]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
New upstream version 2018.04.25
[youtubedl] / 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 mimetype2ext,
27 orderedSet,
28 sanitized_Request,
29 smuggle_url,
30 unescapeHTML,
31 unified_strdate,
32 unsmuggle_url,
33 UnsupportedError,
34 xpath_text,
35 )
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
38 BrightcoveLegacyIE,
39 BrightcoveNewIE,
40 )
41 from .nexx import (
42 NexxIE,
43 NexxEmbedIE,
44 )
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .tube8 import Tube8IE
62 from .vimeo import VimeoIE
63 from .dailymotion import DailymotionIE
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
101 from .vzaar import VzaarIE
102 from .channel9 import Channel9IE
103 from .vshare import VShareIE
104 from .mediasite import MediasiteIE
105 from .springboardplatform import SpringboardPlatformIE
106 from .yapfiles import YapFilesIE
107 from .vice import ViceIE
108 from .xfileshare import XFileShareIE
109
110
111 class GenericIE(InfoExtractor):
112 IE_DESC = 'Generic downloader that works on some sites'
113 _VALID_URL = r'.*'
114 IE_NAME = 'generic'
115 _TESTS = [
116 # Direct link to a video
117 {
118 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
119 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
120 'info_dict': {
121 'id': 'trailer',
122 'ext': 'mp4',
123 'title': 'trailer',
124 'upload_date': '20100513',
125 }
126 },
127 # Direct link to media delivered compressed (until Accept-Encoding is *)
128 {
129 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
130 'md5': '128c42e68b13950268b648275386fc74',
131 'info_dict': {
132 'id': 'FictionJunction-Parallel_Hearts',
133 'ext': 'flac',
134 'title': 'FictionJunction-Parallel_Hearts',
135 'upload_date': '20140522',
136 },
137 'expected_warnings': [
138 'URL could be a direct video link, returning it as such.'
139 ],
140 'skip': 'URL invalid',
141 },
142 # Direct download with broken HEAD
143 {
144 'url': 'http://ai-radio.org:8000/radio.opus',
145 'info_dict': {
146 'id': 'radio',
147 'ext': 'opus',
148 'title': 'radio',
149 },
150 'params': {
151 'skip_download': True, # infinite live stream
152 },
153 'expected_warnings': [
154 r'501.*Not Implemented',
155 r'400.*Bad Request',
156 ],
157 },
158 # Direct link with incorrect MIME type
159 {
160 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
161 'md5': '4ccbebe5f36706d85221f204d7eb5913',
162 'info_dict': {
163 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
164 'id': '5_Lennart_Poettering_-_Systemd',
165 'ext': 'webm',
166 'title': '5_Lennart_Poettering_-_Systemd',
167 'upload_date': '20141120',
168 },
169 'expected_warnings': [
170 'URL could be a direct video link, returning it as such.'
171 ]
172 },
173 # RSS feed
174 {
175 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
176 'info_dict': {
177 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
178 'title': 'Zero Punctuation',
179 'description': 're:.*groundbreaking video review series.*'
180 },
181 'playlist_mincount': 11,
182 },
183 # RSS feed with enclosure
184 {
185 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
186 'info_dict': {
187 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
188 'ext': 'm4v',
189 'upload_date': '20150228',
190 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
191 }
192 },
193 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
194 {
195 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
196 'info_dict': {
197 'id': 'smil',
198 'ext': 'mp4',
199 'title': 'Automatics, robotics and biocybernetics',
200 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
201 'upload_date': '20130627',
202 'formats': 'mincount:16',
203 'subtitles': 'mincount:1',
204 },
205 'params': {
206 'force_generic_extractor': True,
207 'skip_download': True,
208 },
209 },
210 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
211 {
212 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
213 'info_dict': {
214 'id': 'hds',
215 'ext': 'flv',
216 'title': 'hds',
217 'formats': 'mincount:1',
218 },
219 'params': {
220 'skip_download': True,
221 },
222 },
223 # SMIL from https://www.restudy.dk/video/play/id/1637
224 {
225 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
226 'info_dict': {
227 'id': 'video_1637',
228 'ext': 'flv',
229 'title': 'video_1637',
230 'formats': 'mincount:3',
231 },
232 'params': {
233 'skip_download': True,
234 },
235 },
236 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
237 {
238 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
239 'info_dict': {
240 'id': 'smil-service',
241 'ext': 'flv',
242 'title': 'smil-service',
243 'formats': 'mincount:1',
244 },
245 'params': {
246 'skip_download': True,
247 },
248 },
249 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
250 {
251 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
252 'info_dict': {
253 'id': '4719370',
254 'ext': 'mp4',
255 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
256 'formats': 'mincount:3',
257 },
258 'params': {
259 'skip_download': True,
260 },
261 },
262 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
263 {
264 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
265 'info_dict': {
266 'id': 'mZlp2ctYIUEB',
267 'ext': 'mp4',
268 'title': 'Tikibad ontruimd wegens brand',
269 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
270 'thumbnail': r're:^https?://.*\.jpg$',
271 'duration': 33,
272 },
273 'params': {
274 'skip_download': True,
275 },
276 },
277 # MPD from http://dash-mse-test.appspot.com/media.html
278 {
279 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
280 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
281 'info_dict': {
282 'id': 'car-20120827-manifest',
283 'ext': 'mp4',
284 'title': 'car-20120827-manifest',
285 'formats': 'mincount:9',
286 'upload_date': '20130904',
287 },
288 'params': {
289 'format': 'bestvideo',
290 },
291 },
292 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
293 {
294 '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',
295 'info_dict': {
296 'id': 'content',
297 'ext': 'mp4',
298 'title': 'content',
299 'formats': 'mincount:8',
300 },
301 'params': {
302 # m3u8 downloads
303 'skip_download': True,
304 },
305 'skip': 'video gone',
306 },
307 # m3u8 served with Content-Type: text/plain
308 {
309 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
310 'info_dict': {
311 'id': 'index',
312 'ext': 'mp4',
313 'title': 'index',
314 'upload_date': '20140720',
315 'formats': 'mincount:11',
316 },
317 'params': {
318 # m3u8 downloads
319 'skip_download': True,
320 },
321 'skip': 'video gone',
322 },
323 # google redirect
324 {
325 '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',
326 'info_dict': {
327 'id': 'cmQHVoWB5FY',
328 'ext': 'mp4',
329 'upload_date': '20130224',
330 'uploader_id': 'TheVerge',
331 'description': r're:^Chris Ziegler takes a look at the\.*',
332 'uploader': 'The Verge',
333 'title': 'First Firefox OS phones side-by-side',
334 },
335 'params': {
336 'skip_download': False,
337 }
338 },
339 {
340 # redirect in Refresh HTTP header
341 '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',
342 'info_dict': {
343 'id': 'pO8h3EaFRdo',
344 'ext': 'mp4',
345 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
346 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
347 'upload_date': '20150917',
348 'uploader_id': 'brtvofficial',
349 'uploader': 'Boiler Room',
350 },
351 'params': {
352 'skip_download': False,
353 },
354 },
355 {
356 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
357 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
358 'info_dict': {
359 'id': '13601338388002',
360 'ext': 'mp4',
361 'uploader': 'www.hodiho.fr',
362 'title': 'R\u00e9gis plante sa Jeep',
363 }
364 },
365 # bandcamp page with custom domain
366 {
367 'add_ie': ['Bandcamp'],
368 'url': 'http://bronyrock.com/track/the-pony-mash',
369 'info_dict': {
370 'id': '3235767654',
371 'ext': 'mp3',
372 'title': 'The Pony Mash',
373 'uploader': 'M_Pallante',
374 },
375 'skip': 'There is a limit of 200 free downloads / month for the test song',
376 },
377 {
378 # embedded brightcove video
379 # it also tests brightcove videos that need to set the 'Referer'
380 # in the http requests
381 'add_ie': ['BrightcoveLegacy'],
382 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
383 'info_dict': {
384 'id': '2765128793001',
385 'ext': 'mp4',
386 'title': 'Le cours de bourse : lā€™analyse technique',
387 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
388 'uploader': 'BFM BUSINESS',
389 },
390 'params': {
391 'skip_download': True,
392 },
393 },
394 {
395 # embedded with itemprop embedURL and video id spelled as `idVideo`
396 'add_id': ['BrightcoveLegacy'],
397 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
398 'info_dict': {
399 'id': '5255628253001',
400 'ext': 'mp4',
401 'title': 'md5:37c519b1128915607601e75a87995fc0',
402 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
403 'uploader': 'BFM BUSINESS',
404 'uploader_id': '876450612001',
405 'timestamp': 1482255315,
406 'upload_date': '20161220',
407 },
408 'params': {
409 'skip_download': True,
410 },
411 },
412 {
413 # https://github.com/rg3/youtube-dl/issues/2253
414 'url': 'http://bcove.me/i6nfkrc3',
415 'md5': '0ba9446db037002366bab3b3eb30c88c',
416 'info_dict': {
417 'id': '3101154703001',
418 'ext': 'mp4',
419 'title': 'Still no power',
420 'uploader': 'thestar.com',
421 '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.',
422 },
423 'add_ie': ['BrightcoveLegacy'],
424 'skip': 'video gone',
425 },
426 {
427 'url': 'http://www.championat.com/video/football/v/87/87499.html',
428 'md5': 'fb973ecf6e4a78a67453647444222983',
429 'info_dict': {
430 'id': '3414141473001',
431 'ext': 'mp4',
432 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
433 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
434 'uploader': 'Championat',
435 },
436 },
437 {
438 # https://github.com/rg3/youtube-dl/issues/3541
439 'add_ie': ['BrightcoveLegacy'],
440 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
441 'info_dict': {
442 'id': '3866516442001',
443 'ext': 'mp4',
444 'title': 'Leer mij vrouwen kennen: Aflevering 1',
445 'description': 'Leer mij vrouwen kennen: Aflevering 1',
446 'uploader': 'SBS Broadcasting',
447 },
448 'skip': 'Restricted to Netherlands',
449 'params': {
450 'skip_download': True, # m3u8 download
451 },
452 },
453 {
454 # Brightcove video in <iframe>
455 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
456 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
457 'info_dict': {
458 'id': '5360463607001',
459 'ext': 'mp4',
460 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
461 'description': 'č”åˆå›½å„æē«„åŸŗ金会äø­äøœå’ŒåŒ—非åŒŗ域大ä½æć€ä½œę›²å®¶ę‰Žå¾·Ā·čæŖę‹‰å°¼ļ¼ˆZade Diraniļ¼‰åœØ3꜈15ę—„å™åˆ©äŗšå†²ēŖēˆ†å‘7å‘Ø幓ēŗŖåæµę—„之际发åøƒäŗ†äøŗ叙利äŗšč°±å†™ēš„ę­Œę›²ć€Šåæƒč·³ć€‹ļ¼ˆHEARTBEATļ¼‰ļ¼Œäøŗ受到六幓冲ēŖå½±å“ēš„叙利äŗšå„æē«„发å‡ŗå¼ŗēƒˆå‘å–Šļ¼Œå‘¼åäø–ē•Œåšå‡ŗ共同åŠŖ力ļ¼Œä½æ叙利äŗšå„æē«„é‡ę–°čŽ·å¾—äŗ«ęœ‰ę­£åøøē«„幓ē”Ÿę“»ēš„ęƒåˆ©ć€‚',
462 'uploader': 'United Nations',
463 'uploader_id': '1362235914001',
464 'timestamp': 1489593889,
465 'upload_date': '20170315',
466 },
467 'add_ie': ['BrightcoveLegacy'],
468 },
469 {
470 # Brightcove with alternative playerID key
471 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
472 'info_dict': {
473 'id': 'nmeth.2062_SV1',
474 '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',
475 },
476 'playlist': [{
477 'info_dict': {
478 'id': '2228375078001',
479 'ext': 'mp4',
480 'title': 'nmeth.2062-sv1',
481 'description': 'nmeth.2062-sv1',
482 'timestamp': 1363357591,
483 'upload_date': '20130315',
484 'uploader': 'Nature Publishing Group',
485 'uploader_id': '1964492299001',
486 },
487 }],
488 },
489 {
490 # Brightcove with UUID in videoPlayer
491 'url': 'http://www8.hp.com/cn/zh/home.html',
492 'info_dict': {
493 'id': '5255815316001',
494 'ext': 'mp4',
495 'title': 'Sprocket Video - China',
496 'description': 'Sprocket Video - China',
497 'uploader': 'HP-Video Gallery',
498 'timestamp': 1482263210,
499 'upload_date': '20161220',
500 'uploader_id': '1107601872001',
501 },
502 'params': {
503 'skip_download': True, # m3u8 download
504 },
505 'skip': 'video rotates...weekly?',
506 },
507 {
508 # Brightcove:new type [2].
509 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
510 'md5': '2b35148fcf48da41c9fb4591650784f3',
511 'info_dict': {
512 'id': '5348741021001',
513 'ext': 'mp4',
514 'upload_date': '20170306',
515 'uploader_id': '4191638492001',
516 'timestamp': 1488769918,
517 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
518
519 },
520 },
521 {
522 # Alternative brightcove <video> attributes
523 '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/',
524 'info_dict': {
525 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
526 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
527 },
528 'playlist': [{
529 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
530 'info_dict': {
531 'id': '5311302538001',
532 'ext': 'mp4',
533 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
534 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
535 'timestamp': 1486321708,
536 'upload_date': '20170205',
537 'uploader_id': '800000640001',
538 },
539 'only_matching': True,
540 }],
541 },
542 {
543 # Brightcove with UUID in videoPlayer
544 'url': 'http://www8.hp.com/cn/zh/home.html',
545 'info_dict': {
546 'id': '5255815316001',
547 'ext': 'mp4',
548 'title': 'Sprocket Video - China',
549 'description': 'Sprocket Video - China',
550 'uploader': 'HP-Video Gallery',
551 'timestamp': 1482263210,
552 'upload_date': '20161220',
553 'uploader_id': '1107601872001',
554 },
555 'params': {
556 'skip_download': True, # m3u8 download
557 },
558 },
559 # ooyala video
560 {
561 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
562 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
563 'info_dict': {
564 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
565 'ext': 'mp4',
566 'title': '2cc213299525360.mov', # that's what we get
567 'duration': 238.231,
568 },
569 'add_ie': ['Ooyala'],
570 },
571 {
572 # ooyala video embedded with http://player.ooyala.com/iframe.js
573 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
574 'info_dict': {
575 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
576 'ext': 'mp4',
577 'title': '"Steve Jobs: Man in the Machine" trailer',
578 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
579 'duration': 135.427,
580 },
581 'params': {
582 'skip_download': True,
583 },
584 'skip': 'movie expired',
585 },
586 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
587 {
588 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
589 'info_dict': {
590 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
591 'ext': 'mp4',
592 'title': 'Steampunk Fest Comes to Honesdale',
593 'duration': 43.276,
594 },
595 'params': {
596 'skip_download': True,
597 }
598 },
599 # embed.ly video
600 {
601 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
602 'info_dict': {
603 'id': '9ODmcdjQcHQ',
604 'ext': 'mp4',
605 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
606 'upload_date': '20140225',
607 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
608 'uploader': 'Tested',
609 'uploader_id': 'testedcom',
610 },
611 # No need to test YoutubeIE here
612 'params': {
613 'skip_download': True,
614 },
615 },
616 # funnyordie embed
617 {
618 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
619 'info_dict': {
620 'id': '18e820ec3f',
621 'ext': 'mp4',
622 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
623 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
624 },
625 # HEAD requests lead to endless 301, while GET is OK
626 'expected_warnings': ['301'],
627 },
628 # RUTV embed
629 {
630 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
631 'info_dict': {
632 'id': '776940',
633 'ext': 'mp4',
634 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
635 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
636 },
637 'params': {
638 # m3u8 download
639 'skip_download': True,
640 },
641 },
642 # TVC embed
643 {
644 '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/',
645 'info_dict': {
646 'id': '55304',
647 'ext': 'mp4',
648 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
649 },
650 },
651 # SportBox embed
652 {
653 'url': 'http://www.vestifinance.ru/articles/25753',
654 'info_dict': {
655 'id': '25753',
656 'title': 'ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
657 },
658 'playlist': [{
659 'info_dict': {
660 'id': '370908',
661 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
662 'ext': 'mp4',
663 }
664 }, {
665 'info_dict': {
666 'id': '370905',
667 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
668 'ext': 'mp4',
669 }
670 }, {
671 'info_dict': {
672 'id': '370902',
673 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
674 'ext': 'mp4',
675 }
676 }],
677 'params': {
678 # m3u8 download
679 'skip_download': True,
680 },
681 },
682 # Myvi.ru embed
683 {
684 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
685 'info_dict': {
686 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
687 'ext': 'mp4',
688 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
689 'thumbnail': r're:^https?://.*\.jpg$',
690 'duration': 153,
691 }
692 },
693 # XHamster embed
694 {
695 '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',
696 'info_dict': {
697 'id': 'showthread',
698 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
699 },
700 'playlist_mincount': 7,
701 # This forum does not allow <iframe> syntaxes anymore
702 # Now HTML tags are displayed as-is
703 'skip': 'No videos on this page',
704 },
705 # Embedded TED video
706 {
707 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
708 'md5': '65fdff94098e4a607385a60c5177c638',
709 'info_dict': {
710 'id': '1969',
711 'ext': 'mp4',
712 'title': 'Hidden miracles of the natural world',
713 'uploader': 'Louie Schwartzberg',
714 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
715 }
716 },
717 # nowvideo embed hidden behind percent encoding
718 {
719 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
720 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
721 'info_dict': {
722 'id': '06e53103ca9aa',
723 'ext': 'flv',
724 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
725 'description': 'No description',
726 },
727 },
728 # arte embed
729 {
730 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
731 'md5': '7653032cbb25bf6c80d80f217055fa43',
732 'info_dict': {
733 'id': '048195-004_PLUS7-F',
734 'ext': 'flv',
735 'title': 'X:enius',
736 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
737 'upload_date': '20140320',
738 },
739 'params': {
740 'skip_download': 'Requires rtmpdump'
741 },
742 'skip': 'video gone',
743 },
744 # francetv embed
745 {
746 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
747 'info_dict': {
748 'id': 'EV_30231',
749 'ext': 'mp4',
750 'title': 'Alcaline, le concert avec Calogero',
751 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
752 'upload_date': '20150226',
753 'timestamp': 1424989860,
754 'duration': 5400,
755 },
756 'params': {
757 # m3u8 downloads
758 'skip_download': True,
759 },
760 'expected_warnings': [
761 'Forbidden'
762 ]
763 },
764 # CondƩ Nast embed
765 {
766 'url': 'http://www.wired.com/2014/04/honda-asimo/',
767 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
768 'info_dict': {
769 'id': '53501be369702d3275860000',
770 'ext': 'mp4',
771 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
772 }
773 },
774 # Dailymotion embed
775 {
776 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
777 'md5': '441aeeb82eb72c422c7f14ec533999cd',
778 'info_dict': {
779 'id': 'k2mm4bCdJ6CQ2i7c8o2',
780 'ext': 'mp4',
781 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
782 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
783 'uploader': 'Spi0n',
784 'uploader_id': 'xgditw',
785 'upload_date': '20140425',
786 'timestamp': 1398441542,
787 },
788 'add_ie': ['Dailymotion'],
789 },
790 # DailyMail embed
791 {
792 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
793 'info_dict': {
794 'id': '1495629',
795 'ext': 'mp4',
796 'title': 'Care worker punches elderly dementia patient in head 11 times',
797 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
798 },
799 'add_ie': ['DailyMail'],
800 'params': {
801 'skip_download': True,
802 },
803 },
804 # YouTube embed
805 {
806 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
807 'info_dict': {
808 'id': 'FXRb4ykk4S0',
809 'ext': 'mp4',
810 'title': 'The NBL Auction 2014',
811 'uploader': 'BADMINTON England',
812 'uploader_id': 'BADMINTONEvents',
813 'upload_date': '20140603',
814 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
815 },
816 'add_ie': ['Youtube'],
817 'params': {
818 'skip_download': True,
819 }
820 },
821 # MTVSercices embed
822 {
823 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
824 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
825 'info_dict': {
826 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
827 'ext': 'mp4',
828 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
829 'description': 'Two valets share their love for movie star Liam Neesons.',
830 'timestamp': 1349922600,
831 'upload_date': '20121011',
832 },
833 },
834 # YouTube embed via <data-embed-url="">
835 {
836 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
837 'info_dict': {
838 'id': '4vAffPZIT44',
839 'ext': 'mp4',
840 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
841 'uploader': 'Gameloft',
842 'uploader_id': 'gameloft',
843 'upload_date': '20140828',
844 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
845 },
846 'params': {
847 'skip_download': True,
848 }
849 },
850 # YouTube <object> embed
851 {
852 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
853 'md5': '516718101ec834f74318df76259fb3cc',
854 'info_dict': {
855 'id': 'msN87y-iEx0',
856 'ext': 'webm',
857 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
858 'upload_date': '20080526',
859 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
860 'uploader': 'Christopher Sykes',
861 'uploader_id': 'ChristopherJSykes',
862 },
863 'add_ie': ['Youtube'],
864 },
865 # Camtasia studio
866 {
867 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
868 'playlist': [{
869 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
870 'info_dict': {
871 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
872 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
873 'ext': 'flv',
874 'duration': 2235.90,
875 }
876 }, {
877 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
878 'info_dict': {
879 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
880 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
881 'ext': 'flv',
882 'duration': 2235.93,
883 }
884 }],
885 'info_dict': {
886 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
887 }
888 },
889 # Flowplayer
890 {
891 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
892 'md5': '9d65602bf31c6e20014319c7d07fba27',
893 'info_dict': {
894 'id': '5123ea6d5e5a7',
895 'ext': 'mp4',
896 'age_limit': 18,
897 'uploader': 'www.handjobhub.com',
898 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
899 }
900 },
901 # Multiple brightcove videos
902 # https://github.com/rg3/youtube-dl/issues/2283
903 {
904 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
905 'info_dict': {
906 'id': 'always-never',
907 'title': 'Always / Never - The New Yorker',
908 },
909 'playlist_count': 3,
910 'params': {
911 'extract_flat': False,
912 'skip_download': True,
913 }
914 },
915 # MLB embed
916 {
917 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
918 'md5': '96f09a37e44da40dd083e12d9a683327',
919 'info_dict': {
920 'id': '33322633',
921 'ext': 'mp4',
922 'title': 'Ump changes call to ball',
923 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
924 'duration': 48,
925 'timestamp': 1401537900,
926 'upload_date': '20140531',
927 'thumbnail': r're:^https?://.*\.jpg$',
928 },
929 },
930 # Wistia embed
931 {
932 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
933 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
934 'info_dict': {
935 'id': '6e2wtrbdaf',
936 'ext': 'mov',
937 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
938 'description': 'a Paywall Videos video from Remilon',
939 'duration': 644.072,
940 'uploader': 'study.com',
941 'timestamp': 1459678540,
942 'upload_date': '20160403',
943 'filesize': 24687186,
944 },
945 },
946 {
947 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
948 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
949 'info_dict': {
950 'id': 'uxjb0lwrcz',
951 'ext': 'mp4',
952 'title': 'Conversation about Hexagonal Rails Part 1',
953 'description': 'a Martin Fowler video from ThoughtWorks',
954 'duration': 1715.0,
955 'uploader': 'thoughtworks.wistia.com',
956 'timestamp': 1401832161,
957 'upload_date': '20140603',
958 },
959 },
960 # Wistia standard embed (async)
961 {
962 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
963 'info_dict': {
964 'id': '807fafadvk',
965 'ext': 'mp4',
966 'title': 'Drip Brennan Dunn Workshop',
967 'description': 'a JV Webinars video from getdrip-1',
968 'duration': 4986.95,
969 'timestamp': 1463607249,
970 'upload_date': '20160518',
971 },
972 'params': {
973 'skip_download': True,
974 }
975 },
976 # Soundcloud embed
977 {
978 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
979 'info_dict': {
980 'id': '174391317',
981 'ext': 'mp3',
982 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
983 'uploader': 'Sophos Security',
984 'title': 'Chet Chat 171 - Oct 29, 2014',
985 'upload_date': '20141029',
986 }
987 },
988 # Soundcloud multiple embeds
989 {
990 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
991 'info_dict': {
992 'id': '52809',
993 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
994 },
995 'playlist_mincount': 7,
996 },
997 # TuneIn station embed
998 {
999 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1000 'info_dict': {
1001 'id': '204146',
1002 'ext': 'mp3',
1003 'title': 'CNRV',
1004 'location': 'Paris, France',
1005 'is_live': True,
1006 },
1007 'params': {
1008 # Live stream
1009 'skip_download': True,
1010 },
1011 },
1012 # Livestream embed
1013 {
1014 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1015 'info_dict': {
1016 'id': '67864563',
1017 'ext': 'flv',
1018 'upload_date': '20141112',
1019 'title': 'Rosetta #CometLanding webcast HL 10',
1020 }
1021 },
1022 # Another Livestream embed, without 'new.' in URL
1023 {
1024 'url': 'https://www.freespeech.org/',
1025 'info_dict': {
1026 'id': '123537347',
1027 'ext': 'mp4',
1028 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1029 },
1030 'params': {
1031 # Live stream
1032 'skip_download': True,
1033 },
1034 },
1035 # LazyYT
1036 {
1037 'url': 'https://skiplagged.com/',
1038 'info_dict': {
1039 'id': 'skiplagged',
1040 'title': 'Skiplagged: The smart way to find cheap flights',
1041 },
1042 'playlist_mincount': 1,
1043 'add_ie': ['Youtube'],
1044 },
1045 # Cinchcast embed
1046 {
1047 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1048 'info_dict': {
1049 'id': '7141703',
1050 'ext': 'mp3',
1051 'upload_date': '20141126',
1052 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1053 }
1054 },
1055 # Cinerama player
1056 {
1057 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1058 'info_dict': {
1059 'id': '730m_DandD_1901_512k',
1060 'ext': 'mp4',
1061 'uploader': 'www.abc.net.au',
1062 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1063 }
1064 },
1065 # embedded viddler video
1066 {
1067 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1068 'info_dict': {
1069 'id': '4d03aad9',
1070 'ext': 'mp4',
1071 'uploader': 'deadspin',
1072 'title': 'WALL-TO-GORTAT',
1073 'timestamp': 1422285291,
1074 'upload_date': '20150126',
1075 },
1076 'add_ie': ['Viddler'],
1077 },
1078 # Libsyn embed
1079 {
1080 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1081 'info_dict': {
1082 'id': '3377616',
1083 'ext': 'mp3',
1084 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1085 'description': 'md5:601cb790edd05908957dae8aaa866465',
1086 'upload_date': '20150220',
1087 },
1088 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1089 },
1090 # jwplayer YouTube
1091 {
1092 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1093 'info_dict': {
1094 'id': 'Mrj4DVp2zeA',
1095 'ext': 'mp4',
1096 'upload_date': '20150212',
1097 'uploader': 'The National Archives UK',
1098 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1099 'uploader_id': 'NationalArchives08',
1100 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1101 },
1102 },
1103 # jwplayer rtmp
1104 {
1105 'url': 'http://www.suffolk.edu/sjc/live.php',
1106 'info_dict': {
1107 'id': 'live',
1108 'ext': 'flv',
1109 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1110 'uploader': 'www.suffolk.edu',
1111 },
1112 'params': {
1113 'skip_download': True,
1114 },
1115 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1116 },
1117 # Complex jwplayer
1118 {
1119 'url': 'http://www.indiedb.com/games/king-machine/videos',
1120 'info_dict': {
1121 'id': 'videos',
1122 'ext': 'mp4',
1123 'title': 'king machine trailer 1',
1124 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1125 'thumbnail': r're:^https?://.*\.jpg$',
1126 },
1127 },
1128 {
1129 # JWPlayer config passed as variable
1130 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1131 'info_dict': {
1132 'id': '3326530_hq',
1133 'ext': 'mp4',
1134 'title': 'ARIELE | Tube Cup',
1135 'uploader': 'www.txxx.com',
1136 'age_limit': 18,
1137 },
1138 'params': {
1139 'skip_download': True,
1140 }
1141 },
1142 {
1143 # JWPlatform iframe
1144 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1145 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1146 'info_dict': {
1147 'id': 'O0c5JcKT',
1148 'ext': 'mp4',
1149 'upload_date': '20171122',
1150 'timestamp': 1511366290,
1151 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1152 },
1153 'add_ie': [JWPlatformIE.ie_key()],
1154 },
1155 {
1156 # Video.js embed, multiple formats
1157 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1158 'info_dict': {
1159 'id': 'yygqldloqIk',
1160 'ext': 'mp4',
1161 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1162 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1163 'upload_date': '20130314',
1164 'uploader': 'PROстŠ¾Šµ3D',
1165 'uploader_id': 'PROstoe3D',
1166 },
1167 'params': {
1168 'skip_download': True,
1169 },
1170 },
1171 {
1172 # Video.js embed, single format
1173 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1174 'info_dict': {
1175 'id': 'watch',
1176 'ext': 'mp4',
1177 'title': 'Step 1 - Good Foundation',
1178 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1179 },
1180 'params': {
1181 'skip_download': True,
1182 },
1183 },
1184 # rtl.nl embed
1185 {
1186 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1187 'playlist_mincount': 5,
1188 'info_dict': {
1189 'id': 'aanslagen-kopenhagen',
1190 'title': 'Aanslagen Kopenhagen',
1191 }
1192 },
1193 # Zapiks embed
1194 {
1195 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1196 'info_dict': {
1197 'id': '118046',
1198 'ext': 'mp4',
1199 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1200 }
1201 },
1202 # Kaltura embed (different embed code)
1203 {
1204 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1205 'info_dict': {
1206 'id': '1_a52wc67y',
1207 'ext': 'flv',
1208 'upload_date': '20150127',
1209 'uploader_id': 'PremierMedia',
1210 'timestamp': int,
1211 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1212 },
1213 },
1214 # Kaltura embed with single quotes
1215 {
1216 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1217 'info_dict': {
1218 'id': '0_izeg5utt',
1219 'ext': 'mp4',
1220 'title': '35871',
1221 'timestamp': 1355743100,
1222 'upload_date': '20121217',
1223 'uploader_id': 'cplapp@learn360.com',
1224 },
1225 'add_ie': ['Kaltura'],
1226 },
1227 {
1228 # Kaltura embedded via quoted entry_id
1229 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1230 'info_dict': {
1231 'id': '0_utuok90b',
1232 'ext': 'mp4',
1233 'title': '06_matthew_brender_raj_dutt',
1234 'timestamp': 1466638791,
1235 'upload_date': '20160622',
1236 },
1237 'add_ie': ['Kaltura'],
1238 'expected_warnings': [
1239 'Could not send HEAD request'
1240 ],
1241 'params': {
1242 'skip_download': True,
1243 }
1244 },
1245 {
1246 # Kaltura embedded, some fileExt broken (#11480)
1247 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1248 'info_dict': {
1249 'id': '1_sgtvehim',
1250 'ext': 'mp4',
1251 'title': 'Our "Standard Models" of particle physics and cosmology',
1252 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1253 'timestamp': 1321158993,
1254 'upload_date': '20111113',
1255 'uploader_id': 'kps1',
1256 },
1257 'add_ie': ['Kaltura'],
1258 },
1259 {
1260 # Kaltura iframe embed
1261 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1262 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1263 'info_dict': {
1264 'id': '0_f2cfbpwy',
1265 'ext': 'mp4',
1266 'title': 'I. M. Pei: A Centennial Celebration',
1267 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1268 'upload_date': '20170403',
1269 'uploader_id': 'batchUser',
1270 'timestamp': 1491232186,
1271 },
1272 'add_ie': ['Kaltura'],
1273 },
1274 {
1275 # meta twitter:player
1276 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1277 'info_dict': {
1278 'id': '0_01b42zps',
1279 'ext': 'mp4',
1280 'title': 'Main Twerk (Video)',
1281 'upload_date': '20171208',
1282 'uploader_id': 'sebastian.salinas@thechive.com',
1283 'timestamp': 1512713057,
1284 },
1285 'params': {
1286 'skip_download': True,
1287 },
1288 'add_ie': ['Kaltura'],
1289 },
1290 # referrer protected EaglePlatform embed
1291 {
1292 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1293 'info_dict': {
1294 'id': '582306',
1295 'ext': 'mp4',
1296 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1297 'thumbnail': r're:^https?://.*\.jpg$',
1298 'duration': 3382,
1299 'view_count': int,
1300 },
1301 'params': {
1302 'skip_download': True,
1303 },
1304 },
1305 # ClipYou (EaglePlatform) embed (custom URL)
1306 {
1307 'url': 'http://muz-tv.ru/play/7129/',
1308 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1309 'info_dict': {
1310 'id': '12820',
1311 'ext': 'mp4',
1312 'title': "'O Sole Mio",
1313 'thumbnail': r're:^https?://.*\.jpg$',
1314 'duration': 216,
1315 'view_count': int,
1316 },
1317 'params': {
1318 'skip_download': True,
1319 },
1320 'skip': 'This video is unavailable.',
1321 },
1322 # Pladform embed
1323 {
1324 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1325 'info_dict': {
1326 'id': '100183293',
1327 'ext': 'mp4',
1328 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1329 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1330 'thumbnail': r're:^https?://.*\.jpg$',
1331 'duration': 694,
1332 'age_limit': 0,
1333 },
1334 'skip': 'HTTP Error 404: Not Found',
1335 },
1336 # Playwire embed
1337 {
1338 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1339 'info_dict': {
1340 'id': '3519514',
1341 'ext': 'mp4',
1342 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1343 'thumbnail': r're:^https?://.*\.png$',
1344 'duration': 45.115,
1345 },
1346 },
1347 # 5min embed
1348 {
1349 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1350 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1351 'info_dict': {
1352 'id': '518726732',
1353 'ext': 'mp4',
1354 'title': 'Facebook Creates "On This Day" | Crunch Report',
1355 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1356 'timestamp': 1427237531,
1357 'uploader': 'Crunch Report',
1358 'upload_date': '20150324',
1359 },
1360 'params': {
1361 # m3u8 download
1362 'skip_download': True,
1363 },
1364 },
1365 # SVT embed
1366 {
1367 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1368 'info_dict': {
1369 'id': '2900353',
1370 'ext': 'flv',
1371 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1372 'duration': 27,
1373 'age_limit': 0,
1374 },
1375 },
1376 # Crooks and Liars embed
1377 {
1378 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1379 'info_dict': {
1380 'id': '8RUoRhRi',
1381 'ext': 'mp4',
1382 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1383 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1384 'timestamp': 1428207000,
1385 'upload_date': '20150405',
1386 'uploader': 'Heather',
1387 },
1388 },
1389 # Crooks and Liars external embed
1390 {
1391 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1392 'info_dict': {
1393 'id': 'MTE3MjUtMzQ2MzA',
1394 'ext': 'mp4',
1395 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1396 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1397 'timestamp': 1265032391,
1398 'upload_date': '20100201',
1399 'uploader': 'Heather',
1400 },
1401 },
1402 # NBC Sports vplayer embed
1403 {
1404 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1405 'info_dict': {
1406 'id': 'ln7x1qSThw4k',
1407 'ext': 'flv',
1408 'title': "PFT Live: New leader in the 'new-look' defense",
1409 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1410 'uploader': 'NBCU-SPORTS',
1411 'upload_date': '20140107',
1412 'timestamp': 1389118457,
1413 },
1414 'skip': 'Invalid Page URL',
1415 },
1416 # NBC News embed
1417 {
1418 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1419 'md5': '1aa589c675898ae6d37a17913cf68d66',
1420 'info_dict': {
1421 'id': 'x_dtl_oa_LettermanliftPR_160608',
1422 'ext': 'mp4',
1423 'title': 'David Letterman: A Preview',
1424 '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.',
1425 'upload_date': '20160609',
1426 'timestamp': 1465431544,
1427 'uploader': 'NBCU-NEWS',
1428 },
1429 },
1430 # UDN embed
1431 {
1432 'url': 'https://video.udn.com/news/300346',
1433 'md5': 'fd2060e988c326991037b9aff9df21a6',
1434 'info_dict': {
1435 'id': '300346',
1436 'ext': 'mp4',
1437 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1438 'thumbnail': r're:^https?://.*\.jpg$',
1439 },
1440 'params': {
1441 # m3u8 download
1442 'skip_download': True,
1443 },
1444 'expected_warnings': ['Failed to parse JSON Expecting value'],
1445 },
1446 # Ooyala embed
1447 {
1448 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1449 'info_dict': {
1450 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1451 'ext': 'mp4',
1452 'description': 'Index/Match versus VLOOKUP.',
1453 'title': 'This is what separates the Excel masters from the wannabes',
1454 'duration': 191.933,
1455 },
1456 'params': {
1457 # m3u8 downloads
1458 'skip_download': True,
1459 }
1460 },
1461 # Brightcove URL in single quotes
1462 {
1463 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1464 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1465 'info_dict': {
1466 'id': '4255764656001',
1467 'ext': 'mp4',
1468 'title': 'SN Presents: Russell Martin, World Citizen',
1469 'description': 'To understand why he was the Toronto Blue Jaysā€™ 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.',
1470 'uploader': 'Rogers Sportsnet',
1471 'uploader_id': '1704050871',
1472 'upload_date': '20150525',
1473 'timestamp': 1432570283,
1474 },
1475 },
1476 # OnionStudios embed
1477 {
1478 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1479 'info_dict': {
1480 'id': '2855',
1481 'ext': 'mp4',
1482 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1483 'thumbnail': r're:^https?://.*\.jpe?g$',
1484 'uploader': 'ClickHole',
1485 'uploader_id': 'clickhole',
1486 }
1487 },
1488 # SnagFilms embed
1489 {
1490 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1491 'info_dict': {
1492 'id': '74849a00-85a9-11e1-9660-123139220831',
1493 'ext': 'mp4',
1494 'title': '#whilewewatch',
1495 }
1496 },
1497 # AdobeTVVideo embed
1498 {
1499 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1500 'md5': '43662b577c018ad707a63766462b1e87',
1501 'info_dict': {
1502 'id': '2456',
1503 'ext': 'mp4',
1504 'title': 'New experience with Acrobat DC',
1505 'description': 'New experience with Acrobat DC',
1506 'duration': 248.667,
1507 },
1508 },
1509 # BrightcoveInPageEmbed embed
1510 {
1511 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1512 'info_dict': {
1513 'id': '4238694884001',
1514 'ext': 'flv',
1515 'title': 'Tabletop: Dread, Last Thoughts',
1516 'description': 'Tabletop: Dread, Last Thoughts',
1517 'duration': 51690,
1518 },
1519 },
1520 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1521 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1522 {
1523 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1524 'info_dict': {
1525 'id': '4785848093001',
1526 'ext': 'mp4',
1527 'title': 'The Cardinal Pell Interview',
1528 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1529 'uploader': 'GlobeCast Australia - GlobeStream',
1530 'uploader_id': '2733773828001',
1531 'upload_date': '20160304',
1532 'timestamp': 1457083087,
1533 },
1534 'params': {
1535 # m3u8 downloads
1536 'skip_download': True,
1537 },
1538 },
1539 {
1540 # Brightcove embed with whitespace around attribute names
1541 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1542 'info_dict': {
1543 'id': '3167554373001',
1544 'ext': 'mp4',
1545 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1546 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1547 'uploader_id': '1079349493',
1548 'upload_date': '20140207',
1549 'timestamp': 1391810548,
1550 },
1551 'params': {
1552 'skip_download': True,
1553 },
1554 },
1555 # Another form of arte.tv embed
1556 {
1557 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1558 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1559 'info_dict': {
1560 'id': '030273-562_PLUS7-F',
1561 'ext': 'mp4',
1562 'title': 'ARTE Reportage - Nulle part, en France',
1563 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1564 'upload_date': '20160409',
1565 },
1566 },
1567 # LiveLeak embed
1568 {
1569 'url': 'http://www.wykop.pl/link/3088787/',
1570 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1571 'info_dict': {
1572 'id': '874_1459135191',
1573 'ext': 'mp4',
1574 'title': 'Man shows poor quality of new apartment building',
1575 'description': 'The wall is like a sand pile.',
1576 'uploader': 'Lake8737',
1577 },
1578 'add_ie': [LiveLeakIE.ie_key()],
1579 },
1580 # Another LiveLeak embed pattern (#13336)
1581 {
1582 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1583 'info_dict': {
1584 'id': '2eb_1496309988',
1585 'ext': 'mp4',
1586 'title': 'Thief robs place where everyone was armed',
1587 'description': 'md5:694d73ee79e535953cf2488562288eee',
1588 'uploader': 'brazilwtf',
1589 },
1590 'add_ie': [LiveLeakIE.ie_key()],
1591 },
1592 # Duplicated embedded video URLs
1593 {
1594 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1595 'info_dict': {
1596 'id': '149298443_480_16c25b74_2',
1597 'ext': 'mp4',
1598 'title': 'vs. Blue Orange Spring Game',
1599 'uploader': 'www.hudl.com',
1600 },
1601 },
1602 # twitter:player:stream embed
1603 {
1604 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1605 'info_dict': {
1606 'id': 'master',
1607 'ext': 'mp4',
1608 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1609 'uploader': 'www.rtl.be',
1610 },
1611 'params': {
1612 # m3u8 downloads
1613 'skip_download': True,
1614 },
1615 },
1616 # twitter:player embed
1617 {
1618 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1619 'md5': 'a3e0df96369831de324f0778e126653c',
1620 'info_dict': {
1621 'id': '4909620399001',
1622 'ext': 'mp4',
1623 'title': 'What Do Black Holes Sound Like?',
1624 'description': 'what do black holes sound like',
1625 'upload_date': '20160524',
1626 'uploader_id': '29913724001',
1627 'timestamp': 1464107587,
1628 'uploader': 'TheAtlantic',
1629 },
1630 'add_ie': ['BrightcoveLegacy'],
1631 },
1632 # Facebook <iframe> embed
1633 {
1634 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1635 'md5': 'fbcde74f534176ecb015849146dd3aee',
1636 'info_dict': {
1637 'id': '599637780109885',
1638 'ext': 'mp4',
1639 'title': 'Facebook video #599637780109885',
1640 },
1641 },
1642 # Facebook <iframe> embed, plugin video
1643 {
1644 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1645 'info_dict': {
1646 'id': '1754168231264132',
1647 'ext': 'mp4',
1648 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1649 'uploader': 'Tariq Ramadan (official)',
1650 'timestamp': 1496758379,
1651 'upload_date': '20170606',
1652 },
1653 'params': {
1654 'skip_download': True,
1655 },
1656 },
1657 # Facebook API embed
1658 {
1659 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1660 'md5': 'a47372ee61b39a7b90287094d447d94e',
1661 'info_dict': {
1662 'id': '10153467542406923',
1663 'ext': 'mp4',
1664 'title': 'Facebook video #10153467542406923',
1665 },
1666 },
1667 # Wordpress "YouTube Video Importer" plugin
1668 {
1669 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1670 'md5': 'd16797741b560b485194eddda8121b48',
1671 'info_dict': {
1672 'id': 'HNTXWDXV9Is',
1673 'ext': 'mp4',
1674 'title': 'Blue Devils Drumline Stanford lot 2016',
1675 'upload_date': '20160627',
1676 'uploader_id': 'GENOCIDE8GENERAL10',
1677 'uploader': 'cylus cyrus',
1678 },
1679 },
1680 {
1681 # video stored on custom kaltura server
1682 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1683 'md5': '537617d06e64dfed891fa1593c4b30cc',
1684 'info_dict': {
1685 'id': '0_1iotm5bh',
1686 'ext': 'mp4',
1687 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1688 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1689 'uploader_id': 'videos.expansion@el-mundo.net',
1690 'upload_date': '20150429',
1691 'timestamp': 1430303472,
1692 },
1693 'add_ie': ['Kaltura'],
1694 },
1695 {
1696 # Non-standard Vimeo embed
1697 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1698 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1699 'info_dict': {
1700 'id': '148867247',
1701 'ext': 'mp4',
1702 'title': 'Understanding the web - Teaser',
1703 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1704 'upload_date': '20151214',
1705 'uploader': 'OpenClassrooms',
1706 'uploader_id': 'openclassrooms',
1707 },
1708 'add_ie': ['Vimeo'],
1709 },
1710 {
1711 # generic vimeo embed that requires original URL passed as Referer
1712 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1713 'only_matching': True,
1714 },
1715 {
1716 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1717 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1718 'info_dict': {
1719 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1720 'ext': 'mp4',
1721 'title': 'Big Buck Bunny',
1722 'description': 'Royalty free test video',
1723 'timestamp': 1432816365,
1724 'upload_date': '20150528',
1725 'is_live': False,
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 'add_ie': [ArkenaIE.ie_key()],
1731 },
1732 {
1733 '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/',
1734 'info_dict': {
1735 'id': '1c7141f46c',
1736 'ext': 'mp4',
1737 'title': 'ŠŠ ŠšŠžŠ”ŠŖŠœ ŠžŠ¢ Š’Š—Š Š˜Š’: Š˜Š·Ń‚ŠøчŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃ‚Š°Š½Ń†Šøя Š² ŠŸŠ»Š¾Š²Š“ŠøŠ²',
1738 },
1739 'params': {
1740 'skip_download': True,
1741 },
1742 'add_ie': [Vbox7IE.ie_key()],
1743 },
1744 {
1745 # DBTV embeds
1746 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1747 'info_dict': {
1748 'id': '43254897',
1749 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1750 },
1751 'playlist_mincount': 3,
1752 },
1753 {
1754 # Videa embeds
1755 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1756 'info_dict': {
1757 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1758 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1759 },
1760 'playlist_mincount': 2,
1761 },
1762 {
1763 # 20 minuten embed
1764 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1765 'info_dict': {
1766 'id': '523629',
1767 'ext': 'mp4',
1768 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1769 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1770 },
1771 'params': {
1772 'skip_download': True,
1773 },
1774 'add_ie': [TwentyMinutenIE.ie_key()],
1775 },
1776 {
1777 # VideoPress embed
1778 'url': 'https://en.support.wordpress.com/videopress/',
1779 'info_dict': {
1780 'id': 'OcobLTqC',
1781 'ext': 'm4v',
1782 'title': 'IMG_5786',
1783 'timestamp': 1435711927,
1784 'upload_date': '20150701',
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 'add_ie': [VideoPressIE.ie_key()],
1790 },
1791 {
1792 # Rutube embed
1793 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1794 'info_dict': {
1795 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1796 'ext': 'flv',
1797 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1798 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1799 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1800 'upload_date': '20170228',
1801 'uploader_id': '996642',
1802 },
1803 'params': {
1804 'skip_download': True,
1805 },
1806 'add_ie': [RutubeIE.ie_key()],
1807 },
1808 {
1809 # ThePlatform embedded with whitespaces in URLs
1810 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1811 'only_matching': True,
1812 },
1813 {
1814 # Senate ISVP iframe https
1815 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1816 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1817 'info_dict': {
1818 'id': 'govtaff020316',
1819 'ext': 'mp4',
1820 'title': 'Integrated Senate Video Player',
1821 },
1822 'add_ie': [SenateISVPIE.ie_key()],
1823 },
1824 {
1825 # Limelight embeds (1 channel embed + 4 media embeds)
1826 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1827 'info_dict': {
1828 'id': 'FacilitatorTraining2017',
1829 'title': 'Facilitator Training 2017',
1830 },
1831 'playlist_mincount': 5,
1832 },
1833 {
1834 # Limelight embed (LimelightPlayerUtil.embed)
1835 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1836 'info_dict': {
1837 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1838 'ext': 'mp4',
1839 'title': '07448641',
1840 'timestamp': 1499890639,
1841 'upload_date': '20170712',
1842 },
1843 'params': {
1844 'skip_download': True,
1845 },
1846 'add_ie': ['LimelightMedia'],
1847 },
1848 {
1849 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1850 'info_dict': {
1851 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1852 'title': 'Standoff with Walnut Creek murder suspect ends',
1853 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1854 },
1855 'playlist_mincount': 4,
1856 },
1857 {
1858 # WashingtonPost embed
1859 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1860 'info_dict': {
1861 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1862 'ext': 'mp4',
1863 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1864 '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 ā€” and enlisted actors.',
1865 'timestamp': 1455216756,
1866 'uploader': 'The Washington Post',
1867 'upload_date': '20160211',
1868 },
1869 'add_ie': [WashingtonPostIE.ie_key()],
1870 },
1871 {
1872 # Mediaset embed
1873 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1874 'info_dict': {
1875 'id': '720642',
1876 'ext': 'mp4',
1877 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1878 },
1879 'params': {
1880 'skip_download': True,
1881 },
1882 'add_ie': [MediasetIE.ie_key()],
1883 },
1884 {
1885 # JOJ.sk embeds
1886 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1887 'info_dict': {
1888 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1889 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1890 },
1891 'playlist_mincount': 5,
1892 'add_ie': [JojIE.ie_key()],
1893 },
1894 {
1895 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1896 'url': 'https://tvrain.ru/amp/418921/',
1897 'md5': 'cc00413936695987e8de148b67d14f1d',
1898 'info_dict': {
1899 'id': '418921',
1900 'ext': 'mp4',
1901 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1902 },
1903 },
1904 {
1905 # vzaar embed
1906 'url': 'http://help.vzaar.com/article/165-embedding-video',
1907 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1908 'info_dict': {
1909 'id': '8707641',
1910 'ext': 'mp4',
1911 'title': 'Building A Business Online: Principal Chairs Q & A',
1912 },
1913 },
1914 {
1915 # multiple HTML5 videos on one page
1916 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1917 'info_dict': {
1918 'id': 'keyscenarios',
1919 'title': 'Rescue Kit 14 Free Edition - Getting started',
1920 },
1921 'playlist_count': 4,
1922 },
1923 {
1924 # vshare embed
1925 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1926 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1927 'info_dict': {
1928 'id': '0f64ce6',
1929 'title': 'vl14062007715967',
1930 'ext': 'mp4',
1931 }
1932 },
1933 {
1934 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1935 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1936 'info_dict': {
1937 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1938 'ext': 'mp4',
1939 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1940 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1941 'timestamp': 1474354800,
1942 'upload_date': '20160920',
1943 }
1944 },
1945 {
1946 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1947 'info_dict': {
1948 'id': '1731611',
1949 'ext': 'mp4',
1950 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1951 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1952 'timestamp': 1516100691,
1953 'upload_date': '20180116',
1954 },
1955 'params': {
1956 'skip_download': True,
1957 },
1958 'add_ie': [SpringboardPlatformIE.ie_key()],
1959 },
1960 {
1961 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1962 'info_dict': {
1963 'id': 'uPDB5I9wfp8',
1964 'ext': 'webm',
1965 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1966 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1967 'upload_date': '20160219',
1968 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1969 'uploader_id': 'PocoyoBrazil',
1970 },
1971 'add_ie': [YoutubeIE.ie_key()],
1972 'params': {
1973 'skip_download': True,
1974 },
1975 },
1976 {
1977 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1978 'info_dict': {
1979 'id': 'vMDE4NzI1Mjgt690b',
1980 'ext': 'mp4',
1981 'title': 'ŠšŠ¾Ń‚ŃŃ‚Š°',
1982 },
1983 'add_ie': [YapFilesIE.ie_key()],
1984 'params': {
1985 'skip_download': True,
1986 },
1987 },
1988 {
1989 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
1990 'md5': 'b68d276de422ab07ee1d49388103f457',
1991 'info_dict': {
1992 'id': '83645793',
1993 'title': 'Lock up and get excited',
1994 'ext': 'mp4'
1995 },
1996 'skip': 'TODO: fix nested playlists processing in tests',
1997 },
1998 # {
1999 # # TODO: find another test
2000 # # http://schema.org/VideoObject
2001 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2002 # 'md5': '888dcf08b7ea671381f00fab74692755',
2003 # 'info_dict': {
2004 # 'id': 'nyvTSJMKId',
2005 # 'ext': 'mp4',
2006 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2007 # 'description': '#love for cats.',
2008 # 'timestamp': 1461244995,
2009 # 'upload_date': '20160421',
2010 # },
2011 # 'params': {
2012 # 'force_generic_extractor': True,
2013 # },
2014 # }
2015 ]
2016
2017 def report_following_redirect(self, new_url):
2018 """Report information extraction."""
2019 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2020
2021 def _extract_rss(self, url, video_id, doc):
2022 playlist_title = doc.find('./channel/title').text
2023 playlist_desc_el = doc.find('./channel/description')
2024 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2025
2026 entries = []
2027 for it in doc.findall('./channel/item'):
2028 next_url = xpath_text(it, 'link', fatal=False)
2029 if not next_url:
2030 enclosure_nodes = it.findall('./enclosure')
2031 for e in enclosure_nodes:
2032 next_url = e.attrib.get('url')
2033 if next_url:
2034 break
2035
2036 if not next_url:
2037 continue
2038
2039 entries.append({
2040 '_type': 'url_transparent',
2041 'url': next_url,
2042 'title': it.find('title').text,
2043 })
2044
2045 return {
2046 '_type': 'playlist',
2047 'id': url,
2048 'title': playlist_title,
2049 'description': playlist_desc,
2050 'entries': entries,
2051 }
2052
2053 def _extract_camtasia(self, url, video_id, webpage):
2054 """ Returns None if no camtasia video can be found. """
2055
2056 camtasia_cfg = self._search_regex(
2057 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2058 webpage, 'camtasia configuration file', default=None)
2059 if camtasia_cfg is None:
2060 return None
2061
2062 title = self._html_search_meta('DC.title', webpage, fatal=True)
2063
2064 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2065 camtasia_cfg = self._download_xml(
2066 camtasia_url, video_id,
2067 note='Downloading camtasia configuration',
2068 errnote='Failed to download camtasia configuration')
2069 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2070
2071 entries = []
2072 for n in fileset_node.getchildren():
2073 url_n = n.find('./uri')
2074 if url_n is None:
2075 continue
2076
2077 entries.append({
2078 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2079 'title': '%s - %s' % (title, n.tag),
2080 'url': compat_urlparse.urljoin(url, url_n.text),
2081 'duration': float_or_none(n.find('./duration').text),
2082 })
2083
2084 return {
2085 '_type': 'playlist',
2086 'entries': entries,
2087 'title': title,
2088 }
2089
2090 def _real_extract(self, url):
2091 if url.startswith('//'):
2092 return {
2093 '_type': 'url',
2094 'url': self.http_scheme() + url,
2095 }
2096
2097 parsed_url = compat_urlparse.urlparse(url)
2098 if not parsed_url.scheme:
2099 default_search = self._downloader.params.get('default_search')
2100 if default_search is None:
2101 default_search = 'fixup_error'
2102
2103 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2104 if '/' in url:
2105 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2106 return self.url_result('http://' + url)
2107 elif default_search != 'fixup_error':
2108 if default_search == 'auto_warning':
2109 if re.match(r'^(?:url|URL)$', url):
2110 raise ExtractorError(
2111 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2112 expected=True)
2113 else:
2114 self._downloader.report_warning(
2115 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2116 return self.url_result('ytsearch:' + url)
2117
2118 if default_search in ('error', 'fixup_error'):
2119 raise ExtractorError(
2120 '%r is not a valid URL. '
2121 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2122 % (url, url), expected=True)
2123 else:
2124 if ':' not in default_search:
2125 default_search += ':'
2126 return self.url_result(default_search + url)
2127
2128 url, smuggled_data = unsmuggle_url(url)
2129 force_videoid = None
2130 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2131 if smuggled_data and 'force_videoid' in smuggled_data:
2132 force_videoid = smuggled_data['force_videoid']
2133 video_id = force_videoid
2134 else:
2135 video_id = self._generic_id(url)
2136
2137 self.to_screen('%s: Requesting header' % video_id)
2138
2139 head_req = HEADRequest(url)
2140 head_response = self._request_webpage(
2141 head_req, video_id,
2142 note=False, errnote='Could not send HEAD request to %s' % url,
2143 fatal=False)
2144
2145 if head_response is not False:
2146 # Check for redirect
2147 new_url = compat_str(head_response.geturl())
2148 if url != new_url:
2149 self.report_following_redirect(new_url)
2150 if force_videoid:
2151 new_url = smuggle_url(
2152 new_url, {'force_videoid': force_videoid})
2153 return self.url_result(new_url)
2154
2155 full_response = None
2156 if head_response is False:
2157 request = sanitized_Request(url)
2158 request.add_header('Accept-Encoding', '*')
2159 full_response = self._request_webpage(request, video_id)
2160 head_response = full_response
2161
2162 info_dict = {
2163 'id': video_id,
2164 'title': self._generic_title(url),
2165 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2166 }
2167
2168 # Check for direct link to a video
2169 content_type = head_response.headers.get('Content-Type', '').lower()
2170 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2171 if m:
2172 format_id = compat_str(m.group('format_id'))
2173 if format_id.endswith('mpegurl'):
2174 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2175 elif format_id == 'f4m':
2176 formats = self._extract_f4m_formats(url, video_id)
2177 else:
2178 formats = [{
2179 'format_id': format_id,
2180 'url': url,
2181 'vcodec': 'none' if m.group('type') == 'audio' else None
2182 }]
2183 info_dict['direct'] = True
2184 self._sort_formats(formats)
2185 info_dict['formats'] = formats
2186 return info_dict
2187
2188 if not self._downloader.params.get('test', False) and not is_intentional:
2189 force = self._downloader.params.get('force_generic_extractor', False)
2190 self._downloader.report_warning(
2191 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2192
2193 if not full_response:
2194 request = sanitized_Request(url)
2195 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2196 # making it impossible to download only chunk of the file (yet we need only 512kB to
2197 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2198 # that will always result in downloading the whole file that is not desirable.
2199 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2200 # to accept raw bytes and being able to download only a chunk.
2201 # It may probably better to solve this by checking Content-Type for application/octet-stream
2202 # after HEAD request finishes, but not sure if we can rely on this.
2203 request.add_header('Accept-Encoding', '*')
2204 full_response = self._request_webpage(request, video_id)
2205
2206 first_bytes = full_response.read(512)
2207
2208 # Is it an M3U playlist?
2209 if first_bytes.startswith(b'#EXTM3U'):
2210 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2211 self._sort_formats(info_dict['formats'])
2212 return info_dict
2213
2214 # Maybe it's a direct link to a video?
2215 # Be careful not to download the whole thing!
2216 if not is_html(first_bytes):
2217 self._downloader.report_warning(
2218 'URL could be a direct video link, returning it as such.')
2219 info_dict.update({
2220 'direct': True,
2221 'url': url,
2222 })
2223 return info_dict
2224
2225 webpage = self._webpage_read_content(
2226 full_response, url, video_id, prefix=first_bytes)
2227
2228 self.report_extraction(video_id)
2229
2230 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2231 try:
2232 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2233 if doc.tag == 'rss':
2234 return self._extract_rss(url, video_id, doc)
2235 elif doc.tag == 'SmoothStreamingMedia':
2236 info_dict['formats'] = self._parse_ism_formats(doc, url)
2237 self._sort_formats(info_dict['formats'])
2238 return info_dict
2239 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2240 smil = self._parse_smil(doc, url, video_id)
2241 self._sort_formats(smil['formats'])
2242 return smil
2243 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2244 return self.playlist_result(
2245 self._parse_xspf(
2246 doc, video_id, xspf_url=url,
2247 xspf_base_url=compat_str(full_response.geturl())),
2248 video_id)
2249 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2250 info_dict['formats'] = self._parse_mpd_formats(
2251 doc,
2252 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2253 mpd_url=url)
2254 self._sort_formats(info_dict['formats'])
2255 return info_dict
2256 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2257 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2258 self._sort_formats(info_dict['formats'])
2259 return info_dict
2260 except compat_xml_parse_error:
2261 pass
2262
2263 # Is it a Camtasia project?
2264 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2265 if camtasia_res is not None:
2266 return camtasia_res
2267
2268 # Sometimes embedded video player is hidden behind percent encoding
2269 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2270 # Unescaping the whole page allows to handle those cases in a generic way
2271 webpage = compat_urllib_parse_unquote(webpage)
2272
2273 # it's tempting to parse this further, but you would
2274 # have to take into account all the variations like
2275 # Video Title - Site Name
2276 # Site Name | Video Title
2277 # Video Title - Tagline | Site Name
2278 # and so on and so forth; it's just not practical
2279 video_title = self._og_search_title(
2280 webpage, default=None) or self._html_search_regex(
2281 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2282 default='video')
2283
2284 # Try to detect age limit automatically
2285 age_limit = self._rta_search(webpage)
2286 # And then there are the jokers who advertise that they use RTA,
2287 # but actually don't.
2288 AGE_LIMIT_MARKERS = [
2289 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2290 ]
2291 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2292 age_limit = 18
2293
2294 # video uploader is domain name
2295 video_uploader = self._search_regex(
2296 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2297
2298 video_description = self._og_search_description(webpage, default=None)
2299 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2300
2301 info_dict.update({
2302 'title': video_title,
2303 'description': video_description,
2304 'thumbnail': video_thumbnail,
2305 'age_limit': age_limit,
2306 })
2307
2308 # Look for Brightcove Legacy Studio embeds
2309 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2310 if bc_urls:
2311 entries = [{
2312 '_type': 'url',
2313 'url': smuggle_url(bc_url, {'Referer': url}),
2314 'ie_key': 'BrightcoveLegacy'
2315 } for bc_url in bc_urls]
2316
2317 return {
2318 '_type': 'playlist',
2319 'title': video_title,
2320 'id': video_id,
2321 'entries': entries,
2322 }
2323
2324 # Look for Brightcove New Studio embeds
2325 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2326 if bc_urls:
2327 return self.playlist_from_matches(
2328 bc_urls, video_id, video_title,
2329 getter=lambda x: smuggle_url(x, {'referrer': url}),
2330 ie='BrightcoveNew')
2331
2332 # Look for Nexx embeds
2333 nexx_urls = NexxIE._extract_urls(webpage)
2334 if nexx_urls:
2335 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2336
2337 # Look for Nexx iFrame embeds
2338 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2339 if nexx_embed_urls:
2340 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2341
2342 # Look for ThePlatform embeds
2343 tp_urls = ThePlatformIE._extract_urls(webpage)
2344 if tp_urls:
2345 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2346
2347 # Look for Vessel embeds
2348 vessel_urls = VesselIE._extract_urls(webpage)
2349 if vessel_urls:
2350 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2351
2352 # Look for embedded rtl.nl player
2353 matches = re.findall(
2354 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2355 webpage)
2356 if matches:
2357 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2358
2359 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2360 if vimeo_urls:
2361 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2362
2363 vid_me_embed_url = self._search_regex(
2364 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2365 webpage, 'vid.me embed', default=None)
2366 if vid_me_embed_url is not None:
2367 return self.url_result(vid_me_embed_url, 'Vidme')
2368
2369 # Look for YouTube embeds
2370 youtube_urls = YoutubeIE._extract_urls(webpage)
2371 if youtube_urls:
2372 return self.playlist_from_matches(
2373 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2374
2375 matches = DailymotionIE._extract_urls(webpage)
2376 if matches:
2377 return self.playlist_from_matches(matches, video_id, video_title)
2378
2379 # Look for embedded Dailymotion playlist player (#3822)
2380 m = re.search(
2381 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2382 if m:
2383 playlists = re.findall(
2384 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2385 if playlists:
2386 return self.playlist_from_matches(
2387 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2388
2389 # Look for DailyMail embeds
2390 dailymail_urls = DailyMailIE._extract_urls(webpage)
2391 if dailymail_urls:
2392 return self.playlist_from_matches(
2393 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2394
2395 # Look for embedded Wistia player
2396 wistia_url = WistiaIE._extract_url(webpage)
2397 if wistia_url:
2398 return {
2399 '_type': 'url_transparent',
2400 'url': self._proto_relative_url(wistia_url),
2401 'ie_key': WistiaIE.ie_key(),
2402 'uploader': video_uploader,
2403 }
2404
2405 # Look for SVT player
2406 svt_url = SVTIE._extract_url(webpage)
2407 if svt_url:
2408 return self.url_result(svt_url, 'SVT')
2409
2410 # Look for Bandcamp pages with custom domain
2411 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2412 if mobj is not None:
2413 burl = unescapeHTML(mobj.group(1))
2414 # Don't set the extractor because it can be a track url or an album
2415 return self.url_result(burl)
2416
2417 # Look for embedded Vevo player
2418 mobj = re.search(
2419 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2420 if mobj is not None:
2421 return self.url_result(mobj.group('url'))
2422
2423 # Look for embedded Viddler player
2424 mobj = re.search(
2425 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2426 webpage)
2427 if mobj is not None:
2428 return self.url_result(mobj.group('url'))
2429
2430 # Look for NYTimes player
2431 mobj = re.search(
2432 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2433 webpage)
2434 if mobj is not None:
2435 return self.url_result(mobj.group('url'))
2436
2437 # Look for Libsyn player
2438 mobj = re.search(
2439 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2440 if mobj is not None:
2441 return self.url_result(mobj.group('url'))
2442
2443 # Look for Ooyala videos
2444 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2445 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2446 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2447 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2448 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2449 if mobj is not None:
2450 embed_token = self._search_regex(
2451 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2452 webpage, 'ooyala embed token', default=None)
2453 return OoyalaIE._build_url_result(smuggle_url(
2454 mobj.group('ec'), {
2455 'domain': url,
2456 'embed_token': embed_token,
2457 }))
2458
2459 # Look for multiple Ooyala embeds on SBN network websites
2460 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2461 if mobj is not None:
2462 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2463 if embeds:
2464 return self.playlist_from_matches(
2465 embeds, video_id, video_title,
2466 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2467
2468 # Look for Aparat videos
2469 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2470 if mobj is not None:
2471 return self.url_result(mobj.group(1), 'Aparat')
2472
2473 # Look for MPORA videos
2474 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2475 if mobj is not None:
2476 return self.url_result(mobj.group(1), 'Mpora')
2477
2478 # Look for embedded NovaMov-based player
2479 mobj = re.search(
2480 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2481 (?P<url>http://(?:(?:embed|www)\.)?
2482 (?:novamov\.com|
2483 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2484 videoweed\.(?:es|com)|
2485 movshare\.(?:net|sx|ag)|
2486 divxstage\.(?:eu|net|ch|co|at|ag))
2487 /embed\.php.+?)\1''', webpage)
2488 if mobj is not None:
2489 return self.url_result(mobj.group('url'))
2490
2491 # Look for embedded Facebook player
2492 facebook_urls = FacebookIE._extract_urls(webpage)
2493 if facebook_urls:
2494 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2495
2496 # Look for embedded VK player
2497 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2498 if mobj is not None:
2499 return self.url_result(mobj.group('url'), 'VK')
2500
2501 # Look for embedded Odnoklassniki player
2502 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2503 if mobj is not None:
2504 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2505
2506 # Look for embedded ivi player
2507 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2508 if mobj is not None:
2509 return self.url_result(mobj.group('url'), 'Ivi')
2510
2511 # Look for embedded Huffington Post player
2512 mobj = re.search(
2513 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2514 if mobj is not None:
2515 return self.url_result(mobj.group('url'), 'HuffPost')
2516
2517 # Look for embed.ly
2518 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2519 if mobj is not None:
2520 return self.url_result(mobj.group('url'))
2521 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2522 if mobj is not None:
2523 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2524
2525 # Look for funnyordie embed
2526 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2527 if matches:
2528 return self.playlist_from_matches(
2529 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2530
2531 # Look for BBC iPlayer embed
2532 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2533 if matches:
2534 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2535
2536 # Look for embedded RUTV player
2537 rutv_url = RUTVIE._extract_url(webpage)
2538 if rutv_url:
2539 return self.url_result(rutv_url, 'RUTV')
2540
2541 # Look for embedded TVC player
2542 tvc_url = TVCIE._extract_url(webpage)
2543 if tvc_url:
2544 return self.url_result(tvc_url, 'TVC')
2545
2546 # Look for embedded SportBox player
2547 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2548 if sportbox_urls:
2549 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2550
2551 # Look for embedded XHamster player
2552 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2553 if xhamster_urls:
2554 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2555
2556 # Look for embedded TNAFlixNetwork player
2557 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2558 if tnaflix_urls:
2559 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2560
2561 # Look for embedded PornHub player
2562 pornhub_urls = PornHubIE._extract_urls(webpage)
2563 if pornhub_urls:
2564 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2565
2566 # Look for embedded DrTuber player
2567 drtuber_urls = DrTuberIE._extract_urls(webpage)
2568 if drtuber_urls:
2569 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2570
2571 # Look for embedded RedTube player
2572 redtube_urls = RedTubeIE._extract_urls(webpage)
2573 if redtube_urls:
2574 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2575
2576 # Look for embedded Tube8 player
2577 tube8_urls = Tube8IE._extract_urls(webpage)
2578 if tube8_urls:
2579 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2580
2581 # Look for embedded Tvigle player
2582 mobj = re.search(
2583 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2584 if mobj is not None:
2585 return self.url_result(mobj.group('url'), 'Tvigle')
2586
2587 # Look for embedded TED player
2588 mobj = re.search(
2589 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2590 if mobj is not None:
2591 return self.url_result(mobj.group('url'), 'TED')
2592
2593 # Look for embedded Ustream videos
2594 ustream_url = UstreamIE._extract_url(webpage)
2595 if ustream_url:
2596 return self.url_result(ustream_url, UstreamIE.ie_key())
2597
2598 # Look for embedded arte.tv player
2599 mobj = re.search(
2600 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2601 webpage)
2602 if mobj is not None:
2603 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2604
2605 # Look for embedded francetv player
2606 mobj = re.search(
2607 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2608 webpage)
2609 if mobj is not None:
2610 return self.url_result(mobj.group('url'))
2611
2612 # Look for embedded smotri.com player
2613 smotri_url = SmotriIE._extract_url(webpage)
2614 if smotri_url:
2615 return self.url_result(smotri_url, 'Smotri')
2616
2617 # Look for embedded Myvi.ru player
2618 myvi_url = MyviIE._extract_url(webpage)
2619 if myvi_url:
2620 return self.url_result(myvi_url)
2621
2622 # Look for embedded soundcloud player
2623 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2624 if soundcloud_urls:
2625 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2626
2627 # Look for tunein player
2628 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2629 if tunein_urls:
2630 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2631
2632 # Look for embedded mtvservices player
2633 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2634 if mtvservices_url:
2635 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2636
2637 # Look for embedded yahoo player
2638 mobj = re.search(
2639 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2640 webpage)
2641 if mobj is not None:
2642 return self.url_result(mobj.group('url'), 'Yahoo')
2643
2644 # Look for embedded sbs.com.au player
2645 mobj = re.search(
2646 r'''(?x)
2647 (?:
2648 <meta\s+property="og:video"\s+content=|
2649 <iframe[^>]+?src=
2650 )
2651 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2652 webpage)
2653 if mobj is not None:
2654 return self.url_result(mobj.group('url'), 'SBS')
2655
2656 # Look for embedded Cinchcast player
2657 mobj = re.search(
2658 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2659 webpage)
2660 if mobj is not None:
2661 return self.url_result(mobj.group('url'), 'Cinchcast')
2662
2663 mobj = re.search(
2664 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2665 webpage)
2666 if not mobj:
2667 mobj = re.search(
2668 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2669 webpage)
2670 if mobj is not None:
2671 return self.url_result(mobj.group('url'), 'MLB')
2672
2673 mobj = re.search(
2674 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2675 webpage)
2676 if mobj is not None:
2677 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2678
2679 mobj = re.search(
2680 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2681 webpage)
2682 if mobj is not None:
2683 return self.url_result(mobj.group('url'), 'Livestream')
2684
2685 # Look for Zapiks embed
2686 mobj = re.search(
2687 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2688 if mobj is not None:
2689 return self.url_result(mobj.group('url'), 'Zapiks')
2690
2691 # Look for Kaltura embeds
2692 kaltura_url = KalturaIE._extract_url(webpage)
2693 if kaltura_url:
2694 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2695
2696 # Look for EaglePlatform embeds
2697 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2698 if eagleplatform_url:
2699 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2700
2701 # Look for ClipYou (uses EaglePlatform) embeds
2702 mobj = re.search(
2703 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2704 if mobj is not None:
2705 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2706
2707 # Look for Pladform embeds
2708 pladform_url = PladformIE._extract_url(webpage)
2709 if pladform_url:
2710 return self.url_result(pladform_url)
2711
2712 # Look for Videomore embeds
2713 videomore_url = VideomoreIE._extract_url(webpage)
2714 if videomore_url:
2715 return self.url_result(videomore_url)
2716
2717 # Look for Webcaster embeds
2718 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2719 if webcaster_url:
2720 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2721
2722 # Look for Playwire embeds
2723 mobj = re.search(
2724 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2725 if mobj is not None:
2726 return self.url_result(mobj.group('url'))
2727
2728 # Look for 5min embeds
2729 mobj = re.search(
2730 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2731 if mobj is not None:
2732 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2733
2734 # Look for Crooks and Liars embeds
2735 mobj = re.search(
2736 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2737 if mobj is not None:
2738 return self.url_result(mobj.group('url'))
2739
2740 # Look for NBC Sports VPlayer embeds
2741 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2742 if nbc_sports_url:
2743 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2744
2745 # Look for NBC News embeds
2746 nbc_news_embed_url = re.search(
2747 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2748 if nbc_news_embed_url:
2749 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2750
2751 # Look for Google Drive embeds
2752 google_drive_url = GoogleDriveIE._extract_url(webpage)
2753 if google_drive_url:
2754 return self.url_result(google_drive_url, 'GoogleDrive')
2755
2756 # Look for UDN embeds
2757 mobj = re.search(
2758 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2759 if mobj is not None:
2760 return self.url_result(
2761 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2762
2763 # Look for Senate ISVP iframe
2764 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2765 if senate_isvp_url:
2766 return self.url_result(senate_isvp_url, 'SenateISVP')
2767
2768 # Look for OnionStudios embeds
2769 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2770 if onionstudios_url:
2771 return self.url_result(onionstudios_url)
2772
2773 # Look for ViewLift embeds
2774 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2775 if viewlift_url:
2776 return self.url_result(viewlift_url)
2777
2778 # Look for JWPlatform embeds
2779 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2780 if jwplatform_urls:
2781 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2782
2783 # Look for Digiteka embeds
2784 digiteka_url = DigitekaIE._extract_url(webpage)
2785 if digiteka_url:
2786 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2787
2788 # Look for Arkena embeds
2789 arkena_url = ArkenaIE._extract_url(webpage)
2790 if arkena_url:
2791 return self.url_result(arkena_url, ArkenaIE.ie_key())
2792
2793 # Look for Piksel embeds
2794 piksel_url = PikselIE._extract_url(webpage)
2795 if piksel_url:
2796 return self.url_result(piksel_url, PikselIE.ie_key())
2797
2798 # Look for Limelight embeds
2799 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2800 if limelight_urls:
2801 return self.playlist_result(
2802 limelight_urls, video_id, video_title, video_description)
2803
2804 # Look for Anvato embeds
2805 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2806 if anvato_urls:
2807 return self.playlist_result(
2808 anvato_urls, video_id, video_title, video_description)
2809
2810 # Look for AdobeTVVideo embeds
2811 mobj = re.search(
2812 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2813 webpage)
2814 if mobj is not None:
2815 return self.url_result(
2816 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2817 'AdobeTVVideo')
2818
2819 # Look for Vine embeds
2820 mobj = re.search(
2821 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2822 webpage)
2823 if mobj is not None:
2824 return self.url_result(
2825 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2826
2827 # Look for VODPlatform embeds
2828 mobj = re.search(
2829 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2830 webpage)
2831 if mobj is not None:
2832 return self.url_result(
2833 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2834
2835 # Look for Mangomolo embeds
2836 mobj = re.search(
2837 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2838 (?:
2839 video\?.*?\bid=(?P<video_id>\d+)|
2840 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2841 ).+?)\1''', webpage)
2842 if mobj is not None:
2843 info = {
2844 '_type': 'url_transparent',
2845 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2846 'title': video_title,
2847 'description': video_description,
2848 'thumbnail': video_thumbnail,
2849 'uploader': video_uploader,
2850 }
2851 video_id = mobj.group('video_id')
2852 if video_id:
2853 info.update({
2854 'ie_key': 'MangomoloVideo',
2855 'id': video_id,
2856 })
2857 else:
2858 info.update({
2859 'ie_key': 'MangomoloLive',
2860 'id': mobj.group('channel_id'),
2861 })
2862 return info
2863
2864 # Look for Instagram embeds
2865 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2866 if instagram_embed_url is not None:
2867 return self.url_result(
2868 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2869
2870 # Look for LiveLeak embeds
2871 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2872 if liveleak_urls:
2873 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2874
2875 # Look for 3Q SDN embeds
2876 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2877 if threeqsdn_url:
2878 return {
2879 '_type': 'url_transparent',
2880 'ie_key': ThreeQSDNIE.ie_key(),
2881 'url': self._proto_relative_url(threeqsdn_url),
2882 'title': video_title,
2883 'description': video_description,
2884 'thumbnail': video_thumbnail,
2885 'uploader': video_uploader,
2886 }
2887
2888 # Look for VBOX7 embeds
2889 vbox7_url = Vbox7IE._extract_url(webpage)
2890 if vbox7_url:
2891 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2892
2893 # Look for DBTV embeds
2894 dbtv_urls = DBTVIE._extract_urls(webpage)
2895 if dbtv_urls:
2896 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2897
2898 # Look for Videa embeds
2899 videa_urls = VideaIE._extract_urls(webpage)
2900 if videa_urls:
2901 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2902
2903 # Look for 20 minuten embeds
2904 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2905 if twentymin_urls:
2906 return self.playlist_from_matches(
2907 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2908
2909 # Look for Openload embeds
2910 openload_urls = OpenloadIE._extract_urls(webpage)
2911 if openload_urls:
2912 return self.playlist_from_matches(
2913 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2914
2915 # Look for VideoPress embeds
2916 videopress_urls = VideoPressIE._extract_urls(webpage)
2917 if videopress_urls:
2918 return self.playlist_from_matches(
2919 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2920
2921 # Look for Rutube embeds
2922 rutube_urls = RutubeIE._extract_urls(webpage)
2923 if rutube_urls:
2924 return self.playlist_from_matches(
2925 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2926
2927 # Look for WashingtonPost embeds
2928 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2929 if wapo_urls:
2930 return self.playlist_from_matches(
2931 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2932
2933 # Look for Mediaset embeds
2934 mediaset_urls = MediasetIE._extract_urls(webpage)
2935 if mediaset_urls:
2936 return self.playlist_from_matches(
2937 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2938
2939 # Look for JOJ.sk embeds
2940 joj_urls = JojIE._extract_urls(webpage)
2941 if joj_urls:
2942 return self.playlist_from_matches(
2943 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2944
2945 # Look for megaphone.fm embeds
2946 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2947 if mpfn_urls:
2948 return self.playlist_from_matches(
2949 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2950
2951 # Look for vzaar embeds
2952 vzaar_urls = VzaarIE._extract_urls(webpage)
2953 if vzaar_urls:
2954 return self.playlist_from_matches(
2955 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2956
2957 channel9_urls = Channel9IE._extract_urls(webpage)
2958 if channel9_urls:
2959 return self.playlist_from_matches(
2960 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2961
2962 vshare_urls = VShareIE._extract_urls(webpage)
2963 if vshare_urls:
2964 return self.playlist_from_matches(
2965 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2966
2967 # Look for Mediasite embeds
2968 mediasite_urls = MediasiteIE._extract_urls(webpage)
2969 if mediasite_urls:
2970 entries = [
2971 self.url_result(smuggle_url(
2972 compat_urlparse.urljoin(url, mediasite_url),
2973 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2974 for mediasite_url in mediasite_urls]
2975 return self.playlist_result(entries, video_id, video_title)
2976
2977 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2978 if springboardplatform_urls:
2979 return self.playlist_from_matches(
2980 springboardplatform_urls, video_id, video_title,
2981 ie=SpringboardPlatformIE.ie_key())
2982
2983 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2984 if yapfiles_urls:
2985 return self.playlist_from_matches(
2986 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2987
2988 vice_urls = ViceIE._extract_urls(webpage)
2989 if vice_urls:
2990 return self.playlist_from_matches(
2991 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2992
2993 xfileshare_urls = XFileShareIE._extract_urls(webpage)
2994 if xfileshare_urls:
2995 return self.playlist_from_matches(
2996 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
2997
2998 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
2999 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3000 webpage)]
3001 if sharevideos_urls:
3002 return self.playlist_from_matches(
3003 sharevideos_urls, video_id, video_title)
3004
3005 def merge_dicts(dict1, dict2):
3006 merged = {}
3007 for k, v in dict1.items():
3008 if v is not None:
3009 merged[k] = v
3010 for k, v in dict2.items():
3011 if v is None:
3012 continue
3013 if (k not in merged or
3014 (isinstance(v, compat_str) and v and
3015 isinstance(merged[k], compat_str) and
3016 not merged[k])):
3017 merged[k] = v
3018 return merged
3019
3020 # Look for HTML5 media
3021 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3022 if entries:
3023 if len(entries) == 1:
3024 entries[0].update({
3025 'id': video_id,
3026 'title': video_title,
3027 })
3028 else:
3029 for num, entry in enumerate(entries, start=1):
3030 entry.update({
3031 'id': '%s-%s' % (video_id, num),
3032 'title': '%s (%d)' % (video_title, num),
3033 })
3034 for entry in entries:
3035 self._sort_formats(entry['formats'])
3036 return self.playlist_result(entries, video_id, video_title)
3037
3038 jwplayer_data = self._find_jwplayer_data(
3039 webpage, video_id, transform_source=js_to_json)
3040 if jwplayer_data:
3041 info = self._parse_jwplayer_data(
3042 jwplayer_data, video_id, require_title=False, base_url=url)
3043 return merge_dicts(info, info_dict)
3044
3045 # Video.js embed
3046 mobj = re.search(
3047 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3048 webpage)
3049 if mobj is not None:
3050 sources = self._parse_json(
3051 mobj.group(1), video_id, transform_source=js_to_json,
3052 fatal=False) or []
3053 if not isinstance(sources, list):
3054 sources = [sources]
3055 formats = []
3056 for source in sources:
3057 src = source.get('src')
3058 if not src or not isinstance(src, compat_str):
3059 continue
3060 src = compat_urlparse.urljoin(url, src)
3061 src_type = source.get('type')
3062 if isinstance(src_type, compat_str):
3063 src_type = src_type.lower()
3064 ext = determine_ext(src).lower()
3065 if src_type == 'video/youtube':
3066 return self.url_result(src, YoutubeIE.ie_key())
3067 if src_type == 'application/dash+xml' or ext == 'mpd':
3068 formats.extend(self._extract_mpd_formats(
3069 src, video_id, mpd_id='dash', fatal=False))
3070 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3071 formats.extend(self._extract_m3u8_formats(
3072 src, video_id, 'mp4', entry_protocol='m3u8_native',
3073 m3u8_id='hls', fatal=False))
3074 else:
3075 formats.append({
3076 'url': src,
3077 'ext': (mimetype2ext(src_type) or
3078 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3079 })
3080 if formats:
3081 self._sort_formats(formats)
3082 info_dict['formats'] = formats
3083 return info_dict
3084
3085 # Looking for http://schema.org/VideoObject
3086 json_ld = self._search_json_ld(
3087 webpage, video_id, default={}, expected_type='VideoObject')
3088 if json_ld.get('url'):
3089 return merge_dicts(json_ld, info_dict)
3090
3091 def check_video(vurl):
3092 if YoutubeIE.suitable(vurl):
3093 return True
3094 if RtmpIE.suitable(vurl):
3095 return True
3096 vpath = compat_urlparse.urlparse(vurl).path
3097 vext = determine_ext(vpath)
3098 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3099
3100 def filter_video(urls):
3101 return list(filter(check_video, urls))
3102
3103 # Start with something easy: JW Player in SWFObject
3104 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3105 if not found:
3106 # Look for gorilla-vid style embedding
3107 found = filter_video(re.findall(r'''(?sx)
3108 (?:
3109 jw_plugins|
3110 JWPlayerOptions|
3111 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3112 )
3113 .*?
3114 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3115 if not found:
3116 # Broaden the search a little bit
3117 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3118 if not found:
3119 # Broaden the findall a little bit: JWPlayer JS loader
3120 found = filter_video(re.findall(
3121 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3122 if not found:
3123 # Flow player
3124 found = filter_video(re.findall(r'''(?xs)
3125 flowplayer\("[^"]+",\s*
3126 \{[^}]+?\}\s*,
3127 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3128 ["']?url["']?\s*:\s*["']([^"']+)["']
3129 ''', webpage))
3130 if not found:
3131 # Cinerama player
3132 found = re.findall(
3133 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3134 if not found:
3135 # Try to find twitter cards info
3136 # twitter:player:stream should be checked before twitter:player since
3137 # it is expected to contain a raw stream (see
3138 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3139 found = filter_video(re.findall(
3140 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3141 if not found:
3142 # We look for Open Graph info:
3143 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3144 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3145 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3146 if m_video_type is not None:
3147 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3148 if not found:
3149 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3150 found = re.search(
3151 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3152 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3153 webpage)
3154 if not found:
3155 # Look also in Refresh HTTP header
3156 refresh_header = head_response.headers.get('Refresh')
3157 if refresh_header:
3158 # In python 2 response HTTP headers are bytestrings
3159 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3160 refresh_header = refresh_header.decode('iso-8859-1')
3161 found = re.search(REDIRECT_REGEX, refresh_header)
3162 if found:
3163 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3164 if new_url != url:
3165 self.report_following_redirect(new_url)
3166 return {
3167 '_type': 'url',
3168 'url': new_url,
3169 }
3170 else:
3171 found = None
3172
3173 if not found:
3174 # twitter:player is a https URL to iframe player that may or may not
3175 # be supported by youtube-dl thus this is checked the very last (see
3176 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3177 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3178 if embed_url and embed_url != url:
3179 return self.url_result(embed_url)
3180
3181 if not found:
3182 raise UnsupportedError(url)
3183
3184 entries = []
3185 for video_url in orderedSet(found):
3186 video_url = unescapeHTML(video_url)
3187 video_url = video_url.replace('\\/', '/')
3188 video_url = compat_urlparse.urljoin(url, video_url)
3189 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3190
3191 # Sometimes, jwplayer extraction will result in a YouTube URL
3192 if YoutubeIE.suitable(video_url):
3193 entries.append(self.url_result(video_url, 'Youtube'))
3194 continue
3195
3196 # here's a fun little line of code for you:
3197 video_id = os.path.splitext(video_id)[0]
3198
3199 entry_info_dict = {
3200 'id': video_id,
3201 'uploader': video_uploader,
3202 'title': video_title,
3203 'age_limit': age_limit,
3204 }
3205
3206 if RtmpIE.suitable(video_url):
3207 entry_info_dict.update({
3208 '_type': 'url_transparent',
3209 'ie_key': RtmpIE.ie_key(),
3210 'url': video_url,
3211 })
3212 entries.append(entry_info_dict)
3213 continue
3214
3215 ext = determine_ext(video_url)
3216 if ext == 'smil':
3217 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3218 elif ext == 'xspf':
3219 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3220 elif ext == 'm3u8':
3221 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3222 elif ext == 'mpd':
3223 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3224 elif ext == 'f4m':
3225 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3226 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3227 # Just matching .ism/manifest is not enough to be reliably sure
3228 # whether it's actually an ISM manifest or some other streaming
3229 # manifest since there are various streaming URL formats
3230 # possible (see [1]) as well as some other shenanigans like
3231 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3232 # so on.
3233 # Thus the most reasonable way to solve this is to delegate
3234 # to generic extractor in order to look into the contents of
3235 # the manifest itself.
3236 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3237 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3238 entry_info_dict = self.url_result(
3239 smuggle_url(video_url, {'to_generic': True}),
3240 GenericIE.ie_key())
3241 else:
3242 entry_info_dict['url'] = video_url
3243
3244 if entry_info_dict.get('formats'):
3245 self._sort_formats(entry_info_dict['formats'])
3246
3247 entries.append(entry_info_dict)
3248
3249 if len(entries) == 1:
3250 return entries[0]
3251 else:
3252 for num, e in enumerate(entries, start=1):
3253 # 'url' results don't have a title
3254 if e.get('title') is not None:
3255 e['title'] = '%s (%d)' % (e['title'], num)
3256 return {
3257 '_type': 'playlist',
3258 'entries': entries,
3259 }