]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
cc4c90b8cef194952e1b7d7517d6036329eb1c79
[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
105
106 class GenericIE(InfoExtractor):
107 IE_DESC = 'Generic downloader that works on some sites'
108 _VALID_URL = r'.*'
109 IE_NAME = 'generic'
110 _TESTS = [
111 # Direct link to a video
112 {
113 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
114 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
115 'info_dict': {
116 'id': 'trailer',
117 'ext': 'mp4',
118 'title': 'trailer',
119 'upload_date': '20100513',
120 }
121 },
122 # Direct link to media delivered compressed (until Accept-Encoding is *)
123 {
124 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
125 'md5': '128c42e68b13950268b648275386fc74',
126 'info_dict': {
127 'id': 'FictionJunction-Parallel_Hearts',
128 'ext': 'flac',
129 'title': 'FictionJunction-Parallel_Hearts',
130 'upload_date': '20140522',
131 },
132 'expected_warnings': [
133 'URL could be a direct video link, returning it as such.'
134 ],
135 'skip': 'URL invalid',
136 },
137 # Direct download with broken HEAD
138 {
139 'url': 'http://ai-radio.org:8000/radio.opus',
140 'info_dict': {
141 'id': 'radio',
142 'ext': 'opus',
143 'title': 'radio',
144 },
145 'params': {
146 'skip_download': True, # infinite live stream
147 },
148 'expected_warnings': [
149 r'501.*Not Implemented',
150 r'400.*Bad Request',
151 ],
152 },
153 # Direct link with incorrect MIME type
154 {
155 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
156 'md5': '4ccbebe5f36706d85221f204d7eb5913',
157 'info_dict': {
158 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
159 'id': '5_Lennart_Poettering_-_Systemd',
160 'ext': 'webm',
161 'title': '5_Lennart_Poettering_-_Systemd',
162 'upload_date': '20141120',
163 },
164 'expected_warnings': [
165 'URL could be a direct video link, returning it as such.'
166 ]
167 },
168 # RSS feed
169 {
170 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'info_dict': {
172 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
173 'title': 'Zero Punctuation',
174 'description': 're:.*groundbreaking video review series.*'
175 },
176 'playlist_mincount': 11,
177 },
178 # RSS feed with enclosure
179 {
180 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
181 'info_dict': {
182 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
183 'ext': 'm4v',
184 'upload_date': '20150228',
185 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 }
187 },
188 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
189 {
190 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
191 'info_dict': {
192 'id': 'smil',
193 'ext': 'mp4',
194 'title': 'Automatics, robotics and biocybernetics',
195 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
196 'upload_date': '20130627',
197 'formats': 'mincount:16',
198 'subtitles': 'mincount:1',
199 },
200 'params': {
201 'force_generic_extractor': True,
202 'skip_download': True,
203 },
204 },
205 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
206 {
207 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
208 'info_dict': {
209 'id': 'hds',
210 'ext': 'flv',
211 'title': 'hds',
212 'formats': 'mincount:1',
213 },
214 'params': {
215 'skip_download': True,
216 },
217 },
218 # SMIL from https://www.restudy.dk/video/play/id/1637
219 {
220 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
221 'info_dict': {
222 'id': 'video_1637',
223 'ext': 'flv',
224 'title': 'video_1637',
225 'formats': 'mincount:3',
226 },
227 'params': {
228 'skip_download': True,
229 },
230 },
231 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
232 {
233 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
234 'info_dict': {
235 'id': 'smil-service',
236 'ext': 'flv',
237 'title': 'smil-service',
238 'formats': 'mincount:1',
239 },
240 'params': {
241 'skip_download': True,
242 },
243 },
244 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
245 {
246 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
247 'info_dict': {
248 'id': '4719370',
249 'ext': 'mp4',
250 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
251 'formats': 'mincount:3',
252 },
253 'params': {
254 'skip_download': True,
255 },
256 },
257 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
258 {
259 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
260 'info_dict': {
261 'id': 'mZlp2ctYIUEB',
262 'ext': 'mp4',
263 'title': 'Tikibad ontruimd wegens brand',
264 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
265 'thumbnail': r're:^https?://.*\.jpg$',
266 'duration': 33,
267 },
268 'params': {
269 'skip_download': True,
270 },
271 },
272 # MPD from http://dash-mse-test.appspot.com/media.html
273 {
274 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
275 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
276 'info_dict': {
277 'id': 'car-20120827-manifest',
278 'ext': 'mp4',
279 'title': 'car-20120827-manifest',
280 'formats': 'mincount:9',
281 'upload_date': '20130904',
282 },
283 'params': {
284 'format': 'bestvideo',
285 },
286 },
287 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
288 {
289 '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',
290 'info_dict': {
291 'id': 'content',
292 'ext': 'mp4',
293 'title': 'content',
294 'formats': 'mincount:8',
295 },
296 'params': {
297 # m3u8 downloads
298 'skip_download': True,
299 },
300 'skip': 'video gone',
301 },
302 # m3u8 served with Content-Type: text/plain
303 {
304 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
305 'info_dict': {
306 'id': 'index',
307 'ext': 'mp4',
308 'title': 'index',
309 'upload_date': '20140720',
310 'formats': 'mincount:11',
311 },
312 'params': {
313 # m3u8 downloads
314 'skip_download': True,
315 },
316 'skip': 'video gone',
317 },
318 # google redirect
319 {
320 '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',
321 'info_dict': {
322 'id': 'cmQHVoWB5FY',
323 'ext': 'mp4',
324 'upload_date': '20130224',
325 'uploader_id': 'TheVerge',
326 'description': r're:^Chris Ziegler takes a look at the\.*',
327 'uploader': 'The Verge',
328 'title': 'First Firefox OS phones side-by-side',
329 },
330 'params': {
331 'skip_download': False,
332 }
333 },
334 {
335 # redirect in Refresh HTTP header
336 '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',
337 'info_dict': {
338 'id': 'pO8h3EaFRdo',
339 'ext': 'mp4',
340 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
341 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
342 'upload_date': '20150917',
343 'uploader_id': 'brtvofficial',
344 'uploader': 'Boiler Room',
345 },
346 'params': {
347 'skip_download': False,
348 },
349 },
350 {
351 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
352 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
353 'info_dict': {
354 'id': '13601338388002',
355 'ext': 'mp4',
356 'uploader': 'www.hodiho.fr',
357 'title': 'R\u00e9gis plante sa Jeep',
358 }
359 },
360 # bandcamp page with custom domain
361 {
362 'add_ie': ['Bandcamp'],
363 'url': 'http://bronyrock.com/track/the-pony-mash',
364 'info_dict': {
365 'id': '3235767654',
366 'ext': 'mp3',
367 'title': 'The Pony Mash',
368 'uploader': 'M_Pallante',
369 },
370 'skip': 'There is a limit of 200 free downloads / month for the test song',
371 },
372 {
373 # embedded brightcove video
374 # it also tests brightcove videos that need to set the 'Referer'
375 # in the http requests
376 'add_ie': ['BrightcoveLegacy'],
377 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
378 'info_dict': {
379 'id': '2765128793001',
380 'ext': 'mp4',
381 'title': 'Le cours de bourse : lā€™analyse technique',
382 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
383 'uploader': 'BFM BUSINESS',
384 },
385 'params': {
386 'skip_download': True,
387 },
388 },
389 {
390 # embedded with itemprop embedURL and video id spelled as `idVideo`
391 'add_id': ['BrightcoveLegacy'],
392 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
393 'info_dict': {
394 'id': '5255628253001',
395 'ext': 'mp4',
396 'title': 'md5:37c519b1128915607601e75a87995fc0',
397 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
398 'uploader': 'BFM BUSINESS',
399 'uploader_id': '876450612001',
400 'timestamp': 1482255315,
401 'upload_date': '20161220',
402 },
403 'params': {
404 'skip_download': True,
405 },
406 },
407 {
408 # https://github.com/rg3/youtube-dl/issues/2253
409 'url': 'http://bcove.me/i6nfkrc3',
410 'md5': '0ba9446db037002366bab3b3eb30c88c',
411 'info_dict': {
412 'id': '3101154703001',
413 'ext': 'mp4',
414 'title': 'Still no power',
415 'uploader': 'thestar.com',
416 '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.',
417 },
418 'add_ie': ['BrightcoveLegacy'],
419 'skip': 'video gone',
420 },
421 {
422 'url': 'http://www.championat.com/video/football/v/87/87499.html',
423 'md5': 'fb973ecf6e4a78a67453647444222983',
424 'info_dict': {
425 'id': '3414141473001',
426 'ext': 'mp4',
427 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
428 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
429 'uploader': 'Championat',
430 },
431 },
432 {
433 # https://github.com/rg3/youtube-dl/issues/3541
434 'add_ie': ['BrightcoveLegacy'],
435 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
436 'info_dict': {
437 'id': '3866516442001',
438 'ext': 'mp4',
439 'title': 'Leer mij vrouwen kennen: Aflevering 1',
440 'description': 'Leer mij vrouwen kennen: Aflevering 1',
441 'uploader': 'SBS Broadcasting',
442 },
443 'skip': 'Restricted to Netherlands',
444 'params': {
445 'skip_download': True, # m3u8 download
446 },
447 },
448 {
449 # Brightcove video in <iframe>
450 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
451 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
452 'info_dict': {
453 'id': '5360463607001',
454 'ext': 'mp4',
455 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
456 '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€‚',
457 'uploader': 'United Nations',
458 'uploader_id': '1362235914001',
459 'timestamp': 1489593889,
460 'upload_date': '20170315',
461 },
462 'add_ie': ['BrightcoveLegacy'],
463 },
464 {
465 # Brightcove with alternative playerID key
466 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
467 'info_dict': {
468 'id': 'nmeth.2062_SV1',
469 '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',
470 },
471 'playlist': [{
472 'info_dict': {
473 'id': '2228375078001',
474 'ext': 'mp4',
475 'title': 'nmeth.2062-sv1',
476 'description': 'nmeth.2062-sv1',
477 'timestamp': 1363357591,
478 'upload_date': '20130315',
479 'uploader': 'Nature Publishing Group',
480 'uploader_id': '1964492299001',
481 },
482 }],
483 },
484 {
485 # Brightcove with UUID in videoPlayer
486 'url': 'http://www8.hp.com/cn/zh/home.html',
487 'info_dict': {
488 'id': '5255815316001',
489 'ext': 'mp4',
490 'title': 'Sprocket Video - China',
491 'description': 'Sprocket Video - China',
492 'uploader': 'HP-Video Gallery',
493 'timestamp': 1482263210,
494 'upload_date': '20161220',
495 'uploader_id': '1107601872001',
496 },
497 'params': {
498 'skip_download': True, # m3u8 download
499 },
500 'skip': 'video rotates...weekly?',
501 },
502 {
503 # Brightcove:new type [2].
504 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
505 'md5': '2b35148fcf48da41c9fb4591650784f3',
506 'info_dict': {
507 'id': '5348741021001',
508 'ext': 'mp4',
509 'upload_date': '20170306',
510 'uploader_id': '4191638492001',
511 'timestamp': 1488769918,
512 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
513
514 },
515 },
516 {
517 # Alternative brightcove <video> attributes
518 '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/',
519 'info_dict': {
520 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
521 '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",
522 },
523 'playlist': [{
524 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
525 'info_dict': {
526 'id': '5311302538001',
527 'ext': 'mp4',
528 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
529 '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)",
530 'timestamp': 1486321708,
531 'upload_date': '20170205',
532 'uploader_id': '800000640001',
533 },
534 'only_matching': True,
535 }],
536 },
537 {
538 # Brightcove with UUID in videoPlayer
539 'url': 'http://www8.hp.com/cn/zh/home.html',
540 'info_dict': {
541 'id': '5255815316001',
542 'ext': 'mp4',
543 'title': 'Sprocket Video - China',
544 'description': 'Sprocket Video - China',
545 'uploader': 'HP-Video Gallery',
546 'timestamp': 1482263210,
547 'upload_date': '20161220',
548 'uploader_id': '1107601872001',
549 },
550 'params': {
551 'skip_download': True, # m3u8 download
552 },
553 },
554 # ooyala video
555 {
556 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
557 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
558 'info_dict': {
559 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
560 'ext': 'mp4',
561 'title': '2cc213299525360.mov', # that's what we get
562 'duration': 238.231,
563 },
564 'add_ie': ['Ooyala'],
565 },
566 {
567 # ooyala video embedded with http://player.ooyala.com/iframe.js
568 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
569 'info_dict': {
570 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
571 'ext': 'mp4',
572 'title': '"Steve Jobs: Man in the Machine" trailer',
573 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
574 'duration': 135.427,
575 },
576 'params': {
577 'skip_download': True,
578 },
579 'skip': 'movie expired',
580 },
581 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
582 {
583 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
584 'info_dict': {
585 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
586 'ext': 'mp4',
587 'title': 'Steampunk Fest Comes to Honesdale',
588 'duration': 43.276,
589 },
590 'params': {
591 'skip_download': True,
592 }
593 },
594 # embed.ly video
595 {
596 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
597 'info_dict': {
598 'id': '9ODmcdjQcHQ',
599 'ext': 'mp4',
600 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
601 'upload_date': '20140225',
602 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
603 'uploader': 'Tested',
604 'uploader_id': 'testedcom',
605 },
606 # No need to test YoutubeIE here
607 'params': {
608 'skip_download': True,
609 },
610 },
611 # funnyordie embed
612 {
613 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
614 'info_dict': {
615 'id': '18e820ec3f',
616 'ext': 'mp4',
617 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
618 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
619 },
620 # HEAD requests lead to endless 301, while GET is OK
621 'expected_warnings': ['301'],
622 },
623 # RUTV embed
624 {
625 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
626 'info_dict': {
627 'id': '776940',
628 'ext': 'mp4',
629 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
630 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
631 },
632 'params': {
633 # m3u8 download
634 'skip_download': True,
635 },
636 },
637 # TVC embed
638 {
639 '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/',
640 'info_dict': {
641 'id': '55304',
642 'ext': 'mp4',
643 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
644 },
645 },
646 # SportBox embed
647 {
648 'url': 'http://www.vestifinance.ru/articles/25753',
649 'info_dict': {
650 'id': '25753',
651 '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"',
652 },
653 'playlist': [{
654 'info_dict': {
655 'id': '370908',
656 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
657 'ext': 'mp4',
658 }
659 }, {
660 'info_dict': {
661 'id': '370905',
662 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
663 'ext': 'mp4',
664 }
665 }, {
666 'info_dict': {
667 'id': '370902',
668 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
669 'ext': 'mp4',
670 }
671 }],
672 'params': {
673 # m3u8 download
674 'skip_download': True,
675 },
676 },
677 # Myvi.ru embed
678 {
679 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
680 'info_dict': {
681 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
682 'ext': 'mp4',
683 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
684 'thumbnail': r're:^https?://.*\.jpg$',
685 'duration': 153,
686 }
687 },
688 # XHamster embed
689 {
690 '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',
691 'info_dict': {
692 'id': 'showthread',
693 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
694 },
695 'playlist_mincount': 7,
696 # This forum does not allow <iframe> syntaxes anymore
697 # Now HTML tags are displayed as-is
698 'skip': 'No videos on this page',
699 },
700 # Embedded TED video
701 {
702 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
703 'md5': '65fdff94098e4a607385a60c5177c638',
704 'info_dict': {
705 'id': '1969',
706 'ext': 'mp4',
707 'title': 'Hidden miracles of the natural world',
708 'uploader': 'Louie Schwartzberg',
709 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
710 }
711 },
712 # nowvideo embed hidden behind percent encoding
713 {
714 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
715 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
716 'info_dict': {
717 'id': '06e53103ca9aa',
718 'ext': 'flv',
719 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
720 'description': 'No description',
721 },
722 },
723 # arte embed
724 {
725 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
726 'md5': '7653032cbb25bf6c80d80f217055fa43',
727 'info_dict': {
728 'id': '048195-004_PLUS7-F',
729 'ext': 'flv',
730 'title': 'X:enius',
731 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
732 'upload_date': '20140320',
733 },
734 'params': {
735 'skip_download': 'Requires rtmpdump'
736 },
737 'skip': 'video gone',
738 },
739 # francetv embed
740 {
741 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
742 'info_dict': {
743 'id': 'EV_30231',
744 'ext': 'mp4',
745 'title': 'Alcaline, le concert avec Calogero',
746 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
747 'upload_date': '20150226',
748 'timestamp': 1424989860,
749 'duration': 5400,
750 },
751 'params': {
752 # m3u8 downloads
753 'skip_download': True,
754 },
755 'expected_warnings': [
756 'Forbidden'
757 ]
758 },
759 # CondƩ Nast embed
760 {
761 'url': 'http://www.wired.com/2014/04/honda-asimo/',
762 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
763 'info_dict': {
764 'id': '53501be369702d3275860000',
765 'ext': 'mp4',
766 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
767 }
768 },
769 # Dailymotion embed
770 {
771 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
772 'md5': '441aeeb82eb72c422c7f14ec533999cd',
773 'info_dict': {
774 'id': 'k2mm4bCdJ6CQ2i7c8o2',
775 'ext': 'mp4',
776 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
777 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
778 'uploader': 'Spi0n',
779 'uploader_id': 'xgditw',
780 'upload_date': '20140425',
781 'timestamp': 1398441542,
782 },
783 'add_ie': ['Dailymotion'],
784 },
785 # DailyMail embed
786 {
787 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
788 'info_dict': {
789 'id': '1495629',
790 'ext': 'mp4',
791 'title': 'Care worker punches elderly dementia patient in head 11 times',
792 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
793 },
794 'add_ie': ['DailyMail'],
795 'params': {
796 'skip_download': True,
797 },
798 },
799 # YouTube embed
800 {
801 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
802 'info_dict': {
803 'id': 'FXRb4ykk4S0',
804 'ext': 'mp4',
805 'title': 'The NBL Auction 2014',
806 'uploader': 'BADMINTON England',
807 'uploader_id': 'BADMINTONEvents',
808 'upload_date': '20140603',
809 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
810 },
811 'add_ie': ['Youtube'],
812 'params': {
813 'skip_download': True,
814 }
815 },
816 # MTVSercices embed
817 {
818 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
819 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
820 'info_dict': {
821 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
822 'ext': 'mp4',
823 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
824 'description': 'Two valets share their love for movie star Liam Neesons.',
825 'timestamp': 1349922600,
826 'upload_date': '20121011',
827 },
828 },
829 # YouTube embed via <data-embed-url="">
830 {
831 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
832 'info_dict': {
833 'id': '4vAffPZIT44',
834 'ext': 'mp4',
835 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
836 'uploader': 'Gameloft',
837 'uploader_id': 'gameloft',
838 'upload_date': '20140828',
839 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
840 },
841 'params': {
842 'skip_download': True,
843 }
844 },
845 # YouTube <object> embed
846 {
847 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
848 'md5': '516718101ec834f74318df76259fb3cc',
849 'info_dict': {
850 'id': 'msN87y-iEx0',
851 'ext': 'webm',
852 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
853 'upload_date': '20080526',
854 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
855 'uploader': 'Christopher Sykes',
856 'uploader_id': 'ChristopherJSykes',
857 },
858 'add_ie': ['Youtube'],
859 },
860 # Camtasia studio
861 {
862 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
863 'playlist': [{
864 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
865 'info_dict': {
866 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
867 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
868 'ext': 'flv',
869 'duration': 2235.90,
870 }
871 }, {
872 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
873 'info_dict': {
874 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
875 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
876 'ext': 'flv',
877 'duration': 2235.93,
878 }
879 }],
880 'info_dict': {
881 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
882 }
883 },
884 # Flowplayer
885 {
886 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
887 'md5': '9d65602bf31c6e20014319c7d07fba27',
888 'info_dict': {
889 'id': '5123ea6d5e5a7',
890 'ext': 'mp4',
891 'age_limit': 18,
892 'uploader': 'www.handjobhub.com',
893 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
894 }
895 },
896 # Multiple brightcove videos
897 # https://github.com/rg3/youtube-dl/issues/2283
898 {
899 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
900 'info_dict': {
901 'id': 'always-never',
902 'title': 'Always / Never - The New Yorker',
903 },
904 'playlist_count': 3,
905 'params': {
906 'extract_flat': False,
907 'skip_download': True,
908 }
909 },
910 # MLB embed
911 {
912 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
913 'md5': '96f09a37e44da40dd083e12d9a683327',
914 'info_dict': {
915 'id': '33322633',
916 'ext': 'mp4',
917 'title': 'Ump changes call to ball',
918 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
919 'duration': 48,
920 'timestamp': 1401537900,
921 'upload_date': '20140531',
922 'thumbnail': r're:^https?://.*\.jpg$',
923 },
924 },
925 # Wistia embed
926 {
927 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
928 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
929 'info_dict': {
930 'id': '6e2wtrbdaf',
931 'ext': 'mov',
932 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
933 'description': 'a Paywall Videos video from Remilon',
934 'duration': 644.072,
935 'uploader': 'study.com',
936 'timestamp': 1459678540,
937 'upload_date': '20160403',
938 'filesize': 24687186,
939 },
940 },
941 {
942 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
943 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
944 'info_dict': {
945 'id': 'uxjb0lwrcz',
946 'ext': 'mp4',
947 'title': 'Conversation about Hexagonal Rails Part 1',
948 'description': 'a Martin Fowler video from ThoughtWorks',
949 'duration': 1715.0,
950 'uploader': 'thoughtworks.wistia.com',
951 'timestamp': 1401832161,
952 'upload_date': '20140603',
953 },
954 },
955 # Wistia standard embed (async)
956 {
957 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
958 'info_dict': {
959 'id': '807fafadvk',
960 'ext': 'mp4',
961 'title': 'Drip Brennan Dunn Workshop',
962 'description': 'a JV Webinars video from getdrip-1',
963 'duration': 4986.95,
964 'timestamp': 1463607249,
965 'upload_date': '20160518',
966 },
967 'params': {
968 'skip_download': True,
969 }
970 },
971 # Soundcloud embed
972 {
973 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
974 'info_dict': {
975 'id': '174391317',
976 'ext': 'mp3',
977 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
978 'uploader': 'Sophos Security',
979 'title': 'Chet Chat 171 - Oct 29, 2014',
980 'upload_date': '20141029',
981 }
982 },
983 # Soundcloud multiple embeds
984 {
985 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
986 'info_dict': {
987 'id': '52809',
988 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
989 },
990 'playlist_mincount': 7,
991 },
992 # TuneIn station embed
993 {
994 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
995 'info_dict': {
996 'id': '204146',
997 'ext': 'mp3',
998 'title': 'CNRV',
999 'location': 'Paris, France',
1000 'is_live': True,
1001 },
1002 'params': {
1003 # Live stream
1004 'skip_download': True,
1005 },
1006 },
1007 # Livestream embed
1008 {
1009 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1010 'info_dict': {
1011 'id': '67864563',
1012 'ext': 'flv',
1013 'upload_date': '20141112',
1014 'title': 'Rosetta #CometLanding webcast HL 10',
1015 }
1016 },
1017 # Another Livestream embed, without 'new.' in URL
1018 {
1019 'url': 'https://www.freespeech.org/',
1020 'info_dict': {
1021 'id': '123537347',
1022 'ext': 'mp4',
1023 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1024 },
1025 'params': {
1026 # Live stream
1027 'skip_download': True,
1028 },
1029 },
1030 # LazyYT
1031 {
1032 'url': 'https://skiplagged.com/',
1033 'info_dict': {
1034 'id': 'skiplagged',
1035 'title': 'Skiplagged: The smart way to find cheap flights',
1036 },
1037 'playlist_mincount': 1,
1038 'add_ie': ['Youtube'],
1039 },
1040 # Cinchcast embed
1041 {
1042 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1043 'info_dict': {
1044 'id': '7141703',
1045 'ext': 'mp3',
1046 'upload_date': '20141126',
1047 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1048 }
1049 },
1050 # Cinerama player
1051 {
1052 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1053 'info_dict': {
1054 'id': '730m_DandD_1901_512k',
1055 'ext': 'mp4',
1056 'uploader': 'www.abc.net.au',
1057 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1058 }
1059 },
1060 # embedded viddler video
1061 {
1062 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1063 'info_dict': {
1064 'id': '4d03aad9',
1065 'ext': 'mp4',
1066 'uploader': 'deadspin',
1067 'title': 'WALL-TO-GORTAT',
1068 'timestamp': 1422285291,
1069 'upload_date': '20150126',
1070 },
1071 'add_ie': ['Viddler'],
1072 },
1073 # Libsyn embed
1074 {
1075 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1076 'info_dict': {
1077 'id': '3377616',
1078 'ext': 'mp3',
1079 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1080 'description': 'md5:601cb790edd05908957dae8aaa866465',
1081 'upload_date': '20150220',
1082 },
1083 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1084 },
1085 # jwplayer YouTube
1086 {
1087 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1088 'info_dict': {
1089 'id': 'Mrj4DVp2zeA',
1090 'ext': 'mp4',
1091 'upload_date': '20150212',
1092 'uploader': 'The National Archives UK',
1093 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1094 'uploader_id': 'NationalArchives08',
1095 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1096 },
1097 },
1098 # jwplayer rtmp
1099 {
1100 'url': 'http://www.suffolk.edu/sjc/live.php',
1101 'info_dict': {
1102 'id': 'live',
1103 'ext': 'flv',
1104 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1105 'uploader': 'www.suffolk.edu',
1106 },
1107 'params': {
1108 'skip_download': True,
1109 },
1110 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1111 },
1112 # Complex jwplayer
1113 {
1114 'url': 'http://www.indiedb.com/games/king-machine/videos',
1115 'info_dict': {
1116 'id': 'videos',
1117 'ext': 'mp4',
1118 'title': 'king machine trailer 1',
1119 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1120 'thumbnail': r're:^https?://.*\.jpg$',
1121 },
1122 },
1123 {
1124 # JWPlayer config passed as variable
1125 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1126 'info_dict': {
1127 'id': '3326530_hq',
1128 'ext': 'mp4',
1129 'title': 'ARIELE | Tube Cup',
1130 'uploader': 'www.txxx.com',
1131 'age_limit': 18,
1132 },
1133 'params': {
1134 'skip_download': True,
1135 }
1136 },
1137 {
1138 # JWPlatform iframe
1139 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1140 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1141 'info_dict': {
1142 'id': 'O0c5JcKT',
1143 'ext': 'mp4',
1144 'upload_date': '20171122',
1145 'timestamp': 1511366290,
1146 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1147 },
1148 'add_ie': [JWPlatformIE.ie_key()],
1149 },
1150 {
1151 # Video.js embed, multiple formats
1152 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1153 'info_dict': {
1154 'id': 'yygqldloqIk',
1155 'ext': 'mp4',
1156 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1157 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1158 'upload_date': '20130314',
1159 'uploader': 'PROстŠ¾Šµ3D',
1160 'uploader_id': 'PROstoe3D',
1161 },
1162 'params': {
1163 'skip_download': True,
1164 },
1165 },
1166 {
1167 # Video.js embed, single format
1168 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1169 'info_dict': {
1170 'id': 'watch',
1171 'ext': 'mp4',
1172 'title': 'Step 1 - Good Foundation',
1173 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1174 },
1175 'params': {
1176 'skip_download': True,
1177 },
1178 },
1179 # rtl.nl embed
1180 {
1181 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1182 'playlist_mincount': 5,
1183 'info_dict': {
1184 'id': 'aanslagen-kopenhagen',
1185 'title': 'Aanslagen Kopenhagen',
1186 }
1187 },
1188 # Zapiks embed
1189 {
1190 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1191 'info_dict': {
1192 'id': '118046',
1193 'ext': 'mp4',
1194 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1195 }
1196 },
1197 # Kaltura embed (different embed code)
1198 {
1199 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1200 'info_dict': {
1201 'id': '1_a52wc67y',
1202 'ext': 'flv',
1203 'upload_date': '20150127',
1204 'uploader_id': 'PremierMedia',
1205 'timestamp': int,
1206 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1207 },
1208 },
1209 # Kaltura embed with single quotes
1210 {
1211 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1212 'info_dict': {
1213 'id': '0_izeg5utt',
1214 'ext': 'mp4',
1215 'title': '35871',
1216 'timestamp': 1355743100,
1217 'upload_date': '20121217',
1218 'uploader_id': 'batchUser',
1219 },
1220 'add_ie': ['Kaltura'],
1221 },
1222 {
1223 # Kaltura embedded via quoted entry_id
1224 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1225 'info_dict': {
1226 'id': '0_utuok90b',
1227 'ext': 'mp4',
1228 'title': '06_matthew_brender_raj_dutt',
1229 'timestamp': 1466638791,
1230 'upload_date': '20160622',
1231 },
1232 'add_ie': ['Kaltura'],
1233 'expected_warnings': [
1234 'Could not send HEAD request'
1235 ],
1236 'params': {
1237 'skip_download': True,
1238 }
1239 },
1240 {
1241 # Kaltura embedded, some fileExt broken (#11480)
1242 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1243 'info_dict': {
1244 'id': '1_sgtvehim',
1245 'ext': 'mp4',
1246 'title': 'Our "Standard Models" of particle physics and cosmology',
1247 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1248 'timestamp': 1321158993,
1249 'upload_date': '20111113',
1250 'uploader_id': 'kps1',
1251 },
1252 'add_ie': ['Kaltura'],
1253 },
1254 {
1255 # Kaltura iframe embed
1256 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1257 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1258 'info_dict': {
1259 'id': '0_f2cfbpwy',
1260 'ext': 'mp4',
1261 'title': 'I. M. Pei: A Centennial Celebration',
1262 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1263 'upload_date': '20170403',
1264 'uploader_id': 'batchUser',
1265 'timestamp': 1491232186,
1266 },
1267 'add_ie': ['Kaltura'],
1268 },
1269 # EaglePlatform embed (generic URL)
1270 {
1271 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1272 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1273 'info_dict': {
1274 'id': '227304',
1275 'ext': 'mp4',
1276 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1277 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1278 'thumbnail': r're:^https?://.*\.jpg$',
1279 'duration': 87,
1280 'view_count': int,
1281 'age_limit': 0,
1282 },
1283 'params': {
1284 'skip_download': True,
1285 },
1286 },
1287 # referrer protected EaglePlatform embed
1288 {
1289 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1290 'info_dict': {
1291 'id': '582306',
1292 'ext': 'mp4',
1293 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1294 'thumbnail': r're:^https?://.*\.jpg$',
1295 'duration': 3382,
1296 'view_count': int,
1297 },
1298 'params': {
1299 'skip_download': True,
1300 },
1301 },
1302 # ClipYou (EaglePlatform) embed (custom URL)
1303 {
1304 'url': 'http://muz-tv.ru/play/7129/',
1305 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1306 'info_dict': {
1307 'id': '12820',
1308 'ext': 'mp4',
1309 'title': "'O Sole Mio",
1310 'thumbnail': r're:^https?://.*\.jpg$',
1311 'duration': 216,
1312 'view_count': int,
1313 },
1314 'params': {
1315 'skip_download': True,
1316 },
1317 'skip': 'This video is unavailable.',
1318 },
1319 # Pladform embed
1320 {
1321 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1322 'info_dict': {
1323 'id': '100183293',
1324 'ext': 'mp4',
1325 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1326 '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°',
1327 'thumbnail': r're:^https?://.*\.jpg$',
1328 'duration': 694,
1329 'age_limit': 0,
1330 },
1331 'skip': 'HTTP Error 404: Not Found',
1332 },
1333 # Playwire embed
1334 {
1335 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1336 'info_dict': {
1337 'id': '3519514',
1338 'ext': 'mp4',
1339 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1340 'thumbnail': r're:^https?://.*\.png$',
1341 'duration': 45.115,
1342 },
1343 },
1344 # 5min embed
1345 {
1346 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1347 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1348 'info_dict': {
1349 'id': '518726732',
1350 'ext': 'mp4',
1351 'title': 'Facebook Creates "On This Day" | Crunch Report',
1352 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1353 'timestamp': 1427237531,
1354 'uploader': 'Crunch Report',
1355 'upload_date': '20150324',
1356 },
1357 'params': {
1358 # m3u8 download
1359 'skip_download': True,
1360 },
1361 },
1362 # SVT embed
1363 {
1364 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1365 'info_dict': {
1366 'id': '2900353',
1367 'ext': 'flv',
1368 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1369 'duration': 27,
1370 'age_limit': 0,
1371 },
1372 },
1373 # Crooks and Liars embed
1374 {
1375 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1376 'info_dict': {
1377 'id': '8RUoRhRi',
1378 'ext': 'mp4',
1379 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1380 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1381 'timestamp': 1428207000,
1382 'upload_date': '20150405',
1383 'uploader': 'Heather',
1384 },
1385 },
1386 # Crooks and Liars external embed
1387 {
1388 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1389 'info_dict': {
1390 'id': 'MTE3MjUtMzQ2MzA',
1391 'ext': 'mp4',
1392 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1393 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1394 'timestamp': 1265032391,
1395 'upload_date': '20100201',
1396 'uploader': 'Heather',
1397 },
1398 },
1399 # NBC Sports vplayer embed
1400 {
1401 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1402 'info_dict': {
1403 'id': 'ln7x1qSThw4k',
1404 'ext': 'flv',
1405 'title': "PFT Live: New leader in the 'new-look' defense",
1406 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1407 'uploader': 'NBCU-SPORTS',
1408 'upload_date': '20140107',
1409 'timestamp': 1389118457,
1410 },
1411 'skip': 'Invalid Page URL',
1412 },
1413 # NBC News embed
1414 {
1415 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1416 'md5': '1aa589c675898ae6d37a17913cf68d66',
1417 'info_dict': {
1418 'id': 'x_dtl_oa_LettermanliftPR_160608',
1419 'ext': 'mp4',
1420 'title': 'David Letterman: A Preview',
1421 '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.',
1422 'upload_date': '20160609',
1423 'timestamp': 1465431544,
1424 'uploader': 'NBCU-NEWS',
1425 },
1426 },
1427 # UDN embed
1428 {
1429 'url': 'https://video.udn.com/news/300346',
1430 'md5': 'fd2060e988c326991037b9aff9df21a6',
1431 'info_dict': {
1432 'id': '300346',
1433 'ext': 'mp4',
1434 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1435 'thumbnail': r're:^https?://.*\.jpg$',
1436 },
1437 'params': {
1438 # m3u8 download
1439 'skip_download': True,
1440 },
1441 'expected_warnings': ['Failed to parse JSON Expecting value'],
1442 },
1443 # Ooyala embed
1444 {
1445 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1446 'info_dict': {
1447 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1448 'ext': 'mp4',
1449 'description': 'Index/Match versus VLOOKUP.',
1450 'title': 'This is what separates the Excel masters from the wannabes',
1451 'duration': 191.933,
1452 },
1453 'params': {
1454 # m3u8 downloads
1455 'skip_download': True,
1456 }
1457 },
1458 # Brightcove URL in single quotes
1459 {
1460 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1461 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1462 'info_dict': {
1463 'id': '4255764656001',
1464 'ext': 'mp4',
1465 'title': 'SN Presents: Russell Martin, World Citizen',
1466 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1467 'uploader': 'Rogers Sportsnet',
1468 'uploader_id': '1704050871',
1469 'upload_date': '20150525',
1470 'timestamp': 1432570283,
1471 },
1472 },
1473 # OnionStudios embed
1474 {
1475 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1476 'info_dict': {
1477 'id': '2855',
1478 'ext': 'mp4',
1479 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1480 'thumbnail': r're:^https?://.*\.jpe?g$',
1481 'uploader': 'ClickHole',
1482 'uploader_id': 'clickhole',
1483 }
1484 },
1485 # SnagFilms embed
1486 {
1487 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1488 'info_dict': {
1489 'id': '74849a00-85a9-11e1-9660-123139220831',
1490 'ext': 'mp4',
1491 'title': '#whilewewatch',
1492 }
1493 },
1494 # AdobeTVVideo embed
1495 {
1496 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1497 'md5': '43662b577c018ad707a63766462b1e87',
1498 'info_dict': {
1499 'id': '2456',
1500 'ext': 'mp4',
1501 'title': 'New experience with Acrobat DC',
1502 'description': 'New experience with Acrobat DC',
1503 'duration': 248.667,
1504 },
1505 },
1506 # BrightcoveInPageEmbed embed
1507 {
1508 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1509 'info_dict': {
1510 'id': '4238694884001',
1511 'ext': 'flv',
1512 'title': 'Tabletop: Dread, Last Thoughts',
1513 'description': 'Tabletop: Dread, Last Thoughts',
1514 'duration': 51690,
1515 },
1516 },
1517 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1518 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1519 {
1520 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1521 'info_dict': {
1522 'id': '4785848093001',
1523 'ext': 'mp4',
1524 'title': 'The Cardinal Pell Interview',
1525 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1526 'uploader': 'GlobeCast Australia - GlobeStream',
1527 'uploader_id': '2733773828001',
1528 'upload_date': '20160304',
1529 'timestamp': 1457083087,
1530 },
1531 'params': {
1532 # m3u8 downloads
1533 'skip_download': True,
1534 },
1535 },
1536 {
1537 # Brightcove embed with whitespace around attribute names
1538 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1539 'info_dict': {
1540 'id': '3167554373001',
1541 'ext': 'mp4',
1542 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1543 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1544 'uploader_id': '1079349493',
1545 'upload_date': '20140207',
1546 'timestamp': 1391810548,
1547 },
1548 'params': {
1549 'skip_download': True,
1550 },
1551 },
1552 # Another form of arte.tv embed
1553 {
1554 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1555 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1556 'info_dict': {
1557 'id': '030273-562_PLUS7-F',
1558 'ext': 'mp4',
1559 'title': 'ARTE Reportage - Nulle part, en France',
1560 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1561 'upload_date': '20160409',
1562 },
1563 },
1564 # LiveLeak embed
1565 {
1566 'url': 'http://www.wykop.pl/link/3088787/',
1567 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1568 'info_dict': {
1569 'id': '874_1459135191',
1570 'ext': 'mp4',
1571 'title': 'Man shows poor quality of new apartment building',
1572 'description': 'The wall is like a sand pile.',
1573 'uploader': 'Lake8737',
1574 },
1575 'add_ie': [LiveLeakIE.ie_key()],
1576 },
1577 # Another LiveLeak embed pattern (#13336)
1578 {
1579 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1580 'info_dict': {
1581 'id': '2eb_1496309988',
1582 'ext': 'mp4',
1583 'title': 'Thief robs place where everyone was armed',
1584 'description': 'md5:694d73ee79e535953cf2488562288eee',
1585 'uploader': 'brazilwtf',
1586 },
1587 'add_ie': [LiveLeakIE.ie_key()],
1588 },
1589 # Duplicated embedded video URLs
1590 {
1591 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1592 'info_dict': {
1593 'id': '149298443_480_16c25b74_2',
1594 'ext': 'mp4',
1595 'title': 'vs. Blue Orange Spring Game',
1596 'uploader': 'www.hudl.com',
1597 },
1598 },
1599 # twitter:player:stream embed
1600 {
1601 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1602 'info_dict': {
1603 'id': 'master',
1604 'ext': 'mp4',
1605 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1606 'uploader': 'www.rtl.be',
1607 },
1608 'params': {
1609 # m3u8 downloads
1610 'skip_download': True,
1611 },
1612 },
1613 # twitter:player embed
1614 {
1615 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1616 'md5': 'a3e0df96369831de324f0778e126653c',
1617 'info_dict': {
1618 'id': '4909620399001',
1619 'ext': 'mp4',
1620 'title': 'What Do Black Holes Sound Like?',
1621 'description': 'what do black holes sound like',
1622 'upload_date': '20160524',
1623 'uploader_id': '29913724001',
1624 'timestamp': 1464107587,
1625 'uploader': 'TheAtlantic',
1626 },
1627 'add_ie': ['BrightcoveLegacy'],
1628 },
1629 # Facebook <iframe> embed
1630 {
1631 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1632 'md5': 'fbcde74f534176ecb015849146dd3aee',
1633 'info_dict': {
1634 'id': '599637780109885',
1635 'ext': 'mp4',
1636 'title': 'Facebook video #599637780109885',
1637 },
1638 },
1639 # Facebook <iframe> embed, plugin video
1640 {
1641 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1642 'info_dict': {
1643 'id': '1754168231264132',
1644 'ext': 'mp4',
1645 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1646 'uploader': 'Tariq Ramadan (official)',
1647 'timestamp': 1496758379,
1648 'upload_date': '20170606',
1649 },
1650 'params': {
1651 'skip_download': True,
1652 },
1653 },
1654 # Facebook API embed
1655 {
1656 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1657 'md5': 'a47372ee61b39a7b90287094d447d94e',
1658 'info_dict': {
1659 'id': '10153467542406923',
1660 'ext': 'mp4',
1661 'title': 'Facebook video #10153467542406923',
1662 },
1663 },
1664 # Wordpress "YouTube Video Importer" plugin
1665 {
1666 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1667 'md5': 'd16797741b560b485194eddda8121b48',
1668 'info_dict': {
1669 'id': 'HNTXWDXV9Is',
1670 'ext': 'mp4',
1671 'title': 'Blue Devils Drumline Stanford lot 2016',
1672 'upload_date': '20160627',
1673 'uploader_id': 'GENOCIDE8GENERAL10',
1674 'uploader': 'cylus cyrus',
1675 },
1676 },
1677 {
1678 # video stored on custom kaltura server
1679 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1680 'md5': '537617d06e64dfed891fa1593c4b30cc',
1681 'info_dict': {
1682 'id': '0_1iotm5bh',
1683 'ext': 'mp4',
1684 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1685 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1686 'uploader_id': 'videos.expansion@el-mundo.net',
1687 'upload_date': '20150429',
1688 'timestamp': 1430303472,
1689 },
1690 'add_ie': ['Kaltura'],
1691 },
1692 {
1693 # Non-standard Vimeo embed
1694 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1695 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1696 'info_dict': {
1697 'id': '148867247',
1698 'ext': 'mp4',
1699 'title': 'Understanding the web - Teaser',
1700 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1701 'upload_date': '20151214',
1702 'uploader': 'OpenClassrooms',
1703 'uploader_id': 'openclassrooms',
1704 },
1705 'add_ie': ['Vimeo'],
1706 },
1707 {
1708 # generic vimeo embed that requires original URL passed as Referer
1709 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1710 'only_matching': True,
1711 },
1712 {
1713 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1714 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1715 'info_dict': {
1716 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1717 'ext': 'mp4',
1718 'title': 'Big Buck Bunny',
1719 'description': 'Royalty free test video',
1720 'timestamp': 1432816365,
1721 'upload_date': '20150528',
1722 'is_live': False,
1723 },
1724 'params': {
1725 'skip_download': True,
1726 },
1727 'add_ie': [ArkenaIE.ie_key()],
1728 },
1729 {
1730 '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/',
1731 'info_dict': {
1732 'id': '1c7141f46c',
1733 'ext': 'mp4',
1734 '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',
1735 },
1736 'params': {
1737 'skip_download': True,
1738 },
1739 'add_ie': [Vbox7IE.ie_key()],
1740 },
1741 {
1742 # DBTV embeds
1743 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1744 'info_dict': {
1745 'id': '43254897',
1746 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1747 },
1748 'playlist_mincount': 3,
1749 },
1750 {
1751 # Videa embeds
1752 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1753 'info_dict': {
1754 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1755 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1756 },
1757 'playlist_mincount': 2,
1758 },
1759 {
1760 # 20 minuten embed
1761 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1762 'info_dict': {
1763 'id': '523629',
1764 'ext': 'mp4',
1765 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1766 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1767 },
1768 'params': {
1769 'skip_download': True,
1770 },
1771 'add_ie': [TwentyMinutenIE.ie_key()],
1772 },
1773 {
1774 # VideoPress embed
1775 'url': 'https://en.support.wordpress.com/videopress/',
1776 'info_dict': {
1777 'id': 'OcobLTqC',
1778 'ext': 'm4v',
1779 'title': 'IMG_5786',
1780 'timestamp': 1435711927,
1781 'upload_date': '20150701',
1782 },
1783 'params': {
1784 'skip_download': True,
1785 },
1786 'add_ie': [VideoPressIE.ie_key()],
1787 },
1788 {
1789 # Rutube embed
1790 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1791 'info_dict': {
1792 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1793 'ext': 'flv',
1794 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1795 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1796 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1797 'upload_date': '20170228',
1798 'uploader_id': '996642',
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 'add_ie': [RutubeIE.ie_key()],
1804 },
1805 {
1806 # ThePlatform embedded with whitespaces in URLs
1807 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1808 'only_matching': True,
1809 },
1810 {
1811 # Senate ISVP iframe https
1812 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1813 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1814 'info_dict': {
1815 'id': 'govtaff020316',
1816 'ext': 'mp4',
1817 'title': 'Integrated Senate Video Player',
1818 },
1819 'add_ie': [SenateISVPIE.ie_key()],
1820 },
1821 {
1822 # Limelight embeds (1 channel embed + 4 media embeds)
1823 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1824 'info_dict': {
1825 'id': 'FacilitatorTraining2017',
1826 'title': 'Facilitator Training 2017',
1827 },
1828 'playlist_mincount': 5,
1829 },
1830 {
1831 # Limelight embed (LimelightPlayerUtil.embed)
1832 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1833 'info_dict': {
1834 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1835 'ext': 'mp4',
1836 'title': '07448641',
1837 'timestamp': 1499890639,
1838 'upload_date': '20170712',
1839 },
1840 'params': {
1841 'skip_download': True,
1842 },
1843 'add_ie': ['LimelightMedia'],
1844 },
1845 {
1846 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1847 'info_dict': {
1848 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1849 'title': 'Standoff with Walnut Creek murder suspect ends',
1850 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1851 },
1852 'playlist_mincount': 4,
1853 },
1854 {
1855 # WashingtonPost embed
1856 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1857 'info_dict': {
1858 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1859 'ext': 'mp4',
1860 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1861 '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.',
1862 'timestamp': 1455216756,
1863 'uploader': 'The Washington Post',
1864 'upload_date': '20160211',
1865 },
1866 'add_ie': [WashingtonPostIE.ie_key()],
1867 },
1868 {
1869 # Mediaset embed
1870 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1871 'info_dict': {
1872 'id': '720642',
1873 'ext': 'mp4',
1874 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1875 },
1876 'params': {
1877 'skip_download': True,
1878 },
1879 'add_ie': [MediasetIE.ie_key()],
1880 },
1881 {
1882 # JOJ.sk embeds
1883 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1884 'info_dict': {
1885 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1886 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1887 },
1888 'playlist_mincount': 5,
1889 'add_ie': [JojIE.ie_key()],
1890 },
1891 {
1892 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1893 'url': 'https://tvrain.ru/amp/418921/',
1894 'md5': 'cc00413936695987e8de148b67d14f1d',
1895 'info_dict': {
1896 'id': '418921',
1897 'ext': 'mp4',
1898 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1899 },
1900 },
1901 {
1902 # vzaar embed
1903 'url': 'http://help.vzaar.com/article/165-embedding-video',
1904 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1905 'info_dict': {
1906 'id': '8707641',
1907 'ext': 'mp4',
1908 'title': 'Building A Business Online: Principal Chairs Q & A',
1909 },
1910 },
1911 {
1912 # multiple HTML5 videos on one page
1913 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1914 'info_dict': {
1915 'id': 'keyscenarios',
1916 'title': 'Rescue Kit 14 Free Edition - Getting started',
1917 },
1918 'playlist_count': 4,
1919 },
1920 {
1921 # vshare embed
1922 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1923 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1924 'info_dict': {
1925 'id': '0f64ce6',
1926 'title': 'vl14062007715967',
1927 'ext': 'mp4',
1928 }
1929 },
1930 {
1931 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1932 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1933 'info_dict': {
1934 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1935 'ext': 'mp4',
1936 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1937 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1938 'timestamp': 1474354800,
1939 'upload_date': '20160920',
1940 }
1941 }
1942 # {
1943 # # TODO: find another test
1944 # # http://schema.org/VideoObject
1945 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1946 # 'md5': '888dcf08b7ea671381f00fab74692755',
1947 # 'info_dict': {
1948 # 'id': 'nyvTSJMKId',
1949 # 'ext': 'mp4',
1950 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1951 # 'description': '#love for cats.',
1952 # 'timestamp': 1461244995,
1953 # 'upload_date': '20160421',
1954 # },
1955 # 'params': {
1956 # 'force_generic_extractor': True,
1957 # },
1958 # }
1959 ]
1960
1961 def report_following_redirect(self, new_url):
1962 """Report information extraction."""
1963 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1964
1965 def _extract_rss(self, url, video_id, doc):
1966 playlist_title = doc.find('./channel/title').text
1967 playlist_desc_el = doc.find('./channel/description')
1968 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1969
1970 entries = []
1971 for it in doc.findall('./channel/item'):
1972 next_url = xpath_text(it, 'link', fatal=False)
1973 if not next_url:
1974 enclosure_nodes = it.findall('./enclosure')
1975 for e in enclosure_nodes:
1976 next_url = e.attrib.get('url')
1977 if next_url:
1978 break
1979
1980 if not next_url:
1981 continue
1982
1983 entries.append({
1984 '_type': 'url_transparent',
1985 'url': next_url,
1986 'title': it.find('title').text,
1987 })
1988
1989 return {
1990 '_type': 'playlist',
1991 'id': url,
1992 'title': playlist_title,
1993 'description': playlist_desc,
1994 'entries': entries,
1995 }
1996
1997 def _extract_camtasia(self, url, video_id, webpage):
1998 """ Returns None if no camtasia video can be found. """
1999
2000 camtasia_cfg = self._search_regex(
2001 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2002 webpage, 'camtasia configuration file', default=None)
2003 if camtasia_cfg is None:
2004 return None
2005
2006 title = self._html_search_meta('DC.title', webpage, fatal=True)
2007
2008 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2009 camtasia_cfg = self._download_xml(
2010 camtasia_url, video_id,
2011 note='Downloading camtasia configuration',
2012 errnote='Failed to download camtasia configuration')
2013 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2014
2015 entries = []
2016 for n in fileset_node.getchildren():
2017 url_n = n.find('./uri')
2018 if url_n is None:
2019 continue
2020
2021 entries.append({
2022 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2023 'title': '%s - %s' % (title, n.tag),
2024 'url': compat_urlparse.urljoin(url, url_n.text),
2025 'duration': float_or_none(n.find('./duration').text),
2026 })
2027
2028 return {
2029 '_type': 'playlist',
2030 'entries': entries,
2031 'title': title,
2032 }
2033
2034 def _real_extract(self, url):
2035 if url.startswith('//'):
2036 return {
2037 '_type': 'url',
2038 'url': self.http_scheme() + url,
2039 }
2040
2041 parsed_url = compat_urlparse.urlparse(url)
2042 if not parsed_url.scheme:
2043 default_search = self._downloader.params.get('default_search')
2044 if default_search is None:
2045 default_search = 'fixup_error'
2046
2047 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2048 if '/' in url:
2049 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2050 return self.url_result('http://' + url)
2051 elif default_search != 'fixup_error':
2052 if default_search == 'auto_warning':
2053 if re.match(r'^(?:url|URL)$', url):
2054 raise ExtractorError(
2055 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2056 expected=True)
2057 else:
2058 self._downloader.report_warning(
2059 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2060 return self.url_result('ytsearch:' + url)
2061
2062 if default_search in ('error', 'fixup_error'):
2063 raise ExtractorError(
2064 '%r is not a valid URL. '
2065 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2066 % (url, url), expected=True)
2067 else:
2068 if ':' not in default_search:
2069 default_search += ':'
2070 return self.url_result(default_search + url)
2071
2072 url, smuggled_data = unsmuggle_url(url)
2073 force_videoid = None
2074 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2075 if smuggled_data and 'force_videoid' in smuggled_data:
2076 force_videoid = smuggled_data['force_videoid']
2077 video_id = force_videoid
2078 else:
2079 video_id = self._generic_id(url)
2080
2081 self.to_screen('%s: Requesting header' % video_id)
2082
2083 head_req = HEADRequest(url)
2084 head_response = self._request_webpage(
2085 head_req, video_id,
2086 note=False, errnote='Could not send HEAD request to %s' % url,
2087 fatal=False)
2088
2089 if head_response is not False:
2090 # Check for redirect
2091 new_url = compat_str(head_response.geturl())
2092 if url != new_url:
2093 self.report_following_redirect(new_url)
2094 if force_videoid:
2095 new_url = smuggle_url(
2096 new_url, {'force_videoid': force_videoid})
2097 return self.url_result(new_url)
2098
2099 full_response = None
2100 if head_response is False:
2101 request = sanitized_Request(url)
2102 request.add_header('Accept-Encoding', '*')
2103 full_response = self._request_webpage(request, video_id)
2104 head_response = full_response
2105
2106 info_dict = {
2107 'id': video_id,
2108 'title': self._generic_title(url),
2109 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2110 }
2111
2112 # Check for direct link to a video
2113 content_type = head_response.headers.get('Content-Type', '').lower()
2114 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2115 if m:
2116 format_id = compat_str(m.group('format_id'))
2117 if format_id.endswith('mpegurl'):
2118 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2119 elif format_id == 'f4m':
2120 formats = self._extract_f4m_formats(url, video_id)
2121 else:
2122 formats = [{
2123 'format_id': format_id,
2124 'url': url,
2125 'vcodec': 'none' if m.group('type') == 'audio' else None
2126 }]
2127 info_dict['direct'] = True
2128 self._sort_formats(formats)
2129 info_dict['formats'] = formats
2130 return info_dict
2131
2132 if not self._downloader.params.get('test', False) and not is_intentional:
2133 force = self._downloader.params.get('force_generic_extractor', False)
2134 self._downloader.report_warning(
2135 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2136
2137 if not full_response:
2138 request = sanitized_Request(url)
2139 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2140 # making it impossible to download only chunk of the file (yet we need only 512kB to
2141 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2142 # that will always result in downloading the whole file that is not desirable.
2143 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2144 # to accept raw bytes and being able to download only a chunk.
2145 # It may probably better to solve this by checking Content-Type for application/octet-stream
2146 # after HEAD request finishes, but not sure if we can rely on this.
2147 request.add_header('Accept-Encoding', '*')
2148 full_response = self._request_webpage(request, video_id)
2149
2150 first_bytes = full_response.read(512)
2151
2152 # Is it an M3U playlist?
2153 if first_bytes.startswith(b'#EXTM3U'):
2154 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2155 self._sort_formats(info_dict['formats'])
2156 return info_dict
2157
2158 # Maybe it's a direct link to a video?
2159 # Be careful not to download the whole thing!
2160 if not is_html(first_bytes):
2161 self._downloader.report_warning(
2162 'URL could be a direct video link, returning it as such.')
2163 info_dict.update({
2164 'direct': True,
2165 'url': url,
2166 })
2167 return info_dict
2168
2169 webpage = self._webpage_read_content(
2170 full_response, url, video_id, prefix=first_bytes)
2171
2172 self.report_extraction(video_id)
2173
2174 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2175 try:
2176 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2177 if doc.tag == 'rss':
2178 return self._extract_rss(url, video_id, doc)
2179 elif doc.tag == 'SmoothStreamingMedia':
2180 info_dict['formats'] = self._parse_ism_formats(doc, url)
2181 self._sort_formats(info_dict['formats'])
2182 return info_dict
2183 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2184 smil = self._parse_smil(doc, url, video_id)
2185 self._sort_formats(smil['formats'])
2186 return smil
2187 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2188 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2189 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2190 info_dict['formats'] = self._parse_mpd_formats(
2191 doc,
2192 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2193 mpd_url=url)
2194 self._sort_formats(info_dict['formats'])
2195 return info_dict
2196 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2197 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2198 self._sort_formats(info_dict['formats'])
2199 return info_dict
2200 except compat_xml_parse_error:
2201 pass
2202
2203 # Is it a Camtasia project?
2204 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2205 if camtasia_res is not None:
2206 return camtasia_res
2207
2208 # Sometimes embedded video player is hidden behind percent encoding
2209 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2210 # Unescaping the whole page allows to handle those cases in a generic way
2211 webpage = compat_urllib_parse_unquote(webpage)
2212
2213 # it's tempting to parse this further, but you would
2214 # have to take into account all the variations like
2215 # Video Title - Site Name
2216 # Site Name | Video Title
2217 # Video Title - Tagline | Site Name
2218 # and so on and so forth; it's just not practical
2219 video_title = self._og_search_title(
2220 webpage, default=None) or self._html_search_regex(
2221 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2222 default='video')
2223
2224 # Try to detect age limit automatically
2225 age_limit = self._rta_search(webpage)
2226 # And then there are the jokers who advertise that they use RTA,
2227 # but actually don't.
2228 AGE_LIMIT_MARKERS = [
2229 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2230 ]
2231 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2232 age_limit = 18
2233
2234 # video uploader is domain name
2235 video_uploader = self._search_regex(
2236 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2237
2238 video_description = self._og_search_description(webpage, default=None)
2239 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2240
2241 info_dict.update({
2242 'title': video_title,
2243 'description': video_description,
2244 'thumbnail': video_thumbnail,
2245 'age_limit': age_limit,
2246 })
2247
2248 # Look for Brightcove Legacy Studio embeds
2249 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2250 if bc_urls:
2251 entries = [{
2252 '_type': 'url',
2253 'url': smuggle_url(bc_url, {'Referer': url}),
2254 'ie_key': 'BrightcoveLegacy'
2255 } for bc_url in bc_urls]
2256
2257 return {
2258 '_type': 'playlist',
2259 'title': video_title,
2260 'id': video_id,
2261 'entries': entries,
2262 }
2263
2264 # Look for Brightcove New Studio embeds
2265 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2266 if bc_urls:
2267 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2268
2269 # Look for Nexx embeds
2270 nexx_urls = NexxIE._extract_urls(webpage)
2271 if nexx_urls:
2272 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2273
2274 # Look for Nexx iFrame embeds
2275 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2276 if nexx_embed_urls:
2277 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2278
2279 # Look for ThePlatform embeds
2280 tp_urls = ThePlatformIE._extract_urls(webpage)
2281 if tp_urls:
2282 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2283
2284 # Look for Vessel embeds
2285 vessel_urls = VesselIE._extract_urls(webpage)
2286 if vessel_urls:
2287 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2288
2289 # Look for embedded rtl.nl player
2290 matches = re.findall(
2291 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2292 webpage)
2293 if matches:
2294 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2295
2296 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2297 if vimeo_urls:
2298 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2299
2300 vid_me_embed_url = self._search_regex(
2301 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2302 webpage, 'vid.me embed', default=None)
2303 if vid_me_embed_url is not None:
2304 return self.url_result(vid_me_embed_url, 'Vidme')
2305
2306 # Look for YouTube embeds
2307 youtube_urls = YoutubeIE._extract_urls(webpage)
2308 if youtube_urls:
2309 return self.playlist_from_matches(
2310 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2311
2312 matches = DailymotionIE._extract_urls(webpage)
2313 if matches:
2314 return self.playlist_from_matches(matches, video_id, video_title)
2315
2316 # Look for embedded Dailymotion playlist player (#3822)
2317 m = re.search(
2318 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2319 if m:
2320 playlists = re.findall(
2321 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2322 if playlists:
2323 return self.playlist_from_matches(
2324 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2325
2326 # Look for DailyMail embeds
2327 dailymail_urls = DailyMailIE._extract_urls(webpage)
2328 if dailymail_urls:
2329 return self.playlist_from_matches(
2330 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2331
2332 # Look for embedded Wistia player
2333 wistia_url = WistiaIE._extract_url(webpage)
2334 if wistia_url:
2335 return {
2336 '_type': 'url_transparent',
2337 'url': self._proto_relative_url(wistia_url),
2338 'ie_key': WistiaIE.ie_key(),
2339 'uploader': video_uploader,
2340 }
2341
2342 # Look for SVT player
2343 svt_url = SVTIE._extract_url(webpage)
2344 if svt_url:
2345 return self.url_result(svt_url, 'SVT')
2346
2347 # Look for Bandcamp pages with custom domain
2348 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2349 if mobj is not None:
2350 burl = unescapeHTML(mobj.group(1))
2351 # Don't set the extractor because it can be a track url or an album
2352 return self.url_result(burl)
2353
2354 # Look for embedded Vevo player
2355 mobj = re.search(
2356 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2357 if mobj is not None:
2358 return self.url_result(mobj.group('url'))
2359
2360 # Look for embedded Viddler player
2361 mobj = re.search(
2362 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2363 webpage)
2364 if mobj is not None:
2365 return self.url_result(mobj.group('url'))
2366
2367 # Look for NYTimes player
2368 mobj = re.search(
2369 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2370 webpage)
2371 if mobj is not None:
2372 return self.url_result(mobj.group('url'))
2373
2374 # Look for Libsyn player
2375 mobj = re.search(
2376 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2377 if mobj is not None:
2378 return self.url_result(mobj.group('url'))
2379
2380 # Look for Ooyala videos
2381 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2382 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2383 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2384 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2385 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2386 if mobj is not None:
2387 embed_token = self._search_regex(
2388 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2389 webpage, 'ooyala embed token', default=None)
2390 return OoyalaIE._build_url_result(smuggle_url(
2391 mobj.group('ec'), {
2392 'domain': url,
2393 'embed_token': embed_token,
2394 }))
2395
2396 # Look for multiple Ooyala embeds on SBN network websites
2397 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2398 if mobj is not None:
2399 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2400 if embeds:
2401 return self.playlist_from_matches(
2402 embeds, video_id, video_title,
2403 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2404
2405 # Look for Aparat videos
2406 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2407 if mobj is not None:
2408 return self.url_result(mobj.group(1), 'Aparat')
2409
2410 # Look for MPORA videos
2411 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2412 if mobj is not None:
2413 return self.url_result(mobj.group(1), 'Mpora')
2414
2415 # Look for embedded NovaMov-based player
2416 mobj = re.search(
2417 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2418 (?P<url>http://(?:(?:embed|www)\.)?
2419 (?:novamov\.com|
2420 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2421 videoweed\.(?:es|com)|
2422 movshare\.(?:net|sx|ag)|
2423 divxstage\.(?:eu|net|ch|co|at|ag))
2424 /embed\.php.+?)\1''', webpage)
2425 if mobj is not None:
2426 return self.url_result(mobj.group('url'))
2427
2428 # Look for embedded Facebook player
2429 facebook_urls = FacebookIE._extract_urls(webpage)
2430 if facebook_urls:
2431 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2432
2433 # Look for embedded VK player
2434 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2435 if mobj is not None:
2436 return self.url_result(mobj.group('url'), 'VK')
2437
2438 # Look for embedded Odnoklassniki player
2439 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2440 if mobj is not None:
2441 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2442
2443 # Look for embedded ivi player
2444 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2445 if mobj is not None:
2446 return self.url_result(mobj.group('url'), 'Ivi')
2447
2448 # Look for embedded Huffington Post player
2449 mobj = re.search(
2450 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2451 if mobj is not None:
2452 return self.url_result(mobj.group('url'), 'HuffPost')
2453
2454 # Look for embed.ly
2455 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2456 if mobj is not None:
2457 return self.url_result(mobj.group('url'))
2458 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2459 if mobj is not None:
2460 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2461
2462 # Look for funnyordie embed
2463 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2464 if matches:
2465 return self.playlist_from_matches(
2466 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2467
2468 # Look for BBC iPlayer embed
2469 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2470 if matches:
2471 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2472
2473 # Look for embedded RUTV player
2474 rutv_url = RUTVIE._extract_url(webpage)
2475 if rutv_url:
2476 return self.url_result(rutv_url, 'RUTV')
2477
2478 # Look for embedded TVC player
2479 tvc_url = TVCIE._extract_url(webpage)
2480 if tvc_url:
2481 return self.url_result(tvc_url, 'TVC')
2482
2483 # Look for embedded SportBox player
2484 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2485 if sportbox_urls:
2486 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2487
2488 # Look for embedded XHamster player
2489 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2490 if xhamster_urls:
2491 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2492
2493 # Look for embedded TNAFlixNetwork player
2494 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2495 if tnaflix_urls:
2496 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2497
2498 # Look for embedded PornHub player
2499 pornhub_urls = PornHubIE._extract_urls(webpage)
2500 if pornhub_urls:
2501 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2502
2503 # Look for embedded DrTuber player
2504 drtuber_urls = DrTuberIE._extract_urls(webpage)
2505 if drtuber_urls:
2506 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2507
2508 # Look for embedded RedTube player
2509 redtube_urls = RedTubeIE._extract_urls(webpage)
2510 if redtube_urls:
2511 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2512
2513 # Look for embedded Tvigle player
2514 mobj = re.search(
2515 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2516 if mobj is not None:
2517 return self.url_result(mobj.group('url'), 'Tvigle')
2518
2519 # Look for embedded TED player
2520 mobj = re.search(
2521 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2522 if mobj is not None:
2523 return self.url_result(mobj.group('url'), 'TED')
2524
2525 # Look for embedded Ustream videos
2526 ustream_url = UstreamIE._extract_url(webpage)
2527 if ustream_url:
2528 return self.url_result(ustream_url, UstreamIE.ie_key())
2529
2530 # Look for embedded arte.tv player
2531 mobj = re.search(
2532 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2533 webpage)
2534 if mobj is not None:
2535 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2536
2537 # Look for embedded francetv player
2538 mobj = re.search(
2539 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2540 webpage)
2541 if mobj is not None:
2542 return self.url_result(mobj.group('url'))
2543
2544 # Look for embedded smotri.com player
2545 smotri_url = SmotriIE._extract_url(webpage)
2546 if smotri_url:
2547 return self.url_result(smotri_url, 'Smotri')
2548
2549 # Look for embedded Myvi.ru player
2550 myvi_url = MyviIE._extract_url(webpage)
2551 if myvi_url:
2552 return self.url_result(myvi_url)
2553
2554 # Look for embedded soundcloud player
2555 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2556 if soundcloud_urls:
2557 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2558
2559 # Look for tunein player
2560 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2561 if tunein_urls:
2562 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2563
2564 # Look for embedded mtvservices player
2565 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2566 if mtvservices_url:
2567 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2568
2569 # Look for embedded yahoo player
2570 mobj = re.search(
2571 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2572 webpage)
2573 if mobj is not None:
2574 return self.url_result(mobj.group('url'), 'Yahoo')
2575
2576 # Look for embedded sbs.com.au player
2577 mobj = re.search(
2578 r'''(?x)
2579 (?:
2580 <meta\s+property="og:video"\s+content=|
2581 <iframe[^>]+?src=
2582 )
2583 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2584 webpage)
2585 if mobj is not None:
2586 return self.url_result(mobj.group('url'), 'SBS')
2587
2588 # Look for embedded Cinchcast player
2589 mobj = re.search(
2590 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2591 webpage)
2592 if mobj is not None:
2593 return self.url_result(mobj.group('url'), 'Cinchcast')
2594
2595 mobj = re.search(
2596 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2597 webpage)
2598 if not mobj:
2599 mobj = re.search(
2600 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2601 webpage)
2602 if mobj is not None:
2603 return self.url_result(mobj.group('url'), 'MLB')
2604
2605 mobj = re.search(
2606 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2607 webpage)
2608 if mobj is not None:
2609 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2610
2611 mobj = re.search(
2612 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2613 webpage)
2614 if mobj is not None:
2615 return self.url_result(mobj.group('url'), 'Livestream')
2616
2617 # Look for Zapiks embed
2618 mobj = re.search(
2619 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2620 if mobj is not None:
2621 return self.url_result(mobj.group('url'), 'Zapiks')
2622
2623 # Look for Kaltura embeds
2624 kaltura_url = KalturaIE._extract_url(webpage)
2625 if kaltura_url:
2626 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2627
2628 # Look for EaglePlatform embeds
2629 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2630 if eagleplatform_url:
2631 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2632
2633 # Look for ClipYou (uses EaglePlatform) embeds
2634 mobj = re.search(
2635 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2636 if mobj is not None:
2637 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2638
2639 # Look for Pladform embeds
2640 pladform_url = PladformIE._extract_url(webpage)
2641 if pladform_url:
2642 return self.url_result(pladform_url)
2643
2644 # Look for Videomore embeds
2645 videomore_url = VideomoreIE._extract_url(webpage)
2646 if videomore_url:
2647 return self.url_result(videomore_url)
2648
2649 # Look for Webcaster embeds
2650 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2651 if webcaster_url:
2652 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2653
2654 # Look for Playwire embeds
2655 mobj = re.search(
2656 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2657 if mobj is not None:
2658 return self.url_result(mobj.group('url'))
2659
2660 # Look for 5min embeds
2661 mobj = re.search(
2662 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2663 if mobj is not None:
2664 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2665
2666 # Look for Crooks and Liars embeds
2667 mobj = re.search(
2668 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2669 if mobj is not None:
2670 return self.url_result(mobj.group('url'))
2671
2672 # Look for NBC Sports VPlayer embeds
2673 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2674 if nbc_sports_url:
2675 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2676
2677 # Look for NBC News embeds
2678 nbc_news_embed_url = re.search(
2679 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2680 if nbc_news_embed_url:
2681 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2682
2683 # Look for Google Drive embeds
2684 google_drive_url = GoogleDriveIE._extract_url(webpage)
2685 if google_drive_url:
2686 return self.url_result(google_drive_url, 'GoogleDrive')
2687
2688 # Look for UDN embeds
2689 mobj = re.search(
2690 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2691 if mobj is not None:
2692 return self.url_result(
2693 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2694
2695 # Look for Senate ISVP iframe
2696 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2697 if senate_isvp_url:
2698 return self.url_result(senate_isvp_url, 'SenateISVP')
2699
2700 # Look for OnionStudios embeds
2701 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2702 if onionstudios_url:
2703 return self.url_result(onionstudios_url)
2704
2705 # Look for ViewLift embeds
2706 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2707 if viewlift_url:
2708 return self.url_result(viewlift_url)
2709
2710 # Look for JWPlatform embeds
2711 jwplatform_url = JWPlatformIE._extract_url(webpage)
2712 if jwplatform_url:
2713 return self.url_result(jwplatform_url, 'JWPlatform')
2714
2715 # Look for Digiteka embeds
2716 digiteka_url = DigitekaIE._extract_url(webpage)
2717 if digiteka_url:
2718 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2719
2720 # Look for Arkena embeds
2721 arkena_url = ArkenaIE._extract_url(webpage)
2722 if arkena_url:
2723 return self.url_result(arkena_url, ArkenaIE.ie_key())
2724
2725 # Look for Piksel embeds
2726 piksel_url = PikselIE._extract_url(webpage)
2727 if piksel_url:
2728 return self.url_result(piksel_url, PikselIE.ie_key())
2729
2730 # Look for Limelight embeds
2731 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2732 if limelight_urls:
2733 return self.playlist_result(
2734 limelight_urls, video_id, video_title, video_description)
2735
2736 # Look for Anvato embeds
2737 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2738 if anvato_urls:
2739 return self.playlist_result(
2740 anvato_urls, video_id, video_title, video_description)
2741
2742 # Look for AdobeTVVideo embeds
2743 mobj = re.search(
2744 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2745 webpage)
2746 if mobj is not None:
2747 return self.url_result(
2748 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2749 'AdobeTVVideo')
2750
2751 # Look for Vine embeds
2752 mobj = re.search(
2753 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2754 webpage)
2755 if mobj is not None:
2756 return self.url_result(
2757 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2758
2759 # Look for VODPlatform embeds
2760 mobj = re.search(
2761 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2762 webpage)
2763 if mobj is not None:
2764 return self.url_result(
2765 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2766
2767 # Look for Mangomolo embeds
2768 mobj = re.search(
2769 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2770 (?:
2771 video\?.*?\bid=(?P<video_id>\d+)|
2772 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2773 ).+?)\1''', webpage)
2774 if mobj is not None:
2775 info = {
2776 '_type': 'url_transparent',
2777 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2778 'title': video_title,
2779 'description': video_description,
2780 'thumbnail': video_thumbnail,
2781 'uploader': video_uploader,
2782 }
2783 video_id = mobj.group('video_id')
2784 if video_id:
2785 info.update({
2786 'ie_key': 'MangomoloVideo',
2787 'id': video_id,
2788 })
2789 else:
2790 info.update({
2791 'ie_key': 'MangomoloLive',
2792 'id': mobj.group('channel_id'),
2793 })
2794 return info
2795
2796 # Look for Instagram embeds
2797 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2798 if instagram_embed_url is not None:
2799 return self.url_result(
2800 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2801
2802 # Look for LiveLeak embeds
2803 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2804 if liveleak_urls:
2805 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2806
2807 # Look for 3Q SDN embeds
2808 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2809 if threeqsdn_url:
2810 return {
2811 '_type': 'url_transparent',
2812 'ie_key': ThreeQSDNIE.ie_key(),
2813 'url': self._proto_relative_url(threeqsdn_url),
2814 'title': video_title,
2815 'description': video_description,
2816 'thumbnail': video_thumbnail,
2817 'uploader': video_uploader,
2818 }
2819
2820 # Look for VBOX7 embeds
2821 vbox7_url = Vbox7IE._extract_url(webpage)
2822 if vbox7_url:
2823 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2824
2825 # Look for DBTV embeds
2826 dbtv_urls = DBTVIE._extract_urls(webpage)
2827 if dbtv_urls:
2828 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2829
2830 # Look for Videa embeds
2831 videa_urls = VideaIE._extract_urls(webpage)
2832 if videa_urls:
2833 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2834
2835 # Look for 20 minuten embeds
2836 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2837 if twentymin_urls:
2838 return self.playlist_from_matches(
2839 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2840
2841 # Look for Openload embeds
2842 openload_urls = OpenloadIE._extract_urls(webpage)
2843 if openload_urls:
2844 return self.playlist_from_matches(
2845 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2846
2847 # Look for VideoPress embeds
2848 videopress_urls = VideoPressIE._extract_urls(webpage)
2849 if videopress_urls:
2850 return self.playlist_from_matches(
2851 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2852
2853 # Look for Rutube embeds
2854 rutube_urls = RutubeIE._extract_urls(webpage)
2855 if rutube_urls:
2856 return self.playlist_from_matches(
2857 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2858
2859 # Look for WashingtonPost embeds
2860 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2861 if wapo_urls:
2862 return self.playlist_from_matches(
2863 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2864
2865 # Look for Mediaset embeds
2866 mediaset_urls = MediasetIE._extract_urls(webpage)
2867 if mediaset_urls:
2868 return self.playlist_from_matches(
2869 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2870
2871 # Look for JOJ.sk embeds
2872 joj_urls = JojIE._extract_urls(webpage)
2873 if joj_urls:
2874 return self.playlist_from_matches(
2875 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2876
2877 # Look for megaphone.fm embeds
2878 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2879 if mpfn_urls:
2880 return self.playlist_from_matches(
2881 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2882
2883 # Look for vzaar embeds
2884 vzaar_urls = VzaarIE._extract_urls(webpage)
2885 if vzaar_urls:
2886 return self.playlist_from_matches(
2887 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2888
2889 channel9_urls = Channel9IE._extract_urls(webpage)
2890 if channel9_urls:
2891 return self.playlist_from_matches(
2892 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2893
2894 vshare_urls = VShareIE._extract_urls(webpage)
2895 if vshare_urls:
2896 return self.playlist_from_matches(
2897 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2898
2899 # Look for Mediasite embeds
2900 mediasite_urls = MediasiteIE._extract_urls(webpage)
2901 if mediasite_urls:
2902 entries = [
2903 self.url_result(smuggle_url(
2904 compat_urlparse.urljoin(url, mediasite_url),
2905 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2906 for mediasite_url in mediasite_urls]
2907 return self.playlist_result(entries, video_id, video_title)
2908
2909 def merge_dicts(dict1, dict2):
2910 merged = {}
2911 for k, v in dict1.items():
2912 if v is not None:
2913 merged[k] = v
2914 for k, v in dict2.items():
2915 if v is None:
2916 continue
2917 if (k not in merged or
2918 (isinstance(v, compat_str) and v and
2919 isinstance(merged[k], compat_str) and
2920 not merged[k])):
2921 merged[k] = v
2922 return merged
2923
2924 # Look for HTML5 media
2925 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2926 if entries:
2927 if len(entries) == 1:
2928 entries[0].update({
2929 'id': video_id,
2930 'title': video_title,
2931 })
2932 else:
2933 for num, entry in enumerate(entries, start=1):
2934 entry.update({
2935 'id': '%s-%s' % (video_id, num),
2936 'title': '%s (%d)' % (video_title, num),
2937 })
2938 for entry in entries:
2939 self._sort_formats(entry['formats'])
2940 return self.playlist_result(entries, video_id, video_title)
2941
2942 jwplayer_data = self._find_jwplayer_data(
2943 webpage, video_id, transform_source=js_to_json)
2944 if jwplayer_data:
2945 info = self._parse_jwplayer_data(
2946 jwplayer_data, video_id, require_title=False, base_url=url)
2947 return merge_dicts(info, info_dict)
2948
2949 # Video.js embed
2950 mobj = re.search(
2951 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2952 webpage)
2953 if mobj is not None:
2954 sources = self._parse_json(
2955 mobj.group(1), video_id, transform_source=js_to_json,
2956 fatal=False) or []
2957 if not isinstance(sources, list):
2958 sources = [sources]
2959 formats = []
2960 for source in sources:
2961 src = source.get('src')
2962 if not src or not isinstance(src, compat_str):
2963 continue
2964 src = compat_urlparse.urljoin(url, src)
2965 src_type = source.get('type')
2966 if isinstance(src_type, compat_str):
2967 src_type = src_type.lower()
2968 ext = determine_ext(src).lower()
2969 if src_type == 'video/youtube':
2970 return self.url_result(src, YoutubeIE.ie_key())
2971 if src_type == 'application/dash+xml' or ext == 'mpd':
2972 formats.extend(self._extract_mpd_formats(
2973 src, video_id, mpd_id='dash', fatal=False))
2974 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2975 formats.extend(self._extract_m3u8_formats(
2976 src, video_id, 'mp4', entry_protocol='m3u8_native',
2977 m3u8_id='hls', fatal=False))
2978 else:
2979 formats.append({
2980 'url': src,
2981 'ext': (mimetype2ext(src_type) or
2982 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2983 })
2984 if formats:
2985 self._sort_formats(formats)
2986 info_dict['formats'] = formats
2987 return info_dict
2988
2989 # Looking for http://schema.org/VideoObject
2990 json_ld = self._search_json_ld(
2991 webpage, video_id, default={}, expected_type='VideoObject')
2992 if json_ld.get('url'):
2993 return merge_dicts(json_ld, info_dict)
2994
2995 def check_video(vurl):
2996 if YoutubeIE.suitable(vurl):
2997 return True
2998 if RtmpIE.suitable(vurl):
2999 return True
3000 vpath = compat_urlparse.urlparse(vurl).path
3001 vext = determine_ext(vpath)
3002 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3003
3004 def filter_video(urls):
3005 return list(filter(check_video, urls))
3006
3007 # Start with something easy: JW Player in SWFObject
3008 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3009 if not found:
3010 # Look for gorilla-vid style embedding
3011 found = filter_video(re.findall(r'''(?sx)
3012 (?:
3013 jw_plugins|
3014 JWPlayerOptions|
3015 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3016 )
3017 .*?
3018 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3019 if not found:
3020 # Broaden the search a little bit
3021 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3022 if not found:
3023 # Broaden the findall a little bit: JWPlayer JS loader
3024 found = filter_video(re.findall(
3025 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3026 if not found:
3027 # Flow player
3028 found = filter_video(re.findall(r'''(?xs)
3029 flowplayer\("[^"]+",\s*
3030 \{[^}]+?\}\s*,
3031 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3032 ["']?url["']?\s*:\s*["']([^"']+)["']
3033 ''', webpage))
3034 if not found:
3035 # Cinerama player
3036 found = re.findall(
3037 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3038 if not found:
3039 # Try to find twitter cards info
3040 # twitter:player:stream should be checked before twitter:player since
3041 # it is expected to contain a raw stream (see
3042 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3043 found = filter_video(re.findall(
3044 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3045 if not found:
3046 # We look for Open Graph info:
3047 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3048 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3049 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3050 if m_video_type is not None:
3051 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3052 if not found:
3053 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3054 found = re.search(
3055 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3056 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3057 webpage)
3058 if not found:
3059 # Look also in Refresh HTTP header
3060 refresh_header = head_response.headers.get('Refresh')
3061 if refresh_header:
3062 # In python 2 response HTTP headers are bytestrings
3063 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3064 refresh_header = refresh_header.decode('iso-8859-1')
3065 found = re.search(REDIRECT_REGEX, refresh_header)
3066 if found:
3067 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3068 if new_url != url:
3069 self.report_following_redirect(new_url)
3070 return {
3071 '_type': 'url',
3072 'url': new_url,
3073 }
3074 else:
3075 found = None
3076
3077 if not found:
3078 # twitter:player is a https URL to iframe player that may or may not
3079 # be supported by youtube-dl thus this is checked the very last (see
3080 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3081 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3082 if embed_url and embed_url != url:
3083 return self.url_result(embed_url)
3084
3085 if not found:
3086 raise UnsupportedError(url)
3087
3088 entries = []
3089 for video_url in orderedSet(found):
3090 video_url = unescapeHTML(video_url)
3091 video_url = video_url.replace('\\/', '/')
3092 video_url = compat_urlparse.urljoin(url, video_url)
3093 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3094
3095 # Sometimes, jwplayer extraction will result in a YouTube URL
3096 if YoutubeIE.suitable(video_url):
3097 entries.append(self.url_result(video_url, 'Youtube'))
3098 continue
3099
3100 # here's a fun little line of code for you:
3101 video_id = os.path.splitext(video_id)[0]
3102
3103 entry_info_dict = {
3104 'id': video_id,
3105 'uploader': video_uploader,
3106 'title': video_title,
3107 'age_limit': age_limit,
3108 }
3109
3110 if RtmpIE.suitable(video_url):
3111 entry_info_dict.update({
3112 '_type': 'url_transparent',
3113 'ie_key': RtmpIE.ie_key(),
3114 'url': video_url,
3115 })
3116 entries.append(entry_info_dict)
3117 continue
3118
3119 ext = determine_ext(video_url)
3120 if ext == 'smil':
3121 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3122 elif ext == 'xspf':
3123 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3124 elif ext == 'm3u8':
3125 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3126 elif ext == 'mpd':
3127 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3128 elif ext == 'f4m':
3129 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3130 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3131 # Just matching .ism/manifest is not enough to be reliably sure
3132 # whether it's actually an ISM manifest or some other streaming
3133 # manifest since there are various streaming URL formats
3134 # possible (see [1]) as well as some other shenanigans like
3135 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3136 # so on.
3137 # Thus the most reasonable way to solve this is to delegate
3138 # to generic extractor in order to look into the contents of
3139 # the manifest itself.
3140 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3141 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3142 entry_info_dict = self.url_result(
3143 smuggle_url(video_url, {'to_generic': True}),
3144 GenericIE.ie_key())
3145 else:
3146 entry_info_dict['url'] = video_url
3147
3148 if entry_info_dict.get('formats'):
3149 self._sort_formats(entry_info_dict['formats'])
3150
3151 entries.append(entry_info_dict)
3152
3153 if len(entries) == 1:
3154 return entries[0]
3155 else:
3156 for num, e in enumerate(entries, start=1):
3157 # 'url' results don't have a title
3158 if e.get('title') is not None:
3159 e['title'] = '%s (%d)' % (e['title'], num)
3160 return {
3161 '_type': 'playlist',
3162 'entries': entries,
3163 }