVP')
3219
3220 # Look for Kinja embeds
3221 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3222 if kinja_embed_urls:
3223 return self.playlist_from_matches(
3224 kinja_embed_urls, video_id, video_title)
3225
3226 # Look for OnionStudios embeds
3227 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3228 if onionstudios_url:
3229 return self.url_result(onionstudios_url)
3230
3231 # Look for Blogger embeds
3232 blogger_urls = BloggerIE._extract_urls(webpage)
3233 if blogger_urls:
3234 return self.playlist_from_matches(blogger_urls, video_id, video_title, ie=BloggerIE.ie_key())
3235
3236 # Look for ViewLift embeds
3237 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3238 if viewlift_url:
3239 return self.url_result(viewlift_url)
3240
3241 # Look for JWPlatform embeds
3242 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3243 if jwplatform_urls:
3244 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3245
3246 # Look for Digiteka embeds
3247 digiteka_url = DigitekaIE._extract_url(webpage)
3248 if digiteka_url:
3249 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3250
3251 # Look for Arkena embeds
3252 arkena_url = ArkenaIE._extract_url(webpage)
3253 if arkena_url:
3254 return self.url_result(arkena_url, ArkenaIE.ie_key())
3255
3256 # Look for Piksel embeds
3257 piksel_url = PikselIE._extract_url(webpage)
3258 if piksel_url:
3259 return self.url_result(piksel_url, PikselIE.ie_key())
3260
3261 # Look for Limelight embeds
3262 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3263 if limelight_urls:
3264 return self.playlist_result(
3265 limelight_urls, video_id, video_title, video_description)
3266
3267 # Look for Anvato embeds
3268 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3269 if anvato_urls:
3270 return self.playlist_result(
3271 anvato_urls, video_id, video_title, video_description)
3272
3273 # Look for AdobeTVVideo embeds
3274 mobj = re.search(
3275 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3276 webpage)
3277 if mobj is not None:
3278 return self.url_result(
3279 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3280 'AdobeTVVideo')
3281
3282 # Look for Vine embeds
3283 mobj = re.search(
3284 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3285 webpage)
3286 if mobj is not None:
3287 return self.url_result(
3288 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3289
3290 # Look for VODPlatform embeds
3291 mobj = re.search(
3292 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3293 webpage)
3294 if mobj is not None:
3295 return self.url_result(
3296 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3297
3298 # Look for Mangomolo embeds
3299 mobj = re.search(
3300 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3301 (?:
3302 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3303 player\.mangomolo\.com/v1
3304 )/
3305 (?:
3306 video\?.*?\bid=(?P<video_id>\d+)|
3307 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3308 ).+?)\1''', webpage)
3309 if mobj is not None:
3310 info = {
3311 '_type': 'url_transparent',
3312 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3313 'title': video_title,
3314 'description': video_description,
3315 'thumbnail': video_thumbnail,
3316 'uploader': video_uploader,
3317 }
3318 video_id = mobj.group('video_id')
3319 if video_id:
3320 info.update({
3321 'ie_key': 'MangomoloVideo',
3322 'id': video_id,
3323 })
3324 else:
3325 info.update({
3326 'ie_key': 'MangomoloLive',
3327 'id': mobj.group('channel_id'),
3328 })
3329 return info
3330
3331 # Look for Instagram embeds
3332 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3333 if instagram_embed_url is not None:
3334 return self.url_result(
3335 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3336
3337 # Look for 3Q SDN embeds
3338 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3339 if threeqsdn_url:
3340 return {
3341 '_type': 'url_transparent',
3342 'ie_key': ThreeQSDNIE.ie_key(),
3343 'url': self._proto_relative_url(threeqsdn_url),
3344 'title': video_title,
3345 'description': video_description,
3346 'thumbnail': video_thumbnail,
3347 'uploader': video_uploader,
3348 }
3349
3350 # Look for VBOX7 embeds
3351 vbox7_url = Vbox7IE._extract_url(webpage)
3352 if vbox7_url:
3353 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3354
3355 # Look for DBTV embeds
3356 dbtv_urls = DBTVIE._extract_urls(webpage)
3357 if dbtv_urls:
3358 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3359
3360 # Look for Videa embeds
3361 videa_urls = VideaIE._extract_urls(webpage)
3362 if videa_urls:
3363 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3364
3365 # Look for 20 minuten embeds
3366 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3367 if twentymin_urls:
3368 return self.playlist_from_matches(
3369 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3370
3371 # Look for VideoPress embeds
3372 videopress_urls = VideoPressIE._extract_urls(webpage)
3373 if videopress_urls:
3374 return self.playlist_from_matches(
3375 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3376
3377 # Look for Rutube embeds
3378 rutube_urls = RutubeIE._extract_urls(webpage)
3379 if rutube_urls:
3380 return self.playlist_from_matches(
3381 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3382
3383 # Look for WashingtonPost embeds
3384 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3385 if wapo_urls:
3386 return self.playlist_from_matches(
3387 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3388
3389 # Look for Mediaset embeds
3390 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3391 if mediaset_urls:
3392 return self.playlist_from_matches(
3393 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3394
3395 # Look for JOJ.sk embeds
3396 joj_urls = JojIE._extract_urls(webpage)
3397 if joj_urls:
3398 return self.playlist_from_matches(
3399 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3400
3401 # Look for megaphone.fm embeds
3402 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3403 if mpfn_urls:
3404 return self.playlist_from_matches(
3405 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3406
3407 # Look for vzaar embeds
3408 vzaar_urls = VzaarIE._extract_urls(webpage)
3409 if vzaar_urls:
3410 return self.playlist_from_matches(
3411 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3412
3413 channel9_urls = Channel9IE._extract_urls(webpage)
3414 if channel9_urls:
3415 return self.playlist_from_matches(
3416 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3417
3418 vshare_urls = VShareIE._extract_urls(webpage)
3419 if vshare_urls:
3420 return self.playlist_from_matches(
3421 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3422
3423 # Look for Mediasite embeds
3424 mediasite_urls = MediasiteIE._extract_urls(webpage)
3425 if mediasite_urls:
3426 entries = [
3427 self.url_result(smuggle_url(
3428 compat_urlparse.urljoin(url, mediasite_url),
3429 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3430 for mediasite_url in mediasite_urls]
3431 return self.playlist_result(entries, video_id, video_title)
3432
3433 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3434 if springboardplatform_urls:
3435 return self.playlist_from_matches(
3436 springboardplatform_urls, video_id, video_title,
3437 ie=SpringboardPlatformIE.ie_key())
3438
3439 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3440 if yapfiles_urls:
3441 return self.playlist_from_matches(
3442 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3443
3444 vice_urls = ViceIE._extract_urls(webpage)
3445 if vice_urls:
3446 return self.playlist_from_matches(
3447 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3448
3449 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3450 if xfileshare_urls:
3451 return self.playlist_from_matches(
3452 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3453
3454 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3455 if cloudflarestream_urls:
3456 return self.playlist_from_matches(
3457 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3458
3459 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3460 if peertube_urls:
3461 return self.playlist_from_matches(
3462 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3463
3464 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3465 if indavideo_urls:
3466 return self.playlist_from_matches(
3467 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3468
3469 apa_urls = APAIE._extract_urls(webpage)
3470 if apa_urls:
3471 return self.playlist_from_matches(
3472 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3473
3474 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3475 if foxnews_urls:
3476 return self.playlist_from_matches(
3477 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3478
3479 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3480 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3481 webpage)]
3482 if sharevideos_urls:
3483 return self.playlist_from_matches(
3484 sharevideos_urls, video_id, video_title)
3485
3486 viqeo_urls = ViqeoIE._extract_urls(webpage)
3487 if viqeo_urls:
3488 return self.playlist_from_matches(
3489 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3490
3491 expressen_urls = ExpressenIE._extract_urls(webpage)
3492 if expressen_urls:
3493 return self.playlist_from_matches(
3494 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3495
3496 zype_urls = ZypeIE._extract_urls(webpage)
3497 if zype_urls:
3498 return self.playlist_from_matches(
3499 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3500
3501 gedi_urls = GediDigitalIE._extract_urls(webpage)
3502 if gedi_urls:
3503 return self.playlist_from_matches(
3504 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
3505
3506 # Look for RCS media group embeds
3507 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3508 if rcs_urls:
3509 return self.playlist_from_matches(
3510 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3511
3512 wimtv_urls = WimTVIE._extract_urls(webpage)
3513 if wimtv_urls:
3514 return self.playlist_from_matches(
3515 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3516
3517 bitchute_urls = BitChuteIE._extract_urls(webpage)
3518 if bitchute_urls:
3519 return self.playlist_from_matches(
3520 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3521
3522 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3523 if len(rumble_urls) == 1:
3524 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3525 if rumble_urls:
3526 return self.playlist_from_matches(
3527 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3528
3529 tvp_urls = TVPEmbedIE._extract_urls(webpage)
3530 if tvp_urls:
3531 return self.playlist_from_matches(tvp_urls, video_id, video_title, ie=TVPEmbedIE.ie_key())
3532
3533 # Look for HTML5 media
3534 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3535 if entries:
3536 self.report_detected('HTML5 media')
3537 if len(entries) == 1:
3538 entries[0].update({
3539 'id': video_id,
3540 'title': video_title,
3541 })
3542 else:
3543 for num, entry in enumerate(entries, start=1):
3544 entry.update({
3545 'id': '%s-%s' % (video_id, num),
3546 'title': '%s (%d)' % (video_title, num),
3547 })
3548 for entry in entries:
3549 self._sort_formats(entry['formats'])
3550 return self.playlist_result(entries, video_id, video_title)
3551
3552 jwplayer_data = self._find_jwplayer_data(
3553 webpage, video_id, transform_source=js_to_json)
3554 if jwplayer_data:
3555 if isinstance(jwplayer_data.get('playlist'), str):
3556 self.report_detected('JW Player playlist')
3557 return {
3558 **info_dict,
3559 '_type': 'url',
3560 'ie_key': JWPlatformIE.ie_key(),
3561 'url': jwplayer_data['playlist'],
3562 }
3563 try:
3564 info = self._parse_jwplayer_data(
3565 jwplayer_data, video_id, require_title=False, base_url=url)
3566 self.report_detected('JW Player data')
3567 return merge_dicts(info, info_dict)
3568 except ExtractorError:
3569 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3570 pass
3571
3572 # Video.js embed
3573 mobj = re.search(
3574 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3575 webpage)
3576 if mobj is not None:
3577 sources = self._parse_json(
3578 mobj.group(1), video_id, transform_source=js_to_json,
3579 fatal=False) or []
3580 if not isinstance(sources, list):
3581 sources = [sources]
3582 formats = []
3583 subtitles = {}
3584 for source in sources:
3585 src = source.get('src')
3586 if not src or not isinstance(src, compat_str):
3587 continue
3588 src = compat_urlparse.urljoin(url, src)
3589 src_type = source.get('type')
3590 if isinstance(src_type, compat_str):
3591 src_type = src_type.lower()
3592 ext = determine_ext(src).lower()
3593 if src_type == 'video/youtube':
3594 return self.url_result(src, YoutubeIE.ie_key())
3595 if src_type == 'application/dash+xml' or ext == 'mpd':
3596 fmts, subs = self._extract_mpd_formats_and_subtitles(
3597 src, video_id, mpd_id='dash', fatal=False)
3598 formats.extend(fmts)
3599 self._merge_subtitles(subs, target=subtitles)
3600 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3601 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3602 src, video_id, 'mp4', entry_protocol='m3u8_native',
3603 m3u8_id='hls', fatal=False)
3604 formats.extend(fmts)
3605 self._merge_subtitles(subs, target=subtitles)
3606 else:
3607 formats.append({
3608 'url': src,
3609 'ext': (mimetype2ext(src_type)
3610 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3611 'http_headers': {
3612 'Referer': full_response.geturl(),
3613 },
3614 })
3615 if formats or subtitles:
3616 self.report_detected('video.js embed')
3617 self._sort_formats(formats)
3618 info_dict['formats'] = formats
3619 info_dict['subtitles'] = subtitles
3620 return info_dict
3621
3622 # Looking for http://schema.org/VideoObject
3623 json_ld = self._search_json_ld(webpage, video_id, default={})
3624 if json_ld.get('url'):
3625 self.report_detected('JSON LD')
3626 return merge_dicts(json_ld, info_dict)
3627
3628 def check_video(vurl):
3629 if YoutubeIE.suitable(vurl):
3630 return True
3631 if RtmpIE.suitable(vurl):
3632 return True
3633 vpath = compat_urlparse.urlparse(vurl).path
3634 vext = determine_ext(vpath)
3635 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3636
3637 def filter_video(urls):
3638 return list(filter(check_video, urls))
3639
3640 # Start with something easy: JW Player in SWFObject
3641 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3642 if found:
3643 self.report_detected('JW Player in SFWObject')
3644 else:
3645 # Look for gorilla-vid style embedding
3646 found = filter_video(re.findall(r'''(?sx)
3647 (?:
3648 jw_plugins|
3649 JWPlayerOptions|
3650 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3651 )
3652 .*?
3653 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3654 if found:
3655 self.report_detected('JW Player embed')
3656 if not found:
3657 # Look for generic KVS player
3658 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3659 if found:
3660 self.report_detected('KWS Player')
3661 if found.group('maj_ver') not in ['4', '5']:
3662 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3663 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3664 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3665
3666 # extract the part after the last / as the display_id from the
3667 # canonical URL.
3668 display_id = self._search_regex(
3669 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3670 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3671 webpage, 'display_id', fatal=False
3672 )
3673 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3674
3675 thumbnail = flashvars['preview_url']
3676 if thumbnail.startswith('//'):
3677 protocol, _, _ = url.partition('/')
3678 thumbnail = protocol + thumbnail
3679
3680 formats = []
3681 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3682 if key in flashvars and '/get_file/' in flashvars[key]:
3683 next_format = {
3684 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3685 'format_id': flashvars.get(key + '_text', key),
3686 'ext': 'mp4',
3687 }
3688 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3689 if height:
3690 next_format['height'] = int(height.group(1))
3691 else:
3692 next_format['quality'] = 1
3693 formats.append(next_format)
3694 self._sort_formats(formats)
3695
3696 return {
3697 'id': flashvars['video_id'],
3698 'display_id': display_id,
3699 'title': title,
3700 'thumbnail': thumbnail,
3701 'formats': formats,
3702 }
3703 if not found:
3704 # Broaden the search a little bit
3705 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3706 if found:
3707 self.report_detected('video file')
3708 if not found:
3709 # Broaden the findall a little bit: JWPlayer JS loader
3710 found = filter_video(re.findall(
3711 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3712 if found:
3713 self.report_detected('JW Player JS loader')
3714 if not found:
3715 # Flow player
3716 found = filter_video(re.findall(r'''(?xs)
3717 flowplayer\("[^"]+",\s*
3718 \{[^}]+?\}\s*,
3719 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3720 ["']?url["']?\s*:\s*["']([^"']+)["']
3721 ''', webpage))
3722 if found:
3723 self.report_detected('Flow Player')
3724 if not found:
3725 # Cinerama player
3726 found = re.findall(
3727 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3728 if found:
3729 self.report_detected('Cinerama player')
3730 if not found:
3731 # Try to find twitter cards info
3732 # twitter:player:stream should be checked before twitter:player since
3733 # it is expected to contain a raw stream (see
3734 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3735 found = filter_video(re.findall(
3736 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3737 if found:
3738 self.report_detected('Twitter card')
3739 if not found:
3740 # We look for Open Graph info:
3741 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3742 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3743 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3744 if m_video_type is not None:
3745 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3746 if found:
3747 self.report_detected('Open Graph video info')
3748 if not found:
3749 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3750 found = re.search(
3751 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3752 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3753 webpage)
3754 if not found:
3755 # Look also in Refresh HTTP header
3756 refresh_header = head_response.headers.get('Refresh')
3757 if refresh_header:
3758 # In python 2 response HTTP headers are bytestrings
3759 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3760 refresh_header = refresh_header.decode('iso-8859-1')
3761 found = re.search(REDIRECT_REGEX, refresh_header)
3762 if found:
3763 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3764 if new_url != url:
3765 self.report_following_redirect(new_url)
3766 return {
3767 '_type': 'url',
3768 'url': new_url,
3769 }
3770 else:
3771 found = None
3772
3773 if not found:
3774 # twitter:player is a https URL to iframe player that may or may not
3775 # be supported by yt-dlp thus this is checked the very last (see
3776 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3777 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3778 if embed_url and embed_url != url:
3779 self.report_detected('twitter:player iframe')
3780 return self.url_result(embed_url)
3781
3782 if not found:
3783 raise UnsupportedError(url)
3784
3785 entries = []
3786 for video_url in orderedSet(found):
3787 video_url = unescapeHTML(video_url)
3788 video_url = video_url.replace('\\/', '/')
3789 video_url = compat_urlparse.urljoin(url, video_url)
3790 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3791
3792 # Sometimes, jwplayer extraction will result in a YouTube URL
3793 if YoutubeIE.suitable(video_url):
3794 entries.append(self.url_result(video_url, 'Youtube'))
3795 continue
3796
3797 # here's a fun little line of code for you:
3798 video_id = os.path.splitext(video_id)[0]
3799
3800 entry_info_dict = {
3801 'id': video_id,
3802 'uploader': video_uploader,
3803 'title': video_title,
3804 'age_limit': age_limit,
3805 }
3806
3807 if RtmpIE.suitable(video_url):
3808 entry_info_dict.update({
3809 '_type': 'url_transparent',
3810 'ie_key': RtmpIE.ie_key(),
3811 'url': video_url,
3812 })
3813 entries.append(entry_info_dict)
3814 continue
3815
3816 ext = determine_ext(video_url)
3817 if ext == 'smil':
3818 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
3819 elif ext == 'xspf':
3820 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3821 elif ext == 'm3u8':
3822 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
3823 elif ext == 'mpd':
3824 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3825 elif ext == 'f4m':
3826 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3827 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3828 # Just matching .ism/manifest is not enough to be reliably sure
3829 # whether it's actually an ISM manifest or some other streaming
3830 # manifest since there are various streaming URL formats
3831 # possible (see [1]) as well as some other shenanigans like
3832 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3833 # so on.
3834 # Thus the most reasonable way to solve this is to delegate
3835 # to generic extractor in order to look into the contents of
3836 # the manifest itself.
3837 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3838 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3839 entry_info_dict = self.url_result(
3840 smuggle_url(video_url, {'to_generic': True}),
3841 GenericIE.ie_key())
3842 else:
3843 entry_info_dict['url'] = video_url
3844
3845 if entry_info_dict.get('formats'):
3846 self._sort_formats(entry_info_dict['formats'])
3847
3848 entries.append(entry_info_dict)
3849
3850 if len(entries) == 1:
3851 return entries[0]
3852 else:
3853 for num, e in enumerate(entries, start=1):
3854 # 'url' results don't have a title
3855 if e.get('title') is not None:
3856 e['title'] = '%s (%d)' % (e['title'], num)
3857 return {
3858 '_type': 'playlist',
3859 'entries': entries,
3860 }