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 parse_resolution,
32 sanitized_Request,
33 smuggle_url,
34 unescapeHTML,
35 unified_timestamp,
36 unsmuggle_url,
37 UnsupportedError,
38 url_or_none,
39 urljoin,
40 xpath_attr,
41 xpath_text,
42 xpath_with_ns,
43 )
44 from .commonprotocols import RtmpIE
45 from .brightcove import (
46 BrightcoveLegacyIE,
47 BrightcoveNewIE,
48 )
49 from .nexx import (
50 NexxIE,
51 NexxEmbedIE,
52 )
53 from .nbc import NBCSportsVPlayerIE
54 from .ooyala import OoyalaIE
55 from .rutv import RUTVIE
56 from .tvc import TVCIE
57 from .sportbox import SportBoxIE
58 from .myvi import MyviIE
59 from .condenast import CondeNastIE
60 from .udn import UDNEmbedIE
61 from .senateisvp import SenateISVPIE
62 from .svt import SVTIE
63 from .pornhub import PornHubIE
64 from .xhamster import XHamsterEmbedIE
65 from .tnaflix import TNAFlixNetworkEmbedIE
66 from .drtuber import DrTuberIE
67 from .redtube import RedTubeIE
68 from .tube8 import Tube8IE
69 from .mofosex import MofosexEmbedIE
70 from .spankwire import SpankwireIE
71 from .youporn import YouPornIE
72 from .vimeo import (
73 VimeoIE,
74 VHXEmbedIE,
75 )
76 from .dailymotion import DailymotionIE
77 from .dailymail import DailyMailIE
78 from .onionstudios import OnionStudiosIE
79 from .viewlift import ViewLiftEmbedIE
80 from .mtv import MTVServicesEmbeddedIE
81 from .pladform import PladformIE
82 from .videomore import VideomoreIE
83 from .webcaster import WebcasterFeedIE
84 from .googledrive import GoogleDriveIE
85 from .jwplatform import JWPlatformIE
86 from .digiteka import DigitekaIE
87 from .arkena import ArkenaIE
88 from .instagram import InstagramIE
89 from .threeqsdn import ThreeQSDNIE
90 from .theplatform import ThePlatformIE
91 from .kaltura import KalturaIE
92 from .eagleplatform import EaglePlatformIE
93 from .facebook import FacebookIE
94 from .soundcloud import SoundcloudEmbedIE
95 from .tunein import TuneInBaseIE
96 from .vbox7 import Vbox7IE
97 from .dbtv import DBTVIE
98 from .piksel import PikselIE
99 from .videa import VideaIE
100 from .twentymin import TwentyMinutenIE
101 from .ustream import UstreamIE
102 from .arte import ArteTVEmbedIE
103 from .videopress import VideoPressIE
104 from .rutube import RutubeIE
105 from .limelight import LimelightBaseIE
106 from .anvato import AnvatoIE
107 from .washingtonpost import WashingtonPostIE
108 from .wistia import WistiaIE
109 from .mediaset import MediasetIE
110 from .joj import JojIE
111 from .megaphone import MegaphoneIE
112 from .vzaar import VzaarIE
113 from .channel9 import Channel9IE
114 from .vshare import VShareIE
115 from .mediasite import MediasiteIE
116 from .springboardplatform import SpringboardPlatformIE
117 from .yapfiles import YapFilesIE
118 from .vice import ViceIE
119 from .xfileshare import XFileShareIE
120 from .cloudflarestream import CloudflareStreamIE
121 from .peertube import PeerTubeIE
122 from .teachable import TeachableIE
123 from .indavideo import IndavideoEmbedIE
124 from .apa import APAIE
125 from .foxnews import FoxNewsIE
126 from .viqeo import ViqeoIE
127 from .expressen import ExpressenIE
128 from .zype import ZypeIE
129 from .odnoklassniki import OdnoklassnikiIE
130 from .vk import VKIE
131 from .kinja import KinjaEmbedIE
132 from .arcpublishing import ArcPublishingIE
133 from .medialaan import MedialaanIE
134 from .simplecast import SimplecastIE
135
136
137 class GenericIE(InfoExtractor):
138 IE_DESC = 'Generic downloader that works on some sites'
139 _VALID_URL = r'.*'
140 IE_NAME = 'generic'
141 _TESTS = [
142 # Direct link to a video
143 {
144 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
145 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
146 'info_dict': {
147 'id': 'trailer',
148 'ext': 'mp4',
149 'title': 'trailer',
150 'upload_date': '20100513',
151 }
152 },
153 # Direct link to media delivered compressed (until Accept-Encoding is *)
154 {
155 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
156 'md5': '128c42e68b13950268b648275386fc74',
157 'info_dict': {
158 'id': 'FictionJunction-Parallel_Hearts',
159 'ext': 'flac',
160 'title': 'FictionJunction-Parallel_Hearts',
161 'upload_date': '20140522',
162 },
163 'expected_warnings': [
164 'URL could be a direct video link, returning it as such.'
165 ],
166 'skip': 'URL invalid',
167 },
168 # Direct download with broken HEAD
169 {
170 'url': 'http://ai-radio.org:8000/radio.opus',
171 'info_dict': {
172 'id': 'radio',
173 'ext': 'opus',
174 'title': 'radio',
175 },
176 'params': {
177 'skip_download': True, # infinite live stream
178 },
179 'expected_warnings': [
180 r'501.*Not Implemented',
181 r'400.*Bad Request',
182 ],
183 },
184 # Direct link with incorrect MIME type
185 {
186 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
187 'md5': '4ccbebe5f36706d85221f204d7eb5913',
188 'info_dict': {
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'id': '5_Lennart_Poettering_-_Systemd',
191 'ext': 'webm',
192 'title': '5_Lennart_Poettering_-_Systemd',
193 'upload_date': '20141120',
194 },
195 'expected_warnings': [
196 'URL could be a direct video link, returning it as such.'
197 ]
198 },
199 # RSS feed
200 {
201 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
202 'info_dict': {
203 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
204 'title': 'Zero Punctuation',
205 'description': 're:.*groundbreaking video review series.*'
206 },
207 'playlist_mincount': 11,
208 },
209 # RSS feed with enclosure
210 {
211 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
212 'info_dict': {
213 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
214 'title': 'MSNBC Rachel Maddow (video)',
215 'description': 're:.*her unique approach to storytelling.*',
216 },
217 'playlist': [{
218 'info_dict': {
219 'ext': 'mov',
220 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
221 'title': 're:MSNBC Rachel Maddow',
222 'description': 're:.*her unique approach to storytelling.*',
223 'timestamp': int,
224 'upload_date': compat_str,
225 'duration': float,
226 },
227 }],
228 },
229 # RSS feed with item with description and thumbnails
230 {
231 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
232 'info_dict': {
233 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
234 'title': 're:.*100% Hydrogen.*',
235 'description': 're:.*In this episode.*',
236 },
237 'playlist': [{
238 'info_dict': {
239 'ext': 'm4a',
240 'id': 'c1c879525ce2cb640b344507e682c36d',
241 'title': 're:Hydrogen!',
242 'description': 're:.*In this episode we are going.*',
243 'timestamp': 1567977776,
244 'upload_date': '20190908',
245 'duration': 459,
246 'thumbnail': r're:^https?://.*\.jpg$',
247 'episode_number': 1,
248 'season_number': 1,
249 'age_limit': 0,
250 },
251 }],
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # RSS feed with enclosures and unsupported link URLs
257 {
258 'url': 'http://www.hellointernet.fm/podcast?format=rss',
259 'info_dict': {
260 'id': 'http://www.hellointernet.fm/podcast?format=rss',
261 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
262 'title': 'Hello Internet',
263 },
264 'playlist_mincount': 100,
265 },
266 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
267 {
268 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
269 'info_dict': {
270 'id': 'smil',
271 'ext': 'mp4',
272 'title': 'Automatics, robotics and biocybernetics',
273 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
274 'upload_date': '20130627',
275 'formats': 'mincount:16',
276 'subtitles': 'mincount:1',
277 },
278 'params': {
279 'force_generic_extractor': True,
280 'skip_download': True,
281 },
282 },
283 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
284 {
285 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
286 'info_dict': {
287 'id': 'hds',
288 'ext': 'flv',
289 'title': 'hds',
290 'formats': 'mincount:1',
291 },
292 'params': {
293 'skip_download': True,
294 },
295 },
296 # SMIL from https://www.restudy.dk/video/play/id/1637
297 {
298 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
299 'info_dict': {
300 'id': 'video_1637',
301 'ext': 'flv',
302 'title': 'video_1637',
303 'formats': 'mincount:3',
304 },
305 'params': {
306 'skip_download': True,
307 },
308 },
309 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
310 {
311 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
312 'info_dict': {
313 'id': 'smil-service',
314 'ext': 'flv',
315 'title': 'smil-service',
316 'formats': 'mincount:1',
317 },
318 'params': {
319 'skip_download': True,
320 },
321 },
322 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
323 {
324 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
325 'info_dict': {
326 'id': '4719370',
327 'ext': 'mp4',
328 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
329 'formats': 'mincount:3',
330 },
331 'params': {
332 'skip_download': True,
333 },
334 },
335 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
336 {
337 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
338 'info_dict': {
339 'id': 'mZlp2ctYIUEB',
340 'ext': 'mp4',
341 'title': 'Tikibad ontruimd wegens brand',
342 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
343 'thumbnail': r're:^https?://.*\.jpg$',
344 'duration': 33,
345 },
346 'params': {
347 'skip_download': True,
348 },
349 },
350 # MPD from http://dash-mse-test.appspot.com/media.html
351 {
352 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
353 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
354 'info_dict': {
355 'id': 'car-20120827-manifest',
356 'ext': 'mp4',
357 'title': 'car-20120827-manifest',
358 'formats': 'mincount:9',
359 'upload_date': '20130904',
360 },
361 'params': {
362 'format': 'bestvideo',
363 },
364 },
365 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
366 {
367 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
368 'info_dict': {
369 'id': 'content',
370 'ext': 'mp4',
371 'title': 'content',
372 'formats': 'mincount:8',
373 },
374 'params': {
375 # m3u8 downloads
376 'skip_download': True,
377 },
378 'skip': 'video gone',
379 },
380 # m3u8 served with Content-Type: text/plain
381 {
382 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
383 'info_dict': {
384 'id': 'index',
385 'ext': 'mp4',
386 'title': 'index',
387 'upload_date': '20140720',
388 'formats': 'mincount:11',
389 },
390 'params': {
391 # m3u8 downloads
392 'skip_download': True,
393 },
394 'skip': 'video gone',
395 },
396 # google redirect
397 {
398 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
399 'info_dict': {
400 'id': 'cmQHVoWB5FY',
401 'ext': 'mp4',
402 'upload_date': '20130224',
403 'uploader_id': 'TheVerge',
404 'description': r're:^Chris Ziegler takes a look at the\.*',
405 'uploader': 'The Verge',
406 'title': 'First Firefox OS phones side-by-side',
407 },
408 'params': {
409 'skip_download': False,
410 }
411 },
412 {
413 # redirect in Refresh HTTP header
414 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
415 'info_dict': {
416 'id': 'pO8h3EaFRdo',
417 'ext': 'mp4',
418 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
419 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
420 'upload_date': '20150917',
421 'uploader_id': 'brtvofficial',
422 'uploader': 'Boiler Room',
423 },
424 'params': {
425 'skip_download': False,
426 },
427 },
428 {
429 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
430 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
431 'info_dict': {
432 'id': '13601338388002',
433 'ext': 'mp4',
434 'uploader': 'www.hodiho.fr',
435 'title': 'R\u00e9gis plante sa Jeep',
436 }
437 },
438 # bandcamp page with custom domain
439 {
440 'add_ie': ['Bandcamp'],
441 'url': 'http://bronyrock.com/track/the-pony-mash',
442 'info_dict': {
443 'id': '3235767654',
444 'ext': 'mp3',
445 'title': 'The Pony Mash',
446 'uploader': 'M_Pallante',
447 },
448 'skip': 'There is a limit of 200 free downloads / month for the test song',
449 },
450 {
451 # embedded brightcove video
452 # it also tests brightcove videos that need to set the 'Referer'
453 # in the http requests
454 'add_ie': ['BrightcoveLegacy'],
455 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
456 'info_dict': {
457 'id': '2765128793001',
458 'ext': 'mp4',
459 'title': 'Le cours de bourse : l’analyse technique',
460 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
461 'uploader': 'BFM BUSINESS',
462 },
463 'params': {
464 'skip_download': True,
465 },
466 },
467 {
468 # embedded with itemprop embedURL and video id spelled as `idVideo`
469 'add_id': ['BrightcoveLegacy'],
470 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
471 'info_dict': {
472 'id': '5255628253001',
473 'ext': 'mp4',
474 'title': 'md5:37c519b1128915607601e75a87995fc0',
475 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
476 'uploader': 'BFM BUSINESS',
477 'uploader_id': '876450612001',
478 'timestamp': 1482255315,
479 'upload_date': '20161220',
480 },
481 'params': {
482 'skip_download': True,
483 },
484 },
485 {
486 # https://github.com/ytdl-org/youtube-dl/issues/2253
487 'url': 'http://bcove.me/i6nfkrc3',
488 'md5': '0ba9446db037002366bab3b3eb30c88c',
489 'info_dict': {
490 'id': '3101154703001',
491 'ext': 'mp4',
492 'title': 'Still no power',
493 'uploader': 'thestar.com',
494 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
495 },
496 'add_ie': ['BrightcoveLegacy'],
497 'skip': 'video gone',
498 },
499 {
500 'url': 'http://www.championat.com/video/football/v/87/87499.html',
501 'md5': 'fb973ecf6e4a78a67453647444222983',
502 'info_dict': {
503 'id': '3414141473001',
504 'ext': 'mp4',
505 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
506 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
507 'uploader': 'Championat',
508 },
509 },
510 {
511 # https://github.com/ytdl-org/youtube-dl/issues/3541
512 'add_ie': ['BrightcoveLegacy'],
513 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
514 'info_dict': {
515 'id': '3866516442001',
516 'ext': 'mp4',
517 'title': 'Leer mij vrouwen kennen: Aflevering 1',
518 'description': 'Leer mij vrouwen kennen: Aflevering 1',
519 'uploader': 'SBS Broadcasting',
520 },
521 'skip': 'Restricted to Netherlands',
522 'params': {
523 'skip_download': True, # m3u8 download
524 },
525 },
526 {
527 # Brightcove video in <iframe>
528 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
529 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
530 'info_dict': {
531 'id': '5360463607001',
532 'ext': 'mp4',
533 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
534 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
535 'uploader': 'United Nations',
536 'uploader_id': '1362235914001',
537 'timestamp': 1489593889,
538 'upload_date': '20170315',
539 },
540 'add_ie': ['BrightcoveLegacy'],
541 },
542 {
543 # Brightcove with alternative playerID key
544 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
545 'info_dict': {
546 'id': 'nmeth.2062_SV1',
547 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
548 },
549 'playlist': [{
550 'info_dict': {
551 'id': '2228375078001',
552 'ext': 'mp4',
553 'title': 'nmeth.2062-sv1',
554 'description': 'nmeth.2062-sv1',
555 'timestamp': 1363357591,
556 'upload_date': '20130315',
557 'uploader': 'Nature Publishing Group',
558 'uploader_id': '1964492299001',
559 },
560 }],
561 },
562 {
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'info_dict': {
566 'id': '5255815316001',
567 'ext': 'mp4',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
574 },
575 'params': {
576 'skip_download': True, # m3u8 download
577 },
578 'skip': 'video rotates...weekly?',
579 },
580 {
581 # Brightcove:new type [2].
582 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
583 'md5': '2b35148fcf48da41c9fb4591650784f3',
584 'info_dict': {
585 'id': '5348741021001',
586 'ext': 'mp4',
587 'upload_date': '20170306',
588 'uploader_id': '4191638492001',
589 'timestamp': 1488769918,
590 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
591
592 },
593 },
594 {
595 # Alternative brightcove <video> attributes
596 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
597 'info_dict': {
598 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
599 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
600 },
601 'playlist': [{
602 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
603 'info_dict': {
604 'id': '5311302538001',
605 'ext': 'mp4',
606 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
607 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
608 'timestamp': 1486321708,
609 'upload_date': '20170205',
610 'uploader_id': '800000640001',
611 },
612 'only_matching': True,
613 }],
614 },
615 {
616 # Brightcove with UUID in videoPlayer
617 'url': 'http://www8.hp.com/cn/zh/home.html',
618 'info_dict': {
619 'id': '5255815316001',
620 'ext': 'mp4',
621 'title': 'Sprocket Video - China',
622 'description': 'Sprocket Video - China',
623 'uploader': 'HP-Video Gallery',
624 'timestamp': 1482263210,
625 'upload_date': '20161220',
626 'uploader_id': '1107601872001',
627 },
628 'params': {
629 'skip_download': True, # m3u8 download
630 },
631 },
632 # ooyala video
633 {
634 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
635 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
636 'info_dict': {
637 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
638 'ext': 'mp4',
639 'title': '2cc213299525360.mov', # that's what we get
640 'duration': 238.231,
641 },
642 'add_ie': ['Ooyala'],
643 },
644 {
645 # ooyala video embedded with http://player.ooyala.com/iframe.js
646 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
647 'info_dict': {
648 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
649 'ext': 'mp4',
650 'title': '"Steve Jobs: Man in the Machine" trailer',
651 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
652 'duration': 135.427,
653 },
654 'params': {
655 'skip_download': True,
656 },
657 'skip': 'movie expired',
658 },
659 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
660 {
661 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
662 'info_dict': {
663 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
664 'ext': 'mp4',
665 'title': 'Steampunk Fest Comes to Honesdale',
666 'duration': 43.276,
667 },
668 'params': {
669 'skip_download': True,
670 }
671 },
672 # embed.ly video
673 {
674 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
675 'info_dict': {
676 'id': '9ODmcdjQcHQ',
677 'ext': 'mp4',
678 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
679 'upload_date': '20140225',
680 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
681 'uploader': 'Tested',
682 'uploader_id': 'testedcom',
683 },
684 # No need to test YoutubeIE here
685 'params': {
686 'skip_download': True,
687 },
688 },
689 # funnyordie embed
690 {
691 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
692 'info_dict': {
693 'id': '18e820ec3f',
694 'ext': 'mp4',
695 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
696 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
697 },
698 # HEAD requests lead to endless 301, while GET is OK
699 'expected_warnings': ['301'],
700 },
701 # RUTV embed
702 {
703 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
704 'info_dict': {
705 'id': '776940',
706 'ext': 'mp4',
707 'title': 'Охотское море стало целиком российским',
708 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
709 },
710 'params': {
711 # m3u8 download
712 'skip_download': True,
713 },
714 },
715 # TVC embed
716 {
717 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
718 'info_dict': {
719 'id': '55304',
720 'ext': 'mp4',
721 'title': 'Дошкольное воспитание',
722 },
723 },
724 # SportBox embed
725 {
726 'url': 'http://www.vestifinance.ru/articles/25753',
727 'info_dict': {
728 'id': '25753',
729 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
730 },
731 'playlist': [{
732 'info_dict': {
733 'id': '370908',
734 'title': 'Госзаказ. День 3',
735 'ext': 'mp4',
736 }
737 }, {
738 'info_dict': {
739 'id': '370905',
740 'title': 'Госзаказ. День 2',
741 'ext': 'mp4',
742 }
743 }, {
744 'info_dict': {
745 'id': '370902',
746 'title': 'Госзаказ. День 1',
747 'ext': 'mp4',
748 }
749 }],
750 'params': {
751 # m3u8 download
752 'skip_download': True,
753 },
754 },
755 # Myvi.ru embed
756 {
757 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
758 'info_dict': {
759 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
760 'ext': 'mp4',
761 'title': 'Ужастики, русский трейлер (2015)',
762 'thumbnail': r're:^https?://.*\.jpg$',
763 'duration': 153,
764 }
765 },
766 # XHamster embed
767 {
768 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
769 'info_dict': {
770 'id': 'showthread',
771 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
772 },
773 'playlist_mincount': 7,
774 # This forum does not allow <iframe> syntaxes anymore
775 # Now HTML tags are displayed as-is
776 'skip': 'No videos on this page',
777 },
778 # Embedded TED video
779 {
780 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
781 'md5': '65fdff94098e4a607385a60c5177c638',
782 'info_dict': {
783 'id': '1969',
784 'ext': 'mp4',
785 'title': 'Hidden miracles of the natural world',
786 'uploader': 'Louie Schwartzberg',
787 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
788 }
789 },
790 # nowvideo embed hidden behind percent encoding
791 {
792 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
793 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
794 'info_dict': {
795 'id': '06e53103ca9aa',
796 'ext': 'flv',
797 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
798 'description': 'No description',
799 },
800 },
801 # arte embed
802 {
803 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
804 'md5': '7653032cbb25bf6c80d80f217055fa43',
805 'info_dict': {
806 'id': '048195-004_PLUS7-F',
807 'ext': 'flv',
808 'title': 'X:enius',
809 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
810 'upload_date': '20140320',
811 },
812 'params': {
813 'skip_download': 'Requires rtmpdump'
814 },
815 'skip': 'video gone',
816 },
817 # francetv embed
818 {
819 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
820 'info_dict': {
821 'id': 'EV_30231',
822 'ext': 'mp4',
823 'title': 'Alcaline, le concert avec Calogero',
824 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
825 'upload_date': '20150226',
826 'timestamp': 1424989860,
827 'duration': 5400,
828 },
829 'params': {
830 # m3u8 downloads
831 'skip_download': True,
832 },
833 'expected_warnings': [
834 'Forbidden'
835 ]
836 },
837 # Condé Nast embed
838 {
839 'url': 'http://www.wired.com/2014/04/honda-asimo/',
840 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
841 'info_dict': {
842 'id': '53501be369702d3275860000',
843 'ext': 'mp4',
844 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
845 }
846 },
847 # Dailymotion embed
848 {
849 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
850 'md5': '441aeeb82eb72c422c7f14ec533999cd',
851 'info_dict': {
852 'id': 'k2mm4bCdJ6CQ2i7c8o2',
853 'ext': 'mp4',
854 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
855 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
856 'uploader': 'Spi0n',
857 'uploader_id': 'xgditw',
858 'upload_date': '20140425',
859 'timestamp': 1398441542,
860 },
861 'add_ie': ['Dailymotion'],
862 },
863 # DailyMail embed
864 {
865 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
866 'info_dict': {
867 'id': '1495629',
868 'ext': 'mp4',
869 'title': 'Care worker punches elderly dementia patient in head 11 times',
870 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
871 },
872 'add_ie': ['DailyMail'],
873 'params': {
874 'skip_download': True,
875 },
876 },
877 # YouTube embed
878 {
879 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
880 'info_dict': {
881 'id': 'FXRb4ykk4S0',
882 'ext': 'mp4',
883 'title': 'The NBL Auction 2014',
884 'uploader': 'BADMINTON England',
885 'uploader_id': 'BADMINTONEvents',
886 'upload_date': '20140603',
887 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
888 },
889 'add_ie': ['Youtube'],
890 'params': {
891 'skip_download': True,
892 }
893 },
894 # MTVServices embed
895 {
896 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
897 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
898 'info_dict': {
899 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
900 'ext': 'mp4',
901 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
902 'description': 'Two valets share their love for movie star Liam Neesons.',
903 'timestamp': 1349922600,
904 'upload_date': '20121011',
905 },
906 },
907 # YouTube embed via <data-embed-url="">
908 {
909 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
910 'info_dict': {
911 'id': '4vAffPZIT44',
912 'ext': 'mp4',
913 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
914 'uploader': 'Gameloft',
915 'uploader_id': 'gameloft',
916 'upload_date': '20140828',
917 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
918 },
919 'params': {
920 'skip_download': True,
921 }
922 },
923 # YouTube <object> embed
924 {
925 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
926 'md5': '516718101ec834f74318df76259fb3cc',
927 'info_dict': {
928 'id': 'msN87y-iEx0',
929 'ext': 'webm',
930 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
931 'upload_date': '20080526',
932 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
933 'uploader': 'Christopher Sykes',
934 'uploader_id': 'ChristopherJSykes',
935 },
936 'add_ie': ['Youtube'],
937 },
938 # Camtasia studio
939 {
940 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
941 'playlist': [{
942 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
943 'info_dict': {
944 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
945 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
946 'ext': 'flv',
947 'duration': 2235.90,
948 }
949 }, {
950 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
951 'info_dict': {
952 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
953 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
954 'ext': 'flv',
955 'duration': 2235.93,
956 }
957 }],
958 'info_dict': {
959 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
960 }
961 },
962 # Flowplayer
963 {
964 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
965 'md5': '9d65602bf31c6e20014319c7d07fba27',
966 'info_dict': {
967 'id': '5123ea6d5e5a7',
968 'ext': 'mp4',
969 'age_limit': 18,
970 'uploader': 'www.handjobhub.com',
971 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
972 }
973 },
974 # Multiple brightcove videos
975 # https://github.com/ytdl-org/youtube-dl/issues/2283
976 {
977 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
978 'info_dict': {
979 'id': 'always-never',
980 'title': 'Always / Never - The New Yorker',
981 },
982 'playlist_count': 3,
983 'params': {
984 'extract_flat': False,
985 'skip_download': True,
986 }
987 },
988 # MLB embed
989 {
990 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
991 'md5': '96f09a37e44da40dd083e12d9a683327',
992 'info_dict': {
993 'id': '33322633',
994 'ext': 'mp4',
995 'title': 'Ump changes call to ball',
996 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
997 'duration': 48,
998 'timestamp': 1401537900,
999 'upload_date': '20140531',
1000 'thumbnail': r're:^https?://.*\.jpg$',
1001 },
1002 },
1003 # Wistia embed
1004 {
1005 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1006 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1007 'info_dict': {
1008 'id': '6e2wtrbdaf',
1009 'ext': 'mov',
1010 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1011 'description': 'a Paywall Videos video from Remilon',
1012 'duration': 644.072,
1013 'uploader': 'study.com',
1014 'timestamp': 1459678540,
1015 'upload_date': '20160403',
1016 'filesize': 24687186,
1017 },
1018 },
1019 {
1020 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1021 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1022 'info_dict': {
1023 'id': 'uxjb0lwrcz',
1024 'ext': 'mp4',
1025 'title': 'Conversation about Hexagonal Rails Part 1',
1026 'description': 'a Martin Fowler video from ThoughtWorks',
1027 'duration': 1715.0,
1028 'uploader': 'thoughtworks.wistia.com',
1029 'timestamp': 1401832161,
1030 'upload_date': '20140603',
1031 },
1032 },
1033 # Wistia standard embed (async)
1034 {
1035 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1036 'info_dict': {
1037 'id': '807fafadvk',
1038 'ext': 'mp4',
1039 'title': 'Drip Brennan Dunn Workshop',
1040 'description': 'a JV Webinars video from getdrip-1',
1041 'duration': 4986.95,
1042 'timestamp': 1463607249,
1043 'upload_date': '20160518',
1044 },
1045 'params': {
1046 'skip_download': True,
1047 }
1048 },
1049 # Soundcloud embed
1050 {
1051 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1052 'info_dict': {
1053 'id': '174391317',
1054 'ext': 'mp3',
1055 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1056 'uploader': 'Sophos Security',
1057 'title': 'Chet Chat 171 - Oct 29, 2014',
1058 'upload_date': '20141029',
1059 }
1060 },
1061 # Soundcloud multiple embeds
1062 {
1063 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1064 'info_dict': {
1065 'id': '52809',
1066 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1067 },
1068 'playlist_mincount': 7,
1069 },
1070 # TuneIn station embed
1071 {
1072 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1073 'info_dict': {
1074 'id': '204146',
1075 'ext': 'mp3',
1076 'title': 'CNRV',
1077 'location': 'Paris, France',
1078 'is_live': True,
1079 },
1080 'params': {
1081 # Live stream
1082 'skip_download': True,
1083 },
1084 },
1085 # Livestream embed
1086 {
1087 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1088 'info_dict': {
1089 'id': '67864563',
1090 'ext': 'flv',
1091 'upload_date': '20141112',
1092 'title': 'Rosetta #CometLanding webcast HL 10',
1093 }
1094 },
1095 # Another Livestream embed, without 'new.' in URL
1096 {
1097 'url': 'https://www.freespeech.org/',
1098 'info_dict': {
1099 'id': '123537347',
1100 'ext': 'mp4',
1101 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1102 },
1103 'params': {
1104 # Live stream
1105 'skip_download': True,
1106 },
1107 },
1108 # LazyYT
1109 {
1110 'url': 'https://skiplagged.com/',
1111 'info_dict': {
1112 'id': 'skiplagged',
1113 'title': 'Skiplagged: The smart way to find cheap flights',
1114 },
1115 'playlist_mincount': 1,
1116 'add_ie': ['Youtube'],
1117 },
1118 # Cinchcast embed
1119 {
1120 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1121 'info_dict': {
1122 'id': '7141703',
1123 'ext': 'mp3',
1124 'upload_date': '20141126',
1125 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1126 }
1127 },
1128 # Cinerama player
1129 {
1130 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1131 'info_dict': {
1132 'id': '730m_DandD_1901_512k',
1133 'ext': 'mp4',
1134 'uploader': 'www.abc.net.au',
1135 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1136 }
1137 },
1138 # embedded viddler video
1139 {
1140 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1141 'info_dict': {
1142 'id': '4d03aad9',
1143 'ext': 'mp4',
1144 'uploader': 'deadspin',
1145 'title': 'WALL-TO-GORTAT',
1146 'timestamp': 1422285291,
1147 'upload_date': '20150126',
1148 },
1149 'add_ie': ['Viddler'],
1150 },
1151 # Libsyn embed
1152 {
1153 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1154 'info_dict': {
1155 'id': '3377616',
1156 'ext': 'mp3',
1157 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1158 'description': 'md5:601cb790edd05908957dae8aaa866465',
1159 'upload_date': '20150220',
1160 },
1161 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1162 },
1163 # jwplayer YouTube
1164 {
1165 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1166 'info_dict': {
1167 'id': 'Mrj4DVp2zeA',
1168 'ext': 'mp4',
1169 'upload_date': '20150212',
1170 'uploader': 'The National Archives UK',
1171 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1172 'uploader_id': 'NationalArchives08',
1173 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1174 },
1175 },
1176 # jwplayer rtmp
1177 {
1178 'url': 'http://www.suffolk.edu/sjc/live.php',
1179 'info_dict': {
1180 'id': 'live',
1181 'ext': 'flv',
1182 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1183 'uploader': 'www.suffolk.edu',
1184 },
1185 'params': {
1186 'skip_download': True,
1187 },
1188 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1189 },
1190 # Complex jwplayer
1191 {
1192 'url': 'http://www.indiedb.com/games/king-machine/videos',
1193 'info_dict': {
1194 'id': 'videos',
1195 'ext': 'mp4',
1196 'title': 'king machine trailer 1',
1197 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1198 'thumbnail': r're:^https?://.*\.jpg$',
1199 },
1200 },
1201 {
1202 # JWPlayer config passed as variable
1203 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1204 'info_dict': {
1205 'id': '3326530_hq',
1206 'ext': 'mp4',
1207 'title': 'ARIELE | Tube Cup',
1208 'uploader': 'www.txxx.com',
1209 'age_limit': 18,
1210 },
1211 'params': {
1212 'skip_download': True,
1213 }
1214 },
1215 {
1216 # JWPlatform iframe
1217 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1218 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1219 'info_dict': {
1220 'id': 'O0c5JcKT',
1221 'ext': 'mp4',
1222 'upload_date': '20171122',
1223 'timestamp': 1511366290,
1224 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1225 },
1226 'add_ie': [JWPlatformIE.ie_key()],
1227 },
1228 {
1229 # Video.js embed, multiple formats
1230 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1231 'info_dict': {
1232 'id': 'yygqldloqIk',
1233 'ext': 'mp4',
1234 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1235 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1236 'upload_date': '20130314',
1237 'uploader': 'PROстое3D',
1238 'uploader_id': 'PROstoe3D',
1239 },
1240 'params': {
1241 'skip_download': True,
1242 },
1243 },
1244 {
1245 # Video.js embed, single format
1246 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1247 'info_dict': {
1248 'id': 'watch',
1249 'ext': 'mp4',
1250 'title': 'Step 1 - Good Foundation',
1251 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1252 },
1253 'params': {
1254 'skip_download': True,
1255 },
1256 },
1257 # rtl.nl embed
1258 {
1259 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1260 'playlist_mincount': 5,
1261 'info_dict': {
1262 'id': 'aanslagen-kopenhagen',
1263 'title': 'Aanslagen Kopenhagen',
1264 }
1265 },
1266 # Zapiks embed
1267 {
1268 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1269 'info_dict': {
1270 'id': '118046',
1271 'ext': 'mp4',
1272 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1273 }
1274 },
1275 # Kaltura embed (different embed code)
1276 {
1277 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1278 'info_dict': {
1279 'id': '1_a52wc67y',
1280 'ext': 'flv',
1281 'upload_date': '20150127',
1282 'uploader_id': 'PremierMedia',
1283 'timestamp': int,
1284 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1285 },
1286 },
1287 # Kaltura embed with single quotes
1288 {
1289 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1290 'info_dict': {
1291 'id': '0_izeg5utt',
1292 'ext': 'mp4',
1293 'title': '35871',
1294 'timestamp': 1355743100,
1295 'upload_date': '20121217',
1296 'uploader_id': 'cplapp@learn360.com',
1297 },
1298 'add_ie': ['Kaltura'],
1299 },
1300 {
1301 # Kaltura embedded via quoted entry_id
1302 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1303 'info_dict': {
1304 'id': '0_utuok90b',
1305 'ext': 'mp4',
1306 'title': '06_matthew_brender_raj_dutt',
1307 'timestamp': 1466638791,
1308 'upload_date': '20160622',
1309 },
1310 'add_ie': ['Kaltura'],
1311 'expected_warnings': [
1312 'Could not send HEAD request'
1313 ],
1314 'params': {
1315 'skip_download': True,
1316 }
1317 },
1318 {
1319 # Kaltura embedded, some fileExt broken (#11480)
1320 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1321 'info_dict': {
1322 'id': '1_sgtvehim',
1323 'ext': 'mp4',
1324 'title': 'Our "Standard Models" of particle physics and cosmology',
1325 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1326 'timestamp': 1321158993,
1327 'upload_date': '20111113',
1328 'uploader_id': 'kps1',
1329 },
1330 'add_ie': ['Kaltura'],
1331 },
1332 {
1333 # Kaltura iframe embed
1334 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1335 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1336 'info_dict': {
1337 'id': '0_f2cfbpwy',
1338 'ext': 'mp4',
1339 'title': 'I. M. Pei: A Centennial Celebration',
1340 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1341 'upload_date': '20170403',
1342 'uploader_id': 'batchUser',
1343 'timestamp': 1491232186,
1344 },
1345 'add_ie': ['Kaltura'],
1346 },
1347 {
1348 # Kaltura iframe embed, more sophisticated
1349 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1350 'info_dict': {
1351 'id': '1_9gzouybz',
1352 'ext': 'mp4',
1353 'title': 'lecture-05sep2017',
1354 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1355 'upload_date': '20170913',
1356 'uploader_id': 'eps2',
1357 'timestamp': 1505340777,
1358 },
1359 'params': {
1360 'skip_download': True,
1361 },
1362 'add_ie': ['Kaltura'],
1363 },
1364 {
1365 # meta twitter:player
1366 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1367 'info_dict': {
1368 'id': '0_01b42zps',
1369 'ext': 'mp4',
1370 'title': 'Main Twerk (Video)',
1371 'upload_date': '20171208',
1372 'uploader_id': 'sebastian.salinas@thechive.com',
1373 'timestamp': 1512713057,
1374 },
1375 'params': {
1376 'skip_download': True,
1377 },
1378 'add_ie': ['Kaltura'],
1379 },
1380 # referrer protected EaglePlatform embed
1381 {
1382 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1383 'info_dict': {
1384 'id': '582306',
1385 'ext': 'mp4',
1386 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1387 'thumbnail': r're:^https?://.*\.jpg$',
1388 'duration': 3382,
1389 'view_count': int,
1390 },
1391 'params': {
1392 'skip_download': True,
1393 },
1394 },
1395 # ClipYou (EaglePlatform) embed (custom URL)
1396 {
1397 'url': 'http://muz-tv.ru/play/7129/',
1398 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1399 'info_dict': {
1400 'id': '12820',
1401 'ext': 'mp4',
1402 'title': "'O Sole Mio",
1403 'thumbnail': r're:^https?://.*\.jpg$',
1404 'duration': 216,
1405 'view_count': int,
1406 },
1407 'params': {
1408 'skip_download': True,
1409 },
1410 'skip': 'This video is unavailable.',
1411 },
1412 # Pladform embed
1413 {
1414 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1415 'info_dict': {
1416 'id': '100183293',
1417 'ext': 'mp4',
1418 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1419 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1420 'thumbnail': r're:^https?://.*\.jpg$',
1421 'duration': 694,
1422 'age_limit': 0,
1423 },
1424 'skip': 'HTTP Error 404: Not Found',
1425 },
1426 # Playwire embed
1427 {
1428 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1429 'info_dict': {
1430 'id': '3519514',
1431 'ext': 'mp4',
1432 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1433 'thumbnail': r're:^https?://.*\.png$',
1434 'duration': 45.115,
1435 },
1436 },
1437 # 5min embed
1438 {
1439 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1440 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1441 'info_dict': {
1442 'id': '518726732',
1443 'ext': 'mp4',
1444 'title': 'Facebook Creates "On This Day" | Crunch Report',
1445 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1446 'timestamp': 1427237531,
1447 'uploader': 'Crunch Report',
1448 'upload_date': '20150324',
1449 },
1450 'params': {
1451 # m3u8 download
1452 'skip_download': True,
1453 },
1454 },
1455 # Crooks and Liars embed
1456 {
1457 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1458 'info_dict': {
1459 'id': '8RUoRhRi',
1460 'ext': 'mp4',
1461 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1462 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1463 'timestamp': 1428207000,
1464 'upload_date': '20150405',
1465 'uploader': 'Heather',
1466 },
1467 },
1468 # Crooks and Liars external embed
1469 {
1470 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1471 'info_dict': {
1472 'id': 'MTE3MjUtMzQ2MzA',
1473 'ext': 'mp4',
1474 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1475 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1476 'timestamp': 1265032391,
1477 'upload_date': '20100201',
1478 'uploader': 'Heather',
1479 },
1480 },
1481 # NBC Sports vplayer embed
1482 {
1483 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1484 'info_dict': {
1485 'id': 'ln7x1qSThw4k',
1486 'ext': 'flv',
1487 'title': "PFT Live: New leader in the 'new-look' defense",
1488 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1489 'uploader': 'NBCU-SPORTS',
1490 'upload_date': '20140107',
1491 'timestamp': 1389118457,
1492 },
1493 'skip': 'Invalid Page URL',
1494 },
1495 # NBC News embed
1496 {
1497 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1498 'md5': '1aa589c675898ae6d37a17913cf68d66',
1499 'info_dict': {
1500 'id': 'x_dtl_oa_LettermanliftPR_160608',
1501 'ext': 'mp4',
1502 'title': 'David Letterman: A Preview',
1503 '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.',
1504 'upload_date': '20160609',
1505 'timestamp': 1465431544,
1506 'uploader': 'NBCU-NEWS',
1507 },
1508 },
1509 # UDN embed
1510 {
1511 'url': 'https://video.udn.com/news/300346',
1512 'md5': 'fd2060e988c326991037b9aff9df21a6',
1513 'info_dict': {
1514 'id': '300346',
1515 'ext': 'mp4',
1516 'title': '中一中男師變性 全校師生力挺',
1517 'thumbnail': r're:^https?://.*\.jpg$',
1518 },
1519 'params': {
1520 # m3u8 download
1521 'skip_download': True,
1522 },
1523 'expected_warnings': ['Failed to parse JSON Expecting value'],
1524 },
1525 # Brightcove URL in single quotes
1526 {
1527 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1528 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1529 'info_dict': {
1530 'id': '4255764656001',
1531 'ext': 'mp4',
1532 'title': 'SN Presents: Russell Martin, World Citizen',
1533 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1534 'uploader': 'Rogers Sportsnet',
1535 'uploader_id': '1704050871',
1536 'upload_date': '20150525',
1537 'timestamp': 1432570283,
1538 },
1539 },
1540 # Kinja embed
1541 {
1542 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1543 'info_dict': {
1544 'id': '106351',
1545 'ext': 'mp4',
1546 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1547 'description': 'Migrated from OnionStudios',
1548 'thumbnail': r're:^https?://.*\.jpe?g$',
1549 'uploader': 'clickhole',
1550 'upload_date': '20150527',
1551 'timestamp': 1432744860,
1552 }
1553 },
1554 # SnagFilms embed
1555 {
1556 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1557 'info_dict': {
1558 'id': '74849a00-85a9-11e1-9660-123139220831',
1559 'ext': 'mp4',
1560 'title': '#whilewewatch',
1561 }
1562 },
1563 # AdobeTVVideo embed
1564 {
1565 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1566 'md5': '43662b577c018ad707a63766462b1e87',
1567 'info_dict': {
1568 'id': '2456',
1569 'ext': 'mp4',
1570 'title': 'New experience with Acrobat DC',
1571 'description': 'New experience with Acrobat DC',
1572 'duration': 248.667,
1573 },
1574 },
1575 # BrightcoveInPageEmbed embed
1576 {
1577 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1578 'info_dict': {
1579 'id': '4238694884001',
1580 'ext': 'flv',
1581 'title': 'Tabletop: Dread, Last Thoughts',
1582 'description': 'Tabletop: Dread, Last Thoughts',
1583 'duration': 51690,
1584 },
1585 },
1586 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1587 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1588 {
1589 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1590 'info_dict': {
1591 'id': '4785848093001',
1592 'ext': 'mp4',
1593 'title': 'The Cardinal Pell Interview',
1594 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1595 'uploader': 'GlobeCast Australia - GlobeStream',
1596 'uploader_id': '2733773828001',
1597 'upload_date': '20160304',
1598 'timestamp': 1457083087,
1599 },
1600 'params': {
1601 # m3u8 downloads
1602 'skip_download': True,
1603 },
1604 },
1605 {
1606 # Brightcove embed with whitespace around attribute names
1607 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1608 'info_dict': {
1609 'id': '3167554373001',
1610 'ext': 'mp4',
1611 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1612 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1613 'uploader_id': '1079349493',
1614 'upload_date': '20140207',
1615 'timestamp': 1391810548,
1616 },
1617 'params': {
1618 'skip_download': True,
1619 },
1620 },
1621 # Another form of arte.tv embed
1622 {
1623 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1624 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1625 'info_dict': {
1626 'id': '030273-562_PLUS7-F',
1627 'ext': 'mp4',
1628 'title': 'ARTE Reportage - Nulle part, en France',
1629 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1630 'upload_date': '20160409',
1631 },
1632 },
1633 # Duplicated embedded video URLs
1634 {
1635 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1636 'info_dict': {
1637 'id': '149298443_480_16c25b74_2',
1638 'ext': 'mp4',
1639 'title': 'vs. Blue Orange Spring Game',
1640 'uploader': 'www.hudl.com',
1641 },
1642 },
1643 # twitter:player:stream embed
1644 {
1645 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1646 'info_dict': {
1647 'id': 'master',
1648 'ext': 'mp4',
1649 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1650 'uploader': 'www.rtl.be',
1651 },
1652 'params': {
1653 # m3u8 downloads
1654 'skip_download': True,
1655 },
1656 },
1657 # twitter:player embed
1658 {
1659 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1660 'md5': 'a3e0df96369831de324f0778e126653c',
1661 'info_dict': {
1662 'id': '4909620399001',
1663 'ext': 'mp4',
1664 'title': 'What Do Black Holes Sound Like?',
1665 'description': 'what do black holes sound like',
1666 'upload_date': '20160524',
1667 'uploader_id': '29913724001',
1668 'timestamp': 1464107587,
1669 'uploader': 'TheAtlantic',
1670 },
1671 'add_ie': ['BrightcoveLegacy'],
1672 },
1673 # Facebook <iframe> embed
1674 {
1675 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1676 'md5': 'fbcde74f534176ecb015849146dd3aee',
1677 'info_dict': {
1678 'id': '599637780109885',
1679 'ext': 'mp4',
1680 'title': 'Facebook video #599637780109885',
1681 },
1682 },
1683 # Facebook <iframe> embed, plugin video
1684 {
1685 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1686 'info_dict': {
1687 'id': '1754168231264132',
1688 'ext': 'mp4',
1689 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1690 'uploader': 'Tariq Ramadan (official)',
1691 'timestamp': 1496758379,
1692 'upload_date': '20170606',
1693 },
1694 'params': {
1695 'skip_download': True,
1696 },
1697 },
1698 # Facebook API embed
1699 {
1700 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1701 'md5': 'a47372ee61b39a7b90287094d447d94e',
1702 'info_dict': {
1703 'id': '10153467542406923',
1704 'ext': 'mp4',
1705 'title': 'Facebook video #10153467542406923',
1706 },
1707 },
1708 # Wordpress "YouTube Video Importer" plugin
1709 {
1710 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1711 'md5': 'd16797741b560b485194eddda8121b48',
1712 'info_dict': {
1713 'id': 'HNTXWDXV9Is',
1714 'ext': 'mp4',
1715 'title': 'Blue Devils Drumline Stanford lot 2016',
1716 'upload_date': '20160627',
1717 'uploader_id': 'GENOCIDE8GENERAL10',
1718 'uploader': 'cylus cyrus',
1719 },
1720 },
1721 {
1722 # video stored on custom kaltura server
1723 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1724 'md5': '537617d06e64dfed891fa1593c4b30cc',
1725 'info_dict': {
1726 'id': '0_1iotm5bh',
1727 'ext': 'mp4',
1728 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1729 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1730 'uploader_id': 'videos.expansion@el-mundo.net',
1731 'upload_date': '20150429',
1732 'timestamp': 1430303472,
1733 },
1734 'add_ie': ['Kaltura'],
1735 },
1736 {
1737 # multiple kaltura embeds, nsfw
1738 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1739 'info_dict': {
1740 'id': 'kamila-avec-video-jaime-sadomie',
1741 'title': "Kamila avec vídeo “J'aime sadomie”",
1742 },
1743 'playlist_count': 8,
1744 },
1745 {
1746 # Non-standard Vimeo embed
1747 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1748 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1749 'info_dict': {
1750 'id': '148867247',
1751 'ext': 'mp4',
1752 'title': 'Understanding the web - Teaser',
1753 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1754 'upload_date': '20151214',
1755 'uploader': 'OpenClassrooms',
1756 'uploader_id': 'openclassrooms',
1757 },
1758 'add_ie': ['Vimeo'],
1759 },
1760 {
1761 # generic vimeo embed that requires original URL passed as Referer
1762 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1763 'only_matching': True,
1764 },
1765 {
1766 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1767 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1768 'info_dict': {
1769 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1770 'ext': 'mp4',
1771 'title': 'Big Buck Bunny',
1772 'description': 'Royalty free test video',
1773 'timestamp': 1432816365,
1774 'upload_date': '20150528',
1775 'is_live': False,
1776 },
1777 'params': {
1778 'skip_download': True,
1779 },
1780 'add_ie': [ArkenaIE.ie_key()],
1781 },
1782 {
1783 '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/',
1784 'info_dict': {
1785 'id': '1c7141f46c',
1786 'ext': 'mp4',
1787 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1788 },
1789 'params': {
1790 'skip_download': True,
1791 },
1792 'add_ie': [Vbox7IE.ie_key()],
1793 },
1794 {
1795 # DBTV embeds
1796 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1797 'info_dict': {
1798 'id': '43254897',
1799 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1800 },
1801 'playlist_mincount': 3,
1802 },
1803 {
1804 # Videa embeds
1805 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1806 'info_dict': {
1807 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1808 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1809 },
1810 'playlist_mincount': 2,
1811 },
1812 {
1813 # 20 minuten embed
1814 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1815 'info_dict': {
1816 'id': '523629',
1817 'ext': 'mp4',
1818 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1819 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1820 },
1821 'params': {
1822 'skip_download': True,
1823 },
1824 'add_ie': [TwentyMinutenIE.ie_key()],
1825 },
1826 {
1827 # VideoPress embed
1828 'url': 'https://en.support.wordpress.com/videopress/',
1829 'info_dict': {
1830 'id': 'OcobLTqC',
1831 'ext': 'm4v',
1832 'title': 'IMG_5786',
1833 'timestamp': 1435711927,
1834 'upload_date': '20150701',
1835 },
1836 'params': {
1837 'skip_download': True,
1838 },
1839 'add_ie': [VideoPressIE.ie_key()],
1840 },
1841 {
1842 # Rutube embed
1843 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1844 'info_dict': {
1845 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1846 'ext': 'flv',
1847 'title': 'Магаззино: Казань 2',
1848 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1849 'uploader': 'Магаззино',
1850 'upload_date': '20170228',
1851 'uploader_id': '996642',
1852 },
1853 'params': {
1854 'skip_download': True,
1855 },
1856 'add_ie': [RutubeIE.ie_key()],
1857 },
1858 {
1859 # ThePlatform embedded with whitespaces in URLs
1860 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1861 'only_matching': True,
1862 },
1863 {
1864 # Senate ISVP iframe https
1865 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1866 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1867 'info_dict': {
1868 'id': 'govtaff020316',
1869 'ext': 'mp4',
1870 'title': 'Integrated Senate Video Player',
1871 },
1872 'add_ie': [SenateISVPIE.ie_key()],
1873 },
1874 {
1875 # Limelight embeds (1 channel embed + 4 media embeds)
1876 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1877 'info_dict': {
1878 'id': 'FacilitatorTraining2017',
1879 'title': 'Facilitator Training 2017',
1880 },
1881 'playlist_mincount': 5,
1882 },
1883 {
1884 # Limelight embed (LimelightPlayerUtil.embed)
1885 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1886 'info_dict': {
1887 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1888 'ext': 'mp4',
1889 'title': '07448641',
1890 'timestamp': 1499890639,
1891 'upload_date': '20170712',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 'add_ie': ['LimelightMedia'],
1897 },
1898 {
1899 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1900 'info_dict': {
1901 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1902 'title': 'Standoff with Walnut Creek murder suspect ends',
1903 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1904 },
1905 'playlist_mincount': 4,
1906 },
1907 {
1908 # WashingtonPost embed
1909 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1910 'info_dict': {
1911 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1912 'ext': 'mp4',
1913 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1914 '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.',
1915 'timestamp': 1455216756,
1916 'uploader': 'The Washington Post',
1917 'upload_date': '20160211',
1918 },
1919 'add_ie': [WashingtonPostIE.ie_key()],
1920 },
1921 {
1922 # Mediaset embed
1923 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1924 'info_dict': {
1925 'id': '720642',
1926 'ext': 'mp4',
1927 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1928 },
1929 'params': {
1930 'skip_download': True,
1931 },
1932 'add_ie': [MediasetIE.ie_key()],
1933 },
1934 {
1935 # JOJ.sk embeds
1936 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1937 'info_dict': {
1938 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1939 'title': 'Slovenskom sa prehnala vlna silných búrok',
1940 },
1941 'playlist_mincount': 5,
1942 'add_ie': [JojIE.ie_key()],
1943 },
1944 {
1945 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1946 'url': 'https://tvrain.ru/amp/418921/',
1947 'md5': 'cc00413936695987e8de148b67d14f1d',
1948 'info_dict': {
1949 'id': '418921',
1950 'ext': 'mp4',
1951 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1952 },
1953 },
1954 {
1955 # vzaar embed
1956 'url': 'http://help.vzaar.com/article/165-embedding-video',
1957 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1958 'info_dict': {
1959 'id': '8707641',
1960 'ext': 'mp4',
1961 'title': 'Building A Business Online: Principal Chairs Q & A',
1962 },
1963 },
1964 {
1965 # multiple HTML5 videos on one page
1966 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1967 'info_dict': {
1968 'id': 'keyscenarios',
1969 'title': 'Rescue Kit 14 Free Edition - Getting started',
1970 },
1971 'playlist_count': 4,
1972 },
1973 {
1974 # vshare embed
1975 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1976 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1977 'info_dict': {
1978 'id': '0f64ce6',
1979 'title': 'vl14062007715967',
1980 'ext': 'mp4',
1981 }
1982 },
1983 {
1984 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1985 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1986 'info_dict': {
1987 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1988 'ext': 'mp4',
1989 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1990 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1991 'timestamp': 1474354800,
1992 'upload_date': '20160920',
1993 }
1994 },
1995 {
1996 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1997 'info_dict': {
1998 'id': '1731611',
1999 'ext': 'mp4',
2000 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2001 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2002 'timestamp': 1516100691,
2003 'upload_date': '20180116',
2004 },
2005 'params': {
2006 'skip_download': True,
2007 },
2008 'add_ie': [SpringboardPlatformIE.ie_key()],
2009 },
2010 {
2011 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2012 'info_dict': {
2013 'id': 'vMDE4NzI1Mjgt690b',
2014 'ext': 'mp4',
2015 'title': 'Котята',
2016 },
2017 'add_ie': [YapFilesIE.ie_key()],
2018 'params': {
2019 'skip_download': True,
2020 },
2021 },
2022 {
2023 # CloudflareStream embed
2024 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2025 'info_dict': {
2026 'id': '31c9291ab41fac05471db4e73aa11717',
2027 'ext': 'mp4',
2028 'title': '31c9291ab41fac05471db4e73aa11717',
2029 },
2030 'add_ie': [CloudflareStreamIE.ie_key()],
2031 'params': {
2032 'skip_download': True,
2033 },
2034 },
2035 {
2036 # PeerTube embed
2037 'url': 'https://joinpeertube.org/fr/home/',
2038 'info_dict': {
2039 'id': 'home',
2040 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2041 },
2042 'playlist_count': 2,
2043 },
2044 {
2045 # Indavideo embed
2046 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2047 'info_dict': {
2048 'id': '1693903',
2049 'ext': 'mp4',
2050 'title': 'Így kell otthon hamburgert sütni',
2051 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2052 'timestamp': 1426330212,
2053 'upload_date': '20150314',
2054 'uploader': 'StreetKitchen',
2055 'uploader_id': '546363',
2056 },
2057 'add_ie': [IndavideoEmbedIE.ie_key()],
2058 'params': {
2059 'skip_download': True,
2060 },
2061 },
2062 {
2063 # APA embed via JWPlatform embed
2064 'url': 'http://www.vol.at/blue-man-group/5593454',
2065 'info_dict': {
2066 'id': 'jjv85FdZ',
2067 'ext': 'mp4',
2068 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2069 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2070 'thumbnail': r're:^https?://.*\.jpg$',
2071 'duration': 254,
2072 'timestamp': 1519211149,
2073 'upload_date': '20180221',
2074 },
2075 'params': {
2076 'skip_download': True,
2077 },
2078 },
2079 {
2080 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2081 'md5': 'b68d276de422ab07ee1d49388103f457',
2082 'info_dict': {
2083 'id': '83645793',
2084 'title': 'Lock up and get excited',
2085 'ext': 'mp4'
2086 },
2087 'skip': 'TODO: fix nested playlists processing in tests',
2088 },
2089 {
2090 # Viqeo embeds
2091 'url': 'https://viqeo.tv/',
2092 'info_dict': {
2093 'id': 'viqeo',
2094 'title': 'All-new video platform',
2095 },
2096 'playlist_count': 6,
2097 },
2098 {
2099 # Squarespace video embed, 2019-08-28
2100 'url': 'http://ootboxford.com',
2101 'info_dict': {
2102 'id': 'Tc7b_JGdZfw',
2103 'title': 'Out of the Blue, at Childish Things 10',
2104 'ext': 'mp4',
2105 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2106 'uploader_id': 'helendouglashouse',
2107 'uploader': 'Helen & Douglas House',
2108 'upload_date': '20140328',
2109 },
2110 'params': {
2111 'skip_download': True,
2112 },
2113 },
2114 # {
2115 # # Zype embed
2116 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2117 # 'info_dict': {
2118 # 'id': '5b400b834b32992a310622b9',
2119 # 'ext': 'mp4',
2120 # 'title': 'Smoky Barbecue Favorites',
2121 # 'thumbnail': r're:^https?://.*\.jpe?g',
2122 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2123 # 'upload_date': '20170909',
2124 # 'timestamp': 1504915200,
2125 # },
2126 # 'add_ie': [ZypeIE.ie_key()],
2127 # 'params': {
2128 # 'skip_download': True,
2129 # },
2130 # },
2131 {
2132 # videojs embed
2133 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2134 'info_dict': {
2135 'id': 'shell',
2136 'ext': 'mp4',
2137 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2138 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2139 'thumbnail': r're:^https?://.*\.jpg$',
2140 },
2141 'params': {
2142 'skip_download': True,
2143 },
2144 'expected_warnings': ['Failed to download MPD manifest'],
2145 },
2146 {
2147 # DailyMotion embed with DM.player
2148 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2149 'info_dict': {
2150 'id': 'k6aKkGHd9FJs4mtJN39',
2151 'ext': 'mp4',
2152 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2153 'description': 'This video is private.',
2154 'uploader_id': 'x1jf30l',
2155 'uploader': 'beIN SPORTS USA',
2156 'upload_date': '20190528',
2157 'timestamp': 1559062971,
2158 },
2159 'params': {
2160 'skip_download': True,
2161 },
2162 },
2163 # {
2164 # # TODO: find another test
2165 # # http://schema.org/VideoObject
2166 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2167 # 'md5': '888dcf08b7ea671381f00fab74692755',
2168 # 'info_dict': {
2169 # 'id': 'nyvTSJMKId',
2170 # 'ext': 'mp4',
2171 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2172 # 'description': '#love for cats.',
2173 # 'timestamp': 1461244995,
2174 # 'upload_date': '20160421',
2175 # },
2176 # 'params': {
2177 # 'force_generic_extractor': True,
2178 # },
2179 # },
2180 {
2181 # VHX Embed
2182 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2183 'info_dict': {
2184 'id': '858208',
2185 'ext': 'mp4',
2186 'title': 'Untitled',
2187 'uploader_id': 'user80538407',
2188 'uploader': 'OTT Videos',
2189 },
2190 },
2191 {
2192 # ArcPublishing PoWa video player
2193 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2194 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2195 'info_dict': {
2196 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2197 'ext': 'mp4',
2198 'title': 'Senate candidates wave to voters on Anchorage streets',
2199 'description': 'md5:91f51a6511f090617353dc720318b20e',
2200 'timestamp': 1604378735,
2201 'upload_date': '20201103',
2202 'duration': 1581,
2203 },
2204 },
2205 {
2206 # MyChannels SDK embed
2207 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2208 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2209 'md5': '90c0699c37006ef18e198c032d81739c',
2210 'info_dict': {
2211 'id': '194165',
2212 'ext': 'mp4',
2213 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2214 'timestamp': 1611740340,
2215 'upload_date': '20210127',
2216 'duration': 159,
2217 },
2218 },
2219 {
2220 # Simplecast player embed
2221 'url': 'https://www.bio.org/podcast',
2222 'info_dict': {
2223 'id': 'podcast',
2224 'title': 'I AM BIO Podcast | BIO',
2225 },
2226 'playlist_mincount': 52,
2227 },
2228 {
2229 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2230 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2231 'only_matching': True,
2232 }, {
2233 # KVS Player
2234 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2235 'info_dict': {
2236 'id': '105',
2237 'display_id': 'kelis-4th-of-july',
2238 'ext': 'mp4',
2239 'title': 'Kelis - 4th Of July',
2240 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2241 },
2242 }, {
2243 # KVS Player
2244 'url': 'https://www.kvs-demo.com/embed/105/',
2245 'info_dict': {
2246 'id': '105',
2247 'display_id': 'kelis-4th-of-july',
2248 'ext': 'mp4',
2249 'title': 'Kelis - 4th Of July / Embed Player',
2250 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2251 },
2252 'params': {
2253 'skip_download': True,
2254 },
2255 }, {
2256 # KVS Player (tested also in thisvid.py)
2257 'url': 'https://youix.com/video/leningrad-zoj/',
2258 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2259 'info_dict': {
2260 'id': '18485',
2261 'display_id': 'leningrad-zoj',
2262 'ext': 'mp4',
2263 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2264 'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
2265 },
2266 }, {
2267 # KVS Player
2268 'url': 'https://youix.com/embed/18485',
2269 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2270 'info_dict': {
2271 'id': '18485',
2272 'display_id': 'leningrad-zoj',
2273 'ext': 'mp4',
2274 'title': 'Ленинград - ЗОЖ',
2275 'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
2276 },
2277 }, {
2278 # KVS Player
2279 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2280 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2281 'info_dict': {
2282 'id': '21217',
2283 'display_id': '40-nochey-2016',
2284 'ext': 'mp4',
2285 'title': '40 ночей (2016) - BogMedia.org',
2286 'description': 'md5:4e6d7d622636eb7948275432eb256dc3',
2287 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2288 },
2289 }, {
2290 # KVS Player (for sites that serve kt_player.js via non-https urls)
2291 'url': 'http://www.camhub.world/embed/389508',
2292 'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
2293 'info_dict': {
2294 'id': '389508',
2295 'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
2296 'ext': 'mp4',
2297 'title': 'Syren De Mer onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
2298 'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
2299 },
2300 }, {
2301 'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
2302 'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
2303 'info_dict': {
2304 'id': '5',
2305 'display_id': 'selena-gomez-pov-deep-fakes',
2306 'ext': 'mp4',
2307 'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes',
2308 'description': 'md5:17d1f84b578c9c26875ac5ef9a932354',
2309 'height': 720,
2310 'age_limit': 18,
2311 },
2312 }, {
2313 'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
2314 'md5': 'e2f0a4c329f7986280b7328e24036d60',
2315 'info_dict': {
2316 'id': '284002',
2317 'display_id': 'just-out-of-the-shower-joi',
2318 'ext': 'mp4',
2319 'title': 'Just Out Of The Shower JOI - Shooshtime',
2320 'height': 720,
2321 'age_limit': 18,
2322 },
2323 },
2324 ]
2325
2326 def report_following_redirect(self, new_url):
2327 """Report information extraction."""
2328 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2329
2330 def _extract_rss(self, url, video_id, doc):
2331 playlist_title = doc.find('./channel/title').text
2332 playlist_desc_el = doc.find('./channel/description')
2333 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2334
2335 NS_MAP = {
2336 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2337 }
2338
2339 entries = []
2340 for it in doc.findall('./channel/item'):
2341 next_url = None
2342 enclosure_nodes = it.findall('./enclosure')
2343 for e in enclosure_nodes:
2344 next_url = e.attrib.get('url')
2345 if next_url:
2346 break
2347
2348 if not next_url:
2349 next_url = xpath_text(it, 'link', fatal=False)
2350
2351 if not next_url:
2352 continue
2353
2354 def itunes(key):
2355 return xpath_text(
2356 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2357 default=None)
2358
2359 duration = itunes('duration')
2360 explicit = (itunes('explicit') or '').lower()
2361 if explicit in ('true', 'yes'):
2362 age_limit = 18
2363 elif explicit in ('false', 'no'):
2364 age_limit = 0
2365 else:
2366 age_limit = None
2367
2368 entries.append({
2369 '_type': 'url_transparent',
2370 'url': next_url,
2371 'title': it.find('title').text,
2372 'description': xpath_text(it, 'description', default=None),
2373 'timestamp': unified_timestamp(
2374 xpath_text(it, 'pubDate', default=None)),
2375 'duration': int_or_none(duration) or parse_duration(duration),
2376 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2377 'episode': itunes('title'),
2378 'episode_number': int_or_none(itunes('episode')),
2379 'season_number': int_or_none(itunes('season')),
2380 'age_limit': age_limit,
2381 })
2382
2383 return {
2384 '_type': 'playlist',
2385 'id': url,
2386 'title': playlist_title,
2387 'description': playlist_desc,
2388 'entries': entries,
2389 }
2390
2391 def _extract_camtasia(self, url, video_id, webpage):
2392 """ Returns None if no camtasia video can be found. """
2393
2394 camtasia_cfg = self._search_regex(
2395 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2396 webpage, 'camtasia configuration file', default=None)
2397 if camtasia_cfg is None:
2398 return None
2399
2400 title = self._html_search_meta('DC.title', webpage, fatal=True)
2401
2402 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2403 camtasia_cfg = self._download_xml(
2404 camtasia_url, video_id,
2405 note='Downloading camtasia configuration',
2406 errnote='Failed to download camtasia configuration')
2407 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2408
2409 entries = []
2410 for n in fileset_node.getchildren():
2411 url_n = n.find('./uri')
2412 if url_n is None:
2413 continue
2414
2415 entries.append({
2416 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2417 'title': '%s - %s' % (title, n.tag),
2418 'url': compat_urlparse.urljoin(url, url_n.text),
2419 'duration': float_or_none(n.find('./duration').text),
2420 })
2421
2422 return {
2423 '_type': 'playlist',
2424 'entries': entries,
2425 'title': title,
2426 }
2427
2428 def _extract_kvs(self, url, webpage, video_id):
2429
2430 def getlicensetoken(license):
2431 modlicense = license.replace('$', '').replace('0', '1')
2432 center = int(len(modlicense) / 2)
2433 fronthalf = int(modlicense[:center + 1])
2434 backhalf = int(modlicense[center:])
2435
2436 modlicense = compat_str(4 * abs(fronthalf - backhalf))
2437
2438 def parts():
2439 for o in range(0, center + 1):
2440 for i in range(1, 5):
2441 yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
2442
2443 return ''.join(parts())
2444
2445 def getrealurl(video_url, license_code):
2446 if not video_url.startswith('function/0/'):
2447 return video_url # not obfuscated
2448
2449 url_path, _, url_query = video_url.partition('?')
2450 urlparts = url_path.split('/')[2:]
2451 license = getlicensetoken(license_code)
2452 newmagic = urlparts[5][:32]
2453
2454 def spells(x, o):
2455 l = (o + sum(int(n) for n in license[o:])) % 32
2456 for i in range(0, len(x)):
2457 yield {l: x[o], o: x[l]}.get(i, x[i])
2458
2459 for o in range(len(newmagic) - 1, -1, -1):
2460 newmagic = ''.join(spells(newmagic, o))
2461
2462 urlparts[5] = newmagic + urlparts[5][32:]
2463 return '/'.join(urlparts) + '?' + url_query
2464
2465 flashvars = self._search_regex(
2466 r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
2467 webpage, 'flashvars')
2468 flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
2469
2470 # extract the part after the last / as the display_id from the
2471 # canonical URL.
2472 display_id = self._search_regex(
2473 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
2474 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
2475 webpage, 'display_id', fatal=False
2476 )
2477 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
2478
2479 thumbnail = flashvars['preview_url']
2480 if thumbnail.startswith('//'):
2481 protocol, _, _ = url.partition('/')
2482 thumbnail = protocol + thumbnail
2483
2484 url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
2485 formats = []
2486 for key in url_keys:
2487 if '/get_file/' not in flashvars[key]:
2488 continue
2489 format_id = flashvars.get(key + '_text', key)
2490 formats.append(merge_dicts(
2491 parse_resolution(format_id) or parse_resolution(flashvars[key]), {
2492 'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
2493 'format_id': format_id,
2494 'ext': 'mp4',
2495 'http_headers': {'Referer': url},
2496 }))
2497 if not formats[-1].get('height'):
2498 formats[-1]['quality'] = 1
2499
2500 self._sort_formats(formats)
2501
2502 return {
2503 'id': flashvars['video_id'],
2504 'display_id': display_id,
2505 'title': title,
2506 'thumbnail': thumbnail,
2507 'formats': formats,
2508 }
2509
2510 def _real_extract(self, url):
2511 if url.startswith('//'):
2512 return self.url_result(self.http_scheme() + url)
2513
2514 parsed_url = compat_urlparse.urlparse(url)
2515 if not parsed_url.scheme:
2516 default_search = self._downloader.params.get('default_search')
2517 if default_search is None:
2518 default_search = 'fixup_error'
2519
2520 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2521 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2522 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2523 return self.url_result('http://' + url)
2524 elif default_search != 'fixup_error':
2525 if default_search == 'auto_warning':
2526 if re.match(r'^(?:url|URL)$', url):
2527 raise ExtractorError(
2528 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2529 expected=True)
2530 else:
2531 self._downloader.report_warning(
2532 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2533 return self.url_result('ytsearch:' + url)
2534
2535 if default_search in ('error', 'fixup_error'):
2536 raise ExtractorError(
2537 '%r is not a valid URL. '
2538 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2539 % (url, url), expected=True)
2540 else:
2541 if ':' not in default_search:
2542 default_search += ':'
2543 return self.url_result(default_search + url)
2544
2545 url, smuggled_data = unsmuggle_url(url)
2546 force_videoid = None
2547 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2548 if smuggled_data and 'force_videoid' in smuggled_data:
2549 force_videoid = smuggled_data['force_videoid']
2550 video_id = force_videoid
2551 else:
2552 video_id = self._generic_id(url)
2553
2554 self.to_screen('%s: Requesting header' % video_id)
2555
2556 head_req = HEADRequest(url)
2557 head_response = self._request_webpage(
2558 head_req, video_id,
2559 note=False, errnote='Could not send HEAD request to %s' % url,
2560 fatal=False)
2561
2562 if head_response is not False:
2563 # Check for redirect
2564 new_url = head_response.geturl()
2565 if url != new_url:
2566 self.report_following_redirect(new_url)
2567 if force_videoid:
2568 new_url = smuggle_url(
2569 new_url, {'force_videoid': force_videoid})
2570 return self.url_result(new_url)
2571
2572 full_response = None
2573 if head_response is False:
2574 request = sanitized_Request(url)
2575 request.add_header('Accept-Encoding', '*')
2576 full_response = self._request_webpage(request, video_id)
2577 head_response = full_response
2578
2579 info_dict = {
2580 'id': video_id,
2581 'title': self._generic_title(url),
2582 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2583 }
2584
2585 # Check for direct link to a video
2586 content_type = head_response.headers.get('Content-Type', '').lower()
2587 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2588 if m:
2589 format_id = compat_str(m.group('format_id'))
2590 if format_id.endswith('mpegurl'):
2591 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2592 elif format_id == 'f4m':
2593 formats = self._extract_f4m_formats(url, video_id)
2594 else:
2595 formats = [{
2596 'format_id': format_id,
2597 'url': url,
2598 'vcodec': 'none' if m.group('type') == 'audio' else None
2599 }]
2600 info_dict['direct'] = True
2601 self._sort_formats(formats)
2602 info_dict['formats'] = formats
2603 return info_dict
2604
2605 if not self._downloader.params.get('test', False) and not is_intentional:
2606 force = self._downloader.params.get('force_generic_extractor', False)
2607 self._downloader.report_warning(
2608 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2609
2610 if not full_response:
2611 request = sanitized_Request(url)
2612 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2613 # making it impossible to download only chunk of the file (yet we need only 512kB to
2614 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2615 # that will always result in downloading the whole file that is not desirable.
2616 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2617 # to accept raw bytes and being able to download only a chunk.
2618 # It may probably better to solve this by checking Content-Type for application/octet-stream
2619 # after HEAD request finishes, but not sure if we can rely on this.
2620 request.add_header('Accept-Encoding', '*')
2621 full_response = self._request_webpage(request, video_id)
2622
2623 first_bytes = full_response.read(512)
2624
2625 # Is it an M3U playlist?
2626 if first_bytes.startswith(b'#EXTM3U'):
2627 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2628 self._sort_formats(info_dict['formats'])
2629 return info_dict
2630
2631 # Maybe it's a direct link to a video?
2632 # Be careful not to download the whole thing!
2633 if not is_html(first_bytes):
2634 self._downloader.report_warning(
2635 'URL could be a direct video link, returning it as such.')
2636 info_dict.update({
2637 'direct': True,
2638 'url': url,
2639 })
2640 return info_dict
2641
2642 webpage = self._webpage_read_content(
2643 full_response, url, video_id, prefix=first_bytes)
2644
2645 if '<title>DPG Media Privacy Gate</title>' in webpage:
2646 webpage = self._download_webpage(url, video_id)
2647
2648 self.report_extraction(video_id)
2649
2650 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2651 try:
2652 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2653 if doc.tag == 'rss':
2654 return self._extract_rss(url, video_id, doc)
2655 elif doc.tag == 'SmoothStreamingMedia':
2656 info_dict['formats'] = self._parse_ism_formats(doc, url)
2657 self._sort_formats(info_dict['formats'])
2658 return info_dict
2659 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2660 smil = self._parse_smil(doc, url, video_id)
2661 self._sort_formats(smil['formats'])
2662 return smil
2663 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2664 return self.playlist_result(
2665 self._parse_xspf(
2666 doc, video_id, xspf_url=url,
2667 xspf_base_url=full_response.geturl()),
2668 video_id)
2669 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2670 info_dict['formats'] = self._parse_mpd_formats(
2671 doc,
2672 mpd_base_url=full_response.geturl().rpartition('/')[0],
2673 mpd_url=url)
2674 self._sort_formats(info_dict['formats'])
2675 return info_dict
2676 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2677 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2678 self._sort_formats(info_dict['formats'])
2679 return info_dict
2680 except compat_xml_parse_error:
2681 pass
2682
2683 # Is it a Camtasia project?
2684 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2685 if camtasia_res is not None:
2686 return camtasia_res
2687
2688 # Sometimes embedded video player is hidden behind percent encoding
2689 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2690 # Unescaping the whole page allows to handle those cases in a generic way
2691 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2692 # There probably should be a second run of generic extractor on unescaped webpage.
2693 # webpage = compat_urllib_parse_unquote(webpage)
2694
2695 # Unescape squarespace embeds to be detected by generic extractor,
2696 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2697 webpage = re.sub(
2698 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2699 lambda x: unescapeHTML(x.group(0)), webpage)
2700
2701 # it's tempting to parse this further, but you would
2702 # have to take into account all the variations like
2703 # Video Title - Site Name
2704 # Site Name | Video Title
2705 # Video Title - Tagline | Site Name
2706 # and so on and so forth; it's just not practical
2707 video_title = self._og_search_title(
2708 webpage, default=None) or self._html_search_regex(
2709 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2710 default='video')
2711
2712 # Try to detect age limit automatically
2713 age_limit = self._rta_search(webpage)
2714 # And then there are the jokers who advertise that they use RTA,
2715 # but actually don't.
2716 AGE_LIMIT_MARKERS = [
2717 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2718 r'>[^<]*you acknowledge you are at least (\d+) years old',
2719 r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
2720 ]
2721 for marker in AGE_LIMIT_MARKERS:
2722 m = re.search(marker, webpage)
2723 if not m:
2724 continue
2725 age_limit = max(
2726 age_limit or 0,
2727 int_or_none(m.groups() and m.group(1), default=18))
2728
2729 # video uploader is domain name
2730 video_uploader = self._search_regex(
2731 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2732
2733 video_description = self._og_search_description(webpage, default=None)
2734 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2735
2736 info_dict.update({
2737 'title': video_title,
2738 'description': video_description,
2739 'thumbnail': video_thumbnail,
2740 'age_limit': age_limit,
2741 })
2742
2743 # Look for Brightcove Legacy Studio embeds
2744 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2745 if bc_urls:
2746 entries = [{
2747 '_type': 'url',
2748 'url': smuggle_url(bc_url, {'Referer': url}),
2749 'ie_key': 'BrightcoveLegacy'
2750 } for bc_url in bc_urls]
2751
2752 return {
2753 '_type': 'playlist',
2754 'title': video_title,
2755 'id': video_id,
2756 'entries': entries,
2757 }
2758
2759 # Look for Brightcove New Studio embeds
2760 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2761 if bc_urls:
2762 return self.playlist_from_matches(
2763 bc_urls, video_id, video_title,
2764 getter=lambda x: smuggle_url(x, {'referrer': url}),
2765 ie='BrightcoveNew')
2766
2767 # Look for Nexx embeds
2768 nexx_urls = NexxIE._extract_urls(webpage)
2769 if nexx_urls:
2770 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2771
2772 # Look for Nexx iFrame embeds
2773 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2774 if nexx_embed_urls:
2775 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2776
2777 # Look for ThePlatform embeds
2778 tp_urls = ThePlatformIE._extract_urls(webpage)
2779 if tp_urls:
2780 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2781
2782 arc_urls = ArcPublishingIE._extract_urls(webpage)
2783 if arc_urls:
2784 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2785
2786 mychannels_urls = MedialaanIE._extract_urls(webpage)
2787 if mychannels_urls:
2788 return self.playlist_from_matches(
2789 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2790
2791 # Look for embedded rtl.nl player
2792 matches = re.findall(
2793 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2794 webpage)
2795 if matches:
2796 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2797
2798 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2799 if vimeo_urls:
2800 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2801
2802 vhx_url = VHXEmbedIE._extract_url(webpage)
2803 if vhx_url:
2804 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2805
2806 vid_me_embed_url = self._search_regex(
2807 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2808 webpage, 'vid.me embed', default=None)
2809 if vid_me_embed_url is not None:
2810 return self.url_result(vid_me_embed_url, 'Vidme')
2811
2812 # Look for YouTube embeds
2813 youtube_urls = YoutubeIE._extract_urls(webpage)
2814 if youtube_urls:
2815 return self.playlist_from_matches(
2816 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2817
2818 matches = DailymotionIE._extract_urls(webpage)
2819 if matches:
2820 return self.playlist_from_matches(matches, video_id, video_title)
2821
2822 # Look for embedded Dailymotion playlist player (#3822)
2823 m = re.search(
2824 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2825 if m:
2826 playlists = re.findall(
2827 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2828 if playlists:
2829 return self.playlist_from_matches(
2830 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2831
2832 # Look for DailyMail embeds
2833 dailymail_urls = DailyMailIE._extract_urls(webpage)
2834 if dailymail_urls:
2835 return self.playlist_from_matches(
2836 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2837
2838 # Look for Teachable embeds, must be before Wistia
2839 teachable_url = TeachableIE._extract_url(webpage, url)
2840 if teachable_url:
2841 return self.url_result(teachable_url)
2842
2843 # Look for embedded Wistia player
2844 wistia_urls = WistiaIE._extract_urls(webpage)
2845 if wistia_urls:
2846 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2847 for entry in playlist['entries']:
2848 entry.update({
2849 '_type': 'url_transparent',
2850 'uploader': video_uploader,
2851 })
2852 return playlist
2853
2854 # Look for SVT player
2855 svt_url = SVTIE._extract_url(webpage)
2856 if svt_url:
2857 return self.url_result(svt_url, 'SVT')
2858
2859 # Look for Bandcamp pages with custom domain
2860 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2861 if mobj is not None:
2862 burl = unescapeHTML(mobj.group(1))
2863 # Don't set the extractor because it can be a track url or an album
2864 return self.url_result(burl)
2865
2866 # Look for embedded Vevo player
2867 mobj = re.search(
2868 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2869 if mobj is not None:
2870 return self.url_result(mobj.group('url'))
2871
2872 # Look for embedded Viddler player
2873 mobj = re.search(
2874 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2875 webpage)
2876 if mobj is not None:
2877 return self.url_result(mobj.group('url'))
2878
2879 # Look for NYTimes player
2880 mobj = re.search(
2881 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2882 webpage)
2883 if mobj is not None:
2884 return self.url_result(mobj.group('url'))
2885
2886 # Look for Libsyn player
2887 mobj = re.search(
2888 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2889 if mobj is not None:
2890 return self.url_result(mobj.group('url'))
2891
2892 # Look for Ooyala videos
2893 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2894 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2895 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2896 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2897 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2898 if mobj is not None:
2899 embed_token = self._search_regex(
2900 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2901 webpage, 'ooyala embed token', default=None)
2902 return OoyalaIE._build_url_result(smuggle_url(
2903 mobj.group('ec'), {
2904 'domain': url,
2905 'embed_token': embed_token,
2906 }))
2907
2908 # Look for multiple Ooyala embeds on SBN network websites
2909 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2910 if mobj is not None:
2911 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2912 if embeds:
2913 return self.playlist_from_matches(
2914 embeds, video_id, video_title,
2915 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2916
2917 # Look for Aparat videos
2918 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2919 if mobj is not None:
2920 return self.url_result(mobj.group(1), 'Aparat')
2921
2922 # Look for MPORA videos
2923 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2924 if mobj is not None:
2925 return self.url_result(mobj.group(1), 'Mpora')
2926
2927 # Look for embedded Facebook player
2928 facebook_urls = FacebookIE._extract_urls(webpage)
2929 if facebook_urls:
2930 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2931
2932 # Look for embedded VK player
2933 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2934 if mobj is not None:
2935 return self.url_result(mobj.group('url'), 'VK')
2936
2937 # Look for embedded Odnoklassniki player
2938 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2939 if odnoklassniki_url:
2940 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2941
2942 # Look for sibnet embedded player
2943 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2944 if sibnet_urls:
2945 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2946
2947 # Look for embedded ivi player
2948 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2949 if mobj is not None:
2950 return self.url_result(mobj.group('url'), 'Ivi')
2951
2952 # Look for embedded Huffington Post player
2953 mobj = re.search(
2954 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2955 if mobj is not None:
2956 return self.url_result(mobj.group('url'), 'HuffPost')
2957
2958 # Look for embed.ly
2959 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2960 if mobj is not None:
2961 return self.url_result(mobj.group('url'))
2962 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2963 if mobj is not None:
2964 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2965
2966 # Look for funnyordie embed
2967 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2968 if matches:
2969 return self.playlist_from_matches(
2970 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2971
2972 # Look for Simplecast embeds
2973 simplecast_urls = SimplecastIE._extract_urls(webpage)
2974 if simplecast_urls:
2975 return self.playlist_from_matches(
2976 simplecast_urls, video_id, video_title)
2977
2978 # Look for BBC iPlayer embed
2979 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2980 if matches:
2981 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2982
2983 # Look for embedded RUTV player
2984 rutv_url = RUTVIE._extract_url(webpage)
2985 if rutv_url:
2986 return self.url_result(rutv_url, 'RUTV')
2987
2988 # Look for embedded TVC player
2989 tvc_url = TVCIE._extract_url(webpage)
2990 if tvc_url:
2991 return self.url_result(tvc_url, 'TVC')
2992
2993 # Look for embedded SportBox player
2994 sportbox_urls = SportBoxIE._extract_urls(webpage)
2995 if sportbox_urls:
2996 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2997
2998 # Look for embedded XHamster player
2999 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
3000 if xhamster_urls:
3001 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
3002
3003 # Look for embedded TNAFlixNetwork player
3004 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
3005 if tnaflix_urls:
3006 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
3007
3008 # Look for embedded PornHub player
3009 pornhub_urls = PornHubIE._extract_urls(webpage)
3010 if pornhub_urls:
3011 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
3012
3013 # Look for embedded DrTuber player
3014 drtuber_urls = DrTuberIE._extract_urls(webpage)
3015 if drtuber_urls:
3016 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
3017
3018 # Look for embedded RedTube player
3019 redtube_urls = RedTubeIE._extract_urls(webpage)
3020 if redtube_urls:
3021 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
3022
3023 # Look for embedded Tube8 player
3024 tube8_urls = Tube8IE._extract_urls(webpage)
3025 if tube8_urls:
3026 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
3027
3028 # Look for embedded Mofosex player
3029 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3030 if mofosex_urls:
3031 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3032
3033 # Look for embedded Spankwire player
3034 spankwire_urls = SpankwireIE._extract_urls(webpage)
3035 if spankwire_urls:
3036 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3037
3038 # Look for embedded YouPorn player
3039 youporn_urls = YouPornIE._extract_urls(webpage)
3040 if youporn_urls:
3041 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3042
3043 # Look for embedded Tvigle player
3044 mobj = re.search(
3045 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3046 if mobj is not None:
3047 return self.url_result(mobj.group('url'), 'Tvigle')
3048
3049 # Look for embedded TED player
3050 mobj = re.search(
3051 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
3052 if mobj is not None:
3053 return self.url_result(mobj.group('url'), 'TED')
3054
3055 # Look for embedded Ustream videos
3056 ustream_url = UstreamIE._extract_url(webpage)
3057 if ustream_url:
3058 return self.url_result(ustream_url, UstreamIE.ie_key())
3059
3060 # Look for embedded arte.tv player
3061 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3062 if arte_urls:
3063 return self.playlist_from_matches(arte_urls, video_id, video_title)
3064
3065 # Look for embedded francetv player
3066 mobj = re.search(
3067 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3068 webpage)
3069 if mobj is not None:
3070 return self.url_result(mobj.group('url'))
3071
3072 # Look for embedded Myvi.ru player
3073 myvi_url = MyviIE._extract_url(webpage)
3074 if myvi_url:
3075 return self.url_result(myvi_url)
3076
3077 # Look for embedded soundcloud player
3078 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3079 if soundcloud_urls:
3080 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3081
3082 # Look for tunein player
3083 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3084 if tunein_urls:
3085 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3086
3087 # Look for embedded mtvservices player
3088 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3089 if mtvservices_url:
3090 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3091
3092 # Look for embedded yahoo player
3093 mobj = re.search(
3094 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3095 webpage)
3096 if mobj is not None:
3097 return self.url_result(mobj.group('url'), 'Yahoo')
3098
3099 # Look for embedded sbs.com.au player
3100 mobj = re.search(
3101 r'''(?x)
3102 (?:
3103 <meta\s+property="og:video"\s+content=|
3104 <iframe[^>]+?src=
3105 )
3106 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3107 webpage)
3108 if mobj is not None:
3109 return self.url_result(mobj.group('url'), 'SBS')
3110
3111 # Look for embedded Cinchcast player
3112 mobj = re.search(
3113 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3114 webpage)
3115 if mobj is not None:
3116 return self.url_result(mobj.group('url'), 'Cinchcast')
3117
3118 mobj = re.search(
3119 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
3120 webpage)
3121 if not mobj:
3122 mobj = re.search(
3123 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3124 webpage)
3125 if mobj is not None:
3126 return self.url_result(mobj.group('url'), 'MLB')
3127
3128 mobj = re.search(
3129 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3130 webpage)
3131 if mobj is not None:
3132 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3133
3134 mobj = re.search(
3135 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
3136 webpage)
3137 if mobj is not None:
3138 return self.url_result(mobj.group('url'), 'Livestream')
3139
3140 # Look for Zapiks embed
3141 mobj = re.search(
3142 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3143 if mobj is not None:
3144 return self.url_result(mobj.group('url'), 'Zapiks')
3145
3146 # Look for Kaltura embeds
3147 kaltura_urls = KalturaIE._extract_urls(webpage)
3148 if kaltura_urls:
3149 return self.playlist_from_matches(
3150 kaltura_urls, video_id, video_title,
3151 getter=lambda x: smuggle_url(x, {'source_url': url}),
3152 ie=KalturaIE.ie_key())
3153
3154 # Look for EaglePlatform embeds
3155 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3156 if eagleplatform_url:
3157 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3158
3159 # Look for ClipYou (uses EaglePlatform) embeds
3160 mobj = re.search(
3161 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3162 if mobj is not None:
3163 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3164
3165 # Look for Pladform embeds
3166 pladform_url = PladformIE._extract_url(webpage)
3167 if pladform_url:
3168 return self.url_result(pladform_url)
3169
3170 # Look for Videomore embeds
3171 videomore_url = VideomoreIE._extract_url(webpage)
3172 if videomore_url:
3173 return self.url_result(videomore_url)
3174
3175 # Look for Webcaster embeds
3176 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3177 if webcaster_url:
3178 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3179
3180 # Look for Playwire embeds
3181 mobj = re.search(
3182 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3183 if mobj is not None:
3184 return self.url_result(mobj.group('url'))
3185
3186 # Look for 5min embeds
3187 mobj = re.search(
3188 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3189 if mobj is not None:
3190 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3191
3192 # Look for Crooks and Liars embeds
3193 mobj = re.search(
3194 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3195 if mobj is not None:
3196 return self.url_result(mobj.group('url'))
3197
3198 # Look for NBC Sports VPlayer embeds
3199 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3200 if nbc_sports_url:
3201 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3202
3203 # Look for NBC News embeds
3204 nbc_news_embed_url = re.search(
3205 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3206 if nbc_news_embed_url:
3207 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3208
3209 # Look for Google Drive embeds
3210 google_drive_url = GoogleDriveIE._extract_url(webpage)
3211 if google_drive_url:
3212 return self.url_result(google_drive_url, 'GoogleDrive')
3213
3214 # Look for UDN embeds
3215 mobj = re.search(
3216 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3217 if mobj is not None:
3218 return self.url_result(
3219 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3220
3221 # Look for Senate ISVP iframe
3222 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3223 if senate_isvp_url:
3224 return self.url_result(senate_isvp_url, 'SenateISVP')
3225
3226 # Look for Kinja embeds
3227 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3228 if kinja_embed_urls:
3229 return self.playlist_from_matches(
3230 kinja_embed_urls, video_id, video_title)
3231
3232 # Look for OnionStudios embeds
3233 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3234 if onionstudios_url:
3235 return self.url_result(onionstudios_url)
3236
3237 # Look for ViewLift embeds
3238 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3239 if viewlift_url:
3240 return self.url_result(viewlift_url)
3241
3242 # Look for JWPlatform embeds
3243 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3244 if jwplatform_urls:
3245 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3246
3247 # Look for Digiteka embeds
3248 digiteka_url = DigitekaIE._extract_url(webpage)
3249 if digiteka_url:
3250 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3251
3252 # Look for Arkena embeds
3253 arkena_url = ArkenaIE._extract_url(webpage)
3254 if arkena_url:
3255 return self.url_result(arkena_url, ArkenaIE.ie_key())
3256
3257 # Look for Piksel embeds
3258 piksel_url = PikselIE._extract_url(webpage)
3259 if piksel_url:
3260 return self.url_result(piksel_url, PikselIE.ie_key())
3261
3262 # Look for Limelight embeds
3263 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3264 if limelight_urls:
3265 return self.playlist_result(
3266 limelight_urls, video_id, video_title, video_description)
3267
3268 # Look for Anvato embeds
3269 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3270 if anvato_urls:
3271 return self.playlist_result(
3272 anvato_urls, video_id, video_title, video_description)
3273
3274 # Look for AdobeTVVideo embeds
3275 mobj = re.search(
3276 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3277 webpage)
3278 if mobj is not None:
3279 return self.url_result(
3280 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3281 'AdobeTVVideo')
3282
3283 # Look for Vine embeds
3284 mobj = re.search(
3285 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3286 webpage)
3287 if mobj is not None:
3288 return self.url_result(
3289 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3290
3291 # Look for VODPlatform embeds
3292 mobj = re.search(
3293 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3294 webpage)
3295 if mobj is not None:
3296 return self.url_result(
3297 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3298
3299 # Look for Mangomolo embeds
3300 mobj = re.search(
3301 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3302 (?:
3303 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3304 player\.mangomolo\.com/v1
3305 )/
3306 (?:
3307 video\?.*?\bid=(?P<video_id>\d+)|
3308 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3309 ).+?)\1''', webpage)
3310 if mobj is not None:
3311 info = {
3312 '_type': 'url_transparent',
3313 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3314 'title': video_title,
3315 'description': video_description,
3316 'thumbnail': video_thumbnail,
3317 'uploader': video_uploader,
3318 }
3319 video_id = mobj.group('video_id')
3320 if video_id:
3321 info.update({
3322 'ie_key': 'MangomoloVideo',
3323 'id': video_id,
3324 })
3325 else:
3326 info.update({
3327 'ie_key': 'MangomoloLive',
3328 'id': mobj.group('channel_id'),
3329 })
3330 return info
3331
3332 # Look for Instagram embeds
3333 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3334 if instagram_embed_url is not None:
3335 return self.url_result(
3336 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3337
3338 # Look for 3Q SDN embeds
3339 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3340 if threeqsdn_url:
3341 return {
3342 '_type': 'url_transparent',
3343 'ie_key': ThreeQSDNIE.ie_key(),
3344 'url': self._proto_relative_url(threeqsdn_url),
3345 'title': video_title,
3346 'description': video_description,
3347 'thumbnail': video_thumbnail,
3348 'uploader': video_uploader,
3349 }
3350
3351 # Look for VBOX7 embeds
3352 vbox7_url = Vbox7IE._extract_url(webpage)
3353 if vbox7_url:
3354 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3355
3356 # Look for DBTV embeds
3357 dbtv_urls = DBTVIE._extract_urls(webpage)
3358 if dbtv_urls:
3359 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3360
3361 # Look for Videa embeds
3362 videa_urls = VideaIE._extract_urls(webpage)
3363 if videa_urls:
3364 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3365
3366 # Look for 20 minuten embeds
3367 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3368 if twentymin_urls:
3369 return self.playlist_from_matches(
3370 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3371
3372 # Look for VideoPress embeds
3373 videopress_urls = VideoPressIE._extract_urls(webpage)
3374 if videopress_urls:
3375 return self.playlist_from_matches(
3376 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3377
3378 # Look for Rutube embeds
3379 rutube_urls = RutubeIE._extract_urls(webpage)
3380 if rutube_urls:
3381 return self.playlist_from_matches(
3382 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3383
3384 # Look for WashingtonPost embeds
3385 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3386 if wapo_urls:
3387 return self.playlist_from_matches(
3388 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3389
3390 # Look for Mediaset embeds
3391 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3392 if mediaset_urls:
3393 return self.playlist_from_matches(
3394 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3395
3396 # Look for JOJ.sk embeds
3397 joj_urls = JojIE._extract_urls(webpage)
3398 if joj_urls:
3399 return self.playlist_from_matches(
3400 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3401
3402 # Look for megaphone.fm embeds
3403 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3404 if mpfn_urls:
3405 return self.playlist_from_matches(
3406 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3407
3408 # Look for vzaar embeds
3409 vzaar_urls = VzaarIE._extract_urls(webpage)
3410 if vzaar_urls:
3411 return self.playlist_from_matches(
3412 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3413
3414 channel9_urls = Channel9IE._extract_urls(webpage)
3415 if channel9_urls:
3416 return self.playlist_from_matches(
3417 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3418
3419 vshare_urls = VShareIE._extract_urls(webpage)
3420 if vshare_urls:
3421 return self.playlist_from_matches(
3422 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3423
3424 # Look for Mediasite embeds
3425 mediasite_urls = MediasiteIE._extract_urls(webpage)
3426 if mediasite_urls:
3427 entries = [
3428 self.url_result(smuggle_url(
3429 compat_urlparse.urljoin(url, mediasite_url),
3430 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3431 for mediasite_url in mediasite_urls]
3432 return self.playlist_result(entries, video_id, video_title)
3433
3434 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3435 if springboardplatform_urls:
3436 return self.playlist_from_matches(
3437 springboardplatform_urls, video_id, video_title,
3438 ie=SpringboardPlatformIE.ie_key())
3439
3440 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3441 if yapfiles_urls:
3442 return self.playlist_from_matches(
3443 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3444
3445 vice_urls = ViceIE._extract_urls(webpage)
3446 if vice_urls:
3447 return self.playlist_from_matches(
3448 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3449
3450 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3451 if xfileshare_urls:
3452 return self.playlist_from_matches(
3453 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3454
3455 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3456 if cloudflarestream_urls:
3457 return self.playlist_from_matches(
3458 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3459
3460 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3461 if peertube_urls:
3462 return self.playlist_from_matches(
3463 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3464
3465 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3466 if indavideo_urls:
3467 return self.playlist_from_matches(
3468 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3469
3470 apa_urls = APAIE._extract_urls(webpage)
3471 if apa_urls:
3472 return self.playlist_from_matches(
3473 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3474
3475 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3476 if foxnews_urls:
3477 return self.playlist_from_matches(
3478 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3479
3480 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3481 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3482 webpage)]
3483 if sharevideos_urls:
3484 return self.playlist_from_matches(
3485 sharevideos_urls, video_id, video_title)
3486
3487 viqeo_urls = ViqeoIE._extract_urls(webpage)
3488 if viqeo_urls:
3489 return self.playlist_from_matches(
3490 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3491
3492 expressen_urls = ExpressenIE._extract_urls(webpage)
3493 if expressen_urls:
3494 return self.playlist_from_matches(
3495 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3496
3497 zype_urls = ZypeIE._extract_urls(webpage)
3498 if zype_urls:
3499 return self.playlist_from_matches(
3500 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3501
3502 # Look for HTML5 media
3503 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3504 if entries:
3505 if len(entries) == 1:
3506 entries[0].update({
3507 'id': video_id,
3508 'title': video_title,
3509 })
3510 else:
3511 for num, entry in enumerate(entries, start=1):
3512 entry.update({
3513 'id': '%s-%s' % (video_id, num),
3514 'title': '%s (%d)' % (video_title, num),
3515 })
3516 for entry in entries:
3517 self._sort_formats(entry['formats'])
3518 return self.playlist_result(entries, video_id, video_title)
3519
3520 jwplayer_data = self._find_jwplayer_data(
3521 webpage, video_id, transform_source=js_to_json)
3522 if jwplayer_data:
3523 try:
3524 info = self._parse_jwplayer_data(
3525 jwplayer_data, video_id, require_title=False, base_url=url)
3526 return merge_dicts(info, info_dict)
3527 except ExtractorError:
3528 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3529 pass
3530
3531 # Video.js embed
3532 mobj = re.search(
3533 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3534 webpage)
3535 if mobj is not None:
3536 sources = self._parse_json(
3537 mobj.group(1), video_id, transform_source=js_to_json,
3538 fatal=False) or []
3539 if not isinstance(sources, list):
3540 sources = [sources]
3541 formats = []
3542 for source in sources:
3543 src = source.get('src')
3544 if not src or not isinstance(src, compat_str):
3545 continue
3546 src = compat_urlparse.urljoin(url, src)
3547 src_type = source.get('type')
3548 if isinstance(src_type, compat_str):
3549 src_type = src_type.lower()
3550 ext = determine_ext(src).lower()
3551 if src_type == 'video/youtube':
3552 return self.url_result(src, YoutubeIE.ie_key())
3553 if src_type == 'application/dash+xml' or ext == 'mpd':
3554 formats.extend(self._extract_mpd_formats(
3555 src, video_id, mpd_id='dash', fatal=False))
3556 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3557 formats.extend(self._extract_m3u8_formats(
3558 src, video_id, 'mp4', entry_protocol='m3u8_native',
3559 m3u8_id='hls', fatal=False))
3560 else:
3561 formats.append({
3562 'url': src,
3563 'ext': (mimetype2ext(src_type)
3564 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3565 'http_headers': {
3566 'Referer': full_response.geturl(),
3567 },
3568 })
3569 if formats:
3570 self._sort_formats(formats)
3571 info_dict['formats'] = formats
3572 return info_dict
3573
3574 # Look for generic KVS player (before ld+json for tests)
3575 found = self._search_regex(
3576 (r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>\d+(?:\.\d+)+)\1[^>]*>',
3577 # kt_player('kt_player', 'https://i.shoosh.co/player/kt_player.swf?v=5.5.1', ...
3578 r'kt_player\s*\(\s*(["\'])(?:(?!\1)[\w\W])+\1\s*,\s*(["\'])https?://(?:\S+?/)+kt_player\.swf\?v=(?P<ver>\d+(?:\.\d+)+)\2\s*,',
3579 ), webpage, 'KVS player', group='ver', default=False)
3580 if found:
3581 self.report_extraction('%s: KVS Player' % (video_id, ))
3582 if found.split('.')[0] not in ('4', '5', '6'):
3583 self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
3584 return merge_dicts(
3585 self._extract_kvs(url, webpage, video_id),
3586 info_dict)
3587
3588 # Looking for http://schema.org/VideoObject
3589 json_ld = self._search_json_ld(
3590 webpage, video_id, default={}, expected_type='VideoObject')
3591 if json_ld.get('url'):
3592 return merge_dicts(json_ld, info_dict)
3593
3594 def check_video(vurl):
3595 if YoutubeIE.suitable(vurl):
3596 return True
3597 if RtmpIE.suitable(vurl):
3598 return True
3599 vpath = compat_urlparse.urlparse(vurl).path
3600 vext = determine_ext(vpath)
3601 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3602
3603 def filter_video(urls):
3604 return list(filter(check_video, urls))
3605
3606 # Start with something easy: JW Player in SWFObject
3607 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3608 if not found:
3609 # Look for gorilla-vid style embedding
3610 found = filter_video(re.findall(r'''(?sx)
3611 (?:
3612 jw_plugins|
3613 JWPlayerOptions|
3614 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3615 )
3616 .*?
3617 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3618 if not found:
3619 # Broaden the search a little bit
3620 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3621 if not found:
3622 # Broaden the findall a little bit: JWPlayer JS loader
3623 found = filter_video(re.findall(
3624 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3625 if not found:
3626 # Flow player
3627 found = filter_video(re.findall(r'''(?xs)
3628 flowplayer\("[^"]+",\s*
3629 \{[^}]+?\}\s*,
3630 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3631 ["']?url["']?\s*:\s*["']([^"']+)["']
3632 ''', webpage))
3633 if not found:
3634 # Cinerama player
3635 found = re.findall(
3636 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3637 if not found:
3638 # Try to find twitter cards info
3639 # twitter:player:stream should be checked before twitter:player since
3640 # it is expected to contain a raw stream (see
3641 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3642 found = filter_video(re.findall(
3643 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3644 if not found:
3645 # We look for Open Graph info:
3646 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3647 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3648 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3649 if m_video_type is not None:
3650 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3651 if not found:
3652 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3653 found = re.search(
3654 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3655 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3656 webpage)
3657 if not found:
3658 # Look also in Refresh HTTP header
3659 refresh_header = head_response.headers.get('Refresh')
3660 if refresh_header:
3661 # In python 2 response HTTP headers are bytestrings
3662 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3663 refresh_header = refresh_header.decode('iso-8859-1')
3664 found = re.search(REDIRECT_REGEX, refresh_header)
3665 if found:
3666 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3667 if new_url != url:
3668 self.report_following_redirect(new_url)
3669 return {
3670 '_type': 'url',
3671 'url': new_url,
3672 }
3673 else:
3674 found = None
3675
3676 if not found:
3677 # twitter:player is a https URL to iframe player that may or may not
3678 # be supported by youtube-dl thus this is checked the very last (see
3679 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3680 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3681 if embed_url and embed_url != url:
3682 return self.url_result(embed_url)
3683
3684 if not found:
3685 raise UnsupportedError(url)
3686
3687 entries = []
3688 for video_url in orderedSet(found):
3689 video_url = unescapeHTML(video_url)
3690 video_url = video_url.replace('\\/', '/')
3691 video_url = compat_urlparse.urljoin(url, video_url)
3692 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3693
3694 # Sometimes, jwplayer extraction will result in a YouTube URL
3695 if YoutubeIE.suitable(video_url):
3696 entries.append(self.url_result(video_url, 'Youtube'))
3697 continue
3698
3699 # here's a fun little line of code for you:
3700 video_id = os.path.splitext(video_id)[0]
3701
3702 entry_info_dict = {
3703 'id': video_id,
3704 'uploader': video_uploader,
3705 'title': video_title,
3706 'age_limit': age_limit,
3707 }
3708
3709 if RtmpIE.suitable(video_url):
3710 entry_info_dict.update({
3711 '_type': 'url_transparent',
3712 'ie_key': RtmpIE.ie_key(),
3713 'url': video_url,
3714 })
3715 entries.append(entry_info_dict)
3716 continue
3717
3718 ext = determine_ext(video_url)
3719 if ext == 'smil':
3720 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3721 elif ext == 'xspf':
3722 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3723 elif ext == 'm3u8':
3724 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3725 elif ext == 'mpd':
3726 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3727 elif ext == 'f4m':
3728 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3729 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3730 # Just matching .ism/manifest is not enough to be reliably sure
3731 # whether it's actually an ISM manifest or some other streaming
3732 # manifest since there are various streaming URL formats
3733 # possible (see [1]) as well as some other shenanigans like
3734 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3735 # so on.
3736 # Thus the most reasonable way to solve this is to delegate
3737 # to generic extractor in order to look into the contents of
3738 # the manifest itself.
3739 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3740 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3741 entry_info_dict = self.url_result(
3742 smuggle_url(video_url, {'to_generic': True}),
3743 GenericIE.ie_key())
3744 else:
3745 entry_info_dict['url'] = video_url
3746
3747 if entry_info_dict.get('formats'):
3748 self._sort_formats(entry_info_dict['formats'])
3749
3750 entries.append(entry_info_dict)
3751
3752 if len(entries) == 1:
3753 return entries[0]
3754 else:
3755 for num, e in enumerate(entries, start=1):
3756 # 'url' results don't have a title
3757 if e.get('title') is not None:
3758 e['title'] = '%s (%d)' % (e['title'], num)
3759 return {
3760 '_type': 'playlist',
3761 'entries': entries,
3762 }
|