]> jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/generic.py
Preparing for release
[yt-dlp.git] / youtube_dlc / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 int_or_none,
24 is_html,
25 js_to_json,
26 KNOWN_EXTENSIONS,
27 merge_dicts,
28 mimetype2ext,
29 orderedSet,
30 parse_duration,
31 sanitized_Request,
32 smuggle_url,
33 unescapeHTML,
34 unified_timestamp,
35 unsmuggle_url,
36 UnsupportedError,
37 url_or_none,
38 xpath_attr,
39 xpath_text,
40 xpath_with_ns,
41 )
42 from .commonprotocols import RtmpIE
43 from .brightcove import (
44 BrightcoveLegacyIE,
45 BrightcoveNewIE,
46 )
47 from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50 )
51 from .nbc import NBCSportsVPlayerIE
52 from .ooyala import OoyalaIE
53 from .rutv import RUTVIE
54 from .tvc import TVCIE
55 from .sportbox import SportBoxIE
56 from .myvi import MyviIE
57 from .condenast import CondeNastIE
58 from .udn import UDNEmbedIE
59 from .senateisvp import SenateISVPIE
60 from .svt import SVTIE
61 from .pornhub import PornHubIE
62 from .xhamster import XHamsterEmbedIE
63 from .tnaflix import TNAFlixNetworkEmbedIE
64 from .drtuber import DrTuberIE
65 from .redtube import RedTubeIE
66 from .tube8 import Tube8IE
67 from .mofosex import MofosexEmbedIE
68 from .spankwire import SpankwireIE
69 from .youporn import YouPornIE
70 from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73 )
74 from .dailymotion import DailymotionIE
75 from .dailymail import DailyMailIE
76 from .onionstudios import OnionStudiosIE
77 from .viewlift import ViewLiftEmbedIE
78 from .mtv import MTVServicesEmbeddedIE
79 from .pladform import PladformIE
80 from .videomore import VideomoreIE
81 from .webcaster import WebcasterFeedIE
82 from .googledrive import GoogleDriveIE
83 from .jwplatform import JWPlatformIE
84 from .digiteka import DigitekaIE
85 from .arkena import ArkenaIE
86 from .instagram import InstagramIE
87 from .liveleak import LiveLeakIE
88 from .threeqsdn import ThreeQSDNIE
89 from .theplatform import ThePlatformIE
90 from .kaltura import KalturaIE
91 from .eagleplatform import EaglePlatformIE
92 from .facebook import FacebookIE
93 from .soundcloud import SoundcloudEmbedIE
94 from .tunein import TuneInBaseIE
95 from .vbox7 import Vbox7IE
96 from .dbtv import DBTVIE
97 from .piksel import PikselIE
98 from .videa import VideaIE
99 from .twentymin import TwentyMinutenIE
100 from .ustream import UstreamIE
101 from .arte import ArteTVEmbedIE
102 from .videopress import VideoPressIE
103 from .rutube import RutubeIE
104 from .limelight import LimelightBaseIE
105 from .anvato import AnvatoIE
106 from .washingtonpost import WashingtonPostIE
107 from .wistia import WistiaIE
108 from .mediaset import MediasetIE
109 from .joj import JojIE
110 from .megaphone import MegaphoneIE
111 from .vzaar import VzaarIE
112 from .channel9 import Channel9IE
113 from .vshare import VShareIE
114 from .mediasite import MediasiteIE
115 from .springboardplatform import SpringboardPlatformIE
116 from .yapfiles import YapFilesIE
117 from .vice import ViceIE
118 from .xfileshare import XFileShareIE
119 from .cloudflarestream import CloudflareStreamIE
120 from .peertube import PeerTubeIE
121 from .teachable import TeachableIE
122 from .indavideo import IndavideoEmbedIE
123 from .apa import APAIE
124 from .foxnews import FoxNewsIE
125 from .viqeo import ViqeoIE
126 from .expressen import ExpressenIE
127 from .zype import ZypeIE
128 from .odnoklassniki import OdnoklassnikiIE
129 from .kinja import KinjaEmbedIE
130 from .gedi import GediEmbedsIE
131 from .rcs import RCSEmbedsIE
132 from .bitchute import BitChuteIE
133 from .arcpublishing import ArcPublishingIE
134
135
136 class GenericIE(InfoExtractor):
137 IE_DESC = 'Generic downloader that works on some sites'
138 _VALID_URL = r'.*'
139 IE_NAME = 'generic'
140 _TESTS = [
141 # Direct link to a video
142 {
143 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
144 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
145 'info_dict': {
146 'id': 'trailer',
147 'ext': 'mp4',
148 'title': 'trailer',
149 'upload_date': '20100513',
150 }
151 },
152 # Direct link to media delivered compressed (until Accept-Encoding is *)
153 {
154 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
155 'md5': '128c42e68b13950268b648275386fc74',
156 'info_dict': {
157 'id': 'FictionJunction-Parallel_Hearts',
158 'ext': 'flac',
159 'title': 'FictionJunction-Parallel_Hearts',
160 'upload_date': '20140522',
161 },
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
164 ],
165 'skip': 'URL invalid',
166 },
167 # Direct download with broken HEAD
168 {
169 'url': 'http://ai-radio.org:8000/radio.opus',
170 'info_dict': {
171 'id': 'radio',
172 'ext': 'opus',
173 'title': 'radio',
174 },
175 'params': {
176 'skip_download': True, # infinite live stream
177 },
178 'expected_warnings': [
179 r'501.*Not Implemented',
180 r'400.*Bad Request',
181 ],
182 },
183 # Direct link with incorrect MIME type
184 {
185 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
186 'md5': '4ccbebe5f36706d85221f204d7eb5913',
187 'info_dict': {
188 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
189 'id': '5_Lennart_Poettering_-_Systemd',
190 'ext': 'webm',
191 'title': '5_Lennart_Poettering_-_Systemd',
192 'upload_date': '20141120',
193 },
194 'expected_warnings': [
195 'URL could be a direct video link, returning it as such.'
196 ]
197 },
198 # RSS feed
199 {
200 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
201 'info_dict': {
202 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
203 'title': 'Zero Punctuation',
204 'description': 're:.*groundbreaking video review series.*'
205 },
206 'playlist_mincount': 11,
207 },
208 # RSS feed with enclosure
209 {
210 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
211 'info_dict': {
212 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
213 'title': 'MSNBC Rachel Maddow (video)',
214 'description': 're:.*her unique approach to storytelling.*',
215 },
216 'playlist': [{
217 'info_dict': {
218 'ext': 'mov',
219 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
220 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
221 'description': 're:.*her unique approach to storytelling.*',
222 'upload_date': '20201204',
223 },
224 }],
225 },
226 # RSS feed with item with description and thumbnails
227 {
228 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
229 'info_dict': {
230 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
231 'title': 're:.*100% Hydrogen.*',
232 'description': 're:.*In this episode.*',
233 },
234 'playlist': [{
235 'info_dict': {
236 'ext': 'm4a',
237 'id': 'c1c879525ce2cb640b344507e682c36d',
238 'title': 're:Hydrogen!',
239 'description': 're:.*In this episode we are going.*',
240 'timestamp': 1567977776,
241 'upload_date': '20190908',
242 'duration': 459,
243 'thumbnail': r're:^https?://.*\.jpg$',
244 'episode_number': 1,
245 'season_number': 1,
246 'age_limit': 0,
247 },
248 }],
249 'params': {
250 'skip_download': True,
251 },
252 },
253 # RSS feed with enclosures and unsupported link URLs
254 {
255 'url': 'http://www.hellointernet.fm/podcast?format=rss',
256 'info_dict': {
257 'id': 'http://www.hellointernet.fm/podcast?format=rss',
258 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
259 'title': 'Hello Internet',
260 },
261 'playlist_mincount': 100,
262 },
263 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
264 {
265 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
266 'info_dict': {
267 'id': 'smil',
268 'ext': 'mp4',
269 'title': 'Automatics, robotics and biocybernetics',
270 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
271 'upload_date': '20130627',
272 'formats': 'mincount:16',
273 'subtitles': 'mincount:1',
274 },
275 'params': {
276 'force_generic_extractor': True,
277 'skip_download': True,
278 },
279 },
280 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
281 {
282 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
283 'info_dict': {
284 'id': 'hds',
285 'ext': 'flv',
286 'title': 'hds',
287 'formats': 'mincount:1',
288 },
289 'params': {
290 'skip_download': True,
291 },
292 },
293 # SMIL from https://www.restudy.dk/video/play/id/1637
294 {
295 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
296 'info_dict': {
297 'id': 'video_1637',
298 'ext': 'flv',
299 'title': 'video_1637',
300 'formats': 'mincount:3',
301 },
302 'params': {
303 'skip_download': True,
304 },
305 },
306 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
307 {
308 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
309 'info_dict': {
310 'id': 'smil-service',
311 'ext': 'flv',
312 'title': 'smil-service',
313 'formats': 'mincount:1',
314 },
315 'params': {
316 'skip_download': True,
317 },
318 },
319 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
320 {
321 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
322 'info_dict': {
323 'id': '4719370',
324 'ext': 'mp4',
325 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
326 'formats': 'mincount:3',
327 },
328 'params': {
329 'skip_download': True,
330 },
331 },
332 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
333 {
334 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
335 'info_dict': {
336 'id': 'mZlp2ctYIUEB',
337 'ext': 'mp4',
338 'title': 'Tikibad ontruimd wegens brand',
339 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
340 'thumbnail': r're:^https?://.*\.jpg$',
341 'duration': 33,
342 },
343 'params': {
344 'skip_download': True,
345 },
346 },
347 # MPD from http://dash-mse-test.appspot.com/media.html
348 {
349 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
350 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
351 'info_dict': {
352 'id': 'car-20120827-manifest',
353 'ext': 'mp4',
354 'title': 'car-20120827-manifest',
355 'formats': 'mincount:9',
356 'upload_date': '20130904',
357 },
358 'params': {
359 'format': 'bestvideo',
360 },
361 },
362 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
363 {
364 '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',
365 'info_dict': {
366 'id': 'content',
367 'ext': 'mp4',
368 'title': 'content',
369 'formats': 'mincount:8',
370 },
371 'params': {
372 # m3u8 downloads
373 'skip_download': True,
374 },
375 'skip': 'video gone',
376 },
377 # m3u8 served with Content-Type: text/plain
378 {
379 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
380 'info_dict': {
381 'id': 'index',
382 'ext': 'mp4',
383 'title': 'index',
384 'upload_date': '20140720',
385 'formats': 'mincount:11',
386 },
387 'params': {
388 # m3u8 downloads
389 'skip_download': True,
390 },
391 'skip': 'video gone',
392 },
393 # google redirect
394 {
395 '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',
396 'info_dict': {
397 'id': 'cmQHVoWB5FY',
398 'ext': 'mp4',
399 'upload_date': '20130224',
400 'uploader_id': 'TheVerge',
401 'description': r're:^Chris Ziegler takes a look at the\.*',
402 'uploader': 'The Verge',
403 'title': 'First Firefox OS phones side-by-side',
404 },
405 'params': {
406 'skip_download': False,
407 }
408 },
409 {
410 # redirect in Refresh HTTP header
411 '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',
412 'info_dict': {
413 'id': 'pO8h3EaFRdo',
414 'ext': 'mp4',
415 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
416 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
417 'upload_date': '20150917',
418 'uploader_id': 'brtvofficial',
419 'uploader': 'Boiler Room',
420 },
421 'params': {
422 'skip_download': False,
423 },
424 },
425 {
426 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
427 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
428 'info_dict': {
429 'id': '13601338388002',
430 'ext': 'mp4',
431 'uploader': 'www.hodiho.fr',
432 'title': 'R\u00e9gis plante sa Jeep',
433 }
434 },
435 # bandcamp page with custom domain
436 {
437 'add_ie': ['Bandcamp'],
438 'url': 'http://bronyrock.com/track/the-pony-mash',
439 'info_dict': {
440 'id': '3235767654',
441 'ext': 'mp3',
442 'title': 'The Pony Mash',
443 'uploader': 'M_Pallante',
444 },
445 'skip': 'There is a limit of 200 free downloads / month for the test song',
446 },
447 {
448 # embedded brightcove video
449 # it also tests brightcove videos that need to set the 'Referer'
450 # in the http requests
451 'add_ie': ['BrightcoveLegacy'],
452 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
453 'info_dict': {
454 'id': '2765128793001',
455 'ext': 'mp4',
456 'title': 'Le cours de bourse : l’analyse technique',
457 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
458 'uploader': 'BFM BUSINESS',
459 },
460 'params': {
461 'skip_download': True,
462 },
463 },
464 {
465 # embedded with itemprop embedURL and video id spelled as `idVideo`
466 'add_id': ['BrightcoveLegacy'],
467 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
468 'info_dict': {
469 'id': '5255628253001',
470 'ext': 'mp4',
471 'title': 'md5:37c519b1128915607601e75a87995fc0',
472 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
473 'uploader': 'BFM BUSINESS',
474 'uploader_id': '876450612001',
475 'timestamp': 1482255315,
476 'upload_date': '20161220',
477 },
478 'params': {
479 'skip_download': True,
480 },
481 },
482 {
483 # https://github.com/ytdl-org/youtube-dl/issues/2253
484 'url': 'http://bcove.me/i6nfkrc3',
485 'md5': '0ba9446db037002366bab3b3eb30c88c',
486 'info_dict': {
487 'id': '3101154703001',
488 'ext': 'mp4',
489 'title': 'Still no power',
490 'uploader': 'thestar.com',
491 '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.',
492 },
493 'add_ie': ['BrightcoveLegacy'],
494 'skip': 'video gone',
495 },
496 {
497 'url': 'http://www.championat.com/video/football/v/87/87499.html',
498 'md5': 'fb973ecf6e4a78a67453647444222983',
499 'info_dict': {
500 'id': '3414141473001',
501 'ext': 'mp4',
502 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
503 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
504 'uploader': 'Championat',
505 },
506 },
507 {
508 # https://github.com/ytdl-org/youtube-dl/issues/3541
509 'add_ie': ['BrightcoveLegacy'],
510 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
511 'info_dict': {
512 'id': '3866516442001',
513 'ext': 'mp4',
514 'title': 'Leer mij vrouwen kennen: Aflevering 1',
515 'description': 'Leer mij vrouwen kennen: Aflevering 1',
516 'uploader': 'SBS Broadcasting',
517 },
518 'skip': 'Restricted to Netherlands',
519 'params': {
520 'skip_download': True, # m3u8 download
521 },
522 },
523 {
524 # Brightcove video in <iframe>
525 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
526 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
527 'info_dict': {
528 'id': '5360463607001',
529 'ext': 'mp4',
530 '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',
531 '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。',
532 'uploader': 'United Nations',
533 'uploader_id': '1362235914001',
534 'timestamp': 1489593889,
535 'upload_date': '20170315',
536 },
537 'add_ie': ['BrightcoveLegacy'],
538 },
539 {
540 # Brightcove with alternative playerID key
541 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
542 'info_dict': {
543 'id': 'nmeth.2062_SV1',
544 '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',
545 },
546 'playlist': [{
547 'info_dict': {
548 'id': '2228375078001',
549 'ext': 'mp4',
550 'title': 'nmeth.2062-sv1',
551 'description': 'nmeth.2062-sv1',
552 'timestamp': 1363357591,
553 'upload_date': '20130315',
554 'uploader': 'Nature Publishing Group',
555 'uploader_id': '1964492299001',
556 },
557 }],
558 },
559 {
560 # Brightcove with UUID in videoPlayer
561 'url': 'http://www8.hp.com/cn/zh/home.html',
562 'info_dict': {
563 'id': '5255815316001',
564 'ext': 'mp4',
565 'title': 'Sprocket Video - China',
566 'description': 'Sprocket Video - China',
567 'uploader': 'HP-Video Gallery',
568 'timestamp': 1482263210,
569 'upload_date': '20161220',
570 'uploader_id': '1107601872001',
571 },
572 'params': {
573 'skip_download': True, # m3u8 download
574 },
575 'skip': 'video rotates...weekly?',
576 },
577 {
578 # Brightcove:new type [2].
579 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
580 'md5': '2b35148fcf48da41c9fb4591650784f3',
581 'info_dict': {
582 'id': '5348741021001',
583 'ext': 'mp4',
584 'upload_date': '20170306',
585 'uploader_id': '4191638492001',
586 'timestamp': 1488769918,
587 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
588
589 },
590 },
591 {
592 # Alternative brightcove <video> attributes
593 '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/',
594 'info_dict': {
595 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
596 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
597 },
598 'playlist': [{
599 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
600 'info_dict': {
601 'id': '5311302538001',
602 'ext': 'mp4',
603 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
604 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
605 'timestamp': 1486321708,
606 'upload_date': '20170205',
607 'uploader_id': '800000640001',
608 },
609 'only_matching': True,
610 }],
611 },
612 {
613 # Brightcove with UUID in videoPlayer
614 'url': 'http://www8.hp.com/cn/zh/home.html',
615 'info_dict': {
616 'id': '5255815316001',
617 'ext': 'mp4',
618 'title': 'Sprocket Video - China',
619 'description': 'Sprocket Video - China',
620 'uploader': 'HP-Video Gallery',
621 'timestamp': 1482263210,
622 'upload_date': '20161220',
623 'uploader_id': '1107601872001',
624 },
625 'params': {
626 'skip_download': True, # m3u8 download
627 },
628 },
629 # ooyala video
630 {
631 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
632 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
633 'info_dict': {
634 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
635 'ext': 'mp4',
636 'title': '2cc213299525360.mov', # that's what we get
637 'duration': 238.231,
638 },
639 'add_ie': ['Ooyala'],
640 },
641 {
642 # ooyala video embedded with http://player.ooyala.com/iframe.js
643 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
644 'info_dict': {
645 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
646 'ext': 'mp4',
647 'title': '"Steve Jobs: Man in the Machine" trailer',
648 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
649 'duration': 135.427,
650 },
651 'params': {
652 'skip_download': True,
653 },
654 'skip': 'movie expired',
655 },
656 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
657 {
658 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
659 'info_dict': {
660 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
661 'ext': 'mp4',
662 'title': 'Steampunk Fest Comes to Honesdale',
663 'duration': 43.276,
664 },
665 'params': {
666 'skip_download': True,
667 }
668 },
669 # embed.ly video
670 {
671 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
672 'info_dict': {
673 'id': '9ODmcdjQcHQ',
674 'ext': 'mp4',
675 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
676 'upload_date': '20140225',
677 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
678 'uploader': 'Tested',
679 'uploader_id': 'testedcom',
680 },
681 # No need to test YoutubeIE here
682 'params': {
683 'skip_download': True,
684 },
685 },
686 # funnyordie embed
687 {
688 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
689 'info_dict': {
690 'id': '18e820ec3f',
691 'ext': 'mp4',
692 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
693 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
694 },
695 # HEAD requests lead to endless 301, while GET is OK
696 'expected_warnings': ['301'],
697 },
698 # RUTV embed
699 {
700 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
701 'info_dict': {
702 'id': '776940',
703 'ext': 'mp4',
704 'title': 'Охотское море стало целиком российским',
705 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
706 },
707 'params': {
708 # m3u8 download
709 'skip_download': True,
710 },
711 },
712 # TVC embed
713 {
714 '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/',
715 'info_dict': {
716 'id': '55304',
717 'ext': 'mp4',
718 'title': 'Дошкольное воспитание',
719 },
720 },
721 # SportBox embed
722 {
723 'url': 'http://www.vestifinance.ru/articles/25753',
724 'info_dict': {
725 'id': '25753',
726 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
727 },
728 'playlist': [{
729 'info_dict': {
730 'id': '370908',
731 'title': 'Госзаказ. День 3',
732 'ext': 'mp4',
733 }
734 }, {
735 'info_dict': {
736 'id': '370905',
737 'title': 'Госзаказ. День 2',
738 'ext': 'mp4',
739 }
740 }, {
741 'info_dict': {
742 'id': '370902',
743 'title': 'Госзаказ. День 1',
744 'ext': 'mp4',
745 }
746 }],
747 'params': {
748 # m3u8 download
749 'skip_download': True,
750 },
751 },
752 # Myvi.ru embed
753 {
754 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
755 'info_dict': {
756 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
757 'ext': 'mp4',
758 'title': 'Ужастики, русский трейлер (2015)',
759 'thumbnail': r're:^https?://.*\.jpg$',
760 'duration': 153,
761 }
762 },
763 # XHamster embed
764 {
765 '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',
766 'info_dict': {
767 'id': 'showthread',
768 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
769 },
770 'playlist_mincount': 7,
771 # This forum does not allow <iframe> syntaxes anymore
772 # Now HTML tags are displayed as-is
773 'skip': 'No videos on this page',
774 },
775 # Embedded TED video
776 {
777 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
778 'md5': '65fdff94098e4a607385a60c5177c638',
779 'info_dict': {
780 'id': '1969',
781 'ext': 'mp4',
782 'title': 'Hidden miracles of the natural world',
783 'uploader': 'Louie Schwartzberg',
784 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
785 }
786 },
787 # nowvideo embed hidden behind percent encoding
788 {
789 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
790 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
791 'info_dict': {
792 'id': '06e53103ca9aa',
793 'ext': 'flv',
794 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
795 'description': 'No description',
796 },
797 },
798 # arte embed
799 {
800 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
801 'md5': '7653032cbb25bf6c80d80f217055fa43',
802 'info_dict': {
803 'id': '048195-004_PLUS7-F',
804 'ext': 'flv',
805 'title': 'X:enius',
806 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
807 'upload_date': '20140320',
808 },
809 'params': {
810 'skip_download': 'Requires rtmpdump'
811 },
812 'skip': 'video gone',
813 },
814 # francetv embed
815 {
816 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
817 'info_dict': {
818 'id': 'EV_30231',
819 'ext': 'mp4',
820 'title': 'Alcaline, le concert avec Calogero',
821 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
822 'upload_date': '20150226',
823 'timestamp': 1424989860,
824 'duration': 5400,
825 },
826 'params': {
827 # m3u8 downloads
828 'skip_download': True,
829 },
830 'expected_warnings': [
831 'Forbidden'
832 ]
833 },
834 # Condé Nast embed
835 {
836 'url': 'http://www.wired.com/2014/04/honda-asimo/',
837 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
838 'info_dict': {
839 'id': '53501be369702d3275860000',
840 'ext': 'mp4',
841 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
842 }
843 },
844 # Dailymotion embed
845 {
846 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
847 'md5': '441aeeb82eb72c422c7f14ec533999cd',
848 'info_dict': {
849 'id': 'k2mm4bCdJ6CQ2i7c8o2',
850 'ext': 'mp4',
851 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
852 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
853 'uploader': 'Spi0n',
854 'uploader_id': 'xgditw',
855 'upload_date': '20140425',
856 'timestamp': 1398441542,
857 },
858 'add_ie': ['Dailymotion'],
859 },
860 # DailyMail embed
861 {
862 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
863 'info_dict': {
864 'id': '1495629',
865 'ext': 'mp4',
866 'title': 'Care worker punches elderly dementia patient in head 11 times',
867 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
868 },
869 'add_ie': ['DailyMail'],
870 'params': {
871 'skip_download': True,
872 },
873 },
874 # YouTube embed
875 {
876 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
877 'info_dict': {
878 'id': 'FXRb4ykk4S0',
879 'ext': 'mp4',
880 'title': 'The NBL Auction 2014',
881 'uploader': 'BADMINTON England',
882 'uploader_id': 'BADMINTONEvents',
883 'upload_date': '20140603',
884 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
885 },
886 'add_ie': ['Youtube'],
887 'params': {
888 'skip_download': True,
889 }
890 },
891 # MTVServices embed
892 {
893 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
894 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
895 'info_dict': {
896 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
897 'ext': 'mp4',
898 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
899 'description': 'Two valets share their love for movie star Liam Neesons.',
900 'timestamp': 1349922600,
901 'upload_date': '20121011',
902 },
903 },
904 # YouTube embed via <data-embed-url="">
905 {
906 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
907 'info_dict': {
908 'id': '4vAffPZIT44',
909 'ext': 'mp4',
910 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
911 'uploader': 'Gameloft',
912 'uploader_id': 'gameloft',
913 'upload_date': '20140828',
914 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
915 },
916 'params': {
917 'skip_download': True,
918 }
919 },
920 # YouTube <object> embed
921 {
922 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
923 'md5': '516718101ec834f74318df76259fb3cc',
924 'info_dict': {
925 'id': 'msN87y-iEx0',
926 'ext': 'webm',
927 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
928 'upload_date': '20080526',
929 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
930 'uploader': 'Christopher Sykes',
931 'uploader_id': 'ChristopherJSykes',
932 },
933 'add_ie': ['Youtube'],
934 },
935 # Camtasia studio
936 {
937 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
938 'playlist': [{
939 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
940 'info_dict': {
941 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
942 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
943 'ext': 'flv',
944 'duration': 2235.90,
945 }
946 }, {
947 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
948 'info_dict': {
949 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
950 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
951 'ext': 'flv',
952 'duration': 2235.93,
953 }
954 }],
955 'info_dict': {
956 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
957 }
958 },
959 # Flowplayer
960 {
961 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
962 'md5': '9d65602bf31c6e20014319c7d07fba27',
963 'info_dict': {
964 'id': '5123ea6d5e5a7',
965 'ext': 'mp4',
966 'age_limit': 18,
967 'uploader': 'www.handjobhub.com',
968 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
969 }
970 },
971 # Multiple brightcove videos
972 # https://github.com/ytdl-org/youtube-dl/issues/2283
973 {
974 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
975 'info_dict': {
976 'id': 'always-never',
977 'title': 'Always / Never - The New Yorker',
978 },
979 'playlist_count': 3,
980 'params': {
981 'extract_flat': False,
982 'skip_download': True,
983 }
984 },
985 # MLB embed
986 {
987 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
988 'md5': '96f09a37e44da40dd083e12d9a683327',
989 'info_dict': {
990 'id': '33322633',
991 'ext': 'mp4',
992 'title': 'Ump changes call to ball',
993 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
994 'duration': 48,
995 'timestamp': 1401537900,
996 'upload_date': '20140531',
997 'thumbnail': r're:^https?://.*\.jpg$',
998 },
999 },
1000 # Wistia embed
1001 {
1002 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1003 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1004 'info_dict': {
1005 'id': '6e2wtrbdaf',
1006 'ext': 'mov',
1007 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1008 'description': 'a Paywall Videos video from Remilon',
1009 'duration': 644.072,
1010 'uploader': 'study.com',
1011 'timestamp': 1459678540,
1012 'upload_date': '20160403',
1013 'filesize': 24687186,
1014 },
1015 },
1016 {
1017 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1018 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1019 'info_dict': {
1020 'id': 'uxjb0lwrcz',
1021 'ext': 'mp4',
1022 'title': 'Conversation about Hexagonal Rails Part 1',
1023 'description': 'a Martin Fowler video from ThoughtWorks',
1024 'duration': 1715.0,
1025 'uploader': 'thoughtworks.wistia.com',
1026 'timestamp': 1401832161,
1027 'upload_date': '20140603',
1028 },
1029 },
1030 # Wistia standard embed (async)
1031 {
1032 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1033 'info_dict': {
1034 'id': '807fafadvk',
1035 'ext': 'mp4',
1036 'title': 'Drip Brennan Dunn Workshop',
1037 'description': 'a JV Webinars video from getdrip-1',
1038 'duration': 4986.95,
1039 'timestamp': 1463607249,
1040 'upload_date': '20160518',
1041 },
1042 'params': {
1043 'skip_download': True,
1044 }
1045 },
1046 # Soundcloud embed
1047 {
1048 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1049 'info_dict': {
1050 'id': '174391317',
1051 'ext': 'mp3',
1052 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1053 'uploader': 'Sophos Security',
1054 'title': 'Chet Chat 171 - Oct 29, 2014',
1055 'upload_date': '20141029',
1056 }
1057 },
1058 # Soundcloud multiple embeds
1059 {
1060 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1061 'info_dict': {
1062 'id': '52809',
1063 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1064 },
1065 'playlist_mincount': 7,
1066 },
1067 # TuneIn station embed
1068 {
1069 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1070 'info_dict': {
1071 'id': '204146',
1072 'ext': 'mp3',
1073 'title': 'CNRV',
1074 'location': 'Paris, France',
1075 'is_live': True,
1076 },
1077 'params': {
1078 # Live stream
1079 'skip_download': True,
1080 },
1081 },
1082 # Livestream embed
1083 {
1084 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1085 'info_dict': {
1086 'id': '67864563',
1087 'ext': 'flv',
1088 'upload_date': '20141112',
1089 'title': 'Rosetta #CometLanding webcast HL 10',
1090 }
1091 },
1092 # Another Livestream embed, without 'new.' in URL
1093 {
1094 'url': 'https://www.freespeech.org/',
1095 'info_dict': {
1096 'id': '123537347',
1097 'ext': 'mp4',
1098 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1099 },
1100 'params': {
1101 # Live stream
1102 'skip_download': True,
1103 },
1104 },
1105 # LazyYT
1106 {
1107 'url': 'https://skiplagged.com/',
1108 'info_dict': {
1109 'id': 'skiplagged',
1110 'title': 'Skiplagged: The smart way to find cheap flights',
1111 },
1112 'playlist_mincount': 1,
1113 'add_ie': ['Youtube'],
1114 },
1115 # Cinchcast embed
1116 {
1117 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1118 'info_dict': {
1119 'id': '7141703',
1120 'ext': 'mp3',
1121 'upload_date': '20141126',
1122 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1123 }
1124 },
1125 # Cinerama player
1126 {
1127 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1128 'info_dict': {
1129 'id': '730m_DandD_1901_512k',
1130 'ext': 'mp4',
1131 'uploader': 'www.abc.net.au',
1132 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1133 }
1134 },
1135 # embedded viddler video
1136 {
1137 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1138 'info_dict': {
1139 'id': '4d03aad9',
1140 'ext': 'mp4',
1141 'uploader': 'deadspin',
1142 'title': 'WALL-TO-GORTAT',
1143 'timestamp': 1422285291,
1144 'upload_date': '20150126',
1145 },
1146 'add_ie': ['Viddler'],
1147 },
1148 # Libsyn embed
1149 {
1150 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1151 'info_dict': {
1152 'id': '3377616',
1153 'ext': 'mp3',
1154 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1155 'description': 'md5:601cb790edd05908957dae8aaa866465',
1156 'upload_date': '20150220',
1157 },
1158 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1159 },
1160 # jwplayer YouTube
1161 {
1162 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1163 'info_dict': {
1164 'id': 'Mrj4DVp2zeA',
1165 'ext': 'mp4',
1166 'upload_date': '20150212',
1167 'uploader': 'The National Archives UK',
1168 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1169 'uploader_id': 'NationalArchives08',
1170 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1171 },
1172 },
1173 # jwplayer rtmp
1174 {
1175 'url': 'http://www.suffolk.edu/sjc/live.php',
1176 'info_dict': {
1177 'id': 'live',
1178 'ext': 'flv',
1179 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1180 'uploader': 'www.suffolk.edu',
1181 },
1182 'params': {
1183 'skip_download': True,
1184 },
1185 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1186 },
1187 # Complex jwplayer
1188 {
1189 'url': 'http://www.indiedb.com/games/king-machine/videos',
1190 'info_dict': {
1191 'id': 'videos',
1192 'ext': 'mp4',
1193 'title': 'king machine trailer 1',
1194 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1195 'thumbnail': r're:^https?://.*\.jpg$',
1196 },
1197 },
1198 {
1199 # JWPlayer config passed as variable
1200 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1201 'info_dict': {
1202 'id': '3326530_hq',
1203 'ext': 'mp4',
1204 'title': 'ARIELE | Tube Cup',
1205 'uploader': 'www.txxx.com',
1206 'age_limit': 18,
1207 },
1208 'params': {
1209 'skip_download': True,
1210 }
1211 },
1212 {
1213 # JWPlatform iframe
1214 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1215 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1216 'info_dict': {
1217 'id': 'O0c5JcKT',
1218 'ext': 'mp4',
1219 'upload_date': '20171122',
1220 'timestamp': 1511366290,
1221 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1222 },
1223 'add_ie': [JWPlatformIE.ie_key()],
1224 },
1225 {
1226 # Video.js embed, multiple formats
1227 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1228 'info_dict': {
1229 'id': 'yygqldloqIk',
1230 'ext': 'mp4',
1231 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1232 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1233 'upload_date': '20130314',
1234 'uploader': 'PROстое3D',
1235 'uploader_id': 'PROstoe3D',
1236 },
1237 'params': {
1238 'skip_download': True,
1239 },
1240 },
1241 {
1242 # Video.js embed, single format
1243 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1244 'info_dict': {
1245 'id': 'watch',
1246 'ext': 'mp4',
1247 'title': 'Step 1 - Good Foundation',
1248 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1249 },
1250 'params': {
1251 'skip_download': True,
1252 },
1253 },
1254 # rtl.nl embed
1255 {
1256 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1257 'playlist_mincount': 5,
1258 'info_dict': {
1259 'id': 'aanslagen-kopenhagen',
1260 'title': 'Aanslagen Kopenhagen',
1261 }
1262 },
1263 # Zapiks embed
1264 {
1265 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1266 'info_dict': {
1267 'id': '118046',
1268 'ext': 'mp4',
1269 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1270 }
1271 },
1272 # Kaltura embed (different embed code)
1273 {
1274 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1275 'info_dict': {
1276 'id': '1_a52wc67y',
1277 'ext': 'flv',
1278 'upload_date': '20150127',
1279 'uploader_id': 'PremierMedia',
1280 'timestamp': int,
1281 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1282 },
1283 },
1284 # Kaltura embed with single quotes
1285 {
1286 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1287 'info_dict': {
1288 'id': '0_izeg5utt',
1289 'ext': 'mp4',
1290 'title': '35871',
1291 'timestamp': 1355743100,
1292 'upload_date': '20121217',
1293 'uploader_id': 'cplapp@learn360.com',
1294 },
1295 'add_ie': ['Kaltura'],
1296 },
1297 {
1298 # Kaltura embedded via quoted entry_id
1299 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1300 'info_dict': {
1301 'id': '0_utuok90b',
1302 'ext': 'mp4',
1303 'title': '06_matthew_brender_raj_dutt',
1304 'timestamp': 1466638791,
1305 'upload_date': '20160622',
1306 },
1307 'add_ie': ['Kaltura'],
1308 'expected_warnings': [
1309 'Could not send HEAD request'
1310 ],
1311 'params': {
1312 'skip_download': True,
1313 }
1314 },
1315 {
1316 # Kaltura embedded, some fileExt broken (#11480)
1317 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1318 'info_dict': {
1319 'id': '1_sgtvehim',
1320 'ext': 'mp4',
1321 'title': 'Our "Standard Models" of particle physics and cosmology',
1322 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1323 'timestamp': 1321158993,
1324 'upload_date': '20111113',
1325 'uploader_id': 'kps1',
1326 },
1327 'add_ie': ['Kaltura'],
1328 },
1329 {
1330 # Kaltura iframe embed
1331 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1332 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1333 'info_dict': {
1334 'id': '0_f2cfbpwy',
1335 'ext': 'mp4',
1336 'title': 'I. M. Pei: A Centennial Celebration',
1337 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1338 'upload_date': '20170403',
1339 'uploader_id': 'batchUser',
1340 'timestamp': 1491232186,
1341 },
1342 'add_ie': ['Kaltura'],
1343 },
1344 {
1345 # Kaltura iframe embed, more sophisticated
1346 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1347 'info_dict': {
1348 'id': '1_9gzouybz',
1349 'ext': 'mp4',
1350 'title': 'lecture-05sep2017',
1351 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1352 'upload_date': '20170913',
1353 'uploader_id': 'eps2',
1354 'timestamp': 1505340777,
1355 },
1356 'params': {
1357 'skip_download': True,
1358 },
1359 'add_ie': ['Kaltura'],
1360 },
1361 {
1362 # meta twitter:player
1363 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1364 'info_dict': {
1365 'id': '0_01b42zps',
1366 'ext': 'mp4',
1367 'title': 'Main Twerk (Video)',
1368 'upload_date': '20171208',
1369 'uploader_id': 'sebastian.salinas@thechive.com',
1370 'timestamp': 1512713057,
1371 },
1372 'params': {
1373 'skip_download': True,
1374 },
1375 'add_ie': ['Kaltura'],
1376 },
1377 # referrer protected EaglePlatform embed
1378 {
1379 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1380 'info_dict': {
1381 'id': '582306',
1382 'ext': 'mp4',
1383 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1384 'thumbnail': r're:^https?://.*\.jpg$',
1385 'duration': 3382,
1386 'view_count': int,
1387 },
1388 'params': {
1389 'skip_download': True,
1390 },
1391 },
1392 # ClipYou (EaglePlatform) embed (custom URL)
1393 {
1394 'url': 'http://muz-tv.ru/play/7129/',
1395 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1396 'info_dict': {
1397 'id': '12820',
1398 'ext': 'mp4',
1399 'title': "'O Sole Mio",
1400 'thumbnail': r're:^https?://.*\.jpg$',
1401 'duration': 216,
1402 'view_count': int,
1403 },
1404 'params': {
1405 'skip_download': True,
1406 },
1407 'skip': 'This video is unavailable.',
1408 },
1409 # Pladform embed
1410 {
1411 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1412 'info_dict': {
1413 'id': '100183293',
1414 'ext': 'mp4',
1415 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1416 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1417 'thumbnail': r're:^https?://.*\.jpg$',
1418 'duration': 694,
1419 'age_limit': 0,
1420 },
1421 'skip': 'HTTP Error 404: Not Found',
1422 },
1423 # Playwire embed
1424 {
1425 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1426 'info_dict': {
1427 'id': '3519514',
1428 'ext': 'mp4',
1429 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1430 'thumbnail': r're:^https?://.*\.png$',
1431 'duration': 45.115,
1432 },
1433 },
1434 # 5min embed
1435 {
1436 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1437 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1438 'info_dict': {
1439 'id': '518726732',
1440 'ext': 'mp4',
1441 'title': 'Facebook Creates "On This Day" | Crunch Report',
1442 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1443 'timestamp': 1427237531,
1444 'uploader': 'Crunch Report',
1445 'upload_date': '20150324',
1446 },
1447 'params': {
1448 # m3u8 download
1449 'skip_download': True,
1450 },
1451 },
1452 # Crooks and Liars embed
1453 {
1454 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1455 'info_dict': {
1456 'id': '8RUoRhRi',
1457 'ext': 'mp4',
1458 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1459 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1460 'timestamp': 1428207000,
1461 'upload_date': '20150405',
1462 'uploader': 'Heather',
1463 },
1464 },
1465 # Crooks and Liars external embed
1466 {
1467 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1468 'info_dict': {
1469 'id': 'MTE3MjUtMzQ2MzA',
1470 'ext': 'mp4',
1471 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1472 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1473 'timestamp': 1265032391,
1474 'upload_date': '20100201',
1475 'uploader': 'Heather',
1476 },
1477 },
1478 # NBC Sports vplayer embed
1479 {
1480 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1481 'info_dict': {
1482 'id': 'ln7x1qSThw4k',
1483 'ext': 'flv',
1484 'title': "PFT Live: New leader in the 'new-look' defense",
1485 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1486 'uploader': 'NBCU-SPORTS',
1487 'upload_date': '20140107',
1488 'timestamp': 1389118457,
1489 },
1490 'skip': 'Invalid Page URL',
1491 },
1492 # NBC News embed
1493 {
1494 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1495 'md5': '1aa589c675898ae6d37a17913cf68d66',
1496 'info_dict': {
1497 'id': 'x_dtl_oa_LettermanliftPR_160608',
1498 'ext': 'mp4',
1499 'title': 'David Letterman: A Preview',
1500 '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.',
1501 'upload_date': '20160609',
1502 'timestamp': 1465431544,
1503 'uploader': 'NBCU-NEWS',
1504 },
1505 },
1506 # UDN embed
1507 {
1508 'url': 'https://video.udn.com/news/300346',
1509 'md5': 'fd2060e988c326991037b9aff9df21a6',
1510 'info_dict': {
1511 'id': '300346',
1512 'ext': 'mp4',
1513 'title': '中一中男師變性 全校師生力挺',
1514 'thumbnail': r're:^https?://.*\.jpg$',
1515 },
1516 'params': {
1517 # m3u8 download
1518 'skip_download': True,
1519 },
1520 'expected_warnings': ['Failed to parse JSON Expecting value'],
1521 },
1522 # Brightcove URL in single quotes
1523 {
1524 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1525 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1526 'info_dict': {
1527 'id': '4255764656001',
1528 'ext': 'mp4',
1529 'title': 'SN Presents: Russell Martin, World Citizen',
1530 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1531 'uploader': 'Rogers Sportsnet',
1532 'uploader_id': '1704050871',
1533 'upload_date': '20150525',
1534 'timestamp': 1432570283,
1535 },
1536 },
1537 # Kinja embed
1538 {
1539 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1540 'info_dict': {
1541 'id': '106351',
1542 'ext': 'mp4',
1543 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1544 'description': 'Migrated from OnionStudios',
1545 'thumbnail': r're:^https?://.*\.jpe?g$',
1546 'uploader': 'clickhole',
1547 'upload_date': '20150527',
1548 'timestamp': 1432744860,
1549 }
1550 },
1551 # SnagFilms embed
1552 {
1553 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1554 'info_dict': {
1555 'id': '74849a00-85a9-11e1-9660-123139220831',
1556 'ext': 'mp4',
1557 'title': '#whilewewatch',
1558 }
1559 },
1560 # AdobeTVVideo embed
1561 {
1562 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1563 'md5': '43662b577c018ad707a63766462b1e87',
1564 'info_dict': {
1565 'id': '2456',
1566 'ext': 'mp4',
1567 'title': 'New experience with Acrobat DC',
1568 'description': 'New experience with Acrobat DC',
1569 'duration': 248.667,
1570 },
1571 },
1572 # BrightcoveInPageEmbed embed
1573 {
1574 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1575 'info_dict': {
1576 'id': '4238694884001',
1577 'ext': 'flv',
1578 'title': 'Tabletop: Dread, Last Thoughts',
1579 'description': 'Tabletop: Dread, Last Thoughts',
1580 'duration': 51690,
1581 },
1582 },
1583 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1584 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1585 {
1586 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1587 'info_dict': {
1588 'id': '4785848093001',
1589 'ext': 'mp4',
1590 'title': 'The Cardinal Pell Interview',
1591 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1592 'uploader': 'GlobeCast Australia - GlobeStream',
1593 'uploader_id': '2733773828001',
1594 'upload_date': '20160304',
1595 'timestamp': 1457083087,
1596 },
1597 'params': {
1598 # m3u8 downloads
1599 'skip_download': True,
1600 },
1601 },
1602 {
1603 # Brightcove embed with whitespace around attribute names
1604 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1605 'info_dict': {
1606 'id': '3167554373001',
1607 'ext': 'mp4',
1608 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1609 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1610 'uploader_id': '1079349493',
1611 'upload_date': '20140207',
1612 'timestamp': 1391810548,
1613 },
1614 'params': {
1615 'skip_download': True,
1616 },
1617 },
1618 # Another form of arte.tv embed
1619 {
1620 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1621 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1622 'info_dict': {
1623 'id': '030273-562_PLUS7-F',
1624 'ext': 'mp4',
1625 'title': 'ARTE Reportage - Nulle part, en France',
1626 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1627 'upload_date': '20160409',
1628 },
1629 },
1630 # LiveLeak embed
1631 {
1632 'url': 'http://www.wykop.pl/link/3088787/',
1633 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1634 'info_dict': {
1635 'id': '874_1459135191',
1636 'ext': 'mp4',
1637 'title': 'Man shows poor quality of new apartment building',
1638 'description': 'The wall is like a sand pile.',
1639 'uploader': 'Lake8737',
1640 },
1641 'add_ie': [LiveLeakIE.ie_key()],
1642 },
1643 # Another LiveLeak embed pattern (#13336)
1644 {
1645 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1646 'info_dict': {
1647 'id': '2eb_1496309988',
1648 'ext': 'mp4',
1649 'title': 'Thief robs place where everyone was armed',
1650 'description': 'md5:694d73ee79e535953cf2488562288eee',
1651 'uploader': 'brazilwtf',
1652 },
1653 'add_ie': [LiveLeakIE.ie_key()],
1654 },
1655 # Duplicated embedded video URLs
1656 {
1657 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1658 'info_dict': {
1659 'id': '149298443_480_16c25b74_2',
1660 'ext': 'mp4',
1661 'title': 'vs. Blue Orange Spring Game',
1662 'uploader': 'www.hudl.com',
1663 },
1664 },
1665 # twitter:player:stream embed
1666 {
1667 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1668 'info_dict': {
1669 'id': 'master',
1670 'ext': 'mp4',
1671 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1672 'uploader': 'www.rtl.be',
1673 },
1674 'params': {
1675 # m3u8 downloads
1676 'skip_download': True,
1677 },
1678 },
1679 # twitter:player embed
1680 {
1681 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1682 'md5': 'a3e0df96369831de324f0778e126653c',
1683 'info_dict': {
1684 'id': '4909620399001',
1685 'ext': 'mp4',
1686 'title': 'What Do Black Holes Sound Like?',
1687 'description': 'what do black holes sound like',
1688 'upload_date': '20160524',
1689 'uploader_id': '29913724001',
1690 'timestamp': 1464107587,
1691 'uploader': 'TheAtlantic',
1692 },
1693 'add_ie': ['BrightcoveLegacy'],
1694 },
1695 # Facebook <iframe> embed
1696 {
1697 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1698 'md5': 'fbcde74f534176ecb015849146dd3aee',
1699 'info_dict': {
1700 'id': '599637780109885',
1701 'ext': 'mp4',
1702 'title': 'Facebook video #599637780109885',
1703 },
1704 },
1705 # Facebook <iframe> embed, plugin video
1706 {
1707 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1708 'info_dict': {
1709 'id': '1754168231264132',
1710 'ext': 'mp4',
1711 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1712 'uploader': 'Tariq Ramadan (official)',
1713 'timestamp': 1496758379,
1714 'upload_date': '20170606',
1715 },
1716 'params': {
1717 'skip_download': True,
1718 },
1719 },
1720 # Facebook API embed
1721 {
1722 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1723 'md5': 'a47372ee61b39a7b90287094d447d94e',
1724 'info_dict': {
1725 'id': '10153467542406923',
1726 'ext': 'mp4',
1727 'title': 'Facebook video #10153467542406923',
1728 },
1729 },
1730 # Wordpress "YouTube Video Importer" plugin
1731 {
1732 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1733 'md5': 'd16797741b560b485194eddda8121b48',
1734 'info_dict': {
1735 'id': 'HNTXWDXV9Is',
1736 'ext': 'mp4',
1737 'title': 'Blue Devils Drumline Stanford lot 2016',
1738 'upload_date': '20160627',
1739 'uploader_id': 'GENOCIDE8GENERAL10',
1740 'uploader': 'cylus cyrus',
1741 },
1742 },
1743 {
1744 # video stored on custom kaltura server
1745 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1746 'md5': '537617d06e64dfed891fa1593c4b30cc',
1747 'info_dict': {
1748 'id': '0_1iotm5bh',
1749 'ext': 'mp4',
1750 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1751 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1752 'uploader_id': 'videos.expansion@el-mundo.net',
1753 'upload_date': '20150429',
1754 'timestamp': 1430303472,
1755 },
1756 'add_ie': ['Kaltura'],
1757 },
1758 {
1759 # multiple kaltura embeds, nsfw
1760 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1761 'info_dict': {
1762 'id': 'kamila-avec-video-jaime-sadomie',
1763 'title': "Kamila avec vídeo “J'aime sadomie”",
1764 },
1765 'playlist_count': 8,
1766 },
1767 {
1768 # Non-standard Vimeo embed
1769 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1770 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1771 'info_dict': {
1772 'id': '148867247',
1773 'ext': 'mp4',
1774 'title': 'Understanding the web - Teaser',
1775 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1776 'upload_date': '20151214',
1777 'uploader': 'OpenClassrooms',
1778 'uploader_id': 'openclassrooms',
1779 },
1780 'add_ie': ['Vimeo'],
1781 },
1782 {
1783 # generic vimeo embed that requires original URL passed as Referer
1784 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1785 'only_matching': True,
1786 },
1787 {
1788 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1789 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1790 'info_dict': {
1791 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1792 'ext': 'mp4',
1793 'title': 'Big Buck Bunny',
1794 'description': 'Royalty free test video',
1795 'timestamp': 1432816365,
1796 'upload_date': '20150528',
1797 'is_live': False,
1798 },
1799 'params': {
1800 'skip_download': True,
1801 },
1802 'add_ie': [ArkenaIE.ie_key()],
1803 },
1804 {
1805 '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/',
1806 'info_dict': {
1807 'id': '1c7141f46c',
1808 'ext': 'mp4',
1809 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1810 },
1811 'params': {
1812 'skip_download': True,
1813 },
1814 'add_ie': [Vbox7IE.ie_key()],
1815 },
1816 {
1817 # DBTV embeds
1818 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1819 'info_dict': {
1820 'id': '43254897',
1821 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1822 },
1823 'playlist_mincount': 3,
1824 },
1825 {
1826 # Videa embeds
1827 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1828 'info_dict': {
1829 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1830 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1831 },
1832 'playlist_mincount': 2,
1833 },
1834 {
1835 # 20 minuten embed
1836 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1837 'info_dict': {
1838 'id': '523629',
1839 'ext': 'mp4',
1840 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1841 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1842 },
1843 'params': {
1844 'skip_download': True,
1845 },
1846 'add_ie': [TwentyMinutenIE.ie_key()],
1847 },
1848 {
1849 # VideoPress embed
1850 'url': 'https://en.support.wordpress.com/videopress/',
1851 'info_dict': {
1852 'id': 'OcobLTqC',
1853 'ext': 'm4v',
1854 'title': 'IMG_5786',
1855 'timestamp': 1435711927,
1856 'upload_date': '20150701',
1857 },
1858 'params': {
1859 'skip_download': True,
1860 },
1861 'add_ie': [VideoPressIE.ie_key()],
1862 },
1863 {
1864 # Rutube embed
1865 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1866 'info_dict': {
1867 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1868 'ext': 'flv',
1869 'title': 'Магаззино: Казань 2',
1870 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1871 'uploader': 'Магаззино',
1872 'upload_date': '20170228',
1873 'uploader_id': '996642',
1874 },
1875 'params': {
1876 'skip_download': True,
1877 },
1878 'add_ie': [RutubeIE.ie_key()],
1879 },
1880 {
1881 # ThePlatform embedded with whitespaces in URLs
1882 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1883 'only_matching': True,
1884 },
1885 {
1886 # Senate ISVP iframe https
1887 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1888 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1889 'info_dict': {
1890 'id': 'govtaff020316',
1891 'ext': 'mp4',
1892 'title': 'Integrated Senate Video Player',
1893 },
1894 'add_ie': [SenateISVPIE.ie_key()],
1895 },
1896 {
1897 # Limelight embeds (1 channel embed + 4 media embeds)
1898 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1899 'info_dict': {
1900 'id': 'FacilitatorTraining2017',
1901 'title': 'Facilitator Training 2017',
1902 },
1903 'playlist_mincount': 5,
1904 },
1905 {
1906 # Limelight embed (LimelightPlayerUtil.embed)
1907 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1908 'info_dict': {
1909 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1910 'ext': 'mp4',
1911 'title': '07448641',
1912 'timestamp': 1499890639,
1913 'upload_date': '20170712',
1914 },
1915 'params': {
1916 'skip_download': True,
1917 },
1918 'add_ie': ['LimelightMedia'],
1919 },
1920 {
1921 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1922 'info_dict': {
1923 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1924 'title': 'Standoff with Walnut Creek murder suspect ends',
1925 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1926 },
1927 'playlist_mincount': 4,
1928 },
1929 {
1930 # WashingtonPost embed
1931 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1932 'info_dict': {
1933 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1934 'ext': 'mp4',
1935 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1936 '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.',
1937 'timestamp': 1455216756,
1938 'uploader': 'The Washington Post',
1939 'upload_date': '20160211',
1940 },
1941 'add_ie': [WashingtonPostIE.ie_key()],
1942 },
1943 {
1944 # Mediaset embed
1945 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1946 'info_dict': {
1947 'id': '720642',
1948 'ext': 'mp4',
1949 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1950 },
1951 'params': {
1952 'skip_download': True,
1953 },
1954 'add_ie': [MediasetIE.ie_key()],
1955 },
1956 {
1957 # JOJ.sk embeds
1958 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1959 'info_dict': {
1960 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1961 'title': 'Slovenskom sa prehnala vlna silných búrok',
1962 },
1963 'playlist_mincount': 5,
1964 'add_ie': [JojIE.ie_key()],
1965 },
1966 {
1967 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1968 'url': 'https://tvrain.ru/amp/418921/',
1969 'md5': 'cc00413936695987e8de148b67d14f1d',
1970 'info_dict': {
1971 'id': '418921',
1972 'ext': 'mp4',
1973 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1974 },
1975 },
1976 {
1977 # vzaar embed
1978 'url': 'http://help.vzaar.com/article/165-embedding-video',
1979 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1980 'info_dict': {
1981 'id': '8707641',
1982 'ext': 'mp4',
1983 'title': 'Building A Business Online: Principal Chairs Q & A',
1984 },
1985 },
1986 {
1987 # multiple HTML5 videos on one page
1988 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1989 'info_dict': {
1990 'id': 'keyscenarios',
1991 'title': 'Rescue Kit 14 Free Edition - Getting started',
1992 },
1993 'playlist_count': 4,
1994 },
1995 {
1996 # vshare embed
1997 'url': 'https://youtube-dlc-demo.neocities.org/vshare.html',
1998 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1999 'info_dict': {
2000 'id': '0f64ce6',
2001 'title': 'vl14062007715967',
2002 'ext': 'mp4',
2003 }
2004 },
2005 {
2006 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2007 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2008 'info_dict': {
2009 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2010 'ext': 'mp4',
2011 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2012 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2013 'timestamp': 1474354800,
2014 'upload_date': '20160920',
2015 }
2016 },
2017 {
2018 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2019 'info_dict': {
2020 'id': '1731611',
2021 'ext': 'mp4',
2022 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2023 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2024 'timestamp': 1516100691,
2025 'upload_date': '20180116',
2026 },
2027 'params': {
2028 'skip_download': True,
2029 },
2030 'add_ie': [SpringboardPlatformIE.ie_key()],
2031 },
2032 {
2033 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2034 'info_dict': {
2035 'id': 'vMDE4NzI1Mjgt690b',
2036 'ext': 'mp4',
2037 'title': 'Котята',
2038 },
2039 'add_ie': [YapFilesIE.ie_key()],
2040 'params': {
2041 'skip_download': True,
2042 },
2043 },
2044 {
2045 # CloudflareStream embed
2046 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2047 'info_dict': {
2048 'id': '31c9291ab41fac05471db4e73aa11717',
2049 'ext': 'mp4',
2050 'title': '31c9291ab41fac05471db4e73aa11717',
2051 },
2052 'add_ie': [CloudflareStreamIE.ie_key()],
2053 'params': {
2054 'skip_download': True,
2055 },
2056 },
2057 {
2058 # PeerTube embed
2059 'url': 'https://joinpeertube.org/fr/home/',
2060 'info_dict': {
2061 'id': 'home',
2062 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2063 },
2064 'playlist_count': 2,
2065 },
2066 {
2067 # Indavideo embed
2068 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2069 'info_dict': {
2070 'id': '1693903',
2071 'ext': 'mp4',
2072 'title': 'Így kell otthon hamburgert sütni',
2073 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2074 'timestamp': 1426330212,
2075 'upload_date': '20150314',
2076 'uploader': 'StreetKitchen',
2077 'uploader_id': '546363',
2078 },
2079 'add_ie': [IndavideoEmbedIE.ie_key()],
2080 'params': {
2081 'skip_download': True,
2082 },
2083 },
2084 {
2085 # APA embed via JWPlatform embed
2086 'url': 'http://www.vol.at/blue-man-group/5593454',
2087 'info_dict': {
2088 'id': 'jjv85FdZ',
2089 'ext': 'mp4',
2090 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2091 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2092 'thumbnail': r're:^https?://.*\.jpg$',
2093 'duration': 254,
2094 'timestamp': 1519211149,
2095 'upload_date': '20180221',
2096 },
2097 'params': {
2098 'skip_download': True,
2099 },
2100 },
2101 {
2102 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2103 'md5': 'b68d276de422ab07ee1d49388103f457',
2104 'info_dict': {
2105 'id': '83645793',
2106 'title': 'Lock up and get excited',
2107 'ext': 'mp4'
2108 },
2109 'skip': 'TODO: fix nested playlists processing in tests',
2110 },
2111 {
2112 # Viqeo embeds
2113 'url': 'https://viqeo.tv/',
2114 'info_dict': {
2115 'id': 'viqeo',
2116 'title': 'All-new video platform',
2117 },
2118 'playlist_count': 6,
2119 },
2120 {
2121 # Squarespace video embed, 2019-08-28
2122 'url': 'http://ootboxford.com',
2123 'info_dict': {
2124 'id': 'Tc7b_JGdZfw',
2125 'title': 'Out of the Blue, at Childish Things 10',
2126 'ext': 'mp4',
2127 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2128 'uploader_id': 'helendouglashouse',
2129 'uploader': 'Helen & Douglas House',
2130 'upload_date': '20140328',
2131 },
2132 'params': {
2133 'skip_download': True,
2134 },
2135 },
2136 # {
2137 # # Zype embed
2138 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2139 # 'info_dict': {
2140 # 'id': '5b400b834b32992a310622b9',
2141 # 'ext': 'mp4',
2142 # 'title': 'Smoky Barbecue Favorites',
2143 # 'thumbnail': r're:^https?://.*\.jpe?g',
2144 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2145 # 'upload_date': '20170909',
2146 # 'timestamp': 1504915200,
2147 # },
2148 # 'add_ie': [ZypeIE.ie_key()],
2149 # 'params': {
2150 # 'skip_download': True,
2151 # },
2152 # },
2153 {
2154 # videojs embed
2155 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2156 'info_dict': {
2157 'id': 'shell',
2158 'ext': 'mp4',
2159 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2160 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2161 'thumbnail': r're:^https?://.*\.jpg$',
2162 },
2163 'params': {
2164 'skip_download': True,
2165 },
2166 'expected_warnings': ['Failed to download MPD manifest'],
2167 },
2168 {
2169 # DailyMotion embed with DM.player
2170 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2171 'info_dict': {
2172 'id': 'k6aKkGHd9FJs4mtJN39',
2173 'ext': 'mp4',
2174 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2175 'description': 'This video is private.',
2176 'uploader_id': 'x1jf30l',
2177 'uploader': 'beIN SPORTS USA',
2178 'upload_date': '20190528',
2179 'timestamp': 1559062971,
2180 },
2181 'params': {
2182 'skip_download': True,
2183 },
2184 },
2185 # {
2186 # # TODO: find another test
2187 # # http://schema.org/VideoObject
2188 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2189 # 'md5': '888dcf08b7ea671381f00fab74692755',
2190 # 'info_dict': {
2191 # 'id': 'nyvTSJMKId',
2192 # 'ext': 'mp4',
2193 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2194 # 'description': '#love for cats.',
2195 # 'timestamp': 1461244995,
2196 # 'upload_date': '20160421',
2197 # },
2198 # 'params': {
2199 # 'force_generic_extractor': True,
2200 # },
2201 # },
2202 {
2203 # VHX Embed
2204 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2205 'info_dict': {
2206 'id': '858208',
2207 'ext': 'mp4',
2208 'title': 'Untitled',
2209 'uploader_id': 'user80538407',
2210 'uploader': 'OTT Videos',
2211 },
2212 },
2213 {
2214 # ArcPublishing PoWa video player
2215 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2216 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2217 'info_dict': {
2218 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2219 'ext': 'mp4',
2220 'title': 'Senate candidates wave to voters on Anchorage streets',
2221 'description': 'md5:91f51a6511f090617353dc720318b20e',
2222 'timestamp': 1604378735,
2223 'upload_date': '20201103',
2224 'duration': 1581,
2225 },
2226 },
2227 ]
2228
2229 def report_following_redirect(self, new_url):
2230 """Report information extraction."""
2231 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2232
2233 def _extract_rss(self, url, video_id, doc):
2234 playlist_title = doc.find('./channel/title').text
2235 playlist_desc_el = doc.find('./channel/description')
2236 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2237
2238 NS_MAP = {
2239 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2240 }
2241
2242 entries = []
2243 for it in doc.findall('./channel/item'):
2244 next_url = None
2245 enclosure_nodes = it.findall('./enclosure')
2246 for e in enclosure_nodes:
2247 next_url = e.attrib.get('url')
2248 if next_url:
2249 break
2250
2251 if not next_url:
2252 next_url = xpath_text(it, 'link', fatal=False)
2253
2254 if not next_url:
2255 continue
2256
2257 def itunes(key):
2258 return xpath_text(
2259 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2260 default=None)
2261
2262 duration = itunes('duration')
2263 explicit = (itunes('explicit') or '').lower()
2264 if explicit in ('true', 'yes'):
2265 age_limit = 18
2266 elif explicit in ('false', 'no'):
2267 age_limit = 0
2268 else:
2269 age_limit = None
2270
2271 entries.append({
2272 '_type': 'url_transparent',
2273 'url': next_url,
2274 'title': it.find('title').text,
2275 'description': xpath_text(it, 'description', default=None),
2276 'timestamp': unified_timestamp(
2277 xpath_text(it, 'pubDate', default=None)),
2278 'duration': int_or_none(duration) or parse_duration(duration),
2279 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2280 'episode': itunes('title'),
2281 'episode_number': int_or_none(itunes('episode')),
2282 'season_number': int_or_none(itunes('season')),
2283 'age_limit': age_limit,
2284 })
2285
2286 return {
2287 '_type': 'playlist',
2288 'id': url,
2289 'title': playlist_title,
2290 'description': playlist_desc,
2291 'entries': entries,
2292 }
2293
2294 def _extract_camtasia(self, url, video_id, webpage):
2295 """ Returns None if no camtasia video can be found. """
2296
2297 camtasia_cfg = self._search_regex(
2298 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2299 webpage, 'camtasia configuration file', default=None)
2300 if camtasia_cfg is None:
2301 return None
2302
2303 title = self._html_search_meta('DC.title', webpage, fatal=True)
2304
2305 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2306 camtasia_cfg = self._download_xml(
2307 camtasia_url, video_id,
2308 note='Downloading camtasia configuration',
2309 errnote='Failed to download camtasia configuration')
2310 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2311
2312 entries = []
2313 for n in fileset_node.getchildren():
2314 url_n = n.find('./uri')
2315 if url_n is None:
2316 continue
2317
2318 entries.append({
2319 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2320 'title': '%s - %s' % (title, n.tag),
2321 'url': compat_urlparse.urljoin(url, url_n.text),
2322 'duration': float_or_none(n.find('./duration').text),
2323 })
2324
2325 return {
2326 '_type': 'playlist',
2327 'entries': entries,
2328 'title': title,
2329 }
2330
2331 def _real_extract(self, url):
2332 if url.startswith('//'):
2333 return self.url_result(self.http_scheme() + url)
2334
2335 parsed_url = compat_urlparse.urlparse(url)
2336 if not parsed_url.scheme:
2337 default_search = self._downloader.params.get('default_search')
2338 if default_search is None:
2339 default_search = 'fixup_error'
2340
2341 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2342 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2343 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2344 return self.url_result('http://' + url)
2345 elif default_search != 'fixup_error':
2346 if default_search == 'auto_warning':
2347 if re.match(r'^(?:url|URL)$', url):
2348 raise ExtractorError(
2349 'Invalid URL: %r . Call youtube-dlc like this: youtube-dlc -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2350 expected=True)
2351 else:
2352 self._downloader.report_warning(
2353 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2354 return self.url_result('ytsearch:' + url)
2355
2356 if default_search in ('error', 'fixup_error'):
2357 raise ExtractorError(
2358 '%r is not a valid URL. '
2359 'Set --default-search "ytsearch" (or run youtube-dlc "ytsearch:%s" ) to search YouTube'
2360 % (url, url), expected=True)
2361 else:
2362 if ':' not in default_search:
2363 default_search += ':'
2364 return self.url_result(default_search + url)
2365
2366 url, smuggled_data = unsmuggle_url(url)
2367 force_videoid = None
2368 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2369 if smuggled_data and 'force_videoid' in smuggled_data:
2370 force_videoid = smuggled_data['force_videoid']
2371 video_id = force_videoid
2372 else:
2373 video_id = self._generic_id(url)
2374
2375 self.to_screen('%s: Requesting header' % video_id)
2376
2377 head_req = HEADRequest(url)
2378 head_response = self._request_webpage(
2379 head_req, video_id,
2380 note=False, errnote='Could not send HEAD request to %s' % url,
2381 fatal=False)
2382
2383 if head_response is not False:
2384 # Check for redirect
2385 new_url = head_response.geturl()
2386 if url != new_url:
2387 self.report_following_redirect(new_url)
2388 if force_videoid:
2389 new_url = smuggle_url(
2390 new_url, {'force_videoid': force_videoid})
2391 return self.url_result(new_url)
2392
2393 full_response = None
2394 if head_response is False:
2395 request = sanitized_Request(url)
2396 request.add_header('Accept-Encoding', '*')
2397 full_response = self._request_webpage(request, video_id)
2398 head_response = full_response
2399
2400 info_dict = {
2401 'id': video_id,
2402 'title': self._generic_title(url),
2403 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2404 }
2405
2406 # Check for direct link to a video
2407 content_type = head_response.headers.get('Content-Type', '').lower()
2408 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2409 if m:
2410 format_id = compat_str(m.group('format_id'))
2411 if format_id.endswith('mpegurl'):
2412 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2413 elif format_id == 'f4m':
2414 formats = self._extract_f4m_formats(url, video_id)
2415 else:
2416 formats = [{
2417 'format_id': format_id,
2418 'url': url,
2419 'vcodec': 'none' if m.group('type') == 'audio' else None
2420 }]
2421 info_dict['direct'] = True
2422 self._sort_formats(formats)
2423 info_dict['formats'] = formats
2424 return info_dict
2425
2426 if not self._downloader.params.get('test', False) and not is_intentional:
2427 force = self._downloader.params.get('force_generic_extractor', False)
2428 self._downloader.report_warning(
2429 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2430
2431 if not full_response:
2432 request = sanitized_Request(url)
2433 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2434 # making it impossible to download only chunk of the file (yet we need only 512kB to
2435 # test whether it's HTML or not). According to youtube-dlc default Accept-Encoding
2436 # that will always result in downloading the whole file that is not desirable.
2437 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2438 # to accept raw bytes and being able to download only a chunk.
2439 # It may probably better to solve this by checking Content-Type for application/octet-stream
2440 # after HEAD request finishes, but not sure if we can rely on this.
2441 request.add_header('Accept-Encoding', '*')
2442 full_response = self._request_webpage(request, video_id)
2443
2444 first_bytes = full_response.read(512)
2445
2446 # Is it an M3U playlist?
2447 if first_bytes.startswith(b'#EXTM3U'):
2448 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2449 self._sort_formats(info_dict['formats'])
2450 return info_dict
2451
2452 # Maybe it's a direct link to a video?
2453 # Be careful not to download the whole thing!
2454 if not is_html(first_bytes):
2455 self._downloader.report_warning(
2456 'URL could be a direct video link, returning it as such.')
2457 info_dict.update({
2458 'direct': True,
2459 'url': url,
2460 })
2461 return info_dict
2462
2463 webpage = self._webpage_read_content(
2464 full_response, url, video_id, prefix=first_bytes)
2465
2466 self.report_extraction(video_id)
2467
2468 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2469 try:
2470 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2471 if doc.tag == 'rss':
2472 return self._extract_rss(url, video_id, doc)
2473 elif doc.tag == 'SmoothStreamingMedia':
2474 info_dict['formats'] = self._parse_ism_formats(doc, url)
2475 self._sort_formats(info_dict['formats'])
2476 return info_dict
2477 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2478 smil = self._parse_smil(doc, url, video_id)
2479 self._sort_formats(smil['formats'])
2480 return smil
2481 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2482 return self.playlist_result(
2483 self._parse_xspf(
2484 doc, video_id, xspf_url=url,
2485 xspf_base_url=full_response.geturl()),
2486 video_id)
2487 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2488 info_dict['formats'] = self._parse_mpd_formats(
2489 doc,
2490 mpd_base_url=full_response.geturl().rpartition('/')[0],
2491 mpd_url=url)
2492 self._sort_formats(info_dict['formats'])
2493 return info_dict
2494 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2495 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2496 self._sort_formats(info_dict['formats'])
2497 return info_dict
2498 except compat_xml_parse_error:
2499 pass
2500
2501 # Is it a Camtasia project?
2502 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2503 if camtasia_res is not None:
2504 return camtasia_res
2505
2506 # Sometimes embedded video player is hidden behind percent encoding
2507 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2508 # Unescaping the whole page allows to handle those cases in a generic way
2509 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2510 # There probably should be a second run of generic extractor on unescaped webpage.
2511 # webpage = compat_urllib_parse_unquote(webpage)
2512
2513 # Unescape squarespace embeds to be detected by generic extractor,
2514 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2515 webpage = re.sub(
2516 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2517 lambda x: unescapeHTML(x.group(0)), webpage)
2518
2519 # it's tempting to parse this further, but you would
2520 # have to take into account all the variations like
2521 # Video Title - Site Name
2522 # Site Name | Video Title
2523 # Video Title - Tagline | Site Name
2524 # and so on and so forth; it's just not practical
2525 video_title = self._og_search_title(
2526 webpage, default=None) or self._html_search_regex(
2527 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2528 default='video')
2529
2530 # Try to detect age limit automatically
2531 age_limit = self._rta_search(webpage)
2532 # And then there are the jokers who advertise that they use RTA,
2533 # but actually don't.
2534 AGE_LIMIT_MARKERS = [
2535 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2536 ]
2537 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2538 age_limit = 18
2539
2540 # video uploader is domain name
2541 video_uploader = self._search_regex(
2542 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2543
2544 video_description = self._og_search_description(webpage, default=None)
2545 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2546
2547 info_dict.update({
2548 'title': video_title,
2549 'description': video_description,
2550 'thumbnail': video_thumbnail,
2551 'age_limit': age_limit,
2552 })
2553
2554 # Look for Brightcove Legacy Studio embeds
2555 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2556 if bc_urls:
2557 entries = [{
2558 '_type': 'url',
2559 'url': smuggle_url(bc_url, {'Referer': url}),
2560 'ie_key': 'BrightcoveLegacy'
2561 } for bc_url in bc_urls]
2562
2563 return {
2564 '_type': 'playlist',
2565 'title': video_title,
2566 'id': video_id,
2567 'entries': entries,
2568 }
2569
2570 # Look for Brightcove New Studio embeds
2571 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2572 if bc_urls:
2573 return self.playlist_from_matches(
2574 bc_urls, video_id, video_title,
2575 getter=lambda x: smuggle_url(x, {'referrer': url}),
2576 ie='BrightcoveNew')
2577
2578 # Look for Nexx embeds
2579 nexx_urls = NexxIE._extract_urls(webpage)
2580 if nexx_urls:
2581 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2582
2583 # Look for Nexx iFrame embeds
2584 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2585 if nexx_embed_urls:
2586 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2587
2588 # Look for ThePlatform embeds
2589 tp_urls = ThePlatformIE._extract_urls(webpage)
2590 if tp_urls:
2591 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2592
2593 arc_urls = ArcPublishingIE._extract_urls(webpage)
2594 if arc_urls:
2595 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2596
2597 # Look for embedded rtl.nl player
2598 matches = re.findall(
2599 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2600 webpage)
2601 if matches:
2602 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2603
2604 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2605 if vimeo_urls:
2606 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2607
2608 vhx_url = VHXEmbedIE._extract_url(webpage)
2609 if vhx_url:
2610 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2611
2612 vid_me_embed_url = self._search_regex(
2613 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2614 webpage, 'vid.me embed', default=None)
2615 if vid_me_embed_url is not None:
2616 return self.url_result(vid_me_embed_url, 'Vidme')
2617
2618 # Look for YouTube embeds
2619 youtube_urls = YoutubeIE._extract_urls(webpage)
2620 if youtube_urls:
2621 return self.playlist_from_matches(
2622 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2623
2624 matches = DailymotionIE._extract_urls(webpage)
2625 if matches:
2626 return self.playlist_from_matches(matches, video_id, video_title)
2627
2628 # Look for embedded Dailymotion playlist player (#3822)
2629 m = re.search(
2630 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2631 if m:
2632 playlists = re.findall(
2633 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2634 if playlists:
2635 return self.playlist_from_matches(
2636 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2637
2638 # Look for DailyMail embeds
2639 dailymail_urls = DailyMailIE._extract_urls(webpage)
2640 if dailymail_urls:
2641 return self.playlist_from_matches(
2642 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2643
2644 # Look for Teachable embeds, must be before Wistia
2645 teachable_url = TeachableIE._extract_url(webpage, url)
2646 if teachable_url:
2647 return self.url_result(teachable_url)
2648
2649 # Look for embedded Wistia player
2650 wistia_urls = WistiaIE._extract_urls(webpage)
2651 if wistia_urls:
2652 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2653 for entry in playlist['entries']:
2654 entry.update({
2655 '_type': 'url_transparent',
2656 'uploader': video_uploader,
2657 })
2658 return playlist
2659
2660 # Look for SVT player
2661 svt_url = SVTIE._extract_url(webpage)
2662 if svt_url:
2663 return self.url_result(svt_url, 'SVT')
2664
2665 # Look for Bandcamp pages with custom domain
2666 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2667 if mobj is not None:
2668 burl = unescapeHTML(mobj.group(1))
2669 # Don't set the extractor because it can be a track url or an album
2670 return self.url_result(burl)
2671
2672 # Look for embedded Vevo player
2673 mobj = re.search(
2674 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2675 if mobj is not None:
2676 return self.url_result(mobj.group('url'))
2677
2678 # Look for embedded Viddler player
2679 mobj = re.search(
2680 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2681 webpage)
2682 if mobj is not None:
2683 return self.url_result(mobj.group('url'))
2684
2685 # Look for NYTimes player
2686 mobj = re.search(
2687 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2688 webpage)
2689 if mobj is not None:
2690 return self.url_result(mobj.group('url'))
2691
2692 # Look for Libsyn player
2693 mobj = re.search(
2694 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2695 if mobj is not None:
2696 return self.url_result(mobj.group('url'))
2697
2698 # Look for Ooyala videos
2699 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2700 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2701 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2702 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2703 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2704 if mobj is not None:
2705 embed_token = self._search_regex(
2706 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2707 webpage, 'ooyala embed token', default=None)
2708 return OoyalaIE._build_url_result(smuggle_url(
2709 mobj.group('ec'), {
2710 'domain': url,
2711 'embed_token': embed_token,
2712 }))
2713
2714 # Look for multiple Ooyala embeds on SBN network websites
2715 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2716 if mobj is not None:
2717 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2718 if embeds:
2719 return self.playlist_from_matches(
2720 embeds, video_id, video_title,
2721 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2722
2723 # Look for Aparat videos
2724 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2725 if mobj is not None:
2726 return self.url_result(mobj.group(1), 'Aparat')
2727
2728 # Look for MPORA videos
2729 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2730 if mobj is not None:
2731 return self.url_result(mobj.group(1), 'Mpora')
2732
2733 # Look for embedded Facebook player
2734 facebook_urls = FacebookIE._extract_urls(webpage)
2735 if facebook_urls:
2736 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2737
2738 # Look for embedded VK player
2739 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2740 if mobj is not None:
2741 return self.url_result(mobj.group('url'), 'VK')
2742
2743 # Look for embedded Odnoklassniki player
2744 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2745 if odnoklassniki_url:
2746 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2747
2748 # Look for embedded ivi player
2749 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2750 if mobj is not None:
2751 return self.url_result(mobj.group('url'), 'Ivi')
2752
2753 # Look for embedded Huffington Post player
2754 mobj = re.search(
2755 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2756 if mobj is not None:
2757 return self.url_result(mobj.group('url'), 'HuffPost')
2758
2759 # Look for embed.ly
2760 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2761 if mobj is not None:
2762 return self.url_result(mobj.group('url'))
2763 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2764 if mobj is not None:
2765 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2766
2767 # Look for funnyordie embed
2768 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2769 if matches:
2770 return self.playlist_from_matches(
2771 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2772
2773 # Look for BBC iPlayer embed
2774 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2775 if matches:
2776 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2777
2778 # Look for embedded RUTV player
2779 rutv_url = RUTVIE._extract_url(webpage)
2780 if rutv_url:
2781 return self.url_result(rutv_url, 'RUTV')
2782
2783 # Look for embedded TVC player
2784 tvc_url = TVCIE._extract_url(webpage)
2785 if tvc_url:
2786 return self.url_result(tvc_url, 'TVC')
2787
2788 # Look for embedded SportBox player
2789 sportbox_urls = SportBoxIE._extract_urls(webpage)
2790 if sportbox_urls:
2791 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2792
2793 # Look for embedded XHamster player
2794 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2795 if xhamster_urls:
2796 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2797
2798 # Look for embedded TNAFlixNetwork player
2799 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2800 if tnaflix_urls:
2801 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2802
2803 # Look for embedded PornHub player
2804 pornhub_urls = PornHubIE._extract_urls(webpage)
2805 if pornhub_urls:
2806 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2807
2808 # Look for embedded DrTuber player
2809 drtuber_urls = DrTuberIE._extract_urls(webpage)
2810 if drtuber_urls:
2811 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2812
2813 # Look for embedded RedTube player
2814 redtube_urls = RedTubeIE._extract_urls(webpage)
2815 if redtube_urls:
2816 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2817
2818 # Look for embedded Tube8 player
2819 tube8_urls = Tube8IE._extract_urls(webpage)
2820 if tube8_urls:
2821 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2822
2823 # Look for embedded Mofosex player
2824 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2825 if mofosex_urls:
2826 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2827
2828 # Look for embedded Spankwire player
2829 spankwire_urls = SpankwireIE._extract_urls(webpage)
2830 if spankwire_urls:
2831 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2832
2833 # Look for embedded YouPorn player
2834 youporn_urls = YouPornIE._extract_urls(webpage)
2835 if youporn_urls:
2836 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2837
2838 # Look for embedded Tvigle player
2839 mobj = re.search(
2840 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2841 if mobj is not None:
2842 return self.url_result(mobj.group('url'), 'Tvigle')
2843
2844 # Look for embedded TED player
2845 mobj = re.search(
2846 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2847 if mobj is not None:
2848 return self.url_result(mobj.group('url'), 'TED')
2849
2850 # Look for embedded Ustream videos
2851 ustream_url = UstreamIE._extract_url(webpage)
2852 if ustream_url:
2853 return self.url_result(ustream_url, UstreamIE.ie_key())
2854
2855 # Look for embedded arte.tv player
2856 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2857 if arte_urls:
2858 return self.playlist_from_matches(arte_urls, video_id, video_title)
2859
2860 # Look for embedded francetv player
2861 mobj = re.search(
2862 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2863 webpage)
2864 if mobj is not None:
2865 return self.url_result(mobj.group('url'))
2866
2867 # Look for embedded Myvi.ru player
2868 myvi_url = MyviIE._extract_url(webpage)
2869 if myvi_url:
2870 return self.url_result(myvi_url)
2871
2872 # Look for embedded soundcloud player
2873 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2874 if soundcloud_urls:
2875 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2876
2877 # Look for tunein player
2878 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2879 if tunein_urls:
2880 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2881
2882 # Look for embedded mtvservices player
2883 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2884 if mtvservices_url:
2885 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2886
2887 # Look for embedded yahoo player
2888 mobj = re.search(
2889 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2890 webpage)
2891 if mobj is not None:
2892 return self.url_result(mobj.group('url'), 'Yahoo')
2893
2894 # Look for embedded sbs.com.au player
2895 mobj = re.search(
2896 r'''(?x)
2897 (?:
2898 <meta\s+property="og:video"\s+content=|
2899 <iframe[^>]+?src=
2900 )
2901 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2902 webpage)
2903 if mobj is not None:
2904 return self.url_result(mobj.group('url'), 'SBS')
2905
2906 # Look for embedded Cinchcast player
2907 mobj = re.search(
2908 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2909 webpage)
2910 if mobj is not None:
2911 return self.url_result(mobj.group('url'), 'Cinchcast')
2912
2913 mobj = re.search(
2914 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2915 webpage)
2916 if not mobj:
2917 mobj = re.search(
2918 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2919 webpage)
2920 if mobj is not None:
2921 return self.url_result(mobj.group('url'), 'MLB')
2922
2923 mobj = re.search(
2924 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2925 webpage)
2926 if mobj is not None:
2927 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2928
2929 mobj = re.search(
2930 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2931 webpage)
2932 if mobj is not None:
2933 return self.url_result(mobj.group('url'), 'Livestream')
2934
2935 # Look for Zapiks embed
2936 mobj = re.search(
2937 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2938 if mobj is not None:
2939 return self.url_result(mobj.group('url'), 'Zapiks')
2940
2941 # Look for Kaltura embeds
2942 kaltura_urls = KalturaIE._extract_urls(webpage)
2943 if kaltura_urls:
2944 return self.playlist_from_matches(
2945 kaltura_urls, video_id, video_title,
2946 getter=lambda x: smuggle_url(x, {'source_url': url}),
2947 ie=KalturaIE.ie_key())
2948
2949 # Look for EaglePlatform embeds
2950 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2951 if eagleplatform_url:
2952 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2953
2954 # Look for ClipYou (uses EaglePlatform) embeds
2955 mobj = re.search(
2956 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2957 if mobj is not None:
2958 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2959
2960 # Look for Pladform embeds
2961 pladform_url = PladformIE._extract_url(webpage)
2962 if pladform_url:
2963 return self.url_result(pladform_url)
2964
2965 # Look for Videomore embeds
2966 videomore_url = VideomoreIE._extract_url(webpage)
2967 if videomore_url:
2968 return self.url_result(videomore_url)
2969
2970 # Look for Webcaster embeds
2971 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2972 if webcaster_url:
2973 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2974
2975 # Look for Playwire embeds
2976 mobj = re.search(
2977 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2978 if mobj is not None:
2979 return self.url_result(mobj.group('url'))
2980
2981 # Look for 5min embeds
2982 mobj = re.search(
2983 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2984 if mobj is not None:
2985 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2986
2987 # Look for Crooks and Liars embeds
2988 mobj = re.search(
2989 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2990 if mobj is not None:
2991 return self.url_result(mobj.group('url'))
2992
2993 # Look for NBC Sports VPlayer embeds
2994 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2995 if nbc_sports_url:
2996 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2997
2998 # Look for NBC News embeds
2999 nbc_news_embed_url = re.search(
3000 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3001 if nbc_news_embed_url:
3002 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3003
3004 # Look for Google Drive embeds
3005 google_drive_url = GoogleDriveIE._extract_url(webpage)
3006 if google_drive_url:
3007 return self.url_result(google_drive_url, 'GoogleDrive')
3008
3009 # Look for UDN embeds
3010 mobj = re.search(
3011 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3012 if mobj is not None:
3013 return self.url_result(
3014 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3015
3016 # Look for Senate ISVP iframe
3017 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3018 if senate_isvp_url:
3019 return self.url_result(senate_isvp_url, 'SenateISVP')
3020
3021 # Look for Kinja embeds
3022 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3023 if kinja_embed_urls:
3024 return self.playlist_from_matches(
3025 kinja_embed_urls, video_id, video_title)
3026
3027 # Look for OnionStudios embeds
3028 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3029 if onionstudios_url:
3030 return self.url_result(onionstudios_url)
3031
3032 # Look for ViewLift embeds
3033 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3034 if viewlift_url:
3035 return self.url_result(viewlift_url)
3036
3037 # Look for JWPlatform embeds
3038 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3039 if jwplatform_urls:
3040 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3041
3042 # Look for Digiteka embeds
3043 digiteka_url = DigitekaIE._extract_url(webpage)
3044 if digiteka_url:
3045 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3046
3047 # Look for Arkena embeds
3048 arkena_url = ArkenaIE._extract_url(webpage)
3049 if arkena_url:
3050 return self.url_result(arkena_url, ArkenaIE.ie_key())
3051
3052 # Look for Piksel embeds
3053 piksel_url = PikselIE._extract_url(webpage)
3054 if piksel_url:
3055 return self.url_result(piksel_url, PikselIE.ie_key())
3056
3057 # Look for Limelight embeds
3058 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3059 if limelight_urls:
3060 return self.playlist_result(
3061 limelight_urls, video_id, video_title, video_description)
3062
3063 # Look for Anvato embeds
3064 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3065 if anvato_urls:
3066 return self.playlist_result(
3067 anvato_urls, video_id, video_title, video_description)
3068
3069 # Look for AdobeTVVideo embeds
3070 mobj = re.search(
3071 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3072 webpage)
3073 if mobj is not None:
3074 return self.url_result(
3075 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3076 'AdobeTVVideo')
3077
3078 # Look for Vine embeds
3079 mobj = re.search(
3080 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3081 webpage)
3082 if mobj is not None:
3083 return self.url_result(
3084 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3085
3086 # Look for VODPlatform embeds
3087 mobj = re.search(
3088 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3089 webpage)
3090 if mobj is not None:
3091 return self.url_result(
3092 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3093
3094 # Look for Mangomolo embeds
3095 mobj = re.search(
3096 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3097 (?:
3098 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3099 player\.mangomolo\.com/v1
3100 )/
3101 (?:
3102 video\?.*?\bid=(?P<video_id>\d+)|
3103 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3104 ).+?)\1''', webpage)
3105 if mobj is not None:
3106 info = {
3107 '_type': 'url_transparent',
3108 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3109 'title': video_title,
3110 'description': video_description,
3111 'thumbnail': video_thumbnail,
3112 'uploader': video_uploader,
3113 }
3114 video_id = mobj.group('video_id')
3115 if video_id:
3116 info.update({
3117 'ie_key': 'MangomoloVideo',
3118 'id': video_id,
3119 })
3120 else:
3121 info.update({
3122 'ie_key': 'MangomoloLive',
3123 'id': mobj.group('channel_id'),
3124 })
3125 return info
3126
3127 # Look for Instagram embeds
3128 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3129 if instagram_embed_url is not None:
3130 return self.url_result(
3131 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3132
3133 # Look for LiveLeak embeds
3134 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3135 if liveleak_urls:
3136 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3137
3138 # Look for 3Q SDN embeds
3139 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3140 if threeqsdn_url:
3141 return {
3142 '_type': 'url_transparent',
3143 'ie_key': ThreeQSDNIE.ie_key(),
3144 'url': self._proto_relative_url(threeqsdn_url),
3145 'title': video_title,
3146 'description': video_description,
3147 'thumbnail': video_thumbnail,
3148 'uploader': video_uploader,
3149 }
3150
3151 # Look for VBOX7 embeds
3152 vbox7_url = Vbox7IE._extract_url(webpage)
3153 if vbox7_url:
3154 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3155
3156 # Look for DBTV embeds
3157 dbtv_urls = DBTVIE._extract_urls(webpage)
3158 if dbtv_urls:
3159 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3160
3161 # Look for Videa embeds
3162 videa_urls = VideaIE._extract_urls(webpage)
3163 if videa_urls:
3164 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3165
3166 # Look for 20 minuten embeds
3167 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3168 if twentymin_urls:
3169 return self.playlist_from_matches(
3170 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3171
3172 # Look for VideoPress embeds
3173 videopress_urls = VideoPressIE._extract_urls(webpage)
3174 if videopress_urls:
3175 return self.playlist_from_matches(
3176 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3177
3178 # Look for Rutube embeds
3179 rutube_urls = RutubeIE._extract_urls(webpage)
3180 if rutube_urls:
3181 return self.playlist_from_matches(
3182 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3183
3184 # Look for WashingtonPost embeds
3185 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3186 if wapo_urls:
3187 return self.playlist_from_matches(
3188 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3189
3190 # Look for Mediaset embeds
3191 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3192 if mediaset_urls:
3193 return self.playlist_from_matches(
3194 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3195
3196 # Look for JOJ.sk embeds
3197 joj_urls = JojIE._extract_urls(webpage)
3198 if joj_urls:
3199 return self.playlist_from_matches(
3200 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3201
3202 # Look for megaphone.fm embeds
3203 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3204 if mpfn_urls:
3205 return self.playlist_from_matches(
3206 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3207
3208 # Look for vzaar embeds
3209 vzaar_urls = VzaarIE._extract_urls(webpage)
3210 if vzaar_urls:
3211 return self.playlist_from_matches(
3212 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3213
3214 channel9_urls = Channel9IE._extract_urls(webpage)
3215 if channel9_urls:
3216 return self.playlist_from_matches(
3217 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3218
3219 vshare_urls = VShareIE._extract_urls(webpage)
3220 if vshare_urls:
3221 return self.playlist_from_matches(
3222 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3223
3224 # Look for Mediasite embeds
3225 mediasite_urls = MediasiteIE._extract_urls(webpage)
3226 if mediasite_urls:
3227 entries = [
3228 self.url_result(smuggle_url(
3229 compat_urlparse.urljoin(url, mediasite_url),
3230 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3231 for mediasite_url in mediasite_urls]
3232 return self.playlist_result(entries, video_id, video_title)
3233
3234 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3235 if springboardplatform_urls:
3236 return self.playlist_from_matches(
3237 springboardplatform_urls, video_id, video_title,
3238 ie=SpringboardPlatformIE.ie_key())
3239
3240 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3241 if yapfiles_urls:
3242 return self.playlist_from_matches(
3243 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3244
3245 vice_urls = ViceIE._extract_urls(webpage)
3246 if vice_urls:
3247 return self.playlist_from_matches(
3248 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3249
3250 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3251 if xfileshare_urls:
3252 return self.playlist_from_matches(
3253 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3254
3255 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3256 if cloudflarestream_urls:
3257 return self.playlist_from_matches(
3258 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3259
3260 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3261 if peertube_urls:
3262 return self.playlist_from_matches(
3263 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3264
3265 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3266 if indavideo_urls:
3267 return self.playlist_from_matches(
3268 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3269
3270 apa_urls = APAIE._extract_urls(webpage)
3271 if apa_urls:
3272 return self.playlist_from_matches(
3273 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3274
3275 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3276 if foxnews_urls:
3277 return self.playlist_from_matches(
3278 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3279
3280 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3281 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3282 webpage)]
3283 if sharevideos_urls:
3284 return self.playlist_from_matches(
3285 sharevideos_urls, video_id, video_title)
3286
3287 viqeo_urls = ViqeoIE._extract_urls(webpage)
3288 if viqeo_urls:
3289 return self.playlist_from_matches(
3290 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3291
3292 expressen_urls = ExpressenIE._extract_urls(webpage)
3293 if expressen_urls:
3294 return self.playlist_from_matches(
3295 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3296
3297 zype_urls = ZypeIE._extract_urls(webpage)
3298 if zype_urls:
3299 return self.playlist_from_matches(
3300 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3301
3302 # Look for RCS media group embeds
3303 gedi_urls = GediEmbedsIE._extract_urls(webpage)
3304 if gedi_urls:
3305 return self.playlist_from_matches(
3306 gedi_urls, video_id, video_title, ie=GediEmbedsIE.ie_key())
3307
3308 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3309 if rcs_urls:
3310 return self.playlist_from_matches(
3311 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3312
3313 bitchute_urls = BitChuteIE._extract_urls(webpage)
3314 if bitchute_urls:
3315 return self.playlist_from_matches(
3316 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3317
3318 # Look for HTML5 media
3319 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3320 if entries:
3321 if len(entries) == 1:
3322 entries[0].update({
3323 'id': video_id,
3324 'title': video_title,
3325 })
3326 else:
3327 for num, entry in enumerate(entries, start=1):
3328 entry.update({
3329 'id': '%s-%s' % (video_id, num),
3330 'title': '%s (%d)' % (video_title, num),
3331 })
3332 for entry in entries:
3333 self._sort_formats(entry['formats'])
3334 return self.playlist_result(entries, video_id, video_title)
3335
3336 jwplayer_data = self._find_jwplayer_data(
3337 webpage, video_id, transform_source=js_to_json)
3338 if jwplayer_data:
3339 try:
3340 info = self._parse_jwplayer_data(
3341 jwplayer_data, video_id, require_title=False, base_url=url)
3342 return merge_dicts(info, info_dict)
3343 except ExtractorError:
3344 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3345 pass
3346
3347 # Video.js embed
3348 mobj = re.search(
3349 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3350 webpage)
3351 if mobj is not None:
3352 sources = self._parse_json(
3353 mobj.group(1), video_id, transform_source=js_to_json,
3354 fatal=False) or []
3355 if not isinstance(sources, list):
3356 sources = [sources]
3357 formats = []
3358 for source in sources:
3359 src = source.get('src')
3360 if not src or not isinstance(src, compat_str):
3361 continue
3362 src = compat_urlparse.urljoin(url, src)
3363 src_type = source.get('type')
3364 if isinstance(src_type, compat_str):
3365 src_type = src_type.lower()
3366 ext = determine_ext(src).lower()
3367 if src_type == 'video/youtube':
3368 return self.url_result(src, YoutubeIE.ie_key())
3369 if src_type == 'application/dash+xml' or ext == 'mpd':
3370 formats.extend(self._extract_mpd_formats(
3371 src, video_id, mpd_id='dash', fatal=False))
3372 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3373 formats.extend(self._extract_m3u8_formats(
3374 src, video_id, 'mp4', entry_protocol='m3u8_native',
3375 m3u8_id='hls', fatal=False))
3376 else:
3377 formats.append({
3378 'url': src,
3379 'ext': (mimetype2ext(src_type)
3380 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3381 })
3382 if formats:
3383 self._sort_formats(formats)
3384 info_dict['formats'] = formats
3385 return info_dict
3386
3387 # Looking for http://schema.org/VideoObject
3388 json_ld = self._search_json_ld(
3389 webpage, video_id, default={}, expected_type='VideoObject')
3390 if json_ld.get('url'):
3391 return merge_dicts(json_ld, info_dict)
3392
3393 def check_video(vurl):
3394 if YoutubeIE.suitable(vurl):
3395 return True
3396 if RtmpIE.suitable(vurl):
3397 return True
3398 vpath = compat_urlparse.urlparse(vurl).path
3399 vext = determine_ext(vpath)
3400 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3401
3402 def filter_video(urls):
3403 return list(filter(check_video, urls))
3404
3405 # Start with something easy: JW Player in SWFObject
3406 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3407 if not found:
3408 # Look for gorilla-vid style embedding
3409 found = filter_video(re.findall(r'''(?sx)
3410 (?:
3411 jw_plugins|
3412 JWPlayerOptions|
3413 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3414 )
3415 .*?
3416 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3417 if not found:
3418 # Broaden the search a little bit
3419 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3420 if not found:
3421 # Broaden the findall a little bit: JWPlayer JS loader
3422 found = filter_video(re.findall(
3423 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3424 if not found:
3425 # Flow player
3426 found = filter_video(re.findall(r'''(?xs)
3427 flowplayer\("[^"]+",\s*
3428 \{[^}]+?\}\s*,
3429 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3430 ["']?url["']?\s*:\s*["']([^"']+)["']
3431 ''', webpage))
3432 if not found:
3433 # Cinerama player
3434 found = re.findall(
3435 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3436 if not found:
3437 # Try to find twitter cards info
3438 # twitter:player:stream should be checked before twitter:player since
3439 # it is expected to contain a raw stream (see
3440 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3441 found = filter_video(re.findall(
3442 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3443 if not found:
3444 # We look for Open Graph info:
3445 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3446 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3447 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3448 if m_video_type is not None:
3449 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3450 if not found:
3451 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3452 found = re.search(
3453 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3454 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3455 webpage)
3456 if not found:
3457 # Look also in Refresh HTTP header
3458 refresh_header = head_response.headers.get('Refresh')
3459 if refresh_header:
3460 # In python 2 response HTTP headers are bytestrings
3461 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3462 refresh_header = refresh_header.decode('iso-8859-1')
3463 found = re.search(REDIRECT_REGEX, refresh_header)
3464 if found:
3465 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3466 if new_url != url:
3467 self.report_following_redirect(new_url)
3468 return {
3469 '_type': 'url',
3470 'url': new_url,
3471 }
3472 else:
3473 found = None
3474
3475 if not found:
3476 # twitter:player is a https URL to iframe player that may or may not
3477 # be supported by youtube-dlc thus this is checked the very last (see
3478 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3479 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3480 if embed_url and embed_url != url:
3481 return self.url_result(embed_url)
3482
3483 if not found:
3484 raise UnsupportedError(url)
3485
3486 entries = []
3487 for video_url in orderedSet(found):
3488 video_url = unescapeHTML(video_url)
3489 video_url = video_url.replace('\\/', '/')
3490 video_url = compat_urlparse.urljoin(url, video_url)
3491 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3492
3493 # Sometimes, jwplayer extraction will result in a YouTube URL
3494 if YoutubeIE.suitable(video_url):
3495 entries.append(self.url_result(video_url, 'Youtube'))
3496 continue
3497
3498 # here's a fun little line of code for you:
3499 video_id = os.path.splitext(video_id)[0]
3500
3501 entry_info_dict = {
3502 'id': video_id,
3503 'uploader': video_uploader,
3504 'title': video_title,
3505 'age_limit': age_limit,
3506 }
3507
3508 if RtmpIE.suitable(video_url):
3509 entry_info_dict.update({
3510 '_type': 'url_transparent',
3511 'ie_key': RtmpIE.ie_key(),
3512 'url': video_url,
3513 })
3514 entries.append(entry_info_dict)
3515 continue
3516
3517 ext = determine_ext(video_url)
3518 if ext == 'smil':
3519 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3520 elif ext == 'xspf':
3521 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3522 elif ext == 'm3u8':
3523 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3524 elif ext == 'mpd':
3525 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3526 elif ext == 'f4m':
3527 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3528 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3529 # Just matching .ism/manifest is not enough to be reliably sure
3530 # whether it's actually an ISM manifest or some other streaming
3531 # manifest since there are various streaming URL formats
3532 # possible (see [1]) as well as some other shenanigans like
3533 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3534 # so on.
3535 # Thus the most reasonable way to solve this is to delegate
3536 # to generic extractor in order to look into the contents of
3537 # the manifest itself.
3538 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3539 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3540 entry_info_dict = self.url_result(
3541 smuggle_url(video_url, {'to_generic': True}),
3542 GenericIE.ie_key())
3543 else:
3544 entry_info_dict['url'] = video_url
3545
3546 if entry_info_dict.get('formats'):
3547 self._sort_formats(entry_info_dict['formats'])
3548
3549 entries.append(entry_info_dict)
3550
3551 if len(entries) == 1:
3552 return entries[0]
3553 else:
3554 for num, e in enumerate(entries, start=1):
3555 # 'url' results don't have a title
3556 if e.get('title') is not None:
3557 e['title'] = '%s (%d)' % (e['title'], num)
3558 return {
3559 '_type': 'playlist',
3560 'entries': entries,
3561 }