]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Rapsys Git / youtubedl / blob
? search:
summary | shortlog | log | commit | commitdiff | tree
history | raw | HEAD
New upstream version 2018.01.27
[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 .vimeo import VimeoIE
62 from .dailymotion import DailymotionIE
63 from .dailymail import DailyMailIE
64 from .onionstudios import OnionStudiosIE
65 from .viewlift import ViewLiftEmbedIE
66 from .mtv import MTVServicesEmbeddedIE
67 from .pladform import PladformIE
68 from .videomore import VideomoreIE
69 from .webcaster import WebcasterFeedIE
70 from .googledrive import GoogleDriveIE
71 from .jwplatform import JWPlatformIE
72 from .digiteka import DigitekaIE
73 from .arkena import ArkenaIE
74 from .instagram import InstagramIE
75 from .liveleak import LiveLeakIE
76 from .threeqsdn import ThreeQSDNIE
77 from .theplatform import ThePlatformIE
78 from .vessel import VesselIE
79 from .kaltura import KalturaIE
80 from .eagleplatform import EaglePlatformIE
81 from .facebook import FacebookIE
82 from .soundcloud import SoundcloudIE
83 from .tunein import TuneInBaseIE
84 from .vbox7 import Vbox7IE
85 from .dbtv import DBTVIE
86 from .piksel import PikselIE
87 from .videa import VideaIE
88 from .twentymin import TwentyMinutenIE
89 from .ustream import UstreamIE
90 from .openload import OpenloadIE
91 from .videopress import VideoPressIE
92 from .rutube import RutubeIE
93 from .limelight import LimelightBaseIE
94 from .anvato import AnvatoIE
95 from .washingtonpost import WashingtonPostIE
96 from .wistia import WistiaIE
97 from .mediaset import MediasetIE
98 from .joj import JojIE
99 from .megaphone import MegaphoneIE
100 from .vzaar import VzaarIE
101 from .channel9 import Channel9IE
102 from .vshare import VShareIE
103 from .mediasite import MediasiteIE
104 from .springboardplatform import SpringboardPlatformIE
105
106
107 class GenericIE(InfoExtractor):
108 IE_DESC = 'Generic downloader that works on some sites'
109 _VALID_URL = r'.*'
110 IE_NAME = 'generic'
111 _TESTS = [
112 # Direct link to a video
113 {
114 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
115 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
116 'info_dict': {
117 'id': 'trailer',
118 'ext': 'mp4',
119 'title': 'trailer',
120 'upload_date': '20100513',
121 }
122 },
123 # Direct link to media delivered compressed (until Accept-Encoding is *)
124 {
125 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
126 'md5': '128c42e68b13950268b648275386fc74',
127 'info_dict': {
128 'id': 'FictionJunction-Parallel_Hearts',
129 'ext': 'flac',
130 'title': 'FictionJunction-Parallel_Hearts',
131 'upload_date': '20140522',
132 },
133 'expected_warnings': [
134 'URL could be a direct video link, returning it as such.'
135 ],
136 'skip': 'URL invalid',
137 },
138 # Direct download with broken HEAD
139 {
140 'url': 'http://ai-radio.org:8000/radio.opus',
141 'info_dict': {
142 'id': 'radio',
143 'ext': 'opus',
144 'title': 'radio',
145 },
146 'params': {
147 'skip_download': True, # infinite live stream
148 },
149 'expected_warnings': [
150 r'501.*Not Implemented',
151 r'400.*Bad Request',
152 ],
153 },
154 # Direct link with incorrect MIME type
155 {
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'md5': '4ccbebe5f36706d85221f204d7eb5913',
158 'info_dict': {
159 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
160 'id': '5_Lennart_Poettering_-_Systemd',
161 'ext': 'webm',
162 'title': '5_Lennart_Poettering_-_Systemd',
163 'upload_date': '20141120',
164 },
165 'expected_warnings': [
166 'URL could be a direct video link, returning it as such.'
167 ]
168 },
169 # RSS feed
170 {
171 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
172 'info_dict': {
173 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
174 'title': 'Zero Punctuation',
175 'description': 're:.*groundbreaking video review series.*'
176 },
177 'playlist_mincount': 11,
178 },
179 # RSS feed with enclosure
180 {
181 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
182 'info_dict': {
183 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
184 'ext': 'm4v',
185 'upload_date': '20150228',
186 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
187 }
188 },
189 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
190 {
191 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
192 'info_dict': {
193 'id': 'smil',
194 'ext': 'mp4',
195 'title': 'Automatics, robotics and biocybernetics',
196 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
197 'upload_date': '20130627',
198 'formats': 'mincount:16',
199 'subtitles': 'mincount:1',
200 },
201 'params': {
202 'force_generic_extractor': True,
203 'skip_download': True,
204 },
205 },
206 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
207 {
208 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
209 'info_dict': {
210 'id': 'hds',
211 'ext': 'flv',
212 'title': 'hds',
213 'formats': 'mincount:1',
214 },
215 'params': {
216 'skip_download': True,
217 },
218 },
219 # SMIL from https://www.restudy.dk/video/play/id/1637
220 {
221 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
222 'info_dict': {
223 'id': 'video_1637',
224 'ext': 'flv',
225 'title': 'video_1637',
226 'formats': 'mincount:3',
227 },
228 'params': {
229 'skip_download': True,
230 },
231 },
232 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
233 {
234 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
235 'info_dict': {
236 'id': 'smil-service',
237 'ext': 'flv',
238 'title': 'smil-service',
239 'formats': 'mincount:1',
240 },
241 'params': {
242 'skip_download': True,
243 },
244 },
245 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
246 {
247 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
248 'info_dict': {
249 'id': '4719370',
250 'ext': 'mp4',
251 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
252 'formats': 'mincount:3',
253 },
254 'params': {
255 'skip_download': True,
256 },
257 },
258 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
259 {
260 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
261 'info_dict': {
262 'id': 'mZlp2ctYIUEB',
263 'ext': 'mp4',
264 'title': 'Tikibad ontruimd wegens brand',
265 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
266 'thumbnail': r're:^https?://.*\.jpg$',
267 'duration': 33,
268 },
269 'params': {
270 'skip_download': True,
271 },
272 },
273 # MPD from http://dash-mse-test.appspot.com/media.html
274 {
275 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
276 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
277 'info_dict': {
278 'id': 'car-20120827-manifest',
279 'ext': 'mp4',
280 'title': 'car-20120827-manifest',
281 'formats': 'mincount:9',
282 'upload_date': '20130904',
283 },
284 'params': {
285 'format': 'bestvideo',
286 },
287 },
288 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
289 {
290 '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',
291 'info_dict': {
292 'id': 'content',
293 'ext': 'mp4',
294 'title': 'content',
295 'formats': 'mincount:8',
296 },
297 'params': {
298 # m3u8 downloads
299 'skip_download': True,
300 },
301 'skip': 'video gone',
302 },
303 # m3u8 served with Content-Type: text/plain
304 {
305 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
306 'info_dict': {
307 'id': 'index',
308 'ext': 'mp4',
309 'title': 'index',
310 'upload_date': '20140720',
311 'formats': 'mincount:11',
312 },
313 'params': {
314 # m3u8 downloads
315 'skip_download': True,
316 },
317 'skip': 'video gone',
318 },
319 # google redirect
320 {
321 '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',
322 'info_dict': {
323 'id': 'cmQHVoWB5FY',
324 'ext': 'mp4',
325 'upload_date': '20130224',
326 'uploader_id': 'TheVerge',
327 'description': r're:^Chris Ziegler takes a look at the\.*',
328 'uploader': 'The Verge',
329 'title': 'First Firefox OS phones side-by-side',
330 },
331 'params': {
332 'skip_download': False,
333 }
334 },
335 {
336 # redirect in Refresh HTTP header
337 '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',
338 'info_dict': {
339 'id': 'pO8h3EaFRdo',
340 'ext': 'mp4',
341 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
342 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
343 'upload_date': '20150917',
344 'uploader_id': 'brtvofficial',
345 'uploader': 'Boiler Room',
346 },
347 'params': {
348 'skip_download': False,
349 },
350 },
351 {
352 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
353 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
354 'info_dict': {
355 'id': '13601338388002',
356 'ext': 'mp4',
357 'uploader': 'www.hodiho.fr',
358 'title': 'R\u00e9gis plante sa Jeep',
359 }
360 },
361 # bandcamp page with custom domain
362 {
363 'add_ie': ['Bandcamp'],
364 'url': 'http://bronyrock.com/track/the-pony-mash',
365 'info_dict': {
366 'id': '3235767654',
367 'ext': 'mp3',
368 'title': 'The Pony Mash',
369 'uploader': 'M_Pallante',
370 },
371 'skip': 'There is a limit of 200 free downloads / month for the test song',
372 },
373 {
374 # embedded brightcove video
375 # it also tests brightcove videos that need to set the 'Referer'
376 # in the http requests
377 'add_ie': ['BrightcoveLegacy'],
378 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
379 'info_dict': {
380 'id': '2765128793001',
381 'ext': 'mp4',
382 'title': 'Le cours de bourse : lā€™analyse technique',
383 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
384 'uploader': 'BFM BUSINESS',
385 },
386 'params': {
387 'skip_download': True,
388 },
389 },
390 {
391 # embedded with itemprop embedURL and video id spelled as `idVideo`
392 'add_id': ['BrightcoveLegacy'],
393 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
394 'info_dict': {
395 'id': '5255628253001',
396 'ext': 'mp4',
397 'title': 'md5:37c519b1128915607601e75a87995fc0',
398 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
399 'uploader': 'BFM BUSINESS',
400 'uploader_id': '876450612001',
401 'timestamp': 1482255315,
402 'upload_date': '20161220',
403 },
404 'params': {
405 'skip_download': True,
406 },
407 },
408 {
409 # https://github.com/rg3/youtube-dl/issues/2253
410 'url': 'http://bcove.me/i6nfkrc3',
411 'md5': '0ba9446db037002366bab3b3eb30c88c',
412 'info_dict': {
413 'id': '3101154703001',
414 'ext': 'mp4',
415 'title': 'Still no power',
416 'uploader': 'thestar.com',
417 '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.',
418 },
419 'add_ie': ['BrightcoveLegacy'],
420 'skip': 'video gone',
421 },
422 {
423 'url': 'http://www.championat.com/video/football/v/87/87499.html',
424 'md5': 'fb973ecf6e4a78a67453647444222983',
425 'info_dict': {
426 'id': '3414141473001',
427 'ext': 'mp4',
428 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
429 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
430 'uploader': 'Championat',
431 },
432 },
433 {
434 # https://github.com/rg3/youtube-dl/issues/3541
435 'add_ie': ['BrightcoveLegacy'],
436 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
437 'info_dict': {
438 'id': '3866516442001',
439 'ext': 'mp4',
440 'title': 'Leer mij vrouwen kennen: Aflevering 1',
441 'description': 'Leer mij vrouwen kennen: Aflevering 1',
442 'uploader': 'SBS Broadcasting',
443 },
444 'skip': 'Restricted to Netherlands',
445 'params': {
446 'skip_download': True, # m3u8 download
447 },
448 },
449 {
450 # Brightcove video in <iframe>
451 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
452 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
453 'info_dict': {
454 'id': '5360463607001',
455 'ext': 'mp4',
456 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
457 '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€‚',
458 'uploader': 'United Nations',
459 'uploader_id': '1362235914001',
460 'timestamp': 1489593889,
461 'upload_date': '20170315',
462 },
463 'add_ie': ['BrightcoveLegacy'],
464 },
465 {
466 # Brightcove with alternative playerID key
467 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
468 'info_dict': {
469 'id': 'nmeth.2062_SV1',
470 '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',
471 },
472 'playlist': [{
473 'info_dict': {
474 'id': '2228375078001',
475 'ext': 'mp4',
476 'title': 'nmeth.2062-sv1',
477 'description': 'nmeth.2062-sv1',
478 'timestamp': 1363357591,
479 'upload_date': '20130315',
480 'uploader': 'Nature Publishing Group',
481 'uploader_id': '1964492299001',
482 },
483 }],
484 },
485 {
486 # Brightcove with UUID in videoPlayer
487 'url': 'http://www8.hp.com/cn/zh/home.html',
488 'info_dict': {
489 'id': '5255815316001',
490 'ext': 'mp4',
491 'title': 'Sprocket Video - China',
492 'description': 'Sprocket Video - China',
493 'uploader': 'HP-Video Gallery',
494 'timestamp': 1482263210,
495 'upload_date': '20161220',
496 'uploader_id': '1107601872001',
497 },
498 'params': {
499 'skip_download': True, # m3u8 download
500 },
501 'skip': 'video rotates...weekly?',
502 },
503 {
504 # Brightcove:new type [2].
505 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
506 'md5': '2b35148fcf48da41c9fb4591650784f3',
507 'info_dict': {
508 'id': '5348741021001',
509 'ext': 'mp4',
510 'upload_date': '20170306',
511 'uploader_id': '4191638492001',
512 'timestamp': 1488769918,
513 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
514
515 },
516 },
517 {
518 # Alternative brightcove <video> attributes
519 '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/',
520 'info_dict': {
521 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
522 '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",
523 },
524 'playlist': [{
525 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
526 'info_dict': {
527 'id': '5311302538001',
528 'ext': 'mp4',
529 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
530 '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)",
531 'timestamp': 1486321708,
532 'upload_date': '20170205',
533 'uploader_id': '800000640001',
534 },
535 'only_matching': True,
536 }],
537 },
538 {
539 # Brightcove with UUID in videoPlayer
540 'url': 'http://www8.hp.com/cn/zh/home.html',
541 'info_dict': {
542 'id': '5255815316001',
543 'ext': 'mp4',
544 'title': 'Sprocket Video - China',
545 'description': 'Sprocket Video - China',
546 'uploader': 'HP-Video Gallery',
547 'timestamp': 1482263210,
548 'upload_date': '20161220',
549 'uploader_id': '1107601872001',
550 },
551 'params': {
552 'skip_download': True, # m3u8 download
553 },
554 },
555 # ooyala video
556 {
557 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
558 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
559 'info_dict': {
560 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
561 'ext': 'mp4',
562 'title': '2cc213299525360.mov', # that's what we get
563 'duration': 238.231,
564 },
565 'add_ie': ['Ooyala'],
566 },
567 {
568 # ooyala video embedded with http://player.ooyala.com/iframe.js
569 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
570 'info_dict': {
571 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
572 'ext': 'mp4',
573 'title': '"Steve Jobs: Man in the Machine" trailer',
574 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
575 'duration': 135.427,
576 },
577 'params': {
578 'skip_download': True,
579 },
580 'skip': 'movie expired',
581 },
582 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
583 {
584 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
585 'info_dict': {
586 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
587 'ext': 'mp4',
588 'title': 'Steampunk Fest Comes to Honesdale',
589 'duration': 43.276,
590 },
591 'params': {
592 'skip_download': True,
593 }
594 },
595 # embed.ly video
596 {
597 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
598 'info_dict': {
599 'id': '9ODmcdjQcHQ',
600 'ext': 'mp4',
601 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
602 'upload_date': '20140225',
603 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
604 'uploader': 'Tested',
605 'uploader_id': 'testedcom',
606 },
607 # No need to test YoutubeIE here
608 'params': {
609 'skip_download': True,
610 },
611 },
612 # funnyordie embed
613 {
614 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
615 'info_dict': {
616 'id': '18e820ec3f',
617 'ext': 'mp4',
618 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
619 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
620 },
621 # HEAD requests lead to endless 301, while GET is OK
622 'expected_warnings': ['301'],
623 },
624 # RUTV embed
625 {
626 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
627 'info_dict': {
628 'id': '776940',
629 'ext': 'mp4',
630 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
631 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
632 },
633 'params': {
634 # m3u8 download
635 'skip_download': True,
636 },
637 },
638 # TVC embed
639 {
640 '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/',
641 'info_dict': {
642 'id': '55304',
643 'ext': 'mp4',
644 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
645 },
646 },
647 # SportBox embed
648 {
649 'url': 'http://www.vestifinance.ru/articles/25753',
650 'info_dict': {
651 'id': '25753',
652 '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"',
653 },
654 'playlist': [{
655 'info_dict': {
656 'id': '370908',
657 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
658 'ext': 'mp4',
659 }
660 }, {
661 'info_dict': {
662 'id': '370905',
663 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
664 'ext': 'mp4',
665 }
666 }, {
667 'info_dict': {
668 'id': '370902',
669 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
670 'ext': 'mp4',
671 }
672 }],
673 'params': {
674 # m3u8 download
675 'skip_download': True,
676 },
677 },
678 # Myvi.ru embed
679 {
680 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
681 'info_dict': {
682 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
683 'ext': 'mp4',
684 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
685 'thumbnail': r're:^https?://.*\.jpg$',
686 'duration': 153,
687 }
688 },
689 # XHamster embed
690 {
691 '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',
692 'info_dict': {
693 'id': 'showthread',
694 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
695 },
696 'playlist_mincount': 7,
697 # This forum does not allow <iframe> syntaxes anymore
698 # Now HTML tags are displayed as-is
699 'skip': 'No videos on this page',
700 },
701 # Embedded TED video
702 {
703 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
704 'md5': '65fdff94098e4a607385a60c5177c638',
705 'info_dict': {
706 'id': '1969',
707 'ext': 'mp4',
708 'title': 'Hidden miracles of the natural world',
709 'uploader': 'Louie Schwartzberg',
710 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
711 }
712 },
713 # nowvideo embed hidden behind percent encoding
714 {
715 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
716 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
717 'info_dict': {
718 'id': '06e53103ca9aa',
719 'ext': 'flv',
720 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
721 'description': 'No description',
722 },
723 },
724 # arte embed
725 {
726 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
727 'md5': '7653032cbb25bf6c80d80f217055fa43',
728 'info_dict': {
729 'id': '048195-004_PLUS7-F',
730 'ext': 'flv',
731 'title': 'X:enius',
732 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
733 'upload_date': '20140320',
734 },
735 'params': {
736 'skip_download': 'Requires rtmpdump'
737 },
738 'skip': 'video gone',
739 },
740 # francetv embed
741 {
742 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
743 'info_dict': {
744 'id': 'EV_30231',
745 'ext': 'mp4',
746 'title': 'Alcaline, le concert avec Calogero',
747 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
748 'upload_date': '20150226',
749 'timestamp': 1424989860,
750 'duration': 5400,
751 },
752 'params': {
753 # m3u8 downloads
754 'skip_download': True,
755 },
756 'expected_warnings': [
757 'Forbidden'
758 ]
759 },
760 # CondƩ Nast embed
761 {
762 'url': 'http://www.wired.com/2014/04/honda-asimo/',
763 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
764 'info_dict': {
765 'id': '53501be369702d3275860000',
766 'ext': 'mp4',
767 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
768 }
769 },
770 # Dailymotion embed
771 {
772 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
773 'md5': '441aeeb82eb72c422c7f14ec533999cd',
774 'info_dict': {
775 'id': 'k2mm4bCdJ6CQ2i7c8o2',
776 'ext': 'mp4',
777 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
778 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
779 'uploader': 'Spi0n',
780 'uploader_id': 'xgditw',
781 'upload_date': '20140425',
782 'timestamp': 1398441542,
783 },
784 'add_ie': ['Dailymotion'],
785 },
786 # DailyMail embed
787 {
788 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
789 'info_dict': {
790 'id': '1495629',
791 'ext': 'mp4',
792 'title': 'Care worker punches elderly dementia patient in head 11 times',
793 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
794 },
795 'add_ie': ['DailyMail'],
796 'params': {
797 'skip_download': True,
798 },
799 },
800 # YouTube embed
801 {
802 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
803 'info_dict': {
804 'id': 'FXRb4ykk4S0',
805 'ext': 'mp4',
806 'title': 'The NBL Auction 2014',
807 'uploader': 'BADMINTON England',
808 'uploader_id': 'BADMINTONEvents',
809 'upload_date': '20140603',
810 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
811 },
812 'add_ie': ['Youtube'],
813 'params': {
814 'skip_download': True,
815 }
816 },
817 # MTVSercices embed
818 {
819 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
820 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
821 'info_dict': {
822 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
823 'ext': 'mp4',
824 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
825 'description': 'Two valets share their love for movie star Liam Neesons.',
826 'timestamp': 1349922600,
827 'upload_date': '20121011',
828 },
829 },
830 # YouTube embed via <data-embed-url="">
831 {
832 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
833 'info_dict': {
834 'id': '4vAffPZIT44',
835 'ext': 'mp4',
836 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
837 'uploader': 'Gameloft',
838 'uploader_id': 'gameloft',
839 'upload_date': '20140828',
840 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
841 },
842 'params': {
843 'skip_download': True,
844 }
845 },
846 # YouTube <object> embed
847 {
848 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
849 'md5': '516718101ec834f74318df76259fb3cc',
850 'info_dict': {
851 'id': 'msN87y-iEx0',
852 'ext': 'webm',
853 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
854 'upload_date': '20080526',
855 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
856 'uploader': 'Christopher Sykes',
857 'uploader_id': 'ChristopherJSykes',
858 },
859 'add_ie': ['Youtube'],
860 },
861 # Camtasia studio
862 {
863 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
864 'playlist': [{
865 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
866 'info_dict': {
867 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
868 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
869 'ext': 'flv',
870 'duration': 2235.90,
871 }
872 }, {
873 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
874 'info_dict': {
875 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
876 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
877 'ext': 'flv',
878 'duration': 2235.93,
879 }
880 }],
881 'info_dict': {
882 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
883 }
884 },
885 # Flowplayer
886 {
887 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
888 'md5': '9d65602bf31c6e20014319c7d07fba27',
889 'info_dict': {
890 'id': '5123ea6d5e5a7',
891 'ext': 'mp4',
892 'age_limit': 18,
893 'uploader': 'www.handjobhub.com',
894 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
895 }
896 },
897 # Multiple brightcove videos
898 # https://github.com/rg3/youtube-dl/issues/2283
899 {
900 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
901 'info_dict': {
902 'id': 'always-never',
903 'title': 'Always / Never - The New Yorker',
904 },
905 'playlist_count': 3,
906 'params': {
907 'extract_flat': False,
908 'skip_download': True,
909 }
910 },
911 # MLB embed
912 {
913 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
914 'md5': '96f09a37e44da40dd083e12d9a683327',
915 'info_dict': {
916 'id': '33322633',
917 'ext': 'mp4',
918 'title': 'Ump changes call to ball',
919 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
920 'duration': 48,
921 'timestamp': 1401537900,
922 'upload_date': '20140531',
923 'thumbnail': r're:^https?://.*\.jpg$',
924 },
925 },
926 # Wistia embed
927 {
928 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
929 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
930 'info_dict': {
931 'id': '6e2wtrbdaf',
932 'ext': 'mov',
933 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
934 'description': 'a Paywall Videos video from Remilon',
935 'duration': 644.072,
936 'uploader': 'study.com',
937 'timestamp': 1459678540,
938 'upload_date': '20160403',
939 'filesize': 24687186,
940 },
941 },
942 {
943 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
944 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
945 'info_dict': {
946 'id': 'uxjb0lwrcz',
947 'ext': 'mp4',
948 'title': 'Conversation about Hexagonal Rails Part 1',
949 'description': 'a Martin Fowler video from ThoughtWorks',
950 'duration': 1715.0,
951 'uploader': 'thoughtworks.wistia.com',
952 'timestamp': 1401832161,
953 'upload_date': '20140603',
954 },
955 },
956 # Wistia standard embed (async)
957 {
958 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
959 'info_dict': {
960 'id': '807fafadvk',
961 'ext': 'mp4',
962 'title': 'Drip Brennan Dunn Workshop',
963 'description': 'a JV Webinars video from getdrip-1',
964 'duration': 4986.95,
965 'timestamp': 1463607249,
966 'upload_date': '20160518',
967 },
968 'params': {
969 'skip_download': True,
970 }
971 },
972 # Soundcloud embed
973 {
974 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
975 'info_dict': {
976 'id': '174391317',
977 'ext': 'mp3',
978 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
979 'uploader': 'Sophos Security',
980 'title': 'Chet Chat 171 - Oct 29, 2014',
981 'upload_date': '20141029',
982 }
983 },
984 # Soundcloud multiple embeds
985 {
986 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
987 'info_dict': {
988 'id': '52809',
989 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
990 },
991 'playlist_mincount': 7,
992 },
993 # TuneIn station embed
994 {
995 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
996 'info_dict': {
997 'id': '204146',
998 'ext': 'mp3',
999 'title': 'CNRV',
1000 'location': 'Paris, France',
1001 'is_live': True,
1002 },
1003 'params': {
1004 # Live stream
1005 'skip_download': True,
1006 },
1007 },
1008 # Livestream embed
1009 {
1010 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1011 'info_dict': {
1012 'id': '67864563',
1013 'ext': 'flv',
1014 'upload_date': '20141112',
1015 'title': 'Rosetta #CometLanding webcast HL 10',
1016 }
1017 },
1018 # Another Livestream embed, without 'new.' in URL
1019 {
1020 'url': 'https://www.freespeech.org/',
1021 'info_dict': {
1022 'id': '123537347',
1023 'ext': 'mp4',
1024 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1025 },
1026 'params': {
1027 # Live stream
1028 'skip_download': True,
1029 },
1030 },
1031 # LazyYT
1032 {
1033 'url': 'https://skiplagged.com/',
1034 'info_dict': {
1035 'id': 'skiplagged',
1036 'title': 'Skiplagged: The smart way to find cheap flights',
1037 },
1038 'playlist_mincount': 1,
1039 'add_ie': ['Youtube'],
1040 },
1041 # Cinchcast embed
1042 {
1043 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1044 'info_dict': {
1045 'id': '7141703',
1046 'ext': 'mp3',
1047 'upload_date': '20141126',
1048 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1049 }
1050 },
1051 # Cinerama player
1052 {
1053 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1054 'info_dict': {
1055 'id': '730m_DandD_1901_512k',
1056 'ext': 'mp4',
1057 'uploader': 'www.abc.net.au',
1058 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1059 }
1060 },
1061 # embedded viddler video
1062 {
1063 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1064 'info_dict': {
1065 'id': '4d03aad9',
1066 'ext': 'mp4',
1067 'uploader': 'deadspin',
1068 'title': 'WALL-TO-GORTAT',
1069 'timestamp': 1422285291,
1070 'upload_date': '20150126',
1071 },
1072 'add_ie': ['Viddler'],
1073 },
1074 # Libsyn embed
1075 {
1076 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1077 'info_dict': {
1078 'id': '3377616',
1079 'ext': 'mp3',
1080 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1081 'description': 'md5:601cb790edd05908957dae8aaa866465',
1082 'upload_date': '20150220',
1083 },
1084 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1085 },
1086 # jwplayer YouTube
1087 {
1088 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1089 'info_dict': {
1090 'id': 'Mrj4DVp2zeA',
1091 'ext': 'mp4',
1092 'upload_date': '20150212',
1093 'uploader': 'The National Archives UK',
1094 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1095 'uploader_id': 'NationalArchives08',
1096 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1097 },
1098 },
1099 # jwplayer rtmp
1100 {
1101 'url': 'http://www.suffolk.edu/sjc/live.php',
1102 'info_dict': {
1103 'id': 'live',
1104 'ext': 'flv',
1105 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1106 'uploader': 'www.suffolk.edu',
1107 },
1108 'params': {
1109 'skip_download': True,
1110 },
1111 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1112 },
1113 # Complex jwplayer
1114 {
1115 'url': 'http://www.indiedb.com/games/king-machine/videos',
1116 'info_dict': {
1117 'id': 'videos',
1118 'ext': 'mp4',
1119 'title': 'king machine trailer 1',
1120 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1121 'thumbnail': r're:^https?://.*\.jpg$',
1122 },
1123 },
1124 {
1125 # JWPlayer config passed as variable
1126 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1127 'info_dict': {
1128 'id': '3326530_hq',
1129 'ext': 'mp4',
1130 'title': 'ARIELE | Tube Cup',
1131 'uploader': 'www.txxx.com',
1132 'age_limit': 18,
1133 },
1134 'params': {
1135 'skip_download': True,
1136 }
1137 },
1138 {
1139 # JWPlatform iframe
1140 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1141 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1142 'info_dict': {
1143 'id': 'O0c5JcKT',
1144 'ext': 'mp4',
1145 'upload_date': '20171122',
1146 'timestamp': 1511366290,
1147 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1148 },
1149 'add_ie': [JWPlatformIE.ie_key()],
1150 },
1151 {
1152 # Video.js embed, multiple formats
1153 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1154 'info_dict': {
1155 'id': 'yygqldloqIk',
1156 'ext': 'mp4',
1157 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1158 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1159 'upload_date': '20130314',
1160 'uploader': 'PROстŠ¾Šµ3D',
1161 'uploader_id': 'PROstoe3D',
1162 },
1163 'params': {
1164 'skip_download': True,
1165 },
1166 },
1167 {
1168 # Video.js embed, single format
1169 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1170 'info_dict': {
1171 'id': 'watch',
1172 'ext': 'mp4',
1173 'title': 'Step 1 - Good Foundation',
1174 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1175 },
1176 'params': {
1177 'skip_download': True,
1178 },
1179 },
1180 # rtl.nl embed
1181 {
1182 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1183 'playlist_mincount': 5,
1184 'info_dict': {
1185 'id': 'aanslagen-kopenhagen',
1186 'title': 'Aanslagen Kopenhagen',
1187 }
1188 },
1189 # Zapiks embed
1190 {
1191 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1192 'info_dict': {
1193 'id': '118046',
1194 'ext': 'mp4',
1195 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1196 }
1197 },
1198 # Kaltura embed (different embed code)
1199 {
1200 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1201 'info_dict': {
1202 'id': '1_a52wc67y',
1203 'ext': 'flv',
1204 'upload_date': '20150127',
1205 'uploader_id': 'PremierMedia',
1206 'timestamp': int,
1207 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1208 },
1209 },
1210 # Kaltura embed with single quotes
1211 {
1212 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1213 'info_dict': {
1214 'id': '0_izeg5utt',
1215 'ext': 'mp4',
1216 'title': '35871',
1217 'timestamp': 1355743100,
1218 'upload_date': '20121217',
1219 'uploader_id': 'batchUser',
1220 },
1221 'add_ie': ['Kaltura'],
1222 },
1223 {
1224 # Kaltura embedded via quoted entry_id
1225 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1226 'info_dict': {
1227 'id': '0_utuok90b',
1228 'ext': 'mp4',
1229 'title': '06_matthew_brender_raj_dutt',
1230 'timestamp': 1466638791,
1231 'upload_date': '20160622',
1232 },
1233 'add_ie': ['Kaltura'],
1234 'expected_warnings': [
1235 'Could not send HEAD request'
1236 ],
1237 'params': {
1238 'skip_download': True,
1239 }
1240 },
1241 {
1242 # Kaltura embedded, some fileExt broken (#11480)
1243 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1244 'info_dict': {
1245 'id': '1_sgtvehim',
1246 'ext': 'mp4',
1247 'title': 'Our "Standard Models" of particle physics and cosmology',
1248 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1249 'timestamp': 1321158993,
1250 'upload_date': '20111113',
1251 'uploader_id': 'kps1',
1252 },
1253 'add_ie': ['Kaltura'],
1254 },
1255 {
1256 # Kaltura iframe embed
1257 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1258 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1259 'info_dict': {
1260 'id': '0_f2cfbpwy',
1261 'ext': 'mp4',
1262 'title': 'I. M. Pei: A Centennial Celebration',
1263 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1264 'upload_date': '20170403',
1265 'uploader_id': 'batchUser',
1266 'timestamp': 1491232186,
1267 },
1268 'add_ie': ['Kaltura'],
1269 },
1270 # EaglePlatform embed (generic URL)
1271 {
1272 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1273 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1274 'info_dict': {
1275 'id': '227304',
1276 'ext': 'mp4',
1277 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1278 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1279 'thumbnail': r're:^https?://.*\.jpg$',
1280 'duration': 87,
1281 'view_count': int,
1282 'age_limit': 0,
1283 },
1284 'params': {
1285 'skip_download': True,
1286 },
1287 },
1288 # referrer protected EaglePlatform embed
1289 {
1290 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1291 'info_dict': {
1292 'id': '582306',
1293 'ext': 'mp4',
1294 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1295 'thumbnail': r're:^https?://.*\.jpg$',
1296 'duration': 3382,
1297 'view_count': int,
1298 },
1299 'params': {
1300 'skip_download': True,
1301 },
1302 },
1303 # ClipYou (EaglePlatform) embed (custom URL)
1304 {
1305 'url': 'http://muz-tv.ru/play/7129/',
1306 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1307 'info_dict': {
1308 'id': '12820',
1309 'ext': 'mp4',
1310 'title': "'O Sole Mio",
1311 'thumbnail': r're:^https?://.*\.jpg$',
1312 'duration': 216,
1313 'view_count': int,
1314 },
1315 'params': {
1316 'skip_download': True,
1317 },
1318 'skip': 'This video is unavailable.',
1319 },
1320 # Pladform embed
1321 {
1322 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1323 'info_dict': {
1324 'id': '100183293',
1325 'ext': 'mp4',
1326 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1327 '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°',
1328 'thumbnail': r're:^https?://.*\.jpg$',
1329 'duration': 694,
1330 'age_limit': 0,
1331 },
1332 'skip': 'HTTP Error 404: Not Found',
1333 },
1334 # Playwire embed
1335 {
1336 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1337 'info_dict': {
1338 'id': '3519514',
1339 'ext': 'mp4',
1340 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1341 'thumbnail': r're:^https?://.*\.png$',
1342 'duration': 45.115,
1343 },
1344 },
1345 # 5min embed
1346 {
1347 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1348 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1349 'info_dict': {
1350 'id': '518726732',
1351 'ext': 'mp4',
1352 'title': 'Facebook Creates "On This Day" | Crunch Report',
1353 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1354 'timestamp': 1427237531,
1355 'uploader': 'Crunch Report',
1356 'upload_date': '20150324',
1357 },
1358 'params': {
1359 # m3u8 download
1360 'skip_download': True,
1361 },
1362 },
1363 # SVT embed
1364 {
1365 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1366 'info_dict': {
1367 'id': '2900353',
1368 'ext': 'flv',
1369 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1370 'duration': 27,
1371 'age_limit': 0,
1372 },
1373 },
1374 # Crooks and Liars embed
1375 {
1376 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1377 'info_dict': {
1378 'id': '8RUoRhRi',
1379 'ext': 'mp4',
1380 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1381 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1382 'timestamp': 1428207000,
1383 'upload_date': '20150405',
1384 'uploader': 'Heather',
1385 },
1386 },
1387 # Crooks and Liars external embed
1388 {
1389 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1390 'info_dict': {
1391 'id': 'MTE3MjUtMzQ2MzA',
1392 'ext': 'mp4',
1393 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1394 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1395 'timestamp': 1265032391,
1396 'upload_date': '20100201',
1397 'uploader': 'Heather',
1398 },
1399 },
1400 # NBC Sports vplayer embed
1401 {
1402 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1403 'info_dict': {
1404 'id': 'ln7x1qSThw4k',
1405 'ext': 'flv',
1406 'title': "PFT Live: New leader in the 'new-look' defense",
1407 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1408 'uploader': 'NBCU-SPORTS',
1409 'upload_date': '20140107',
1410 'timestamp': 1389118457,
1411 },
1412 'skip': 'Invalid Page URL',
1413 },
1414 # NBC News embed
1415 {
1416 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1417 'md5': '1aa589c675898ae6d37a17913cf68d66',
1418 'info_dict': {
1419 'id': 'x_dtl_oa_LettermanliftPR_160608',
1420 'ext': 'mp4',
1421 'title': 'David Letterman: A Preview',
1422 '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.',
1423 'upload_date': '20160609',
1424 'timestamp': 1465431544,
1425 'uploader': 'NBCU-NEWS',
1426 },
1427 },
1428 # UDN embed
1429 {
1430 'url': 'https://video.udn.com/news/300346',
1431 'md5': 'fd2060e988c326991037b9aff9df21a6',
1432 'info_dict': {
1433 'id': '300346',
1434 'ext': 'mp4',
1435 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1436 'thumbnail': r're:^https?://.*\.jpg$',
1437 },
1438 'params': {
1439 # m3u8 download
1440 'skip_download': True,
1441 },
1442 'expected_warnings': ['Failed to parse JSON Expecting value'],
1443 },
1444 # Ooyala embed
1445 {
1446 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1447 'info_dict': {
1448 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1449 'ext': 'mp4',
1450 'description': 'Index/Match versus VLOOKUP.',
1451 'title': 'This is what separates the Excel masters from the wannabes',
1452 'duration': 191.933,
1453 },
1454 'params': {
1455 # m3u8 downloads
1456 'skip_download': True,
1457 }
1458 },
1459 # Brightcove URL in single quotes
1460 {
1461 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1462 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1463 'info_dict': {
1464 'id': '4255764656001',
1465 'ext': 'mp4',
1466 'title': 'SN Presents: Russell Martin, World Citizen',
1467 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1468 'uploader': 'Rogers Sportsnet',
1469 'uploader_id': '1704050871',
1470 'upload_date': '20150525',
1471 'timestamp': 1432570283,
1472 },
1473 },
1474 # OnionStudios embed
1475 {
1476 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1477 'info_dict': {
1478 'id': '2855',
1479 'ext': 'mp4',
1480 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1481 'thumbnail': r're:^https?://.*\.jpe?g$',
1482 'uploader': 'ClickHole',
1483 'uploader_id': 'clickhole',
1484 }
1485 },
1486 # SnagFilms embed
1487 {
1488 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1489 'info_dict': {
1490 'id': '74849a00-85a9-11e1-9660-123139220831',
1491 'ext': 'mp4',
1492 'title': '#whilewewatch',
1493 }
1494 },
1495 # AdobeTVVideo embed
1496 {
1497 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1498 'md5': '43662b577c018ad707a63766462b1e87',
1499 'info_dict': {
1500 'id': '2456',
1501 'ext': 'mp4',
1502 'title': 'New experience with Acrobat DC',
1503 'description': 'New experience with Acrobat DC',
1504 'duration': 248.667,
1505 },
1506 },
1507 # BrightcoveInPageEmbed embed
1508 {
1509 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1510 'info_dict': {
1511 'id': '4238694884001',
1512 'ext': 'flv',
1513 'title': 'Tabletop: Dread, Last Thoughts',
1514 'description': 'Tabletop: Dread, Last Thoughts',
1515 'duration': 51690,
1516 },
1517 },
1518 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1519 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1520 {
1521 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1522 'info_dict': {
1523 'id': '4785848093001',
1524 'ext': 'mp4',
1525 'title': 'The Cardinal Pell Interview',
1526 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1527 'uploader': 'GlobeCast Australia - GlobeStream',
1528 'uploader_id': '2733773828001',
1529 'upload_date': '20160304',
1530 'timestamp': 1457083087,
1531 },
1532 'params': {
1533 # m3u8 downloads
1534 'skip_download': True,
1535 },
1536 },
1537 {
1538 # Brightcove embed with whitespace around attribute names
1539 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1540 'info_dict': {
1541 'id': '3167554373001',
1542 'ext': 'mp4',
1543 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1544 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1545 'uploader_id': '1079349493',
1546 'upload_date': '20140207',
1547 'timestamp': 1391810548,
1548 },
1549 'params': {
1550 'skip_download': True,
1551 },
1552 },
1553 # Another form of arte.tv embed
1554 {
1555 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1556 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1557 'info_dict': {
1558 'id': '030273-562_PLUS7-F',
1559 'ext': 'mp4',
1560 'title': 'ARTE Reportage - Nulle part, en France',
1561 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1562 'upload_date': '20160409',
1563 },
1564 },
1565 # LiveLeak embed
1566 {
1567 'url': 'http://www.wykop.pl/link/3088787/',
1568 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1569 'info_dict': {
1570 'id': '874_1459135191',
1571 'ext': 'mp4',
1572 'title': 'Man shows poor quality of new apartment building',
1573 'description': 'The wall is like a sand pile.',
1574 'uploader': 'Lake8737',
1575 },
1576 'add_ie': [LiveLeakIE.ie_key()],
1577 },
1578 # Another LiveLeak embed pattern (#13336)
1579 {
1580 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1581 'info_dict': {
1582 'id': '2eb_1496309988',
1583 'ext': 'mp4',
1584 'title': 'Thief robs place where everyone was armed',
1585 'description': 'md5:694d73ee79e535953cf2488562288eee',
1586 'uploader': 'brazilwtf',
1587 },
1588 'add_ie': [LiveLeakIE.ie_key()],
1589 },
1590 # Duplicated embedded video URLs
1591 {
1592 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1593 'info_dict': {
1594 'id': '149298443_480_16c25b74_2',
1595 'ext': 'mp4',
1596 'title': 'vs. Blue Orange Spring Game',
1597 'uploader': 'www.hudl.com',
1598 },
1599 },
1600 # twitter:player:stream embed
1601 {
1602 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1603 'info_dict': {
1604 'id': 'master',
1605 'ext': 'mp4',
1606 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1607 'uploader': 'www.rtl.be',
1608 },
1609 'params': {
1610 # m3u8 downloads
1611 'skip_download': True,
1612 },
1613 },
1614 # twitter:player embed
1615 {
1616 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1617 'md5': 'a3e0df96369831de324f0778e126653c',
1618 'info_dict': {
1619 'id': '4909620399001',
1620 'ext': 'mp4',
1621 'title': 'What Do Black Holes Sound Like?',
1622 'description': 'what do black holes sound like',
1623 'upload_date': '20160524',
1624 'uploader_id': '29913724001',
1625 'timestamp': 1464107587,
1626 'uploader': 'TheAtlantic',
1627 },
1628 'add_ie': ['BrightcoveLegacy'],
1629 },
1630 # Facebook <iframe> embed
1631 {
1632 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1633 'md5': 'fbcde74f534176ecb015849146dd3aee',
1634 'info_dict': {
1635 'id': '599637780109885',
1636 'ext': 'mp4',
1637 'title': 'Facebook video #599637780109885',
1638 },
1639 },
1640 # Facebook <iframe> embed, plugin video
1641 {
1642 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1643 'info_dict': {
1644 'id': '1754168231264132',
1645 'ext': 'mp4',
1646 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1647 'uploader': 'Tariq Ramadan (official)',
1648 'timestamp': 1496758379,
1649 'upload_date': '20170606',
1650 },
1651 'params': {
1652 'skip_download': True,
1653 },
1654 },
1655 # Facebook API embed
1656 {
1657 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1658 'md5': 'a47372ee61b39a7b90287094d447d94e',
1659 'info_dict': {
1660 'id': '10153467542406923',
1661 'ext': 'mp4',
1662 'title': 'Facebook video #10153467542406923',
1663 },
1664 },
1665 # Wordpress "YouTube Video Importer" plugin
1666 {
1667 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1668 'md5': 'd16797741b560b485194eddda8121b48',
1669 'info_dict': {
1670 'id': 'HNTXWDXV9Is',
1671 'ext': 'mp4',
1672 'title': 'Blue Devils Drumline Stanford lot 2016',
1673 'upload_date': '20160627',
1674 'uploader_id': 'GENOCIDE8GENERAL10',
1675 'uploader': 'cylus cyrus',
1676 },
1677 },
1678 {
1679 # video stored on custom kaltura server
1680 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1681 'md5': '537617d06e64dfed891fa1593c4b30cc',
1682 'info_dict': {
1683 'id': '0_1iotm5bh',
1684 'ext': 'mp4',
1685 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1686 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1687 'uploader_id': 'videos.expansion@el-mundo.net',
1688 'upload_date': '20150429',
1689 'timestamp': 1430303472,
1690 },
1691 'add_ie': ['Kaltura'],
1692 },
1693 {
1694 # Non-standard Vimeo embed
1695 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1696 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1697 'info_dict': {
1698 'id': '148867247',
1699 'ext': 'mp4',
1700 'title': 'Understanding the web - Teaser',
1701 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1702 'upload_date': '20151214',
1703 'uploader': 'OpenClassrooms',
1704 'uploader_id': 'openclassrooms',
1705 },
1706 'add_ie': ['Vimeo'],
1707 },
1708 {
1709 # generic vimeo embed that requires original URL passed as Referer
1710 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1711 'only_matching': True,
1712 },
1713 {
1714 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1715 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1716 'info_dict': {
1717 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1718 'ext': 'mp4',
1719 'title': 'Big Buck Bunny',
1720 'description': 'Royalty free test video',
1721 'timestamp': 1432816365,
1722 'upload_date': '20150528',
1723 'is_live': False,
1724 },
1725 'params': {
1726 'skip_download': True,
1727 },
1728 'add_ie': [ArkenaIE.ie_key()],
1729 },
1730 {
1731 '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/',
1732 'info_dict': {
1733 'id': '1c7141f46c',
1734 'ext': 'mp4',
1735 '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',
1736 },
1737 'params': {
1738 'skip_download': True,
1739 },
1740 'add_ie': [Vbox7IE.ie_key()],
1741 },
1742 {
1743 # DBTV embeds
1744 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1745 'info_dict': {
1746 'id': '43254897',
1747 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1748 },
1749 'playlist_mincount': 3,
1750 },
1751 {
1752 # Videa embeds
1753 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1754 'info_dict': {
1755 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1756 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1757 },
1758 'playlist_mincount': 2,
1759 },
1760 {
1761 # 20 minuten embed
1762 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1763 'info_dict': {
1764 'id': '523629',
1765 'ext': 'mp4',
1766 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1767 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1768 },
1769 'params': {
1770 'skip_download': True,
1771 },
1772 'add_ie': [TwentyMinutenIE.ie_key()],
1773 },
1774 {
1775 # VideoPress embed
1776 'url': 'https://en.support.wordpress.com/videopress/',
1777 'info_dict': {
1778 'id': 'OcobLTqC',
1779 'ext': 'm4v',
1780 'title': 'IMG_5786',
1781 'timestamp': 1435711927,
1782 'upload_date': '20150701',
1783 },
1784 'params': {
1785 'skip_download': True,
1786 },
1787 'add_ie': [VideoPressIE.ie_key()],
1788 },
1789 {
1790 # Rutube embed
1791 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1792 'info_dict': {
1793 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1794 'ext': 'flv',
1795 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1796 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1797 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1798 'upload_date': '20170228',
1799 'uploader_id': '996642',
1800 },
1801 'params': {
1802 'skip_download': True,
1803 },
1804 'add_ie': [RutubeIE.ie_key()],
1805 },
1806 {
1807 # ThePlatform embedded with whitespaces in URLs
1808 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1809 'only_matching': True,
1810 },
1811 {
1812 # Senate ISVP iframe https
1813 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1814 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1815 'info_dict': {
1816 'id': 'govtaff020316',
1817 'ext': 'mp4',
1818 'title': 'Integrated Senate Video Player',
1819 },
1820 'add_ie': [SenateISVPIE.ie_key()],
1821 },
1822 {
1823 # Limelight embeds (1 channel embed + 4 media embeds)
1824 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1825 'info_dict': {
1826 'id': 'FacilitatorTraining2017',
1827 'title': 'Facilitator Training 2017',
1828 },
1829 'playlist_mincount': 5,
1830 },
1831 {
1832 # Limelight embed (LimelightPlayerUtil.embed)
1833 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1834 'info_dict': {
1835 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1836 'ext': 'mp4',
1837 'title': '07448641',
1838 'timestamp': 1499890639,
1839 'upload_date': '20170712',
1840 },
1841 'params': {
1842 'skip_download': True,
1843 },
1844 'add_ie': ['LimelightMedia'],
1845 },
1846 {
1847 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1848 'info_dict': {
1849 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1850 'title': 'Standoff with Walnut Creek murder suspect ends',
1851 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1852 },
1853 'playlist_mincount': 4,
1854 },
1855 {
1856 # WashingtonPost embed
1857 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1858 'info_dict': {
1859 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1860 'ext': 'mp4',
1861 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1862 '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.',
1863 'timestamp': 1455216756,
1864 'uploader': 'The Washington Post',
1865 'upload_date': '20160211',
1866 },
1867 'add_ie': [WashingtonPostIE.ie_key()],
1868 },
1869 {
1870 # Mediaset embed
1871 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1872 'info_dict': {
1873 'id': '720642',
1874 'ext': 'mp4',
1875 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1876 },
1877 'params': {
1878 'skip_download': True,
1879 },
1880 'add_ie': [MediasetIE.ie_key()],
1881 },
1882 {
1883 # JOJ.sk embeds
1884 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1885 'info_dict': {
1886 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1887 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1888 },
1889 'playlist_mincount': 5,
1890 'add_ie': [JojIE.ie_key()],
1891 },
1892 {
1893 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1894 'url': 'https://tvrain.ru/amp/418921/',
1895 'md5': 'cc00413936695987e8de148b67d14f1d',
1896 'info_dict': {
1897 'id': '418921',
1898 'ext': 'mp4',
1899 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1900 },
1901 },
1902 {
1903 # vzaar embed
1904 'url': 'http://help.vzaar.com/article/165-embedding-video',
1905 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1906 'info_dict': {
1907 'id': '8707641',
1908 'ext': 'mp4',
1909 'title': 'Building A Business Online: Principal Chairs Q & A',
1910 },
1911 },
1912 {
1913 # multiple HTML5 videos on one page
1914 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1915 'info_dict': {
1916 'id': 'keyscenarios',
1917 'title': 'Rescue Kit 14 Free Edition - Getting started',
1918 },
1919 'playlist_count': 4,
1920 },
1921 {
1922 # vshare embed
1923 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1924 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1925 'info_dict': {
1926 'id': '0f64ce6',
1927 'title': 'vl14062007715967',
1928 'ext': 'mp4',
1929 }
1930 },
1931 {
1932 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1933 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1934 'info_dict': {
1935 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1936 'ext': 'mp4',
1937 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1938 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1939 'timestamp': 1474354800,
1940 'upload_date': '20160920',
1941 }
1942 },
1943 {
1944 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1945 'info_dict': {
1946 'id': '1731611',
1947 'ext': 'mp4',
1948 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1949 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1950 'timestamp': 1516100691,
1951 'upload_date': '20180116',
1952 },
1953 'params': {
1954 'skip_download': True,
1955 },
1956 'add_ie': [SpringboardPlatformIE.ie_key()],
1957 }
1958 # {
1959 # # TODO: find another test
1960 # # http://schema.org/VideoObject
1961 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1962 # 'md5': '888dcf08b7ea671381f00fab74692755',
1963 # 'info_dict': {
1964 # 'id': 'nyvTSJMKId',
1965 # 'ext': 'mp4',
1966 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1967 # 'description': '#love for cats.',
1968 # 'timestamp': 1461244995,
1969 # 'upload_date': '20160421',
1970 # },
1971 # 'params': {
1972 # 'force_generic_extractor': True,
1973 # },
1974 # }
1975 ]
1976
1977 def report_following_redirect(self, new_url):
1978 """Report information extraction."""
1979 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1980
1981 def _extract_rss(self, url, video_id, doc):
1982 playlist_title = doc.find('./channel/title').text
1983 playlist_desc_el = doc.find('./channel/description')
1984 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1985
1986 entries = []
1987 for it in doc.findall('./channel/item'):
1988 next_url = xpath_text(it, 'link', fatal=False)
1989 if not next_url:
1990 enclosure_nodes = it.findall('./enclosure')
1991 for e in enclosure_nodes:
1992 next_url = e.attrib.get('url')
1993 if next_url:
1994 break
1995
1996 if not next_url:
1997 continue
1998
1999 entries.append({
2000 '_type': 'url_transparent',
2001 'url': next_url,
2002 'title': it.find('title').text,
2003 })
2004
2005 return {
2006 '_type': 'playlist',
2007 'id': url,
2008 'title': playlist_title,
2009 'description': playlist_desc,
2010 'entries': entries,
2011 }
2012
2013 def _extract_camtasia(self, url, video_id, webpage):
2014 """ Returns None if no camtasia video can be found. """
2015
2016 camtasia_cfg = self._search_regex(
2017 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2018 webpage, 'camtasia configuration file', default=None)
2019 if camtasia_cfg is None:
2020 return None
2021
2022 title = self._html_search_meta('DC.title', webpage, fatal=True)
2023
2024 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2025 camtasia_cfg = self._download_xml(
2026 camtasia_url, video_id,
2027 note='Downloading camtasia configuration',
2028 errnote='Failed to download camtasia configuration')
2029 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2030
2031 entries = []
2032 for n in fileset_node.getchildren():
2033 url_n = n.find('./uri')
2034 if url_n is None:
2035 continue
2036
2037 entries.append({
2038 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2039 'title': '%s - %s' % (title, n.tag),
2040 'url': compat_urlparse.urljoin(url, url_n.text),
2041 'duration': float_or_none(n.find('./duration').text),
2042 })
2043
2044 return {
2045 '_type': 'playlist',
2046 'entries': entries,
2047 'title': title,
2048 }
2049
2050 def _real_extract(self, url):
2051 if url.startswith('//'):
2052 return {
2053 '_type': 'url',
2054 'url': self.http_scheme() + url,
2055 }
2056
2057 parsed_url = compat_urlparse.urlparse(url)
2058 if not parsed_url.scheme:
2059 default_search = self._downloader.params.get('default_search')
2060 if default_search is None:
2061 default_search = 'fixup_error'
2062
2063 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2064 if '/' in url:
2065 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2066 return self.url_result('http://' + url)
2067 elif default_search != 'fixup_error':
2068 if default_search == 'auto_warning':
2069 if re.match(r'^(?:url|URL)$', url):
2070 raise ExtractorError(
2071 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2072 expected=True)
2073 else:
2074 self._downloader.report_warning(
2075 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2076 return self.url_result('ytsearch:' + url)
2077
2078 if default_search in ('error', 'fixup_error'):
2079 raise ExtractorError(
2080 '%r is not a valid URL. '
2081 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2082 % (url, url), expected=True)
2083 else:
2084 if ':' not in default_search:
2085 default_search += ':'
2086 return self.url_result(default_search + url)
2087
2088 url, smuggled_data = unsmuggle_url(url)
2089 force_videoid = None
2090 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2091 if smuggled_data and 'force_videoid' in smuggled_data:
2092 force_videoid = smuggled_data['force_videoid']
2093 video_id = force_videoid
2094 else:
2095 video_id = self._generic_id(url)
2096
2097 self.to_screen('%s: Requesting header' % video_id)
2098
2099 head_req = HEADRequest(url)
2100 head_response = self._request_webpage(
2101 head_req, video_id,
2102 note=False, errnote='Could not send HEAD request to %s' % url,
2103 fatal=False)
2104
2105 if head_response is not False:
2106 # Check for redirect
2107 new_url = compat_str(head_response.geturl())
2108 if url != new_url:
2109 self.report_following_redirect(new_url)
2110 if force_videoid:
2111 new_url = smuggle_url(
2112 new_url, {'force_videoid': force_videoid})
2113 return self.url_result(new_url)
2114
2115 full_response = None
2116 if head_response is False:
2117 request = sanitized_Request(url)
2118 request.add_header('Accept-Encoding', '*')
2119 full_response = self._request_webpage(request, video_id)
2120 head_response = full_response
2121
2122 info_dict = {
2123 'id': video_id,
2124 'title': self._generic_title(url),
2125 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2126 }
2127
2128 # Check for direct link to a video
2129 content_type = head_response.headers.get('Content-Type', '').lower()
2130 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2131 if m:
2132 format_id = compat_str(m.group('format_id'))
2133 if format_id.endswith('mpegurl'):
2134 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2135 elif format_id == 'f4m':
2136 formats = self._extract_f4m_formats(url, video_id)
2137 else:
2138 formats = [{
2139 'format_id': format_id,
2140 'url': url,
2141 'vcodec': 'none' if m.group('type') == 'audio' else None
2142 }]
2143 info_dict['direct'] = True
2144 self._sort_formats(formats)
2145 info_dict['formats'] = formats
2146 return info_dict
2147
2148 if not self._downloader.params.get('test', False) and not is_intentional:
2149 force = self._downloader.params.get('force_generic_extractor', False)
2150 self._downloader.report_warning(
2151 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2152
2153 if not full_response:
2154 request = sanitized_Request(url)
2155 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2156 # making it impossible to download only chunk of the file (yet we need only 512kB to
2157 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2158 # that will always result in downloading the whole file that is not desirable.
2159 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2160 # to accept raw bytes and being able to download only a chunk.
2161 # It may probably better to solve this by checking Content-Type for application/octet-stream
2162 # after HEAD request finishes, but not sure if we can rely on this.
2163 request.add_header('Accept-Encoding', '*')
2164 full_response = self._request_webpage(request, video_id)
2165
2166 first_bytes = full_response.read(512)
2167
2168 # Is it an M3U playlist?
2169 if first_bytes.startswith(b'#EXTM3U'):
2170 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2171 self._sort_formats(info_dict['formats'])
2172 return info_dict
2173
2174 # Maybe it's a direct link to a video?
2175 # Be careful not to download the whole thing!
2176 if not is_html(first_bytes):
2177 self._downloader.report_warning(
2178 'URL could be a direct video link, returning it as such.')
2179 info_dict.update({
2180 'direct': True,
2181 'url': url,
2182 })
2183 return info_dict
2184
2185 webpage = self._webpage_read_content(
2186 full_response, url, video_id, prefix=first_bytes)
2187
2188 self.report_extraction(video_id)
2189
2190 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2191 try:
2192 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2193 if doc.tag == 'rss':
2194 return self._extract_rss(url, video_id, doc)
2195 elif doc.tag == 'SmoothStreamingMedia':
2196 info_dict['formats'] = self._parse_ism_formats(doc, url)
2197 self._sort_formats(info_dict['formats'])
2198 return info_dict
2199 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2200 smil = self._parse_smil(doc, url, video_id)
2201 self._sort_formats(smil['formats'])
2202 return smil
2203 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2204 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2205 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2206 info_dict['formats'] = self._parse_mpd_formats(
2207 doc,
2208 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2209 mpd_url=url)
2210 self._sort_formats(info_dict['formats'])
2211 return info_dict
2212 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2213 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2214 self._sort_formats(info_dict['formats'])
2215 return info_dict
2216 except compat_xml_parse_error:
2217 pass
2218
2219 # Is it a Camtasia project?
2220 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2221 if camtasia_res is not None:
2222 return camtasia_res
2223
2224 # Sometimes embedded video player is hidden behind percent encoding
2225 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2226 # Unescaping the whole page allows to handle those cases in a generic way
2227 webpage = compat_urllib_parse_unquote(webpage)
2228
2229 # it's tempting to parse this further, but you would
2230 # have to take into account all the variations like
2231 # Video Title - Site Name
2232 # Site Name | Video Title
2233 # Video Title - Tagline | Site Name
2234 # and so on and so forth; it's just not practical
2235 video_title = self._og_search_title(
2236 webpage, default=None) or self._html_search_regex(
2237 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2238 default='video')
2239
2240 # Try to detect age limit automatically
2241 age_limit = self._rta_search(webpage)
2242 # And then there are the jokers who advertise that they use RTA,
2243 # but actually don't.
2244 AGE_LIMIT_MARKERS = [
2245 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2246 ]
2247 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2248 age_limit = 18
2249
2250 # video uploader is domain name
2251 video_uploader = self._search_regex(
2252 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2253
2254 video_description = self._og_search_description(webpage, default=None)
2255 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2256
2257 info_dict.update({
2258 'title': video_title,
2259 'description': video_description,
2260 'thumbnail': video_thumbnail,
2261 'age_limit': age_limit,
2262 })
2263
2264 # Look for Brightcove Legacy Studio embeds
2265 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2266 if bc_urls:
2267 entries = [{
2268 '_type': 'url',
2269 'url': smuggle_url(bc_url, {'Referer': url}),
2270 'ie_key': 'BrightcoveLegacy'
2271 } for bc_url in bc_urls]
2272
2273 return {
2274 '_type': 'playlist',
2275 'title': video_title,
2276 'id': video_id,
2277 'entries': entries,
2278 }
2279
2280 # Look for Brightcove New Studio embeds
2281 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2282 if bc_urls:
2283 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2284
2285 # Look for Nexx embeds
2286 nexx_urls = NexxIE._extract_urls(webpage)
2287 if nexx_urls:
2288 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2289
2290 # Look for Nexx iFrame embeds
2291 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2292 if nexx_embed_urls:
2293 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2294
2295 # Look for ThePlatform embeds
2296 tp_urls = ThePlatformIE._extract_urls(webpage)
2297 if tp_urls:
2298 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2299
2300 # Look for Vessel embeds
2301 vessel_urls = VesselIE._extract_urls(webpage)
2302 if vessel_urls:
2303 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2304
2305 # Look for embedded rtl.nl player
2306 matches = re.findall(
2307 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2308 webpage)
2309 if matches:
2310 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2311
2312 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2313 if vimeo_urls:
2314 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2315
2316 vid_me_embed_url = self._search_regex(
2317 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2318 webpage, 'vid.me embed', default=None)
2319 if vid_me_embed_url is not None:
2320 return self.url_result(vid_me_embed_url, 'Vidme')
2321
2322 # Look for YouTube embeds
2323 youtube_urls = YoutubeIE._extract_urls(webpage)
2324 if youtube_urls:
2325 return self.playlist_from_matches(
2326 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2327
2328 matches = DailymotionIE._extract_urls(webpage)
2329 if matches:
2330 return self.playlist_from_matches(matches, video_id, video_title)
2331
2332 # Look for embedded Dailymotion playlist player (#3822)
2333 m = re.search(
2334 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2335 if m:
2336 playlists = re.findall(
2337 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2338 if playlists:
2339 return self.playlist_from_matches(
2340 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2341
2342 # Look for DailyMail embeds
2343 dailymail_urls = DailyMailIE._extract_urls(webpage)
2344 if dailymail_urls:
2345 return self.playlist_from_matches(
2346 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2347
2348 # Look for embedded Wistia player
2349 wistia_url = WistiaIE._extract_url(webpage)
2350 if wistia_url:
2351 return {
2352 '_type': 'url_transparent',
2353 'url': self._proto_relative_url(wistia_url),
2354 'ie_key': WistiaIE.ie_key(),
2355 'uploader': video_uploader,
2356 }
2357
2358 # Look for SVT player
2359 svt_url = SVTIE._extract_url(webpage)
2360 if svt_url:
2361 return self.url_result(svt_url, 'SVT')
2362
2363 # Look for Bandcamp pages with custom domain
2364 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2365 if mobj is not None:
2366 burl = unescapeHTML(mobj.group(1))
2367 # Don't set the extractor because it can be a track url or an album
2368 return self.url_result(burl)
2369
2370 # Look for embedded Vevo player
2371 mobj = re.search(
2372 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2373 if mobj is not None:
2374 return self.url_result(mobj.group('url'))
2375
2376 # Look for embedded Viddler player
2377 mobj = re.search(
2378 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2379 webpage)
2380 if mobj is not None:
2381 return self.url_result(mobj.group('url'))
2382
2383 # Look for NYTimes player
2384 mobj = re.search(
2385 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2386 webpage)
2387 if mobj is not None:
2388 return self.url_result(mobj.group('url'))
2389
2390 # Look for Libsyn player
2391 mobj = re.search(
2392 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2393 if mobj is not None:
2394 return self.url_result(mobj.group('url'))
2395
2396 # Look for Ooyala videos
2397 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2398 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2399 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2400 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2401 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2402 if mobj is not None:
2403 embed_token = self._search_regex(
2404 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2405 webpage, 'ooyala embed token', default=None)
2406 return OoyalaIE._build_url_result(smuggle_url(
2407 mobj.group('ec'), {
2408 'domain': url,
2409 'embed_token': embed_token,
2410 }))
2411
2412 # Look for multiple Ooyala embeds on SBN network websites
2413 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2414 if mobj is not None:
2415 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2416 if embeds:
2417 return self.playlist_from_matches(
2418 embeds, video_id, video_title,
2419 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2420
2421 # Look for Aparat videos
2422 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2423 if mobj is not None:
2424 return self.url_result(mobj.group(1), 'Aparat')
2425
2426 # Look for MPORA videos
2427 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2428 if mobj is not None:
2429 return self.url_result(mobj.group(1), 'Mpora')
2430
2431 # Look for embedded NovaMov-based player
2432 mobj = re.search(
2433 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2434 (?P<url>http://(?:(?:embed|www)\.)?
2435 (?:novamov\.com|
2436 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2437 videoweed\.(?:es|com)|
2438 movshare\.(?:net|sx|ag)|
2439 divxstage\.(?:eu|net|ch|co|at|ag))
2440 /embed\.php.+?)\1''', webpage)
2441 if mobj is not None:
2442 return self.url_result(mobj.group('url'))
2443
2444 # Look for embedded Facebook player
2445 facebook_urls = FacebookIE._extract_urls(webpage)
2446 if facebook_urls:
2447 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2448
2449 # Look for embedded VK player
2450 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2451 if mobj is not None:
2452 return self.url_result(mobj.group('url'), 'VK')
2453
2454 # Look for embedded Odnoklassniki player
2455 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2456 if mobj is not None:
2457 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2458
2459 # Look for embedded ivi player
2460 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2461 if mobj is not None:
2462 return self.url_result(mobj.group('url'), 'Ivi')
2463
2464 # Look for embedded Huffington Post player
2465 mobj = re.search(
2466 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2467 if mobj is not None:
2468 return self.url_result(mobj.group('url'), 'HuffPost')
2469
2470 # Look for embed.ly
2471 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2472 if mobj is not None:
2473 return self.url_result(mobj.group('url'))
2474 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2475 if mobj is not None:
2476 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2477
2478 # Look for funnyordie embed
2479 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2480 if matches:
2481 return self.playlist_from_matches(
2482 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2483
2484 # Look for BBC iPlayer embed
2485 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2486 if matches:
2487 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2488
2489 # Look for embedded RUTV player
2490 rutv_url = RUTVIE._extract_url(webpage)
2491 if rutv_url:
2492 return self.url_result(rutv_url, 'RUTV')
2493
2494 # Look for embedded TVC player
2495 tvc_url = TVCIE._extract_url(webpage)
2496 if tvc_url:
2497 return self.url_result(tvc_url, 'TVC')
2498
2499 # Look for embedded SportBox player
2500 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2501 if sportbox_urls:
2502 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2503
2504 # Look for embedded XHamster player
2505 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2506 if xhamster_urls:
2507 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2508
2509 # Look for embedded TNAFlixNetwork player
2510 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2511 if tnaflix_urls:
2512 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2513
2514 # Look for embedded PornHub player
2515 pornhub_urls = PornHubIE._extract_urls(webpage)
2516 if pornhub_urls:
2517 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2518
2519 # Look for embedded DrTuber player
2520 drtuber_urls = DrTuberIE._extract_urls(webpage)
2521 if drtuber_urls:
2522 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2523
2524 # Look for embedded RedTube player
2525 redtube_urls = RedTubeIE._extract_urls(webpage)
2526 if redtube_urls:
2527 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2528
2529 # Look for embedded Tvigle player
2530 mobj = re.search(
2531 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'), 'Tvigle')
2534
2535 # Look for embedded TED player
2536 mobj = re.search(
2537 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2538 if mobj is not None:
2539 return self.url_result(mobj.group('url'), 'TED')
2540
2541 # Look for embedded Ustream videos
2542 ustream_url = UstreamIE._extract_url(webpage)
2543 if ustream_url:
2544 return self.url_result(ustream_url, UstreamIE.ie_key())
2545
2546 # Look for embedded arte.tv player
2547 mobj = re.search(
2548 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2549 webpage)
2550 if mobj is not None:
2551 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2552
2553 # Look for embedded francetv player
2554 mobj = re.search(
2555 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2556 webpage)
2557 if mobj is not None:
2558 return self.url_result(mobj.group('url'))
2559
2560 # Look for embedded smotri.com player
2561 smotri_url = SmotriIE._extract_url(webpage)
2562 if smotri_url:
2563 return self.url_result(smotri_url, 'Smotri')
2564
2565 # Look for embedded Myvi.ru player
2566 myvi_url = MyviIE._extract_url(webpage)
2567 if myvi_url:
2568 return self.url_result(myvi_url)
2569
2570 # Look for embedded soundcloud player
2571 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2572 if soundcloud_urls:
2573 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2574
2575 # Look for tunein player
2576 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2577 if tunein_urls:
2578 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2579
2580 # Look for embedded mtvservices player
2581 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2582 if mtvservices_url:
2583 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2584
2585 # Look for embedded yahoo player
2586 mobj = re.search(
2587 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2588 webpage)
2589 if mobj is not None:
2590 return self.url_result(mobj.group('url'), 'Yahoo')
2591
2592 # Look for embedded sbs.com.au player
2593 mobj = re.search(
2594 r'''(?x)
2595 (?:
2596 <meta\s+property="og:video"\s+content=|
2597 <iframe[^>]+?src=
2598 )
2599 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2600 webpage)
2601 if mobj is not None:
2602 return self.url_result(mobj.group('url'), 'SBS')
2603
2604 # Look for embedded Cinchcast player
2605 mobj = re.search(
2606 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2607 webpage)
2608 if mobj is not None:
2609 return self.url_result(mobj.group('url'), 'Cinchcast')
2610
2611 mobj = re.search(
2612 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2613 webpage)
2614 if not mobj:
2615 mobj = re.search(
2616 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2617 webpage)
2618 if mobj is not None:
2619 return self.url_result(mobj.group('url'), 'MLB')
2620
2621 mobj = re.search(
2622 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2623 webpage)
2624 if mobj is not None:
2625 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2626
2627 mobj = re.search(
2628 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2629 webpage)
2630 if mobj is not None:
2631 return self.url_result(mobj.group('url'), 'Livestream')
2632
2633 # Look for Zapiks embed
2634 mobj = re.search(
2635 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2636 if mobj is not None:
2637 return self.url_result(mobj.group('url'), 'Zapiks')
2638
2639 # Look for Kaltura embeds
2640 kaltura_url = KalturaIE._extract_url(webpage)
2641 if kaltura_url:
2642 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2643
2644 # Look for EaglePlatform embeds
2645 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2646 if eagleplatform_url:
2647 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2648
2649 # Look for ClipYou (uses EaglePlatform) embeds
2650 mobj = re.search(
2651 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2652 if mobj is not None:
2653 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2654
2655 # Look for Pladform embeds
2656 pladform_url = PladformIE._extract_url(webpage)
2657 if pladform_url:
2658 return self.url_result(pladform_url)
2659
2660 # Look for Videomore embeds
2661 videomore_url = VideomoreIE._extract_url(webpage)
2662 if videomore_url:
2663 return self.url_result(videomore_url)
2664
2665 # Look for Webcaster embeds
2666 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2667 if webcaster_url:
2668 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2669
2670 # Look for Playwire embeds
2671 mobj = re.search(
2672 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2673 if mobj is not None:
2674 return self.url_result(mobj.group('url'))
2675
2676 # Look for 5min embeds
2677 mobj = re.search(
2678 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2679 if mobj is not None:
2680 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2681
2682 # Look for Crooks and Liars embeds
2683 mobj = re.search(
2684 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2685 if mobj is not None:
2686 return self.url_result(mobj.group('url'))
2687
2688 # Look for NBC Sports VPlayer embeds
2689 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2690 if nbc_sports_url:
2691 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2692
2693 # Look for NBC News embeds
2694 nbc_news_embed_url = re.search(
2695 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2696 if nbc_news_embed_url:
2697 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2698
2699 # Look for Google Drive embeds
2700 google_drive_url = GoogleDriveIE._extract_url(webpage)
2701 if google_drive_url:
2702 return self.url_result(google_drive_url, 'GoogleDrive')
2703
2704 # Look for UDN embeds
2705 mobj = re.search(
2706 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2707 if mobj is not None:
2708 return self.url_result(
2709 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2710
2711 # Look for Senate ISVP iframe
2712 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2713 if senate_isvp_url:
2714 return self.url_result(senate_isvp_url, 'SenateISVP')
2715
2716 # Look for OnionStudios embeds
2717 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2718 if onionstudios_url:
2719 return self.url_result(onionstudios_url)
2720
2721 # Look for ViewLift embeds
2722 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2723 if viewlift_url:
2724 return self.url_result(viewlift_url)
2725
2726 # Look for JWPlatform embeds
2727 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2728 if jwplatform_urls:
2729 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2730
2731 # Look for Digiteka embeds
2732 digiteka_url = DigitekaIE._extract_url(webpage)
2733 if digiteka_url:
2734 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2735
2736 # Look for Arkena embeds
2737 arkena_url = ArkenaIE._extract_url(webpage)
2738 if arkena_url:
2739 return self.url_result(arkena_url, ArkenaIE.ie_key())
2740
2741 # Look for Piksel embeds
2742 piksel_url = PikselIE._extract_url(webpage)
2743 if piksel_url:
2744 return self.url_result(piksel_url, PikselIE.ie_key())
2745
2746 # Look for Limelight embeds
2747 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2748 if limelight_urls:
2749 return self.playlist_result(
2750 limelight_urls, video_id, video_title, video_description)
2751
2752 # Look for Anvato embeds
2753 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2754 if anvato_urls:
2755 return self.playlist_result(
2756 anvato_urls, video_id, video_title, video_description)
2757
2758 # Look for AdobeTVVideo embeds
2759 mobj = re.search(
2760 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2761 webpage)
2762 if mobj is not None:
2763 return self.url_result(
2764 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2765 'AdobeTVVideo')
2766
2767 # Look for Vine embeds
2768 mobj = re.search(
2769 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2770 webpage)
2771 if mobj is not None:
2772 return self.url_result(
2773 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2774
2775 # Look for VODPlatform embeds
2776 mobj = re.search(
2777 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2778 webpage)
2779 if mobj is not None:
2780 return self.url_result(
2781 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2782
2783 # Look for Mangomolo embeds
2784 mobj = re.search(
2785 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2786 (?:
2787 video\?.*?\bid=(?P<video_id>\d+)|
2788 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2789 ).+?)\1''', webpage)
2790 if mobj is not None:
2791 info = {
2792 '_type': 'url_transparent',
2793 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2794 'title': video_title,
2795 'description': video_description,
2796 'thumbnail': video_thumbnail,
2797 'uploader': video_uploader,
2798 }
2799 video_id = mobj.group('video_id')
2800 if video_id:
2801 info.update({
2802 'ie_key': 'MangomoloVideo',
2803 'id': video_id,
2804 })
2805 else:
2806 info.update({
2807 'ie_key': 'MangomoloLive',
2808 'id': mobj.group('channel_id'),
2809 })
2810 return info
2811
2812 # Look for Instagram embeds
2813 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2814 if instagram_embed_url is not None:
2815 return self.url_result(
2816 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2817
2818 # Look for LiveLeak embeds
2819 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2820 if liveleak_urls:
2821 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2822
2823 # Look for 3Q SDN embeds
2824 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2825 if threeqsdn_url:
2826 return {
2827 '_type': 'url_transparent',
2828 'ie_key': ThreeQSDNIE.ie_key(),
2829 'url': self._proto_relative_url(threeqsdn_url),
2830 'title': video_title,
2831 'description': video_description,
2832 'thumbnail': video_thumbnail,
2833 'uploader': video_uploader,
2834 }
2835
2836 # Look for VBOX7 embeds
2837 vbox7_url = Vbox7IE._extract_url(webpage)
2838 if vbox7_url:
2839 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2840
2841 # Look for DBTV embeds
2842 dbtv_urls = DBTVIE._extract_urls(webpage)
2843 if dbtv_urls:
2844 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2845
2846 # Look for Videa embeds
2847 videa_urls = VideaIE._extract_urls(webpage)
2848 if videa_urls:
2849 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2850
2851 # Look for 20 minuten embeds
2852 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2853 if twentymin_urls:
2854 return self.playlist_from_matches(
2855 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2856
2857 # Look for Openload embeds
2858 openload_urls = OpenloadIE._extract_urls(webpage)
2859 if openload_urls:
2860 return self.playlist_from_matches(
2861 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2862
2863 # Look for VideoPress embeds
2864 videopress_urls = VideoPressIE._extract_urls(webpage)
2865 if videopress_urls:
2866 return self.playlist_from_matches(
2867 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2868
2869 # Look for Rutube embeds
2870 rutube_urls = RutubeIE._extract_urls(webpage)
2871 if rutube_urls:
2872 return self.playlist_from_matches(
2873 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2874
2875 # Look for WashingtonPost embeds
2876 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2877 if wapo_urls:
2878 return self.playlist_from_matches(
2879 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2880
2881 # Look for Mediaset embeds
2882 mediaset_urls = MediasetIE._extract_urls(webpage)
2883 if mediaset_urls:
2884 return self.playlist_from_matches(
2885 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2886
2887 # Look for JOJ.sk embeds
2888 joj_urls = JojIE._extract_urls(webpage)
2889 if joj_urls:
2890 return self.playlist_from_matches(
2891 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2892
2893 # Look for megaphone.fm embeds
2894 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2895 if mpfn_urls:
2896 return self.playlist_from_matches(
2897 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2898
2899 # Look for vzaar embeds
2900 vzaar_urls = VzaarIE._extract_urls(webpage)
2901 if vzaar_urls:
2902 return self.playlist_from_matches(
2903 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2904
2905 channel9_urls = Channel9IE._extract_urls(webpage)
2906 if channel9_urls:
2907 return self.playlist_from_matches(
2908 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2909
2910 vshare_urls = VShareIE._extract_urls(webpage)
2911 if vshare_urls:
2912 return self.playlist_from_matches(
2913 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2914
2915 # Look for Mediasite embeds
2916 mediasite_urls = MediasiteIE._extract_urls(webpage)
2917 if mediasite_urls:
2918 entries = [
2919 self.url_result(smuggle_url(
2920 compat_urlparse.urljoin(url, mediasite_url),
2921 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2922 for mediasite_url in mediasite_urls]
2923 return self.playlist_result(entries, video_id, video_title)
2924
2925 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2926 if springboardplatform_urls:
2927 return self.playlist_from_matches(
2928 springboardplatform_urls, video_id, video_title,
2929 ie=SpringboardPlatformIE.ie_key())
2930
2931 def merge_dicts(dict1, dict2):
2932 merged = {}
2933 for k, v in dict1.items():
2934 if v is not None:
2935 merged[k] = v
2936 for k, v in dict2.items():
2937 if v is None:
2938 continue
2939 if (k not in merged or
2940 (isinstance(v, compat_str) and v and
2941 isinstance(merged[k], compat_str) and
2942 not merged[k])):
2943 merged[k] = v
2944 return merged
2945
2946 # Look for HTML5 media
2947 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2948 if entries:
2949 if len(entries) == 1:
2950 entries[0].update({
2951 'id': video_id,
2952 'title': video_title,
2953 })
2954 else:
2955 for num, entry in enumerate(entries, start=1):
2956 entry.update({
2957 'id': '%s-%s' % (video_id, num),
2958 'title': '%s (%d)' % (video_title, num),
2959 })
2960 for entry in entries:
2961 self._sort_formats(entry['formats'])
2962 return self.playlist_result(entries, video_id, video_title)
2963
2964 jwplayer_data = self._find_jwplayer_data(
2965 webpage, video_id, transform_source=js_to_json)
2966 if jwplayer_data:
2967 info = self._parse_jwplayer_data(
2968 jwplayer_data, video_id, require_title=False, base_url=url)
2969 return merge_dicts(info, info_dict)
2970
2971 # Video.js embed
2972 mobj = re.search(
2973 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2974 webpage)
2975 if mobj is not None:
2976 sources = self._parse_json(
2977 mobj.group(1), video_id, transform_source=js_to_json,
2978 fatal=False) or []
2979 if not isinstance(sources, list):
2980 sources = [sources]
2981 formats = []
2982 for source in sources:
2983 src = source.get('src')
2984 if not src or not isinstance(src, compat_str):
2985 continue
2986 src = compat_urlparse.urljoin(url, src)
2987 src_type = source.get('type')
2988 if isinstance(src_type, compat_str):
2989 src_type = src_type.lower()
2990 ext = determine_ext(src).lower()
2991 if src_type == 'video/youtube':
2992 return self.url_result(src, YoutubeIE.ie_key())
2993 if src_type == 'application/dash+xml' or ext == 'mpd':
2994 formats.extend(self._extract_mpd_formats(
2995 src, video_id, mpd_id='dash', fatal=False))
2996 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2997 formats.extend(self._extract_m3u8_formats(
2998 src, video_id, 'mp4', entry_protocol='m3u8_native',
2999 m3u8_id='hls', fatal=False))
3000 else:
3001 formats.append({
3002 'url': src,
3003 'ext': (mimetype2ext(src_type) or
3004 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3005 })
3006 if formats:
3007 self._sort_formats(formats)
3008 info_dict['formats'] = formats
3009 return info_dict
3010
3011 # Looking for http://schema.org/VideoObject
3012 json_ld = self._search_json_ld(
3013 webpage, video_id, default={}, expected_type='VideoObject')
3014 if json_ld.get('url'):
3015 return merge_dicts(json_ld, info_dict)
3016
3017 def check_video(vurl):
3018 if YoutubeIE.suitable(vurl):
3019 return True
3020 if RtmpIE.suitable(vurl):
3021 return True
3022 vpath = compat_urlparse.urlparse(vurl).path
3023 vext = determine_ext(vpath)
3024 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3025
3026 def filter_video(urls):
3027 return list(filter(check_video, urls))
3028
3029 # Start with something easy: JW Player in SWFObject
3030 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3031 if not found:
3032 # Look for gorilla-vid style embedding
3033 found = filter_video(re.findall(r'''(?sx)
3034 (?:
3035 jw_plugins|
3036 JWPlayerOptions|
3037 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3038 )
3039 .*?
3040 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3041 if not found:
3042 # Broaden the search a little bit
3043 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3044 if not found:
3045 # Broaden the findall a little bit: JWPlayer JS loader
3046 found = filter_video(re.findall(
3047 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3048 if not found:
3049 # Flow player
3050 found = filter_video(re.findall(r'''(?xs)
3051 flowplayer\("[^"]+",\s*
3052 \{[^}]+?\}\s*,
3053 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3054 ["']?url["']?\s*:\s*["']([^"']+)["']
3055 ''', webpage))
3056 if not found:
3057 # Cinerama player
3058 found = re.findall(
3059 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3060 if not found:
3061 # Try to find twitter cards info
3062 # twitter:player:stream should be checked before twitter:player since
3063 # it is expected to contain a raw stream (see
3064 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3065 found = filter_video(re.findall(
3066 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3067 if not found:
3068 # We look for Open Graph info:
3069 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3070 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3071 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3072 if m_video_type is not None:
3073 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3074 if not found:
3075 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3076 found = re.search(
3077 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3078 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3079 webpage)
3080 if not found:
3081 # Look also in Refresh HTTP header
3082 refresh_header = head_response.headers.get('Refresh')
3083 if refresh_header:
3084 # In python 2 response HTTP headers are bytestrings
3085 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3086 refresh_header = refresh_header.decode('iso-8859-1')
3087 found = re.search(REDIRECT_REGEX, refresh_header)
3088 if found:
3089 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3090 if new_url != url:
3091 self.report_following_redirect(new_url)
3092 return {
3093 '_type': 'url',
3094 'url': new_url,
3095 }
3096 else:
3097 found = None
3098
3099 if not found:
3100 # twitter:player is a https URL to iframe player that may or may not
3101 # be supported by youtube-dl thus this is checked the very last (see
3102 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3103 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3104 if embed_url and embed_url != url:
3105 return self.url_result(embed_url)
3106
3107 if not found:
3108 raise UnsupportedError(url)
3109
3110 entries = []
3111 for video_url in orderedSet(found):
3112 video_url = unescapeHTML(video_url)
3113 video_url = video_url.replace('\\/', '/')
3114 video_url = compat_urlparse.urljoin(url, video_url)
3115 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3116
3117 # Sometimes, jwplayer extraction will result in a YouTube URL
3118 if YoutubeIE.suitable(video_url):
3119 entries.append(self.url_result(video_url, 'Youtube'))
3120 continue
3121
3122 # here's a fun little line of code for you:
3123 video_id = os.path.splitext(video_id)[0]
3124
3125 entry_info_dict = {
3126 'id': video_id,
3127 'uploader': video_uploader,
3128 'title': video_title,
3129 'age_limit': age_limit,
3130 }
3131
3132 if RtmpIE.suitable(video_url):
3133 entry_info_dict.update({
3134 '_type': 'url_transparent',
3135 'ie_key': RtmpIE.ie_key(),
3136 'url': video_url,
3137 })
3138 entries.append(entry_info_dict)
3139 continue
3140
3141 ext = determine_ext(video_url)
3142 if ext == 'smil':
3143 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3144 elif ext == 'xspf':
3145 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3146 elif ext == 'm3u8':
3147 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3148 elif ext == 'mpd':
3149 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3150 elif ext == 'f4m':
3151 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3152 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3153 # Just matching .ism/manifest is not enough to be reliably sure
3154 # whether it's actually an ISM manifest or some other streaming
3155 # manifest since there are various streaming URL formats
3156 # possible (see [1]) as well as some other shenanigans like
3157 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3158 # so on.
3159 # Thus the most reasonable way to solve this is to delegate
3160 # to generic extractor in order to look into the contents of
3161 # the manifest itself.
3162 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3163 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3164 entry_info_dict = self.url_result(
3165 smuggle_url(video_url, {'to_generic': True}),
3166 GenericIE.ie_key())
3167 else:
3168 entry_info_dict['url'] = video_url
3169
3170 if entry_info_dict.get('formats'):
3171 self._sort_formats(entry_info_dict['formats'])
3172
3173 entries.append(entry_info_dict)
3174
3175 if len(entries) == 1:
3176 return entries[0]
3177 else:
3178 for num, e in enumerate(entries, start=1):
3179 # 'url' results don't have a title
3180 if e.get('title') is not None:
3181 e['title'] = '%s (%d)' % (e['title'], num)
3182 return {
3183 '_type': 'playlist',
3184 'entries': entries,
3185 }
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...