]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[udemy] Extract asset captions
[yt-dlp.git] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 is_html,
24 js_to_json,
25 KNOWN_EXTENSIONS,
26 merge_dicts,
27 mimetype2ext,
28 orderedSet,
29 sanitized_Request,
30 smuggle_url,
31 unescapeHTML,
32 unified_strdate,
33 unsmuggle_url,
34 UnsupportedError,
35 xpath_text,
36 )
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
39 BrightcoveLegacyIE,
40 BrightcoveNewIE,
41 )
42 from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45 )
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxEmbedIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
111
112
113 class GenericIE(InfoExtractor):
114 IE_DESC = 'Generic downloader that works on some sites'
115 _VALID_URL = r'.*'
116 IE_NAME = 'generic'
117 _TESTS = [
118 # Direct link to a video
119 {
120 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
121 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
122 'info_dict': {
123 'id': 'trailer',
124 'ext': 'mp4',
125 'title': 'trailer',
126 'upload_date': '20100513',
127 }
128 },
129 # Direct link to media delivered compressed (until Accept-Encoding is *)
130 {
131 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
132 'md5': '128c42e68b13950268b648275386fc74',
133 'info_dict': {
134 'id': 'FictionJunction-Parallel_Hearts',
135 'ext': 'flac',
136 'title': 'FictionJunction-Parallel_Hearts',
137 'upload_date': '20140522',
138 },
139 'expected_warnings': [
140 'URL could be a direct video link, returning it as such.'
141 ],
142 'skip': 'URL invalid',
143 },
144 # Direct download with broken HEAD
145 {
146 'url': 'http://ai-radio.org:8000/radio.opus',
147 'info_dict': {
148 'id': 'radio',
149 'ext': 'opus',
150 'title': 'radio',
151 },
152 'params': {
153 'skip_download': True, # infinite live stream
154 },
155 'expected_warnings': [
156 r'501.*Not Implemented',
157 r'400.*Bad Request',
158 ],
159 },
160 # Direct link with incorrect MIME type
161 {
162 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
163 'md5': '4ccbebe5f36706d85221f204d7eb5913',
164 'info_dict': {
165 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
166 'id': '5_Lennart_Poettering_-_Systemd',
167 'ext': 'webm',
168 'title': '5_Lennart_Poettering_-_Systemd',
169 'upload_date': '20141120',
170 },
171 'expected_warnings': [
172 'URL could be a direct video link, returning it as such.'
173 ]
174 },
175 # RSS feed
176 {
177 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
178 'info_dict': {
179 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
180 'title': 'Zero Punctuation',
181 'description': 're:.*groundbreaking video review series.*'
182 },
183 'playlist_mincount': 11,
184 },
185 # RSS feed with enclosure
186 {
187 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
188 'info_dict': {
189 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
190 'ext': 'm4v',
191 'upload_date': '20150228',
192 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
193 }
194 },
195 # RSS feed with enclosures and unsupported link URLs
196 {
197 'url': 'http://www.hellointernet.fm/podcast?format=rss',
198 'info_dict': {
199 'id': 'http://www.hellointernet.fm/podcast?format=rss',
200 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
201 'title': 'Hello Internet',
202 },
203 'playlist_mincount': 100,
204 },
205 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
206 {
207 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
208 'info_dict': {
209 'id': 'smil',
210 'ext': 'mp4',
211 'title': 'Automatics, robotics and biocybernetics',
212 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
213 'upload_date': '20130627',
214 'formats': 'mincount:16',
215 'subtitles': 'mincount:1',
216 },
217 'params': {
218 'force_generic_extractor': True,
219 'skip_download': True,
220 },
221 },
222 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
223 {
224 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
225 'info_dict': {
226 'id': 'hds',
227 'ext': 'flv',
228 'title': 'hds',
229 'formats': 'mincount:1',
230 },
231 'params': {
232 'skip_download': True,
233 },
234 },
235 # SMIL from https://www.restudy.dk/video/play/id/1637
236 {
237 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
238 'info_dict': {
239 'id': 'video_1637',
240 'ext': 'flv',
241 'title': 'video_1637',
242 'formats': 'mincount:3',
243 },
244 'params': {
245 'skip_download': True,
246 },
247 },
248 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
249 {
250 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
251 'info_dict': {
252 'id': 'smil-service',
253 'ext': 'flv',
254 'title': 'smil-service',
255 'formats': 'mincount:1',
256 },
257 'params': {
258 'skip_download': True,
259 },
260 },
261 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
262 {
263 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
264 'info_dict': {
265 'id': '4719370',
266 'ext': 'mp4',
267 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
268 'formats': 'mincount:3',
269 },
270 'params': {
271 'skip_download': True,
272 },
273 },
274 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
275 {
276 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
277 'info_dict': {
278 'id': 'mZlp2ctYIUEB',
279 'ext': 'mp4',
280 'title': 'Tikibad ontruimd wegens brand',
281 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
282 'thumbnail': r're:^https?://.*\.jpg$',
283 'duration': 33,
284 },
285 'params': {
286 'skip_download': True,
287 },
288 },
289 # MPD from http://dash-mse-test.appspot.com/media.html
290 {
291 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
292 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
293 'info_dict': {
294 'id': 'car-20120827-manifest',
295 'ext': 'mp4',
296 'title': 'car-20120827-manifest',
297 'formats': 'mincount:9',
298 'upload_date': '20130904',
299 },
300 'params': {
301 'format': 'bestvideo',
302 },
303 },
304 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
305 {
306 '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',
307 'info_dict': {
308 'id': 'content',
309 'ext': 'mp4',
310 'title': 'content',
311 'formats': 'mincount:8',
312 },
313 'params': {
314 # m3u8 downloads
315 'skip_download': True,
316 },
317 'skip': 'video gone',
318 },
319 # m3u8 served with Content-Type: text/plain
320 {
321 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
322 'info_dict': {
323 'id': 'index',
324 'ext': 'mp4',
325 'title': 'index',
326 'upload_date': '20140720',
327 'formats': 'mincount:11',
328 },
329 'params': {
330 # m3u8 downloads
331 'skip_download': True,
332 },
333 'skip': 'video gone',
334 },
335 # google redirect
336 {
337 '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',
338 'info_dict': {
339 'id': 'cmQHVoWB5FY',
340 'ext': 'mp4',
341 'upload_date': '20130224',
342 'uploader_id': 'TheVerge',
343 'description': r're:^Chris Ziegler takes a look at the\.*',
344 'uploader': 'The Verge',
345 'title': 'First Firefox OS phones side-by-side',
346 },
347 'params': {
348 'skip_download': False,
349 }
350 },
351 {
352 # redirect in Refresh HTTP header
353 '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',
354 'info_dict': {
355 'id': 'pO8h3EaFRdo',
356 'ext': 'mp4',
357 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
358 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
359 'upload_date': '20150917',
360 'uploader_id': 'brtvofficial',
361 'uploader': 'Boiler Room',
362 },
363 'params': {
364 'skip_download': False,
365 },
366 },
367 {
368 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
369 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
370 'info_dict': {
371 'id': '13601338388002',
372 'ext': 'mp4',
373 'uploader': 'www.hodiho.fr',
374 'title': 'R\u00e9gis plante sa Jeep',
375 }
376 },
377 # bandcamp page with custom domain
378 {
379 'add_ie': ['Bandcamp'],
380 'url': 'http://bronyrock.com/track/the-pony-mash',
381 'info_dict': {
382 'id': '3235767654',
383 'ext': 'mp3',
384 'title': 'The Pony Mash',
385 'uploader': 'M_Pallante',
386 },
387 'skip': 'There is a limit of 200 free downloads / month for the test song',
388 },
389 {
390 # embedded brightcove video
391 # it also tests brightcove videos that need to set the 'Referer'
392 # in the http requests
393 'add_ie': ['BrightcoveLegacy'],
394 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
395 'info_dict': {
396 'id': '2765128793001',
397 'ext': 'mp4',
398 'title': 'Le cours de bourse : l’analyse technique',
399 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
400 'uploader': 'BFM BUSINESS',
401 },
402 'params': {
403 'skip_download': True,
404 },
405 },
406 {
407 # embedded with itemprop embedURL and video id spelled as `idVideo`
408 'add_id': ['BrightcoveLegacy'],
409 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
410 'info_dict': {
411 'id': '5255628253001',
412 'ext': 'mp4',
413 'title': 'md5:37c519b1128915607601e75a87995fc0',
414 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
415 'uploader': 'BFM BUSINESS',
416 'uploader_id': '876450612001',
417 'timestamp': 1482255315,
418 'upload_date': '20161220',
419 },
420 'params': {
421 'skip_download': True,
422 },
423 },
424 {
425 # https://github.com/rg3/youtube-dl/issues/2253
426 'url': 'http://bcove.me/i6nfkrc3',
427 'md5': '0ba9446db037002366bab3b3eb30c88c',
428 'info_dict': {
429 'id': '3101154703001',
430 'ext': 'mp4',
431 'title': 'Still no power',
432 'uploader': 'thestar.com',
433 '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.',
434 },
435 'add_ie': ['BrightcoveLegacy'],
436 'skip': 'video gone',
437 },
438 {
439 'url': 'http://www.championat.com/video/football/v/87/87499.html',
440 'md5': 'fb973ecf6e4a78a67453647444222983',
441 'info_dict': {
442 'id': '3414141473001',
443 'ext': 'mp4',
444 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
445 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
446 'uploader': 'Championat',
447 },
448 },
449 {
450 # https://github.com/rg3/youtube-dl/issues/3541
451 'add_ie': ['BrightcoveLegacy'],
452 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
453 'info_dict': {
454 'id': '3866516442001',
455 'ext': 'mp4',
456 'title': 'Leer mij vrouwen kennen: Aflevering 1',
457 'description': 'Leer mij vrouwen kennen: Aflevering 1',
458 'uploader': 'SBS Broadcasting',
459 },
460 'skip': 'Restricted to Netherlands',
461 'params': {
462 'skip_download': True, # m3u8 download
463 },
464 },
465 {
466 # Brightcove video in <iframe>
467 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
468 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
469 'info_dict': {
470 'id': '5360463607001',
471 'ext': 'mp4',
472 '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',
473 '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。',
474 'uploader': 'United Nations',
475 'uploader_id': '1362235914001',
476 'timestamp': 1489593889,
477 'upload_date': '20170315',
478 },
479 'add_ie': ['BrightcoveLegacy'],
480 },
481 {
482 # Brightcove with alternative playerID key
483 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
484 'info_dict': {
485 'id': 'nmeth.2062_SV1',
486 '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',
487 },
488 'playlist': [{
489 'info_dict': {
490 'id': '2228375078001',
491 'ext': 'mp4',
492 'title': 'nmeth.2062-sv1',
493 'description': 'nmeth.2062-sv1',
494 'timestamp': 1363357591,
495 'upload_date': '20130315',
496 'uploader': 'Nature Publishing Group',
497 'uploader_id': '1964492299001',
498 },
499 }],
500 },
501 {
502 # Brightcove with UUID in videoPlayer
503 'url': 'http://www8.hp.com/cn/zh/home.html',
504 'info_dict': {
505 'id': '5255815316001',
506 'ext': 'mp4',
507 'title': 'Sprocket Video - China',
508 'description': 'Sprocket Video - China',
509 'uploader': 'HP-Video Gallery',
510 'timestamp': 1482263210,
511 'upload_date': '20161220',
512 'uploader_id': '1107601872001',
513 },
514 'params': {
515 'skip_download': True, # m3u8 download
516 },
517 'skip': 'video rotates...weekly?',
518 },
519 {
520 # Brightcove:new type [2].
521 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
522 'md5': '2b35148fcf48da41c9fb4591650784f3',
523 'info_dict': {
524 'id': '5348741021001',
525 'ext': 'mp4',
526 'upload_date': '20170306',
527 'uploader_id': '4191638492001',
528 'timestamp': 1488769918,
529 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
530
531 },
532 },
533 {
534 # Alternative brightcove <video> attributes
535 '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/',
536 'info_dict': {
537 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
538 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
539 },
540 'playlist': [{
541 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
542 'info_dict': {
543 'id': '5311302538001',
544 'ext': 'mp4',
545 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
546 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
547 'timestamp': 1486321708,
548 'upload_date': '20170205',
549 'uploader_id': '800000640001',
550 },
551 'only_matching': True,
552 }],
553 },
554 {
555 # Brightcove with UUID in videoPlayer
556 'url': 'http://www8.hp.com/cn/zh/home.html',
557 'info_dict': {
558 'id': '5255815316001',
559 'ext': 'mp4',
560 'title': 'Sprocket Video - China',
561 'description': 'Sprocket Video - China',
562 'uploader': 'HP-Video Gallery',
563 'timestamp': 1482263210,
564 'upload_date': '20161220',
565 'uploader_id': '1107601872001',
566 },
567 'params': {
568 'skip_download': True, # m3u8 download
569 },
570 },
571 # ooyala video
572 {
573 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
574 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
575 'info_dict': {
576 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
577 'ext': 'mp4',
578 'title': '2cc213299525360.mov', # that's what we get
579 'duration': 238.231,
580 },
581 'add_ie': ['Ooyala'],
582 },
583 {
584 # ooyala video embedded with http://player.ooyala.com/iframe.js
585 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
586 'info_dict': {
587 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
588 'ext': 'mp4',
589 'title': '"Steve Jobs: Man in the Machine" trailer',
590 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
591 'duration': 135.427,
592 },
593 'params': {
594 'skip_download': True,
595 },
596 'skip': 'movie expired',
597 },
598 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
599 {
600 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
601 'info_dict': {
602 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
603 'ext': 'mp4',
604 'title': 'Steampunk Fest Comes to Honesdale',
605 'duration': 43.276,
606 },
607 'params': {
608 'skip_download': True,
609 }
610 },
611 # embed.ly video
612 {
613 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
614 'info_dict': {
615 'id': '9ODmcdjQcHQ',
616 'ext': 'mp4',
617 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
618 'upload_date': '20140225',
619 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
620 'uploader': 'Tested',
621 'uploader_id': 'testedcom',
622 },
623 # No need to test YoutubeIE here
624 'params': {
625 'skip_download': True,
626 },
627 },
628 # funnyordie embed
629 {
630 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
631 'info_dict': {
632 'id': '18e820ec3f',
633 'ext': 'mp4',
634 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
635 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
636 },
637 # HEAD requests lead to endless 301, while GET is OK
638 'expected_warnings': ['301'],
639 },
640 # RUTV embed
641 {
642 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
643 'info_dict': {
644 'id': '776940',
645 'ext': 'mp4',
646 'title': 'Охотское море стало целиком российским',
647 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
648 },
649 'params': {
650 # m3u8 download
651 'skip_download': True,
652 },
653 },
654 # TVC embed
655 {
656 '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/',
657 'info_dict': {
658 'id': '55304',
659 'ext': 'mp4',
660 'title': 'Дошкольное воспитание',
661 },
662 },
663 # SportBox embed
664 {
665 'url': 'http://www.vestifinance.ru/articles/25753',
666 'info_dict': {
667 'id': '25753',
668 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
669 },
670 'playlist': [{
671 'info_dict': {
672 'id': '370908',
673 'title': 'Госзаказ. День 3',
674 'ext': 'mp4',
675 }
676 }, {
677 'info_dict': {
678 'id': '370905',
679 'title': 'Госзаказ. День 2',
680 'ext': 'mp4',
681 }
682 }, {
683 'info_dict': {
684 'id': '370902',
685 'title': 'Госзаказ. День 1',
686 'ext': 'mp4',
687 }
688 }],
689 'params': {
690 # m3u8 download
691 'skip_download': True,
692 },
693 },
694 # Myvi.ru embed
695 {
696 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
697 'info_dict': {
698 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
699 'ext': 'mp4',
700 'title': 'Ужастики, русский трейлер (2015)',
701 'thumbnail': r're:^https?://.*\.jpg$',
702 'duration': 153,
703 }
704 },
705 # XHamster embed
706 {
707 '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',
708 'info_dict': {
709 'id': 'showthread',
710 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
711 },
712 'playlist_mincount': 7,
713 # This forum does not allow <iframe> syntaxes anymore
714 # Now HTML tags are displayed as-is
715 'skip': 'No videos on this page',
716 },
717 # Embedded TED video
718 {
719 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
720 'md5': '65fdff94098e4a607385a60c5177c638',
721 'info_dict': {
722 'id': '1969',
723 'ext': 'mp4',
724 'title': 'Hidden miracles of the natural world',
725 'uploader': 'Louie Schwartzberg',
726 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
727 }
728 },
729 # nowvideo embed hidden behind percent encoding
730 {
731 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
732 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
733 'info_dict': {
734 'id': '06e53103ca9aa',
735 'ext': 'flv',
736 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
737 'description': 'No description',
738 },
739 },
740 # arte embed
741 {
742 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
743 'md5': '7653032cbb25bf6c80d80f217055fa43',
744 'info_dict': {
745 'id': '048195-004_PLUS7-F',
746 'ext': 'flv',
747 'title': 'X:enius',
748 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
749 'upload_date': '20140320',
750 },
751 'params': {
752 'skip_download': 'Requires rtmpdump'
753 },
754 'skip': 'video gone',
755 },
756 # francetv embed
757 {
758 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
759 'info_dict': {
760 'id': 'EV_30231',
761 'ext': 'mp4',
762 'title': 'Alcaline, le concert avec Calogero',
763 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
764 'upload_date': '20150226',
765 'timestamp': 1424989860,
766 'duration': 5400,
767 },
768 'params': {
769 # m3u8 downloads
770 'skip_download': True,
771 },
772 'expected_warnings': [
773 'Forbidden'
774 ]
775 },
776 # Condé Nast embed
777 {
778 'url': 'http://www.wired.com/2014/04/honda-asimo/',
779 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
780 'info_dict': {
781 'id': '53501be369702d3275860000',
782 'ext': 'mp4',
783 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
784 }
785 },
786 # Dailymotion embed
787 {
788 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
789 'md5': '441aeeb82eb72c422c7f14ec533999cd',
790 'info_dict': {
791 'id': 'k2mm4bCdJ6CQ2i7c8o2',
792 'ext': 'mp4',
793 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
794 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
795 'uploader': 'Spi0n',
796 'uploader_id': 'xgditw',
797 'upload_date': '20140425',
798 'timestamp': 1398441542,
799 },
800 'add_ie': ['Dailymotion'],
801 },
802 # DailyMail embed
803 {
804 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
805 'info_dict': {
806 'id': '1495629',
807 'ext': 'mp4',
808 'title': 'Care worker punches elderly dementia patient in head 11 times',
809 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
810 },
811 'add_ie': ['DailyMail'],
812 'params': {
813 'skip_download': True,
814 },
815 },
816 # YouTube embed
817 {
818 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
819 'info_dict': {
820 'id': 'FXRb4ykk4S0',
821 'ext': 'mp4',
822 'title': 'The NBL Auction 2014',
823 'uploader': 'BADMINTON England',
824 'uploader_id': 'BADMINTONEvents',
825 'upload_date': '20140603',
826 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
827 },
828 'add_ie': ['Youtube'],
829 'params': {
830 'skip_download': True,
831 }
832 },
833 # MTVSercices embed
834 {
835 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
836 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
837 'info_dict': {
838 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
839 'ext': 'mp4',
840 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
841 'description': 'Two valets share their love for movie star Liam Neesons.',
842 'timestamp': 1349922600,
843 'upload_date': '20121011',
844 },
845 },
846 # YouTube embed via <data-embed-url="">
847 {
848 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
849 'info_dict': {
850 'id': '4vAffPZIT44',
851 'ext': 'mp4',
852 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
853 'uploader': 'Gameloft',
854 'uploader_id': 'gameloft',
855 'upload_date': '20140828',
856 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
857 },
858 'params': {
859 'skip_download': True,
860 }
861 },
862 # YouTube <object> embed
863 {
864 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
865 'md5': '516718101ec834f74318df76259fb3cc',
866 'info_dict': {
867 'id': 'msN87y-iEx0',
868 'ext': 'webm',
869 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
870 'upload_date': '20080526',
871 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
872 'uploader': 'Christopher Sykes',
873 'uploader_id': 'ChristopherJSykes',
874 },
875 'add_ie': ['Youtube'],
876 },
877 # Camtasia studio
878 {
879 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
880 'playlist': [{
881 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
882 'info_dict': {
883 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
884 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
885 'ext': 'flv',
886 'duration': 2235.90,
887 }
888 }, {
889 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
890 'info_dict': {
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
893 'ext': 'flv',
894 'duration': 2235.93,
895 }
896 }],
897 'info_dict': {
898 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
899 }
900 },
901 # Flowplayer
902 {
903 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
904 'md5': '9d65602bf31c6e20014319c7d07fba27',
905 'info_dict': {
906 'id': '5123ea6d5e5a7',
907 'ext': 'mp4',
908 'age_limit': 18,
909 'uploader': 'www.handjobhub.com',
910 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
911 }
912 },
913 # Multiple brightcove videos
914 # https://github.com/rg3/youtube-dl/issues/2283
915 {
916 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
917 'info_dict': {
918 'id': 'always-never',
919 'title': 'Always / Never - The New Yorker',
920 },
921 'playlist_count': 3,
922 'params': {
923 'extract_flat': False,
924 'skip_download': True,
925 }
926 },
927 # MLB embed
928 {
929 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
930 'md5': '96f09a37e44da40dd083e12d9a683327',
931 'info_dict': {
932 'id': '33322633',
933 'ext': 'mp4',
934 'title': 'Ump changes call to ball',
935 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
936 'duration': 48,
937 'timestamp': 1401537900,
938 'upload_date': '20140531',
939 'thumbnail': r're:^https?://.*\.jpg$',
940 },
941 },
942 # Wistia embed
943 {
944 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
945 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
946 'info_dict': {
947 'id': '6e2wtrbdaf',
948 'ext': 'mov',
949 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
950 'description': 'a Paywall Videos video from Remilon',
951 'duration': 644.072,
952 'uploader': 'study.com',
953 'timestamp': 1459678540,
954 'upload_date': '20160403',
955 'filesize': 24687186,
956 },
957 },
958 {
959 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
960 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
961 'info_dict': {
962 'id': 'uxjb0lwrcz',
963 'ext': 'mp4',
964 'title': 'Conversation about Hexagonal Rails Part 1',
965 'description': 'a Martin Fowler video from ThoughtWorks',
966 'duration': 1715.0,
967 'uploader': 'thoughtworks.wistia.com',
968 'timestamp': 1401832161,
969 'upload_date': '20140603',
970 },
971 },
972 # Wistia standard embed (async)
973 {
974 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
975 'info_dict': {
976 'id': '807fafadvk',
977 'ext': 'mp4',
978 'title': 'Drip Brennan Dunn Workshop',
979 'description': 'a JV Webinars video from getdrip-1',
980 'duration': 4986.95,
981 'timestamp': 1463607249,
982 'upload_date': '20160518',
983 },
984 'params': {
985 'skip_download': True,
986 }
987 },
988 # Soundcloud embed
989 {
990 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
991 'info_dict': {
992 'id': '174391317',
993 'ext': 'mp3',
994 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
995 'uploader': 'Sophos Security',
996 'title': 'Chet Chat 171 - Oct 29, 2014',
997 'upload_date': '20141029',
998 }
999 },
1000 # Soundcloud multiple embeds
1001 {
1002 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1003 'info_dict': {
1004 'id': '52809',
1005 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1006 },
1007 'playlist_mincount': 7,
1008 },
1009 # TuneIn station embed
1010 {
1011 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1012 'info_dict': {
1013 'id': '204146',
1014 'ext': 'mp3',
1015 'title': 'CNRV',
1016 'location': 'Paris, France',
1017 'is_live': True,
1018 },
1019 'params': {
1020 # Live stream
1021 'skip_download': True,
1022 },
1023 },
1024 # Livestream embed
1025 {
1026 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1027 'info_dict': {
1028 'id': '67864563',
1029 'ext': 'flv',
1030 'upload_date': '20141112',
1031 'title': 'Rosetta #CometLanding webcast HL 10',
1032 }
1033 },
1034 # Another Livestream embed, without 'new.' in URL
1035 {
1036 'url': 'https://www.freespeech.org/',
1037 'info_dict': {
1038 'id': '123537347',
1039 'ext': 'mp4',
1040 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1041 },
1042 'params': {
1043 # Live stream
1044 'skip_download': True,
1045 },
1046 },
1047 # LazyYT
1048 {
1049 'url': 'https://skiplagged.com/',
1050 'info_dict': {
1051 'id': 'skiplagged',
1052 'title': 'Skiplagged: The smart way to find cheap flights',
1053 },
1054 'playlist_mincount': 1,
1055 'add_ie': ['Youtube'],
1056 },
1057 # Cinchcast embed
1058 {
1059 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1060 'info_dict': {
1061 'id': '7141703',
1062 'ext': 'mp3',
1063 'upload_date': '20141126',
1064 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1065 }
1066 },
1067 # Cinerama player
1068 {
1069 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1070 'info_dict': {
1071 'id': '730m_DandD_1901_512k',
1072 'ext': 'mp4',
1073 'uploader': 'www.abc.net.au',
1074 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1075 }
1076 },
1077 # embedded viddler video
1078 {
1079 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1080 'info_dict': {
1081 'id': '4d03aad9',
1082 'ext': 'mp4',
1083 'uploader': 'deadspin',
1084 'title': 'WALL-TO-GORTAT',
1085 'timestamp': 1422285291,
1086 'upload_date': '20150126',
1087 },
1088 'add_ie': ['Viddler'],
1089 },
1090 # Libsyn embed
1091 {
1092 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1093 'info_dict': {
1094 'id': '3377616',
1095 'ext': 'mp3',
1096 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1097 'description': 'md5:601cb790edd05908957dae8aaa866465',
1098 'upload_date': '20150220',
1099 },
1100 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1101 },
1102 # jwplayer YouTube
1103 {
1104 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1105 'info_dict': {
1106 'id': 'Mrj4DVp2zeA',
1107 'ext': 'mp4',
1108 'upload_date': '20150212',
1109 'uploader': 'The National Archives UK',
1110 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1111 'uploader_id': 'NationalArchives08',
1112 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1113 },
1114 },
1115 # jwplayer rtmp
1116 {
1117 'url': 'http://www.suffolk.edu/sjc/live.php',
1118 'info_dict': {
1119 'id': 'live',
1120 'ext': 'flv',
1121 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1122 'uploader': 'www.suffolk.edu',
1123 },
1124 'params': {
1125 'skip_download': True,
1126 },
1127 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1128 },
1129 # Complex jwplayer
1130 {
1131 'url': 'http://www.indiedb.com/games/king-machine/videos',
1132 'info_dict': {
1133 'id': 'videos',
1134 'ext': 'mp4',
1135 'title': 'king machine trailer 1',
1136 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1137 'thumbnail': r're:^https?://.*\.jpg$',
1138 },
1139 },
1140 {
1141 # JWPlayer config passed as variable
1142 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1143 'info_dict': {
1144 'id': '3326530_hq',
1145 'ext': 'mp4',
1146 'title': 'ARIELE | Tube Cup',
1147 'uploader': 'www.txxx.com',
1148 'age_limit': 18,
1149 },
1150 'params': {
1151 'skip_download': True,
1152 }
1153 },
1154 {
1155 # JWPlatform iframe
1156 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1157 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1158 'info_dict': {
1159 'id': 'O0c5JcKT',
1160 'ext': 'mp4',
1161 'upload_date': '20171122',
1162 'timestamp': 1511366290,
1163 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1164 },
1165 'add_ie': [JWPlatformIE.ie_key()],
1166 },
1167 {
1168 # Video.js embed, multiple formats
1169 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1170 'info_dict': {
1171 'id': 'yygqldloqIk',
1172 'ext': 'mp4',
1173 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1174 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1175 'upload_date': '20130314',
1176 'uploader': 'PROстое3D',
1177 'uploader_id': 'PROstoe3D',
1178 },
1179 'params': {
1180 'skip_download': True,
1181 },
1182 },
1183 {
1184 # Video.js embed, single format
1185 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1186 'info_dict': {
1187 'id': 'watch',
1188 'ext': 'mp4',
1189 'title': 'Step 1 - Good Foundation',
1190 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1191 },
1192 'params': {
1193 'skip_download': True,
1194 },
1195 },
1196 # rtl.nl embed
1197 {
1198 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1199 'playlist_mincount': 5,
1200 'info_dict': {
1201 'id': 'aanslagen-kopenhagen',
1202 'title': 'Aanslagen Kopenhagen',
1203 }
1204 },
1205 # Zapiks embed
1206 {
1207 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1208 'info_dict': {
1209 'id': '118046',
1210 'ext': 'mp4',
1211 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1212 }
1213 },
1214 # Kaltura embed (different embed code)
1215 {
1216 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1217 'info_dict': {
1218 'id': '1_a52wc67y',
1219 'ext': 'flv',
1220 'upload_date': '20150127',
1221 'uploader_id': 'PremierMedia',
1222 'timestamp': int,
1223 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1224 },
1225 },
1226 # Kaltura embed with single quotes
1227 {
1228 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1229 'info_dict': {
1230 'id': '0_izeg5utt',
1231 'ext': 'mp4',
1232 'title': '35871',
1233 'timestamp': 1355743100,
1234 'upload_date': '20121217',
1235 'uploader_id': 'cplapp@learn360.com',
1236 },
1237 'add_ie': ['Kaltura'],
1238 },
1239 {
1240 # Kaltura embedded via quoted entry_id
1241 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1242 'info_dict': {
1243 'id': '0_utuok90b',
1244 'ext': 'mp4',
1245 'title': '06_matthew_brender_raj_dutt',
1246 'timestamp': 1466638791,
1247 'upload_date': '20160622',
1248 },
1249 'add_ie': ['Kaltura'],
1250 'expected_warnings': [
1251 'Could not send HEAD request'
1252 ],
1253 'params': {
1254 'skip_download': True,
1255 }
1256 },
1257 {
1258 # Kaltura embedded, some fileExt broken (#11480)
1259 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1260 'info_dict': {
1261 'id': '1_sgtvehim',
1262 'ext': 'mp4',
1263 'title': 'Our "Standard Models" of particle physics and cosmology',
1264 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1265 'timestamp': 1321158993,
1266 'upload_date': '20111113',
1267 'uploader_id': 'kps1',
1268 },
1269 'add_ie': ['Kaltura'],
1270 },
1271 {
1272 # Kaltura iframe embed
1273 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1274 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1275 'info_dict': {
1276 'id': '0_f2cfbpwy',
1277 'ext': 'mp4',
1278 'title': 'I. M. Pei: A Centennial Celebration',
1279 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1280 'upload_date': '20170403',
1281 'uploader_id': 'batchUser',
1282 'timestamp': 1491232186,
1283 },
1284 'add_ie': ['Kaltura'],
1285 },
1286 {
1287 # Kaltura iframe embed, more sophisticated
1288 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1289 'info_dict': {
1290 'id': '1_9gzouybz',
1291 'ext': 'mp4',
1292 'title': 'lecture-05sep2017',
1293 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1294 'upload_date': '20170913',
1295 'uploader_id': 'eps2',
1296 'timestamp': 1505340777,
1297 },
1298 'params': {
1299 'skip_download': True,
1300 },
1301 'add_ie': ['Kaltura'],
1302 },
1303 {
1304 # meta twitter:player
1305 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1306 'info_dict': {
1307 'id': '0_01b42zps',
1308 'ext': 'mp4',
1309 'title': 'Main Twerk (Video)',
1310 'upload_date': '20171208',
1311 'uploader_id': 'sebastian.salinas@thechive.com',
1312 'timestamp': 1512713057,
1313 },
1314 'params': {
1315 'skip_download': True,
1316 },
1317 'add_ie': ['Kaltura'],
1318 },
1319 # referrer protected EaglePlatform embed
1320 {
1321 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1322 'info_dict': {
1323 'id': '582306',
1324 'ext': 'mp4',
1325 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1326 'thumbnail': r're:^https?://.*\.jpg$',
1327 'duration': 3382,
1328 'view_count': int,
1329 },
1330 'params': {
1331 'skip_download': True,
1332 },
1333 },
1334 # ClipYou (EaglePlatform) embed (custom URL)
1335 {
1336 'url': 'http://muz-tv.ru/play/7129/',
1337 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1338 'info_dict': {
1339 'id': '12820',
1340 'ext': 'mp4',
1341 'title': "'O Sole Mio",
1342 'thumbnail': r're:^https?://.*\.jpg$',
1343 'duration': 216,
1344 'view_count': int,
1345 },
1346 'params': {
1347 'skip_download': True,
1348 },
1349 'skip': 'This video is unavailable.',
1350 },
1351 # Pladform embed
1352 {
1353 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1354 'info_dict': {
1355 'id': '100183293',
1356 'ext': 'mp4',
1357 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1358 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1359 'thumbnail': r're:^https?://.*\.jpg$',
1360 'duration': 694,
1361 'age_limit': 0,
1362 },
1363 'skip': 'HTTP Error 404: Not Found',
1364 },
1365 # Playwire embed
1366 {
1367 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1368 'info_dict': {
1369 'id': '3519514',
1370 'ext': 'mp4',
1371 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1372 'thumbnail': r're:^https?://.*\.png$',
1373 'duration': 45.115,
1374 },
1375 },
1376 # 5min embed
1377 {
1378 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1379 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1380 'info_dict': {
1381 'id': '518726732',
1382 'ext': 'mp4',
1383 'title': 'Facebook Creates "On This Day" | Crunch Report',
1384 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1385 'timestamp': 1427237531,
1386 'uploader': 'Crunch Report',
1387 'upload_date': '20150324',
1388 },
1389 'params': {
1390 # m3u8 download
1391 'skip_download': True,
1392 },
1393 },
1394 # SVT embed
1395 {
1396 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1397 'info_dict': {
1398 'id': '2900353',
1399 'ext': 'flv',
1400 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1401 'duration': 27,
1402 'age_limit': 0,
1403 },
1404 },
1405 # Crooks and Liars embed
1406 {
1407 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1408 'info_dict': {
1409 'id': '8RUoRhRi',
1410 'ext': 'mp4',
1411 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1412 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1413 'timestamp': 1428207000,
1414 'upload_date': '20150405',
1415 'uploader': 'Heather',
1416 },
1417 },
1418 # Crooks and Liars external embed
1419 {
1420 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1421 'info_dict': {
1422 'id': 'MTE3MjUtMzQ2MzA',
1423 'ext': 'mp4',
1424 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1425 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1426 'timestamp': 1265032391,
1427 'upload_date': '20100201',
1428 'uploader': 'Heather',
1429 },
1430 },
1431 # NBC Sports vplayer embed
1432 {
1433 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1434 'info_dict': {
1435 'id': 'ln7x1qSThw4k',
1436 'ext': 'flv',
1437 'title': "PFT Live: New leader in the 'new-look' defense",
1438 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1439 'uploader': 'NBCU-SPORTS',
1440 'upload_date': '20140107',
1441 'timestamp': 1389118457,
1442 },
1443 'skip': 'Invalid Page URL',
1444 },
1445 # NBC News embed
1446 {
1447 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1448 'md5': '1aa589c675898ae6d37a17913cf68d66',
1449 'info_dict': {
1450 'id': 'x_dtl_oa_LettermanliftPR_160608',
1451 'ext': 'mp4',
1452 'title': 'David Letterman: A Preview',
1453 '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.',
1454 'upload_date': '20160609',
1455 'timestamp': 1465431544,
1456 'uploader': 'NBCU-NEWS',
1457 },
1458 },
1459 # UDN embed
1460 {
1461 'url': 'https://video.udn.com/news/300346',
1462 'md5': 'fd2060e988c326991037b9aff9df21a6',
1463 'info_dict': {
1464 'id': '300346',
1465 'ext': 'mp4',
1466 'title': '中一中男師變性 全校師生力挺',
1467 'thumbnail': r're:^https?://.*\.jpg$',
1468 },
1469 'params': {
1470 # m3u8 download
1471 'skip_download': True,
1472 },
1473 'expected_warnings': ['Failed to parse JSON Expecting value'],
1474 },
1475 # Brightcove URL in single quotes
1476 {
1477 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1478 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1479 'info_dict': {
1480 'id': '4255764656001',
1481 'ext': 'mp4',
1482 'title': 'SN Presents: Russell Martin, World Citizen',
1483 '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.',
1484 'uploader': 'Rogers Sportsnet',
1485 'uploader_id': '1704050871',
1486 'upload_date': '20150525',
1487 'timestamp': 1432570283,
1488 },
1489 },
1490 # OnionStudios embed
1491 {
1492 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'info_dict': {
1494 'id': '2855',
1495 'ext': 'mp4',
1496 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1497 'thumbnail': r're:^https?://.*\.jpe?g$',
1498 'uploader': 'ClickHole',
1499 'uploader_id': 'clickhole',
1500 }
1501 },
1502 # SnagFilms embed
1503 {
1504 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1505 'info_dict': {
1506 'id': '74849a00-85a9-11e1-9660-123139220831',
1507 'ext': 'mp4',
1508 'title': '#whilewewatch',
1509 }
1510 },
1511 # AdobeTVVideo embed
1512 {
1513 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1514 'md5': '43662b577c018ad707a63766462b1e87',
1515 'info_dict': {
1516 'id': '2456',
1517 'ext': 'mp4',
1518 'title': 'New experience with Acrobat DC',
1519 'description': 'New experience with Acrobat DC',
1520 'duration': 248.667,
1521 },
1522 },
1523 # BrightcoveInPageEmbed embed
1524 {
1525 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1526 'info_dict': {
1527 'id': '4238694884001',
1528 'ext': 'flv',
1529 'title': 'Tabletop: Dread, Last Thoughts',
1530 'description': 'Tabletop: Dread, Last Thoughts',
1531 'duration': 51690,
1532 },
1533 },
1534 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1535 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1536 {
1537 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1538 'info_dict': {
1539 'id': '4785848093001',
1540 'ext': 'mp4',
1541 'title': 'The Cardinal Pell Interview',
1542 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1543 'uploader': 'GlobeCast Australia - GlobeStream',
1544 'uploader_id': '2733773828001',
1545 'upload_date': '20160304',
1546 'timestamp': 1457083087,
1547 },
1548 'params': {
1549 # m3u8 downloads
1550 'skip_download': True,
1551 },
1552 },
1553 {
1554 # Brightcove embed with whitespace around attribute names
1555 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1556 'info_dict': {
1557 'id': '3167554373001',
1558 'ext': 'mp4',
1559 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1560 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1561 'uploader_id': '1079349493',
1562 'upload_date': '20140207',
1563 'timestamp': 1391810548,
1564 },
1565 'params': {
1566 'skip_download': True,
1567 },
1568 },
1569 # Another form of arte.tv embed
1570 {
1571 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1572 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1573 'info_dict': {
1574 'id': '030273-562_PLUS7-F',
1575 'ext': 'mp4',
1576 'title': 'ARTE Reportage - Nulle part, en France',
1577 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1578 'upload_date': '20160409',
1579 },
1580 },
1581 # LiveLeak embed
1582 {
1583 'url': 'http://www.wykop.pl/link/3088787/',
1584 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1585 'info_dict': {
1586 'id': '874_1459135191',
1587 'ext': 'mp4',
1588 'title': 'Man shows poor quality of new apartment building',
1589 'description': 'The wall is like a sand pile.',
1590 'uploader': 'Lake8737',
1591 },
1592 'add_ie': [LiveLeakIE.ie_key()],
1593 },
1594 # Another LiveLeak embed pattern (#13336)
1595 {
1596 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1597 'info_dict': {
1598 'id': '2eb_1496309988',
1599 'ext': 'mp4',
1600 'title': 'Thief robs place where everyone was armed',
1601 'description': 'md5:694d73ee79e535953cf2488562288eee',
1602 'uploader': 'brazilwtf',
1603 },
1604 'add_ie': [LiveLeakIE.ie_key()],
1605 },
1606 # Duplicated embedded video URLs
1607 {
1608 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1609 'info_dict': {
1610 'id': '149298443_480_16c25b74_2',
1611 'ext': 'mp4',
1612 'title': 'vs. Blue Orange Spring Game',
1613 'uploader': 'www.hudl.com',
1614 },
1615 },
1616 # twitter:player:stream embed
1617 {
1618 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1619 'info_dict': {
1620 'id': 'master',
1621 'ext': 'mp4',
1622 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1623 'uploader': 'www.rtl.be',
1624 },
1625 'params': {
1626 # m3u8 downloads
1627 'skip_download': True,
1628 },
1629 },
1630 # twitter:player embed
1631 {
1632 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1633 'md5': 'a3e0df96369831de324f0778e126653c',
1634 'info_dict': {
1635 'id': '4909620399001',
1636 'ext': 'mp4',
1637 'title': 'What Do Black Holes Sound Like?',
1638 'description': 'what do black holes sound like',
1639 'upload_date': '20160524',
1640 'uploader_id': '29913724001',
1641 'timestamp': 1464107587,
1642 'uploader': 'TheAtlantic',
1643 },
1644 'add_ie': ['BrightcoveLegacy'],
1645 },
1646 # Facebook <iframe> embed
1647 {
1648 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1649 'md5': 'fbcde74f534176ecb015849146dd3aee',
1650 'info_dict': {
1651 'id': '599637780109885',
1652 'ext': 'mp4',
1653 'title': 'Facebook video #599637780109885',
1654 },
1655 },
1656 # Facebook <iframe> embed, plugin video
1657 {
1658 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1659 'info_dict': {
1660 'id': '1754168231264132',
1661 'ext': 'mp4',
1662 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1663 'uploader': 'Tariq Ramadan (official)',
1664 'timestamp': 1496758379,
1665 'upload_date': '20170606',
1666 },
1667 'params': {
1668 'skip_download': True,
1669 },
1670 },
1671 # Facebook API embed
1672 {
1673 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1674 'md5': 'a47372ee61b39a7b90287094d447d94e',
1675 'info_dict': {
1676 'id': '10153467542406923',
1677 'ext': 'mp4',
1678 'title': 'Facebook video #10153467542406923',
1679 },
1680 },
1681 # Wordpress "YouTube Video Importer" plugin
1682 {
1683 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1684 'md5': 'd16797741b560b485194eddda8121b48',
1685 'info_dict': {
1686 'id': 'HNTXWDXV9Is',
1687 'ext': 'mp4',
1688 'title': 'Blue Devils Drumline Stanford lot 2016',
1689 'upload_date': '20160627',
1690 'uploader_id': 'GENOCIDE8GENERAL10',
1691 'uploader': 'cylus cyrus',
1692 },
1693 },
1694 {
1695 # video stored on custom kaltura server
1696 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1697 'md5': '537617d06e64dfed891fa1593c4b30cc',
1698 'info_dict': {
1699 'id': '0_1iotm5bh',
1700 'ext': 'mp4',
1701 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1702 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1703 'uploader_id': 'videos.expansion@el-mundo.net',
1704 'upload_date': '20150429',
1705 'timestamp': 1430303472,
1706 },
1707 'add_ie': ['Kaltura'],
1708 },
1709 {
1710 # Non-standard Vimeo embed
1711 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1712 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1713 'info_dict': {
1714 'id': '148867247',
1715 'ext': 'mp4',
1716 'title': 'Understanding the web - Teaser',
1717 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1718 'upload_date': '20151214',
1719 'uploader': 'OpenClassrooms',
1720 'uploader_id': 'openclassrooms',
1721 },
1722 'add_ie': ['Vimeo'],
1723 },
1724 {
1725 # generic vimeo embed that requires original URL passed as Referer
1726 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1727 'only_matching': True,
1728 },
1729 {
1730 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1731 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1732 'info_dict': {
1733 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1734 'ext': 'mp4',
1735 'title': 'Big Buck Bunny',
1736 'description': 'Royalty free test video',
1737 'timestamp': 1432816365,
1738 'upload_date': '20150528',
1739 'is_live': False,
1740 },
1741 'params': {
1742 'skip_download': True,
1743 },
1744 'add_ie': [ArkenaIE.ie_key()],
1745 },
1746 {
1747 '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/',
1748 'info_dict': {
1749 'id': '1c7141f46c',
1750 'ext': 'mp4',
1751 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1752 },
1753 'params': {
1754 'skip_download': True,
1755 },
1756 'add_ie': [Vbox7IE.ie_key()],
1757 },
1758 {
1759 # DBTV embeds
1760 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1761 'info_dict': {
1762 'id': '43254897',
1763 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1764 },
1765 'playlist_mincount': 3,
1766 },
1767 {
1768 # Videa embeds
1769 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1770 'info_dict': {
1771 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1772 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1773 },
1774 'playlist_mincount': 2,
1775 },
1776 {
1777 # 20 minuten embed
1778 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1779 'info_dict': {
1780 'id': '523629',
1781 'ext': 'mp4',
1782 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1783 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1784 },
1785 'params': {
1786 'skip_download': True,
1787 },
1788 'add_ie': [TwentyMinutenIE.ie_key()],
1789 },
1790 {
1791 # VideoPress embed
1792 'url': 'https://en.support.wordpress.com/videopress/',
1793 'info_dict': {
1794 'id': 'OcobLTqC',
1795 'ext': 'm4v',
1796 'title': 'IMG_5786',
1797 'timestamp': 1435711927,
1798 'upload_date': '20150701',
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 'add_ie': [VideoPressIE.ie_key()],
1804 },
1805 {
1806 # Rutube embed
1807 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1808 'info_dict': {
1809 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1810 'ext': 'flv',
1811 'title': 'Магаззино: Казань 2',
1812 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1813 'uploader': 'Магаззино',
1814 'upload_date': '20170228',
1815 'uploader_id': '996642',
1816 },
1817 'params': {
1818 'skip_download': True,
1819 },
1820 'add_ie': [RutubeIE.ie_key()],
1821 },
1822 {
1823 # ThePlatform embedded with whitespaces in URLs
1824 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1825 'only_matching': True,
1826 },
1827 {
1828 # Senate ISVP iframe https
1829 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1830 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1831 'info_dict': {
1832 'id': 'govtaff020316',
1833 'ext': 'mp4',
1834 'title': 'Integrated Senate Video Player',
1835 },
1836 'add_ie': [SenateISVPIE.ie_key()],
1837 },
1838 {
1839 # Limelight embeds (1 channel embed + 4 media embeds)
1840 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1841 'info_dict': {
1842 'id': 'FacilitatorTraining2017',
1843 'title': 'Facilitator Training 2017',
1844 },
1845 'playlist_mincount': 5,
1846 },
1847 {
1848 # Limelight embed (LimelightPlayerUtil.embed)
1849 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1850 'info_dict': {
1851 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1852 'ext': 'mp4',
1853 'title': '07448641',
1854 'timestamp': 1499890639,
1855 'upload_date': '20170712',
1856 },
1857 'params': {
1858 'skip_download': True,
1859 },
1860 'add_ie': ['LimelightMedia'],
1861 },
1862 {
1863 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1864 'info_dict': {
1865 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1866 'title': 'Standoff with Walnut Creek murder suspect ends',
1867 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1868 },
1869 'playlist_mincount': 4,
1870 },
1871 {
1872 # WashingtonPost embed
1873 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1874 'info_dict': {
1875 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1876 'ext': 'mp4',
1877 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1878 '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.',
1879 'timestamp': 1455216756,
1880 'uploader': 'The Washington Post',
1881 'upload_date': '20160211',
1882 },
1883 'add_ie': [WashingtonPostIE.ie_key()],
1884 },
1885 {
1886 # Mediaset embed
1887 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1888 'info_dict': {
1889 'id': '720642',
1890 'ext': 'mp4',
1891 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 'add_ie': [MediasetIE.ie_key()],
1897 },
1898 {
1899 # JOJ.sk embeds
1900 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1901 'info_dict': {
1902 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'title': 'Slovenskom sa prehnala vlna silných búrok',
1904 },
1905 'playlist_mincount': 5,
1906 'add_ie': [JojIE.ie_key()],
1907 },
1908 {
1909 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1910 'url': 'https://tvrain.ru/amp/418921/',
1911 'md5': 'cc00413936695987e8de148b67d14f1d',
1912 'info_dict': {
1913 'id': '418921',
1914 'ext': 'mp4',
1915 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1916 },
1917 },
1918 {
1919 # vzaar embed
1920 'url': 'http://help.vzaar.com/article/165-embedding-video',
1921 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1922 'info_dict': {
1923 'id': '8707641',
1924 'ext': 'mp4',
1925 'title': 'Building A Business Online: Principal Chairs Q & A',
1926 },
1927 },
1928 {
1929 # multiple HTML5 videos on one page
1930 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1931 'info_dict': {
1932 'id': 'keyscenarios',
1933 'title': 'Rescue Kit 14 Free Edition - Getting started',
1934 },
1935 'playlist_count': 4,
1936 },
1937 {
1938 # vshare embed
1939 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1940 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1941 'info_dict': {
1942 'id': '0f64ce6',
1943 'title': 'vl14062007715967',
1944 'ext': 'mp4',
1945 }
1946 },
1947 {
1948 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1949 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1950 'info_dict': {
1951 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1952 'ext': 'mp4',
1953 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1954 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1955 'timestamp': 1474354800,
1956 'upload_date': '20160920',
1957 }
1958 },
1959 {
1960 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1961 'info_dict': {
1962 'id': '1731611',
1963 'ext': 'mp4',
1964 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1965 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1966 'timestamp': 1516100691,
1967 'upload_date': '20180116',
1968 },
1969 'params': {
1970 'skip_download': True,
1971 },
1972 'add_ie': [SpringboardPlatformIE.ie_key()],
1973 },
1974 {
1975 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1976 'info_dict': {
1977 'id': 'uPDB5I9wfp8',
1978 'ext': 'webm',
1979 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1980 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1981 'upload_date': '20160219',
1982 'uploader': 'Pocoyo - Português (BR)',
1983 'uploader_id': 'PocoyoBrazil',
1984 },
1985 'add_ie': [YoutubeIE.ie_key()],
1986 'params': {
1987 'skip_download': True,
1988 },
1989 },
1990 {
1991 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1992 'info_dict': {
1993 'id': 'vMDE4NzI1Mjgt690b',
1994 'ext': 'mp4',
1995 'title': 'Котята',
1996 },
1997 'add_ie': [YapFilesIE.ie_key()],
1998 'params': {
1999 'skip_download': True,
2000 },
2001 },
2002 {
2003 # CloudflareStream embed
2004 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2005 'info_dict': {
2006 'id': '31c9291ab41fac05471db4e73aa11717',
2007 'ext': 'mp4',
2008 'title': '31c9291ab41fac05471db4e73aa11717',
2009 },
2010 'add_ie': [CloudflareStreamIE.ie_key()],
2011 'params': {
2012 'skip_download': True,
2013 },
2014 },
2015 {
2016 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2017 'md5': 'b68d276de422ab07ee1d49388103f457',
2018 'info_dict': {
2019 'id': '83645793',
2020 'title': 'Lock up and get excited',
2021 'ext': 'mp4'
2022 },
2023 'skip': 'TODO: fix nested playlists processing in tests',
2024 },
2025 # {
2026 # # TODO: find another test
2027 # # http://schema.org/VideoObject
2028 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2029 # 'md5': '888dcf08b7ea671381f00fab74692755',
2030 # 'info_dict': {
2031 # 'id': 'nyvTSJMKId',
2032 # 'ext': 'mp4',
2033 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2034 # 'description': '#love for cats.',
2035 # 'timestamp': 1461244995,
2036 # 'upload_date': '20160421',
2037 # },
2038 # 'params': {
2039 # 'force_generic_extractor': True,
2040 # },
2041 # }
2042 ]
2043
2044 def report_following_redirect(self, new_url):
2045 """Report information extraction."""
2046 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2047
2048 def _extract_rss(self, url, video_id, doc):
2049 playlist_title = doc.find('./channel/title').text
2050 playlist_desc_el = doc.find('./channel/description')
2051 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2052
2053 entries = []
2054 for it in doc.findall('./channel/item'):
2055 next_url = None
2056 enclosure_nodes = it.findall('./enclosure')
2057 for e in enclosure_nodes:
2058 next_url = e.attrib.get('url')
2059 if next_url:
2060 break
2061
2062 if not next_url:
2063 next_url = xpath_text(it, 'link', fatal=False)
2064
2065 if not next_url:
2066 continue
2067
2068 entries.append({
2069 '_type': 'url_transparent',
2070 'url': next_url,
2071 'title': it.find('title').text,
2072 })
2073
2074 return {
2075 '_type': 'playlist',
2076 'id': url,
2077 'title': playlist_title,
2078 'description': playlist_desc,
2079 'entries': entries,
2080 }
2081
2082 def _extract_camtasia(self, url, video_id, webpage):
2083 """ Returns None if no camtasia video can be found. """
2084
2085 camtasia_cfg = self._search_regex(
2086 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2087 webpage, 'camtasia configuration file', default=None)
2088 if camtasia_cfg is None:
2089 return None
2090
2091 title = self._html_search_meta('DC.title', webpage, fatal=True)
2092
2093 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2094 camtasia_cfg = self._download_xml(
2095 camtasia_url, video_id,
2096 note='Downloading camtasia configuration',
2097 errnote='Failed to download camtasia configuration')
2098 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2099
2100 entries = []
2101 for n in fileset_node.getchildren():
2102 url_n = n.find('./uri')
2103 if url_n is None:
2104 continue
2105
2106 entries.append({
2107 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2108 'title': '%s - %s' % (title, n.tag),
2109 'url': compat_urlparse.urljoin(url, url_n.text),
2110 'duration': float_or_none(n.find('./duration').text),
2111 })
2112
2113 return {
2114 '_type': 'playlist',
2115 'entries': entries,
2116 'title': title,
2117 }
2118
2119 def _real_extract(self, url):
2120 if url.startswith('//'):
2121 return {
2122 '_type': 'url',
2123 'url': self.http_scheme() + url,
2124 }
2125
2126 parsed_url = compat_urlparse.urlparse(url)
2127 if not parsed_url.scheme:
2128 default_search = self._downloader.params.get('default_search')
2129 if default_search is None:
2130 default_search = 'fixup_error'
2131
2132 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2133 if '/' in url:
2134 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2135 return self.url_result('http://' + url)
2136 elif default_search != 'fixup_error':
2137 if default_search == 'auto_warning':
2138 if re.match(r'^(?:url|URL)$', url):
2139 raise ExtractorError(
2140 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2141 expected=True)
2142 else:
2143 self._downloader.report_warning(
2144 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2145 return self.url_result('ytsearch:' + url)
2146
2147 if default_search in ('error', 'fixup_error'):
2148 raise ExtractorError(
2149 '%r is not a valid URL. '
2150 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2151 % (url, url), expected=True)
2152 else:
2153 if ':' not in default_search:
2154 default_search += ':'
2155 return self.url_result(default_search + url)
2156
2157 url, smuggled_data = unsmuggle_url(url)
2158 force_videoid = None
2159 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2160 if smuggled_data and 'force_videoid' in smuggled_data:
2161 force_videoid = smuggled_data['force_videoid']
2162 video_id = force_videoid
2163 else:
2164 video_id = self._generic_id(url)
2165
2166 self.to_screen('%s: Requesting header' % video_id)
2167
2168 head_req = HEADRequest(url)
2169 head_response = self._request_webpage(
2170 head_req, video_id,
2171 note=False, errnote='Could not send HEAD request to %s' % url,
2172 fatal=False)
2173
2174 if head_response is not False:
2175 # Check for redirect
2176 new_url = compat_str(head_response.geturl())
2177 if url != new_url:
2178 self.report_following_redirect(new_url)
2179 if force_videoid:
2180 new_url = smuggle_url(
2181 new_url, {'force_videoid': force_videoid})
2182 return self.url_result(new_url)
2183
2184 full_response = None
2185 if head_response is False:
2186 request = sanitized_Request(url)
2187 request.add_header('Accept-Encoding', '*')
2188 full_response = self._request_webpage(request, video_id)
2189 head_response = full_response
2190
2191 info_dict = {
2192 'id': video_id,
2193 'title': self._generic_title(url),
2194 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2195 }
2196
2197 # Check for direct link to a video
2198 content_type = head_response.headers.get('Content-Type', '').lower()
2199 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2200 if m:
2201 format_id = compat_str(m.group('format_id'))
2202 if format_id.endswith('mpegurl'):
2203 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2204 elif format_id == 'f4m':
2205 formats = self._extract_f4m_formats(url, video_id)
2206 else:
2207 formats = [{
2208 'format_id': format_id,
2209 'url': url,
2210 'vcodec': 'none' if m.group('type') == 'audio' else None
2211 }]
2212 info_dict['direct'] = True
2213 self._sort_formats(formats)
2214 info_dict['formats'] = formats
2215 return info_dict
2216
2217 if not self._downloader.params.get('test', False) and not is_intentional:
2218 force = self._downloader.params.get('force_generic_extractor', False)
2219 self._downloader.report_warning(
2220 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2221
2222 if not full_response:
2223 request = sanitized_Request(url)
2224 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2225 # making it impossible to download only chunk of the file (yet we need only 512kB to
2226 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2227 # that will always result in downloading the whole file that is not desirable.
2228 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2229 # to accept raw bytes and being able to download only a chunk.
2230 # It may probably better to solve this by checking Content-Type for application/octet-stream
2231 # after HEAD request finishes, but not sure if we can rely on this.
2232 request.add_header('Accept-Encoding', '*')
2233 full_response = self._request_webpage(request, video_id)
2234
2235 first_bytes = full_response.read(512)
2236
2237 # Is it an M3U playlist?
2238 if first_bytes.startswith(b'#EXTM3U'):
2239 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2240 self._sort_formats(info_dict['formats'])
2241 return info_dict
2242
2243 # Maybe it's a direct link to a video?
2244 # Be careful not to download the whole thing!
2245 if not is_html(first_bytes):
2246 self._downloader.report_warning(
2247 'URL could be a direct video link, returning it as such.')
2248 info_dict.update({
2249 'direct': True,
2250 'url': url,
2251 })
2252 return info_dict
2253
2254 webpage = self._webpage_read_content(
2255 full_response, url, video_id, prefix=first_bytes)
2256
2257 self.report_extraction(video_id)
2258
2259 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2260 try:
2261 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2262 if doc.tag == 'rss':
2263 return self._extract_rss(url, video_id, doc)
2264 elif doc.tag == 'SmoothStreamingMedia':
2265 info_dict['formats'] = self._parse_ism_formats(doc, url)
2266 self._sort_formats(info_dict['formats'])
2267 return info_dict
2268 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2269 smil = self._parse_smil(doc, url, video_id)
2270 self._sort_formats(smil['formats'])
2271 return smil
2272 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2273 return self.playlist_result(
2274 self._parse_xspf(
2275 doc, video_id, xspf_url=url,
2276 xspf_base_url=compat_str(full_response.geturl())),
2277 video_id)
2278 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2279 info_dict['formats'] = self._parse_mpd_formats(
2280 doc,
2281 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2282 mpd_url=url)
2283 self._sort_formats(info_dict['formats'])
2284 return info_dict
2285 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2286 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2287 self._sort_formats(info_dict['formats'])
2288 return info_dict
2289 except compat_xml_parse_error:
2290 pass
2291
2292 # Is it a Camtasia project?
2293 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2294 if camtasia_res is not None:
2295 return camtasia_res
2296
2297 # Sometimes embedded video player is hidden behind percent encoding
2298 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2299 # Unescaping the whole page allows to handle those cases in a generic way
2300 webpage = compat_urllib_parse_unquote(webpage)
2301
2302 # it's tempting to parse this further, but you would
2303 # have to take into account all the variations like
2304 # Video Title - Site Name
2305 # Site Name | Video Title
2306 # Video Title - Tagline | Site Name
2307 # and so on and so forth; it's just not practical
2308 video_title = self._og_search_title(
2309 webpage, default=None) or self._html_search_regex(
2310 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2311 default='video')
2312
2313 # Try to detect age limit automatically
2314 age_limit = self._rta_search(webpage)
2315 # And then there are the jokers who advertise that they use RTA,
2316 # but actually don't.
2317 AGE_LIMIT_MARKERS = [
2318 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2319 ]
2320 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2321 age_limit = 18
2322
2323 # video uploader is domain name
2324 video_uploader = self._search_regex(
2325 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2326
2327 video_description = self._og_search_description(webpage, default=None)
2328 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2329
2330 info_dict.update({
2331 'title': video_title,
2332 'description': video_description,
2333 'thumbnail': video_thumbnail,
2334 'age_limit': age_limit,
2335 })
2336
2337 # Look for Brightcove Legacy Studio embeds
2338 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2339 if bc_urls:
2340 entries = [{
2341 '_type': 'url',
2342 'url': smuggle_url(bc_url, {'Referer': url}),
2343 'ie_key': 'BrightcoveLegacy'
2344 } for bc_url in bc_urls]
2345
2346 return {
2347 '_type': 'playlist',
2348 'title': video_title,
2349 'id': video_id,
2350 'entries': entries,
2351 }
2352
2353 # Look for Brightcove New Studio embeds
2354 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2355 if bc_urls:
2356 return self.playlist_from_matches(
2357 bc_urls, video_id, video_title,
2358 getter=lambda x: smuggle_url(x, {'referrer': url}),
2359 ie='BrightcoveNew')
2360
2361 # Look for Nexx embeds
2362 nexx_urls = NexxIE._extract_urls(webpage)
2363 if nexx_urls:
2364 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2365
2366 # Look for Nexx iFrame embeds
2367 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2368 if nexx_embed_urls:
2369 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2370
2371 # Look for ThePlatform embeds
2372 tp_urls = ThePlatformIE._extract_urls(webpage)
2373 if tp_urls:
2374 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2375
2376 # Look for Vessel embeds
2377 vessel_urls = VesselIE._extract_urls(webpage)
2378 if vessel_urls:
2379 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2380
2381 # Look for embedded rtl.nl player
2382 matches = re.findall(
2383 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2384 webpage)
2385 if matches:
2386 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2387
2388 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2389 if vimeo_urls:
2390 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2391
2392 vid_me_embed_url = self._search_regex(
2393 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2394 webpage, 'vid.me embed', default=None)
2395 if vid_me_embed_url is not None:
2396 return self.url_result(vid_me_embed_url, 'Vidme')
2397
2398 # Look for YouTube embeds
2399 youtube_urls = YoutubeIE._extract_urls(webpage)
2400 if youtube_urls:
2401 return self.playlist_from_matches(
2402 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2403
2404 matches = DailymotionIE._extract_urls(webpage)
2405 if matches:
2406 return self.playlist_from_matches(matches, video_id, video_title)
2407
2408 # Look for embedded Dailymotion playlist player (#3822)
2409 m = re.search(
2410 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2411 if m:
2412 playlists = re.findall(
2413 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2414 if playlists:
2415 return self.playlist_from_matches(
2416 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2417
2418 # Look for DailyMail embeds
2419 dailymail_urls = DailyMailIE._extract_urls(webpage)
2420 if dailymail_urls:
2421 return self.playlist_from_matches(
2422 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2423
2424 # Look for embedded Wistia player
2425 wistia_url = WistiaIE._extract_url(webpage)
2426 if wistia_url:
2427 return {
2428 '_type': 'url_transparent',
2429 'url': self._proto_relative_url(wistia_url),
2430 'ie_key': WistiaIE.ie_key(),
2431 'uploader': video_uploader,
2432 }
2433
2434 # Look for SVT player
2435 svt_url = SVTIE._extract_url(webpage)
2436 if svt_url:
2437 return self.url_result(svt_url, 'SVT')
2438
2439 # Look for Bandcamp pages with custom domain
2440 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2441 if mobj is not None:
2442 burl = unescapeHTML(mobj.group(1))
2443 # Don't set the extractor because it can be a track url or an album
2444 return self.url_result(burl)
2445
2446 # Look for embedded Vevo player
2447 mobj = re.search(
2448 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2449 if mobj is not None:
2450 return self.url_result(mobj.group('url'))
2451
2452 # Look for embedded Viddler player
2453 mobj = re.search(
2454 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2455 webpage)
2456 if mobj is not None:
2457 return self.url_result(mobj.group('url'))
2458
2459 # Look for NYTimes player
2460 mobj = re.search(
2461 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2462 webpage)
2463 if mobj is not None:
2464 return self.url_result(mobj.group('url'))
2465
2466 # Look for Libsyn player
2467 mobj = re.search(
2468 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2469 if mobj is not None:
2470 return self.url_result(mobj.group('url'))
2471
2472 # Look for Ooyala videos
2473 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2474 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2475 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2476 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2477 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2478 if mobj is not None:
2479 embed_token = self._search_regex(
2480 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2481 webpage, 'ooyala embed token', default=None)
2482 return OoyalaIE._build_url_result(smuggle_url(
2483 mobj.group('ec'), {
2484 'domain': url,
2485 'embed_token': embed_token,
2486 }))
2487
2488 # Look for multiple Ooyala embeds on SBN network websites
2489 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2490 if mobj is not None:
2491 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2492 if embeds:
2493 return self.playlist_from_matches(
2494 embeds, video_id, video_title,
2495 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2496
2497 # Look for Aparat videos
2498 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2499 if mobj is not None:
2500 return self.url_result(mobj.group(1), 'Aparat')
2501
2502 # Look for MPORA videos
2503 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2504 if mobj is not None:
2505 return self.url_result(mobj.group(1), 'Mpora')
2506
2507 # Look for embedded NovaMov-based player
2508 mobj = re.search(
2509 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2510 (?P<url>http://(?:(?:embed|www)\.)?
2511 (?:novamov\.com|
2512 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2513 videoweed\.(?:es|com)|
2514 movshare\.(?:net|sx|ag)|
2515 divxstage\.(?:eu|net|ch|co|at|ag))
2516 /embed\.php.+?)\1''', webpage)
2517 if mobj is not None:
2518 return self.url_result(mobj.group('url'))
2519
2520 # Look for embedded Facebook player
2521 facebook_urls = FacebookIE._extract_urls(webpage)
2522 if facebook_urls:
2523 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2524
2525 # Look for embedded VK player
2526 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2527 if mobj is not None:
2528 return self.url_result(mobj.group('url'), 'VK')
2529
2530 # Look for embedded Odnoklassniki player
2531 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2534
2535 # Look for embedded ivi player
2536 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2537 if mobj is not None:
2538 return self.url_result(mobj.group('url'), 'Ivi')
2539
2540 # Look for embedded Huffington Post player
2541 mobj = re.search(
2542 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2543 if mobj is not None:
2544 return self.url_result(mobj.group('url'), 'HuffPost')
2545
2546 # Look for embed.ly
2547 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2548 if mobj is not None:
2549 return self.url_result(mobj.group('url'))
2550 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2551 if mobj is not None:
2552 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2553
2554 # Look for funnyordie embed
2555 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2556 if matches:
2557 return self.playlist_from_matches(
2558 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2559
2560 # Look for BBC iPlayer embed
2561 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2562 if matches:
2563 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2564
2565 # Look for embedded RUTV player
2566 rutv_url = RUTVIE._extract_url(webpage)
2567 if rutv_url:
2568 return self.url_result(rutv_url, 'RUTV')
2569
2570 # Look for embedded TVC player
2571 tvc_url = TVCIE._extract_url(webpage)
2572 if tvc_url:
2573 return self.url_result(tvc_url, 'TVC')
2574
2575 # Look for embedded SportBox player
2576 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2577 if sportbox_urls:
2578 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2579
2580 # Look for embedded XHamster player
2581 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2582 if xhamster_urls:
2583 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2584
2585 # Look for embedded TNAFlixNetwork player
2586 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2587 if tnaflix_urls:
2588 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2589
2590 # Look for embedded PornHub player
2591 pornhub_urls = PornHubIE._extract_urls(webpage)
2592 if pornhub_urls:
2593 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2594
2595 # Look for embedded DrTuber player
2596 drtuber_urls = DrTuberIE._extract_urls(webpage)
2597 if drtuber_urls:
2598 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2599
2600 # Look for embedded RedTube player
2601 redtube_urls = RedTubeIE._extract_urls(webpage)
2602 if redtube_urls:
2603 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2604
2605 # Look for embedded Tube8 player
2606 tube8_urls = Tube8IE._extract_urls(webpage)
2607 if tube8_urls:
2608 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2609
2610 # Look for embedded Tvigle player
2611 mobj = re.search(
2612 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2613 if mobj is not None:
2614 return self.url_result(mobj.group('url'), 'Tvigle')
2615
2616 # Look for embedded TED player
2617 mobj = re.search(
2618 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2619 if mobj is not None:
2620 return self.url_result(mobj.group('url'), 'TED')
2621
2622 # Look for embedded Ustream videos
2623 ustream_url = UstreamIE._extract_url(webpage)
2624 if ustream_url:
2625 return self.url_result(ustream_url, UstreamIE.ie_key())
2626
2627 # Look for embedded arte.tv player
2628 mobj = re.search(
2629 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2630 webpage)
2631 if mobj is not None:
2632 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2633
2634 # Look for embedded francetv player
2635 mobj = re.search(
2636 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2637 webpage)
2638 if mobj is not None:
2639 return self.url_result(mobj.group('url'))
2640
2641 # Look for embedded smotri.com player
2642 smotri_url = SmotriIE._extract_url(webpage)
2643 if smotri_url:
2644 return self.url_result(smotri_url, 'Smotri')
2645
2646 # Look for embedded Myvi.ru player
2647 myvi_url = MyviIE._extract_url(webpage)
2648 if myvi_url:
2649 return self.url_result(myvi_url)
2650
2651 # Look for embedded soundcloud player
2652 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2653 if soundcloud_urls:
2654 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2655
2656 # Look for tunein player
2657 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2658 if tunein_urls:
2659 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2660
2661 # Look for embedded mtvservices player
2662 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2663 if mtvservices_url:
2664 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2665
2666 # Look for embedded yahoo player
2667 mobj = re.search(
2668 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2669 webpage)
2670 if mobj is not None:
2671 return self.url_result(mobj.group('url'), 'Yahoo')
2672
2673 # Look for embedded sbs.com.au player
2674 mobj = re.search(
2675 r'''(?x)
2676 (?:
2677 <meta\s+property="og:video"\s+content=|
2678 <iframe[^>]+?src=
2679 )
2680 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2681 webpage)
2682 if mobj is not None:
2683 return self.url_result(mobj.group('url'), 'SBS')
2684
2685 # Look for embedded Cinchcast player
2686 mobj = re.search(
2687 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2688 webpage)
2689 if mobj is not None:
2690 return self.url_result(mobj.group('url'), 'Cinchcast')
2691
2692 mobj = re.search(
2693 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2694 webpage)
2695 if not mobj:
2696 mobj = re.search(
2697 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2698 webpage)
2699 if mobj is not None:
2700 return self.url_result(mobj.group('url'), 'MLB')
2701
2702 mobj = re.search(
2703 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2704 webpage)
2705 if mobj is not None:
2706 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2707
2708 mobj = re.search(
2709 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2710 webpage)
2711 if mobj is not None:
2712 return self.url_result(mobj.group('url'), 'Livestream')
2713
2714 # Look for Zapiks embed
2715 mobj = re.search(
2716 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2717 if mobj is not None:
2718 return self.url_result(mobj.group('url'), 'Zapiks')
2719
2720 # Look for Kaltura embeds
2721 kaltura_url = KalturaIE._extract_url(webpage)
2722 if kaltura_url:
2723 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2724
2725 # Look for EaglePlatform embeds
2726 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2727 if eagleplatform_url:
2728 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2729
2730 # Look for ClipYou (uses EaglePlatform) embeds
2731 mobj = re.search(
2732 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2733 if mobj is not None:
2734 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2735
2736 # Look for Pladform embeds
2737 pladform_url = PladformIE._extract_url(webpage)
2738 if pladform_url:
2739 return self.url_result(pladform_url)
2740
2741 # Look for Videomore embeds
2742 videomore_url = VideomoreIE._extract_url(webpage)
2743 if videomore_url:
2744 return self.url_result(videomore_url)
2745
2746 # Look for Webcaster embeds
2747 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2748 if webcaster_url:
2749 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2750
2751 # Look for Playwire embeds
2752 mobj = re.search(
2753 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2754 if mobj is not None:
2755 return self.url_result(mobj.group('url'))
2756
2757 # Look for 5min embeds
2758 mobj = re.search(
2759 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2760 if mobj is not None:
2761 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2762
2763 # Look for Crooks and Liars embeds
2764 mobj = re.search(
2765 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2766 if mobj is not None:
2767 return self.url_result(mobj.group('url'))
2768
2769 # Look for NBC Sports VPlayer embeds
2770 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2771 if nbc_sports_url:
2772 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2773
2774 # Look for NBC News embeds
2775 nbc_news_embed_url = re.search(
2776 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2777 if nbc_news_embed_url:
2778 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2779
2780 # Look for Google Drive embeds
2781 google_drive_url = GoogleDriveIE._extract_url(webpage)
2782 if google_drive_url:
2783 return self.url_result(google_drive_url, 'GoogleDrive')
2784
2785 # Look for UDN embeds
2786 mobj = re.search(
2787 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2788 if mobj is not None:
2789 return self.url_result(
2790 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2791
2792 # Look for Senate ISVP iframe
2793 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2794 if senate_isvp_url:
2795 return self.url_result(senate_isvp_url, 'SenateISVP')
2796
2797 # Look for OnionStudios embeds
2798 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2799 if onionstudios_url:
2800 return self.url_result(onionstudios_url)
2801
2802 # Look for ViewLift embeds
2803 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2804 if viewlift_url:
2805 return self.url_result(viewlift_url)
2806
2807 # Look for JWPlatform embeds
2808 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2809 if jwplatform_urls:
2810 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2811
2812 # Look for Digiteka embeds
2813 digiteka_url = DigitekaIE._extract_url(webpage)
2814 if digiteka_url:
2815 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2816
2817 # Look for Arkena embeds
2818 arkena_url = ArkenaIE._extract_url(webpage)
2819 if arkena_url:
2820 return self.url_result(arkena_url, ArkenaIE.ie_key())
2821
2822 # Look for Piksel embeds
2823 piksel_url = PikselIE._extract_url(webpage)
2824 if piksel_url:
2825 return self.url_result(piksel_url, PikselIE.ie_key())
2826
2827 # Look for Limelight embeds
2828 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2829 if limelight_urls:
2830 return self.playlist_result(
2831 limelight_urls, video_id, video_title, video_description)
2832
2833 # Look for Anvato embeds
2834 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2835 if anvato_urls:
2836 return self.playlist_result(
2837 anvato_urls, video_id, video_title, video_description)
2838
2839 # Look for AdobeTVVideo embeds
2840 mobj = re.search(
2841 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2842 webpage)
2843 if mobj is not None:
2844 return self.url_result(
2845 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2846 'AdobeTVVideo')
2847
2848 # Look for Vine embeds
2849 mobj = re.search(
2850 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2851 webpage)
2852 if mobj is not None:
2853 return self.url_result(
2854 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2855
2856 # Look for VODPlatform embeds
2857 mobj = re.search(
2858 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2859 webpage)
2860 if mobj is not None:
2861 return self.url_result(
2862 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2863
2864 # Look for Mangomolo embeds
2865 mobj = re.search(
2866 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2867 (?:
2868 video\?.*?\bid=(?P<video_id>\d+)|
2869 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2870 ).+?)\1''', webpage)
2871 if mobj is not None:
2872 info = {
2873 '_type': 'url_transparent',
2874 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2875 'title': video_title,
2876 'description': video_description,
2877 'thumbnail': video_thumbnail,
2878 'uploader': video_uploader,
2879 }
2880 video_id = mobj.group('video_id')
2881 if video_id:
2882 info.update({
2883 'ie_key': 'MangomoloVideo',
2884 'id': video_id,
2885 })
2886 else:
2887 info.update({
2888 'ie_key': 'MangomoloLive',
2889 'id': mobj.group('channel_id'),
2890 })
2891 return info
2892
2893 # Look for Instagram embeds
2894 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2895 if instagram_embed_url is not None:
2896 return self.url_result(
2897 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2898
2899 # Look for LiveLeak embeds
2900 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2901 if liveleak_urls:
2902 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2903
2904 # Look for 3Q SDN embeds
2905 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2906 if threeqsdn_url:
2907 return {
2908 '_type': 'url_transparent',
2909 'ie_key': ThreeQSDNIE.ie_key(),
2910 'url': self._proto_relative_url(threeqsdn_url),
2911 'title': video_title,
2912 'description': video_description,
2913 'thumbnail': video_thumbnail,
2914 'uploader': video_uploader,
2915 }
2916
2917 # Look for VBOX7 embeds
2918 vbox7_url = Vbox7IE._extract_url(webpage)
2919 if vbox7_url:
2920 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2921
2922 # Look for DBTV embeds
2923 dbtv_urls = DBTVIE._extract_urls(webpage)
2924 if dbtv_urls:
2925 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2926
2927 # Look for Videa embeds
2928 videa_urls = VideaIE._extract_urls(webpage)
2929 if videa_urls:
2930 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2931
2932 # Look for 20 minuten embeds
2933 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2934 if twentymin_urls:
2935 return self.playlist_from_matches(
2936 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2937
2938 # Look for Openload embeds
2939 openload_urls = OpenloadIE._extract_urls(webpage)
2940 if openload_urls:
2941 return self.playlist_from_matches(
2942 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2943
2944 # Look for VideoPress embeds
2945 videopress_urls = VideoPressIE._extract_urls(webpage)
2946 if videopress_urls:
2947 return self.playlist_from_matches(
2948 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2949
2950 # Look for Rutube embeds
2951 rutube_urls = RutubeIE._extract_urls(webpage)
2952 if rutube_urls:
2953 return self.playlist_from_matches(
2954 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2955
2956 # Look for WashingtonPost embeds
2957 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2958 if wapo_urls:
2959 return self.playlist_from_matches(
2960 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2961
2962 # Look for Mediaset embeds
2963 mediaset_urls = MediasetIE._extract_urls(webpage)
2964 if mediaset_urls:
2965 return self.playlist_from_matches(
2966 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2967
2968 # Look for JOJ.sk embeds
2969 joj_urls = JojIE._extract_urls(webpage)
2970 if joj_urls:
2971 return self.playlist_from_matches(
2972 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2973
2974 # Look for megaphone.fm embeds
2975 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2976 if mpfn_urls:
2977 return self.playlist_from_matches(
2978 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2979
2980 # Look for vzaar embeds
2981 vzaar_urls = VzaarIE._extract_urls(webpage)
2982 if vzaar_urls:
2983 return self.playlist_from_matches(
2984 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2985
2986 channel9_urls = Channel9IE._extract_urls(webpage)
2987 if channel9_urls:
2988 return self.playlist_from_matches(
2989 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2990
2991 vshare_urls = VShareIE._extract_urls(webpage)
2992 if vshare_urls:
2993 return self.playlist_from_matches(
2994 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2995
2996 # Look for Mediasite embeds
2997 mediasite_urls = MediasiteIE._extract_urls(webpage)
2998 if mediasite_urls:
2999 entries = [
3000 self.url_result(smuggle_url(
3001 compat_urlparse.urljoin(url, mediasite_url),
3002 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3003 for mediasite_url in mediasite_urls]
3004 return self.playlist_result(entries, video_id, video_title)
3005
3006 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3007 if springboardplatform_urls:
3008 return self.playlist_from_matches(
3009 springboardplatform_urls, video_id, video_title,
3010 ie=SpringboardPlatformIE.ie_key())
3011
3012 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3013 if yapfiles_urls:
3014 return self.playlist_from_matches(
3015 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3016
3017 vice_urls = ViceIE._extract_urls(webpage)
3018 if vice_urls:
3019 return self.playlist_from_matches(
3020 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3021
3022 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3023 if xfileshare_urls:
3024 return self.playlist_from_matches(
3025 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3026
3027 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3028 if cloudflarestream_urls:
3029 return self.playlist_from_matches(
3030 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3031
3032 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3033 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3034 webpage)]
3035 if sharevideos_urls:
3036 return self.playlist_from_matches(
3037 sharevideos_urls, video_id, video_title)
3038
3039 # Look for HTML5 media
3040 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3041 if entries:
3042 if len(entries) == 1:
3043 entries[0].update({
3044 'id': video_id,
3045 'title': video_title,
3046 })
3047 else:
3048 for num, entry in enumerate(entries, start=1):
3049 entry.update({
3050 'id': '%s-%s' % (video_id, num),
3051 'title': '%s (%d)' % (video_title, num),
3052 })
3053 for entry in entries:
3054 self._sort_formats(entry['formats'])
3055 return self.playlist_result(entries, video_id, video_title)
3056
3057 jwplayer_data = self._find_jwplayer_data(
3058 webpage, video_id, transform_source=js_to_json)
3059 if jwplayer_data:
3060 info = self._parse_jwplayer_data(
3061 jwplayer_data, video_id, require_title=False, base_url=url)
3062 return merge_dicts(info, info_dict)
3063
3064 # Video.js embed
3065 mobj = re.search(
3066 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3067 webpage)
3068 if mobj is not None:
3069 sources = self._parse_json(
3070 mobj.group(1), video_id, transform_source=js_to_json,
3071 fatal=False) or []
3072 if not isinstance(sources, list):
3073 sources = [sources]
3074 formats = []
3075 for source in sources:
3076 src = source.get('src')
3077 if not src or not isinstance(src, compat_str):
3078 continue
3079 src = compat_urlparse.urljoin(url, src)
3080 src_type = source.get('type')
3081 if isinstance(src_type, compat_str):
3082 src_type = src_type.lower()
3083 ext = determine_ext(src).lower()
3084 if src_type == 'video/youtube':
3085 return self.url_result(src, YoutubeIE.ie_key())
3086 if src_type == 'application/dash+xml' or ext == 'mpd':
3087 formats.extend(self._extract_mpd_formats(
3088 src, video_id, mpd_id='dash', fatal=False))
3089 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3090 formats.extend(self._extract_m3u8_formats(
3091 src, video_id, 'mp4', entry_protocol='m3u8_native',
3092 m3u8_id='hls', fatal=False))
3093 else:
3094 formats.append({
3095 'url': src,
3096 'ext': (mimetype2ext(src_type) or
3097 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3098 })
3099 if formats:
3100 self._sort_formats(formats)
3101 info_dict['formats'] = formats
3102 return info_dict
3103
3104 # Looking for http://schema.org/VideoObject
3105 json_ld = self._search_json_ld(
3106 webpage, video_id, default={}, expected_type='VideoObject')
3107 if json_ld.get('url'):
3108 return merge_dicts(json_ld, info_dict)
3109
3110 def check_video(vurl):
3111 if YoutubeIE.suitable(vurl):
3112 return True
3113 if RtmpIE.suitable(vurl):
3114 return True
3115 vpath = compat_urlparse.urlparse(vurl).path
3116 vext = determine_ext(vpath)
3117 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3118
3119 def filter_video(urls):
3120 return list(filter(check_video, urls))
3121
3122 # Start with something easy: JW Player in SWFObject
3123 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3124 if not found:
3125 # Look for gorilla-vid style embedding
3126 found = filter_video(re.findall(r'''(?sx)
3127 (?:
3128 jw_plugins|
3129 JWPlayerOptions|
3130 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3131 )
3132 .*?
3133 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3134 if not found:
3135 # Broaden the search a little bit
3136 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3137 if not found:
3138 # Broaden the findall a little bit: JWPlayer JS loader
3139 found = filter_video(re.findall(
3140 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3141 if not found:
3142 # Flow player
3143 found = filter_video(re.findall(r'''(?xs)
3144 flowplayer\("[^"]+",\s*
3145 \{[^}]+?\}\s*,
3146 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3147 ["']?url["']?\s*:\s*["']([^"']+)["']
3148 ''', webpage))
3149 if not found:
3150 # Cinerama player
3151 found = re.findall(
3152 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3153 if not found:
3154 # Try to find twitter cards info
3155 # twitter:player:stream should be checked before twitter:player since
3156 # it is expected to contain a raw stream (see
3157 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3158 found = filter_video(re.findall(
3159 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3160 if not found:
3161 # We look for Open Graph info:
3162 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3163 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3164 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3165 if m_video_type is not None:
3166 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3167 if not found:
3168 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3169 found = re.search(
3170 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3171 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3172 webpage)
3173 if not found:
3174 # Look also in Refresh HTTP header
3175 refresh_header = head_response.headers.get('Refresh')
3176 if refresh_header:
3177 # In python 2 response HTTP headers are bytestrings
3178 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3179 refresh_header = refresh_header.decode('iso-8859-1')
3180 found = re.search(REDIRECT_REGEX, refresh_header)
3181 if found:
3182 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3183 if new_url != url:
3184 self.report_following_redirect(new_url)
3185 return {
3186 '_type': 'url',
3187 'url': new_url,
3188 }
3189 else:
3190 found = None
3191
3192 if not found:
3193 # twitter:player is a https URL to iframe player that may or may not
3194 # be supported by youtube-dl thus this is checked the very last (see
3195 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3196 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3197 if embed_url and embed_url != url:
3198 return self.url_result(embed_url)
3199
3200 if not found:
3201 raise UnsupportedError(url)
3202
3203 entries = []
3204 for video_url in orderedSet(found):
3205 video_url = unescapeHTML(video_url)
3206 video_url = video_url.replace('\\/', '/')
3207 video_url = compat_urlparse.urljoin(url, video_url)
3208 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3209
3210 # Sometimes, jwplayer extraction will result in a YouTube URL
3211 if YoutubeIE.suitable(video_url):
3212 entries.append(self.url_result(video_url, 'Youtube'))
3213 continue
3214
3215 # here's a fun little line of code for you:
3216 video_id = os.path.splitext(video_id)[0]
3217
3218 entry_info_dict = {
3219 'id': video_id,
3220 'uploader': video_uploader,
3221 'title': video_title,
3222 'age_limit': age_limit,
3223 }
3224
3225 if RtmpIE.suitable(video_url):
3226 entry_info_dict.update({
3227 '_type': 'url_transparent',
3228 'ie_key': RtmpIE.ie_key(),
3229 'url': video_url,
3230 })
3231 entries.append(entry_info_dict)
3232 continue
3233
3234 ext = determine_ext(video_url)
3235 if ext == 'smil':
3236 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3237 elif ext == 'xspf':
3238 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3239 elif ext == 'm3u8':
3240 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3241 elif ext == 'mpd':
3242 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3243 elif ext == 'f4m':
3244 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3245 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3246 # Just matching .ism/manifest is not enough to be reliably sure
3247 # whether it's actually an ISM manifest or some other streaming
3248 # manifest since there are various streaming URL formats
3249 # possible (see [1]) as well as some other shenanigans like
3250 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3251 # so on.
3252 # Thus the most reasonable way to solve this is to delegate
3253 # to generic extractor in order to look into the contents of
3254 # the manifest itself.
3255 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3256 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3257 entry_info_dict = self.url_result(
3258 smuggle_url(video_url, {'to_generic': True}),
3259 GenericIE.ie_key())
3260 else:
3261 entry_info_dict['url'] = video_url
3262
3263 if entry_info_dict.get('formats'):
3264 self._sort_formats(entry_info_dict['formats'])
3265
3266 entries.append(entry_info_dict)
3267
3268 if len(entries) == 1:
3269 return entries[0]
3270 else:
3271 for num, e in enumerate(entries, start=1):
3272 # 'url' results don't have a title
3273 if e.get('title') is not None:
3274 e['title'] = '%s (%d)' % (e['title'], num)
3275 return {
3276 '_type': 'playlist',
3277 'entries': entries,
3278 }