]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
2a9c3e2dea0f397bc24b783550216ea42a582283
[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 (
63 DailymotionIE,
64 DailymotionCloudIE,
65 )
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
105
106
107 class GenericIE(InfoExtractor):
108 IE_DESC = 'Generic downloader that works on some sites'
109 _VALID_URL = r'.*'
110 IE_NAME = 'generic'
111 _TESTS = [
112 # Direct link to a video
113 {
114 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
115 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
116 'info_dict': {
117 'id': 'trailer',
118 'ext': 'mp4',
119 'title': 'trailer',
120 'upload_date': '20100513',
121 }
122 },
123 # Direct link to media delivered compressed (until Accept-Encoding is *)
124 {
125 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
126 'md5': '128c42e68b13950268b648275386fc74',
127 'info_dict': {
128 'id': 'FictionJunction-Parallel_Hearts',
129 'ext': 'flac',
130 'title': 'FictionJunction-Parallel_Hearts',
131 'upload_date': '20140522',
132 },
133 'expected_warnings': [
134 'URL could be a direct video link, returning it as such.'
135 ],
136 'skip': 'URL invalid',
137 },
138 # Direct download with broken HEAD
139 {
140 'url': 'http://ai-radio.org:8000/radio.opus',
141 'info_dict': {
142 'id': 'radio',
143 'ext': 'opus',
144 'title': 'radio',
145 },
146 'params': {
147 'skip_download': True, # infinite live stream
148 },
149 'expected_warnings': [
150 r'501.*Not Implemented',
151 r'400.*Bad Request',
152 ],
153 },
154 # Direct link with incorrect MIME type
155 {
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'md5': '4ccbebe5f36706d85221f204d7eb5913',
158 'info_dict': {
159 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
160 'id': '5_Lennart_Poettering_-_Systemd',
161 'ext': 'webm',
162 'title': '5_Lennart_Poettering_-_Systemd',
163 'upload_date': '20141120',
164 },
165 'expected_warnings': [
166 'URL could be a direct video link, returning it as such.'
167 ]
168 },
169 # RSS feed
170 {
171 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
172 'info_dict': {
173 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
174 'title': 'Zero Punctuation',
175 'description': 're:.*groundbreaking video review series.*'
176 },
177 'playlist_mincount': 11,
178 },
179 # RSS feed with enclosure
180 {
181 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
182 'info_dict': {
183 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
184 'ext': 'm4v',
185 'upload_date': '20150228',
186 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
187 }
188 },
189 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
190 {
191 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
192 'info_dict': {
193 'id': 'smil',
194 'ext': 'mp4',
195 'title': 'Automatics, robotics and biocybernetics',
196 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
197 'upload_date': '20130627',
198 'formats': 'mincount:16',
199 'subtitles': 'mincount:1',
200 },
201 'params': {
202 'force_generic_extractor': True,
203 'skip_download': True,
204 },
205 },
206 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
207 {
208 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
209 'info_dict': {
210 'id': 'hds',
211 'ext': 'flv',
212 'title': 'hds',
213 'formats': 'mincount:1',
214 },
215 'params': {
216 'skip_download': True,
217 },
218 },
219 # SMIL from https://www.restudy.dk/video/play/id/1637
220 {
221 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
222 'info_dict': {
223 'id': 'video_1637',
224 'ext': 'flv',
225 'title': 'video_1637',
226 'formats': 'mincount:3',
227 },
228 'params': {
229 'skip_download': True,
230 },
231 },
232 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
233 {
234 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
235 'info_dict': {
236 'id': 'smil-service',
237 'ext': 'flv',
238 'title': 'smil-service',
239 'formats': 'mincount:1',
240 },
241 'params': {
242 'skip_download': True,
243 },
244 },
245 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
246 {
247 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
248 'info_dict': {
249 'id': '4719370',
250 'ext': 'mp4',
251 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
252 'formats': 'mincount:3',
253 },
254 'params': {
255 'skip_download': True,
256 },
257 },
258 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
259 {
260 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
261 'info_dict': {
262 'id': 'mZlp2ctYIUEB',
263 'ext': 'mp4',
264 'title': 'Tikibad ontruimd wegens brand',
265 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
266 'thumbnail': r're:^https?://.*\.jpg$',
267 'duration': 33,
268 },
269 'params': {
270 'skip_download': True,
271 },
272 },
273 # MPD from http://dash-mse-test.appspot.com/media.html
274 {
275 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
276 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
277 'info_dict': {
278 'id': 'car-20120827-manifest',
279 'ext': 'mp4',
280 'title': 'car-20120827-manifest',
281 'formats': 'mincount:9',
282 'upload_date': '20130904',
283 },
284 'params': {
285 'format': 'bestvideo',
286 },
287 },
288 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
289 {
290 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
291 'info_dict': {
292 'id': 'content',
293 'ext': 'mp4',
294 'title': 'content',
295 'formats': 'mincount:8',
296 },
297 'params': {
298 # m3u8 downloads
299 'skip_download': True,
300 },
301 'skip': 'video gone',
302 },
303 # m3u8 served with Content-Type: text/plain
304 {
305 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
306 'info_dict': {
307 'id': 'index',
308 'ext': 'mp4',
309 'title': 'index',
310 'upload_date': '20140720',
311 'formats': 'mincount:11',
312 },
313 'params': {
314 # m3u8 downloads
315 'skip_download': True,
316 },
317 'skip': 'video gone',
318 },
319 # google redirect
320 {
321 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
322 'info_dict': {
323 'id': 'cmQHVoWB5FY',
324 'ext': 'mp4',
325 'upload_date': '20130224',
326 'uploader_id': 'TheVerge',
327 'description': r're:^Chris Ziegler takes a look at the\.*',
328 'uploader': 'The Verge',
329 'title': 'First Firefox OS phones side-by-side',
330 },
331 'params': {
332 'skip_download': False,
333 }
334 },
335 {
336 # redirect in Refresh HTTP header
337 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
338 'info_dict': {
339 'id': 'pO8h3EaFRdo',
340 'ext': 'mp4',
341 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
342 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
343 'upload_date': '20150917',
344 'uploader_id': 'brtvofficial',
345 'uploader': 'Boiler Room',
346 },
347 'params': {
348 'skip_download': False,
349 },
350 },
351 {
352 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
353 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
354 'info_dict': {
355 'id': '13601338388002',
356 'ext': 'mp4',
357 'uploader': 'www.hodiho.fr',
358 'title': 'R\u00e9gis plante sa Jeep',
359 }
360 },
361 # bandcamp page with custom domain
362 {
363 'add_ie': ['Bandcamp'],
364 'url': 'http://bronyrock.com/track/the-pony-mash',
365 'info_dict': {
366 'id': '3235767654',
367 'ext': 'mp3',
368 'title': 'The Pony Mash',
369 'uploader': 'M_Pallante',
370 },
371 'skip': 'There is a limit of 200 free downloads / month for the test song',
372 },
373 {
374 # embedded brightcove video
375 # it also tests brightcove videos that need to set the 'Referer'
376 # in the http requests
377 'add_ie': ['BrightcoveLegacy'],
378 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
379 'info_dict': {
380 'id': '2765128793001',
381 'ext': 'mp4',
382 'title': 'Le cours de bourse : lā€™analyse technique',
383 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
384 'uploader': 'BFM BUSINESS',
385 },
386 'params': {
387 'skip_download': True,
388 },
389 },
390 {
391 # embedded with itemprop embedURL and video id spelled as `idVideo`
392 'add_id': ['BrightcoveLegacy'],
393 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
394 'info_dict': {
395 'id': '5255628253001',
396 'ext': 'mp4',
397 'title': 'md5:37c519b1128915607601e75a87995fc0',
398 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
399 'uploader': 'BFM BUSINESS',
400 'uploader_id': '876450612001',
401 'timestamp': 1482255315,
402 'upload_date': '20161220',
403 },
404 'params': {
405 'skip_download': True,
406 },
407 },
408 {
409 # https://github.com/rg3/youtube-dl/issues/2253
410 'url': 'http://bcove.me/i6nfkrc3',
411 'md5': '0ba9446db037002366bab3b3eb30c88c',
412 'info_dict': {
413 'id': '3101154703001',
414 'ext': 'mp4',
415 'title': 'Still no power',
416 'uploader': 'thestar.com',
417 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
418 },
419 'add_ie': ['BrightcoveLegacy'],
420 'skip': 'video gone',
421 },
422 {
423 'url': 'http://www.championat.com/video/football/v/87/87499.html',
424 'md5': 'fb973ecf6e4a78a67453647444222983',
425 'info_dict': {
426 'id': '3414141473001',
427 'ext': 'mp4',
428 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
429 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
430 'uploader': 'Championat',
431 },
432 },
433 {
434 # https://github.com/rg3/youtube-dl/issues/3541
435 'add_ie': ['BrightcoveLegacy'],
436 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
437 'info_dict': {
438 'id': '3866516442001',
439 'ext': 'mp4',
440 'title': 'Leer mij vrouwen kennen: Aflevering 1',
441 'description': 'Leer mij vrouwen kennen: Aflevering 1',
442 'uploader': 'SBS Broadcasting',
443 },
444 'skip': 'Restricted to Netherlands',
445 'params': {
446 'skip_download': True, # m3u8 download
447 },
448 },
449 {
450 # Brightcove video in <iframe>
451 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
452 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
453 'info_dict': {
454 'id': '5360463607001',
455 'ext': 'mp4',
456 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
457 'description': 'č”åˆå›½å„æē«„åŸŗ金会äø­äøœå’ŒåŒ—非åŒŗ域大ä½æć€ä½œę›²å®¶ę‰Žå¾·Ā·čæŖę‹‰å°¼ļ¼ˆZade Diraniļ¼‰åœØ3꜈15ę—„å™åˆ©äŗšå†²ēŖēˆ†å‘7å‘Ø幓ēŗŖåæµę—„之际发åøƒäŗ†äøŗ叙利äŗšč°±å†™ēš„ę­Œę›²ć€Šåæƒč·³ć€‹ļ¼ˆHEARTBEATļ¼‰ļ¼Œäøŗ受到六幓冲ēŖå½±å“ēš„叙利äŗšå„æē«„发å‡ŗå¼ŗēƒˆå‘å–Šļ¼Œå‘¼åäø–ē•Œåšå‡ŗ共同åŠŖ力ļ¼Œä½æ叙利äŗšå„æē«„é‡ę–°čŽ·å¾—äŗ«ęœ‰ę­£åøøē«„幓ē”Ÿę“»ēš„ęƒåˆ©ć€‚',
458 'uploader': 'United Nations',
459 'uploader_id': '1362235914001',
460 'timestamp': 1489593889,
461 'upload_date': '20170315',
462 },
463 'add_ie': ['BrightcoveLegacy'],
464 },
465 {
466 # Brightcove with alternative playerID key
467 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
468 'info_dict': {
469 'id': 'nmeth.2062_SV1',
470 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
471 },
472 'playlist': [{
473 'info_dict': {
474 'id': '2228375078001',
475 'ext': 'mp4',
476 'title': 'nmeth.2062-sv1',
477 'description': 'nmeth.2062-sv1',
478 'timestamp': 1363357591,
479 'upload_date': '20130315',
480 'uploader': 'Nature Publishing Group',
481 'uploader_id': '1964492299001',
482 },
483 }],
484 },
485 {
486 # Brightcove with UUID in videoPlayer
487 'url': 'http://www8.hp.com/cn/zh/home.html',
488 'info_dict': {
489 'id': '5255815316001',
490 'ext': 'mp4',
491 'title': 'Sprocket Video - China',
492 'description': 'Sprocket Video - China',
493 'uploader': 'HP-Video Gallery',
494 'timestamp': 1482263210,
495 'upload_date': '20161220',
496 'uploader_id': '1107601872001',
497 },
498 'params': {
499 'skip_download': True, # m3u8 download
500 },
501 'skip': 'video rotates...weekly?',
502 },
503 {
504 # Brightcove:new type [2].
505 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
506 'md5': '2b35148fcf48da41c9fb4591650784f3',
507 'info_dict': {
508 'id': '5348741021001',
509 'ext': 'mp4',
510 'upload_date': '20170306',
511 'uploader_id': '4191638492001',
512 'timestamp': 1488769918,
513 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
514
515 },
516 },
517 {
518 # Alternative brightcove <video> attributes
519 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
520 'info_dict': {
521 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
522 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
523 },
524 'playlist': [{
525 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
526 'info_dict': {
527 'id': '5311302538001',
528 'ext': 'mp4',
529 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
530 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
531 'timestamp': 1486321708,
532 'upload_date': '20170205',
533 'uploader_id': '800000640001',
534 },
535 'only_matching': True,
536 }],
537 },
538 {
539 # Brightcove with UUID in videoPlayer
540 'url': 'http://www8.hp.com/cn/zh/home.html',
541 'info_dict': {
542 'id': '5255815316001',
543 'ext': 'mp4',
544 'title': 'Sprocket Video - China',
545 'description': 'Sprocket Video - China',
546 'uploader': 'HP-Video Gallery',
547 'timestamp': 1482263210,
548 'upload_date': '20161220',
549 'uploader_id': '1107601872001',
550 },
551 'params': {
552 'skip_download': True, # m3u8 download
553 },
554 },
555 # ooyala video
556 {
557 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
558 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
559 'info_dict': {
560 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
561 'ext': 'mp4',
562 'title': '2cc213299525360.mov', # that's what we get
563 'duration': 238.231,
564 },
565 'add_ie': ['Ooyala'],
566 },
567 {
568 # ooyala video embedded with http://player.ooyala.com/iframe.js
569 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
570 'info_dict': {
571 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
572 'ext': 'mp4',
573 'title': '"Steve Jobs: Man in the Machine" trailer',
574 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
575 'duration': 135.427,
576 },
577 'params': {
578 'skip_download': True,
579 },
580 'skip': 'movie expired',
581 },
582 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
583 {
584 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
585 'info_dict': {
586 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
587 'ext': 'mp4',
588 'title': 'Steampunk Fest Comes to Honesdale',
589 'duration': 43.276,
590 },
591 'params': {
592 'skip_download': True,
593 }
594 },
595 # embed.ly video
596 {
597 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
598 'info_dict': {
599 'id': '9ODmcdjQcHQ',
600 'ext': 'mp4',
601 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
602 'upload_date': '20140225',
603 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
604 'uploader': 'Tested',
605 'uploader_id': 'testedcom',
606 },
607 # No need to test YoutubeIE here
608 'params': {
609 'skip_download': True,
610 },
611 },
612 # funnyordie embed
613 {
614 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
615 'info_dict': {
616 'id': '18e820ec3f',
617 'ext': 'mp4',
618 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
619 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
620 },
621 # HEAD requests lead to endless 301, while GET is OK
622 'expected_warnings': ['301'],
623 },
624 # RUTV embed
625 {
626 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
627 'info_dict': {
628 'id': '776940',
629 'ext': 'mp4',
630 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
631 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
632 },
633 'params': {
634 # m3u8 download
635 'skip_download': True,
636 },
637 },
638 # TVC embed
639 {
640 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
641 'info_dict': {
642 'id': '55304',
643 'ext': 'mp4',
644 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
645 },
646 },
647 # SportBox embed
648 {
649 'url': 'http://www.vestifinance.ru/articles/25753',
650 'info_dict': {
651 'id': '25753',
652 'title': 'ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
653 },
654 'playlist': [{
655 'info_dict': {
656 'id': '370908',
657 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
658 'ext': 'mp4',
659 }
660 }, {
661 'info_dict': {
662 'id': '370905',
663 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
664 'ext': 'mp4',
665 }
666 }, {
667 'info_dict': {
668 'id': '370902',
669 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
670 'ext': 'mp4',
671 }
672 }],
673 'params': {
674 # m3u8 download
675 'skip_download': True,
676 },
677 },
678 # Myvi.ru embed
679 {
680 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
681 'info_dict': {
682 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
683 'ext': 'mp4',
684 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
685 'thumbnail': r're:^https?://.*\.jpg$',
686 'duration': 153,
687 }
688 },
689 # XHamster embed
690 {
691 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
692 'info_dict': {
693 'id': 'showthread',
694 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
695 },
696 'playlist_mincount': 7,
697 # This forum does not allow <iframe> syntaxes anymore
698 # Now HTML tags are displayed as-is
699 'skip': 'No videos on this page',
700 },
701 # Embedded TED video
702 {
703 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
704 'md5': '65fdff94098e4a607385a60c5177c638',
705 'info_dict': {
706 'id': '1969',
707 'ext': 'mp4',
708 'title': 'Hidden miracles of the natural world',
709 'uploader': 'Louie Schwartzberg',
710 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
711 }
712 },
713 # nowvideo embed hidden behind percent encoding
714 {
715 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
716 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
717 'info_dict': {
718 'id': '06e53103ca9aa',
719 'ext': 'flv',
720 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
721 'description': 'No description',
722 },
723 },
724 # arte embed
725 {
726 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
727 'md5': '7653032cbb25bf6c80d80f217055fa43',
728 'info_dict': {
729 'id': '048195-004_PLUS7-F',
730 'ext': 'flv',
731 'title': 'X:enius',
732 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
733 'upload_date': '20140320',
734 },
735 'params': {
736 'skip_download': 'Requires rtmpdump'
737 },
738 'skip': 'video gone',
739 },
740 # francetv embed
741 {
742 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
743 'info_dict': {
744 'id': 'EV_30231',
745 'ext': 'mp4',
746 'title': 'Alcaline, le concert avec Calogero',
747 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
748 'upload_date': '20150226',
749 'timestamp': 1424989860,
750 'duration': 5400,
751 },
752 'params': {
753 # m3u8 downloads
754 'skip_download': True,
755 },
756 'expected_warnings': [
757 'Forbidden'
758 ]
759 },
760 # CondƩ Nast embed
761 {
762 'url': 'http://www.wired.com/2014/04/honda-asimo/',
763 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
764 'info_dict': {
765 'id': '53501be369702d3275860000',
766 'ext': 'mp4',
767 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
768 }
769 },
770 # Dailymotion embed
771 {
772 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
773 'md5': '441aeeb82eb72c422c7f14ec533999cd',
774 'info_dict': {
775 'id': 'k2mm4bCdJ6CQ2i7c8o2',
776 'ext': 'mp4',
777 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
778 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
779 'uploader': 'Spi0n',
780 'uploader_id': 'xgditw',
781 'upload_date': '20140425',
782 'timestamp': 1398441542,
783 },
784 'add_ie': ['Dailymotion'],
785 },
786 # DailyMail embed
787 {
788 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
789 'info_dict': {
790 'id': '1495629',
791 'ext': 'mp4',
792 'title': 'Care worker punches elderly dementia patient in head 11 times',
793 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
794 },
795 'add_ie': ['DailyMail'],
796 'params': {
797 'skip_download': True,
798 },
799 },
800 # YouTube embed
801 {
802 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
803 'info_dict': {
804 'id': 'FXRb4ykk4S0',
805 'ext': 'mp4',
806 'title': 'The NBL Auction 2014',
807 'uploader': 'BADMINTON England',
808 'uploader_id': 'BADMINTONEvents',
809 'upload_date': '20140603',
810 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
811 },
812 'add_ie': ['Youtube'],
813 'params': {
814 'skip_download': True,
815 }
816 },
817 # MTVSercices embed
818 {
819 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
820 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
821 'info_dict': {
822 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
823 'ext': 'mp4',
824 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
825 'description': 'Two valets share their love for movie star Liam Neesons.',
826 'timestamp': 1349922600,
827 'upload_date': '20121011',
828 },
829 },
830 # YouTube embed via <data-embed-url="">
831 {
832 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
833 'info_dict': {
834 'id': '4vAffPZIT44',
835 'ext': 'mp4',
836 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
837 'uploader': 'Gameloft',
838 'uploader_id': 'gameloft',
839 'upload_date': '20140828',
840 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
841 },
842 'params': {
843 'skip_download': True,
844 }
845 },
846 # YouTube <object> embed
847 {
848 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
849 'md5': '516718101ec834f74318df76259fb3cc',
850 'info_dict': {
851 'id': 'msN87y-iEx0',
852 'ext': 'webm',
853 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
854 'upload_date': '20080526',
855 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
856 'uploader': 'Christopher Sykes',
857 'uploader_id': 'ChristopherJSykes',
858 },
859 'add_ie': ['Youtube'],
860 },
861 # Camtasia studio
862 {
863 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
864 'playlist': [{
865 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
866 'info_dict': {
867 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
868 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
869 'ext': 'flv',
870 'duration': 2235.90,
871 }
872 }, {
873 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
874 'info_dict': {
875 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
876 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
877 'ext': 'flv',
878 'duration': 2235.93,
879 }
880 }],
881 'info_dict': {
882 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
883 }
884 },
885 # Flowplayer
886 {
887 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
888 'md5': '9d65602bf31c6e20014319c7d07fba27',
889 'info_dict': {
890 'id': '5123ea6d5e5a7',
891 'ext': 'mp4',
892 'age_limit': 18,
893 'uploader': 'www.handjobhub.com',
894 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
895 }
896 },
897 # Multiple brightcove videos
898 # https://github.com/rg3/youtube-dl/issues/2283
899 {
900 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
901 'info_dict': {
902 'id': 'always-never',
903 'title': 'Always / Never - The New Yorker',
904 },
905 'playlist_count': 3,
906 'params': {
907 'extract_flat': False,
908 'skip_download': True,
909 }
910 },
911 # MLB embed
912 {
913 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
914 'md5': '96f09a37e44da40dd083e12d9a683327',
915 'info_dict': {
916 'id': '33322633',
917 'ext': 'mp4',
918 'title': 'Ump changes call to ball',
919 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
920 'duration': 48,
921 'timestamp': 1401537900,
922 'upload_date': '20140531',
923 'thumbnail': r're:^https?://.*\.jpg$',
924 },
925 },
926 # Wistia embed
927 {
928 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
929 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
930 'info_dict': {
931 'id': '6e2wtrbdaf',
932 'ext': 'mov',
933 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
934 'description': 'a Paywall Videos video from Remilon',
935 'duration': 644.072,
936 'uploader': 'study.com',
937 'timestamp': 1459678540,
938 'upload_date': '20160403',
939 'filesize': 24687186,
940 },
941 },
942 {
943 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
944 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
945 'info_dict': {
946 'id': 'uxjb0lwrcz',
947 'ext': 'mp4',
948 'title': 'Conversation about Hexagonal Rails Part 1',
949 'description': 'a Martin Fowler video from ThoughtWorks',
950 'duration': 1715.0,
951 'uploader': 'thoughtworks.wistia.com',
952 'timestamp': 1401832161,
953 'upload_date': '20140603',
954 },
955 },
956 # Wistia standard embed (async)
957 {
958 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
959 'info_dict': {
960 'id': '807fafadvk',
961 'ext': 'mp4',
962 'title': 'Drip Brennan Dunn Workshop',
963 'description': 'a JV Webinars video from getdrip-1',
964 'duration': 4986.95,
965 'timestamp': 1463607249,
966 'upload_date': '20160518',
967 },
968 'params': {
969 'skip_download': True,
970 }
971 },
972 # Soundcloud embed
973 {
974 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
975 'info_dict': {
976 'id': '174391317',
977 'ext': 'mp3',
978 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
979 'uploader': 'Sophos Security',
980 'title': 'Chet Chat 171 - Oct 29, 2014',
981 'upload_date': '20141029',
982 }
983 },
984 # Soundcloud multiple embeds
985 {
986 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
987 'info_dict': {
988 'id': '52809',
989 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
990 },
991 'playlist_mincount': 7,
992 },
993 # TuneIn station embed
994 {
995 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
996 'info_dict': {
997 'id': '204146',
998 'ext': 'mp3',
999 'title': 'CNRV',
1000 'location': 'Paris, France',
1001 'is_live': True,
1002 },
1003 'params': {
1004 # Live stream
1005 'skip_download': True,
1006 },
1007 },
1008 # Livestream embed
1009 {
1010 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1011 'info_dict': {
1012 'id': '67864563',
1013 'ext': 'flv',
1014 'upload_date': '20141112',
1015 'title': 'Rosetta #CometLanding webcast HL 10',
1016 }
1017 },
1018 # Another Livestream embed, without 'new.' in URL
1019 {
1020 'url': 'https://www.freespeech.org/',
1021 'info_dict': {
1022 'id': '123537347',
1023 'ext': 'mp4',
1024 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1025 },
1026 'params': {
1027 # Live stream
1028 'skip_download': True,
1029 },
1030 },
1031 # LazyYT
1032 {
1033 'url': 'https://skiplagged.com/',
1034 'info_dict': {
1035 'id': 'skiplagged',
1036 'title': 'Skiplagged: The smart way to find cheap flights',
1037 },
1038 'playlist_mincount': 1,
1039 'add_ie': ['Youtube'],
1040 },
1041 # Cinchcast embed
1042 {
1043 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1044 'info_dict': {
1045 'id': '7141703',
1046 'ext': 'mp3',
1047 'upload_date': '20141126',
1048 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1049 }
1050 },
1051 # Cinerama player
1052 {
1053 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1054 'info_dict': {
1055 'id': '730m_DandD_1901_512k',
1056 'ext': 'mp4',
1057 'uploader': 'www.abc.net.au',
1058 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1059 }
1060 },
1061 # embedded viddler video
1062 {
1063 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1064 'info_dict': {
1065 'id': '4d03aad9',
1066 'ext': 'mp4',
1067 'uploader': 'deadspin',
1068 'title': 'WALL-TO-GORTAT',
1069 'timestamp': 1422285291,
1070 'upload_date': '20150126',
1071 },
1072 'add_ie': ['Viddler'],
1073 },
1074 # Libsyn embed
1075 {
1076 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1077 'info_dict': {
1078 'id': '3377616',
1079 'ext': 'mp3',
1080 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1081 'description': 'md5:601cb790edd05908957dae8aaa866465',
1082 'upload_date': '20150220',
1083 },
1084 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1085 },
1086 # jwplayer YouTube
1087 {
1088 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1089 'info_dict': {
1090 'id': 'Mrj4DVp2zeA',
1091 'ext': 'mp4',
1092 'upload_date': '20150212',
1093 'uploader': 'The National Archives UK',
1094 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1095 'uploader_id': 'NationalArchives08',
1096 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1097 },
1098 },
1099 # jwplayer rtmp
1100 {
1101 'url': 'http://www.suffolk.edu/sjc/',
1102 'info_dict': {
1103 'id': 'sjclive',
1104 'ext': 'flv',
1105 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1106 'uploader': 'www.suffolk.edu',
1107 },
1108 'params': {
1109 'skip_download': True,
1110 },
1111 'skip': 'does not contain a video anymore',
1112 },
1113 # Complex jwplayer
1114 {
1115 'url': 'http://www.indiedb.com/games/king-machine/videos',
1116 'info_dict': {
1117 'id': 'videos',
1118 'ext': 'mp4',
1119 'title': 'king machine trailer 1',
1120 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1121 'thumbnail': r're:^https?://.*\.jpg$',
1122 },
1123 },
1124 {
1125 # JWPlayer config passed as variable
1126 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1127 'info_dict': {
1128 'id': '3326530_hq',
1129 'ext': 'mp4',
1130 'title': 'ARIELE | Tube Cup',
1131 'uploader': 'www.txxx.com',
1132 'age_limit': 18,
1133 },
1134 'params': {
1135 'skip_download': True,
1136 }
1137 },
1138 {
1139 # Video.js embed, multiple formats
1140 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1141 'info_dict': {
1142 'id': 'yygqldloqIk',
1143 'ext': 'mp4',
1144 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1145 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1146 'upload_date': '20130314',
1147 'uploader': 'PROстŠ¾Šµ3D',
1148 'uploader_id': 'PROstoe3D',
1149 },
1150 'params': {
1151 'skip_download': True,
1152 },
1153 },
1154 {
1155 # Video.js embed, single format
1156 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1157 'info_dict': {
1158 'id': 'watch',
1159 'ext': 'mp4',
1160 'title': 'Step 1 - Good Foundation',
1161 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1162 },
1163 'params': {
1164 'skip_download': True,
1165 },
1166 },
1167 # rtl.nl embed
1168 {
1169 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1170 'playlist_mincount': 5,
1171 'info_dict': {
1172 'id': 'aanslagen-kopenhagen',
1173 'title': 'Aanslagen Kopenhagen',
1174 }
1175 },
1176 # Zapiks embed
1177 {
1178 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1179 'info_dict': {
1180 'id': '118046',
1181 'ext': 'mp4',
1182 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1183 }
1184 },
1185 # Kaltura embed (different embed code)
1186 {
1187 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1188 'info_dict': {
1189 'id': '1_a52wc67y',
1190 'ext': 'flv',
1191 'upload_date': '20150127',
1192 'uploader_id': 'PremierMedia',
1193 'timestamp': int,
1194 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1195 },
1196 },
1197 # Kaltura embed with single quotes
1198 {
1199 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1200 'info_dict': {
1201 'id': '0_izeg5utt',
1202 'ext': 'mp4',
1203 'title': '35871',
1204 'timestamp': 1355743100,
1205 'upload_date': '20121217',
1206 'uploader_id': 'batchUser',
1207 },
1208 'add_ie': ['Kaltura'],
1209 },
1210 {
1211 # Kaltura embedded via quoted entry_id
1212 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1213 'info_dict': {
1214 'id': '0_utuok90b',
1215 'ext': 'mp4',
1216 'title': '06_matthew_brender_raj_dutt',
1217 'timestamp': 1466638791,
1218 'upload_date': '20160622',
1219 },
1220 'add_ie': ['Kaltura'],
1221 'expected_warnings': [
1222 'Could not send HEAD request'
1223 ],
1224 'params': {
1225 'skip_download': True,
1226 }
1227 },
1228 {
1229 # Kaltura embedded, some fileExt broken (#11480)
1230 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1231 'info_dict': {
1232 'id': '1_sgtvehim',
1233 'ext': 'mp4',
1234 'title': 'Our "Standard Models" of particle physics and cosmology',
1235 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1236 'timestamp': 1321158993,
1237 'upload_date': '20111113',
1238 'uploader_id': 'kps1',
1239 },
1240 'add_ie': ['Kaltura'],
1241 },
1242 {
1243 # Kaltura iframe embed
1244 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1245 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1246 'info_dict': {
1247 'id': '0_f2cfbpwy',
1248 'ext': 'mp4',
1249 'title': 'I. M. Pei: A Centennial Celebration',
1250 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1251 'upload_date': '20170403',
1252 'uploader_id': 'batchUser',
1253 'timestamp': 1491232186,
1254 },
1255 'add_ie': ['Kaltura'],
1256 },
1257 # EaglePlatform embed (generic URL)
1258 {
1259 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1260 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1261 'info_dict': {
1262 'id': '227304',
1263 'ext': 'mp4',
1264 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1265 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1266 'thumbnail': r're:^https?://.*\.jpg$',
1267 'duration': 87,
1268 'view_count': int,
1269 'age_limit': 0,
1270 },
1271 'params': {
1272 'skip_download': True,
1273 },
1274 },
1275 # referrer protected EaglePlatform embed
1276 {
1277 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1278 'info_dict': {
1279 'id': '582306',
1280 'ext': 'mp4',
1281 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1282 'thumbnail': r're:^https?://.*\.jpg$',
1283 'duration': 3382,
1284 'view_count': int,
1285 },
1286 'params': {
1287 'skip_download': True,
1288 },
1289 },
1290 # ClipYou (EaglePlatform) embed (custom URL)
1291 {
1292 'url': 'http://muz-tv.ru/play/7129/',
1293 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1294 'info_dict': {
1295 'id': '12820',
1296 'ext': 'mp4',
1297 'title': "'O Sole Mio",
1298 'thumbnail': r're:^https?://.*\.jpg$',
1299 'duration': 216,
1300 'view_count': int,
1301 },
1302 'params': {
1303 'skip_download': True,
1304 },
1305 'skip': 'This video is unavailable.',
1306 },
1307 # Pladform embed
1308 {
1309 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1310 'info_dict': {
1311 'id': '100183293',
1312 'ext': 'mp4',
1313 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1314 '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°',
1315 'thumbnail': r're:^https?://.*\.jpg$',
1316 'duration': 694,
1317 'age_limit': 0,
1318 },
1319 'skip': 'HTTP Error 404: Not Found',
1320 },
1321 # Playwire embed
1322 {
1323 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1324 'info_dict': {
1325 'id': '3519514',
1326 'ext': 'mp4',
1327 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1328 'thumbnail': r're:^https?://.*\.png$',
1329 'duration': 45.115,
1330 },
1331 },
1332 # 5min embed
1333 {
1334 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1335 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1336 'info_dict': {
1337 'id': '518726732',
1338 'ext': 'mp4',
1339 'title': 'Facebook Creates "On This Day" | Crunch Report',
1340 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1341 'timestamp': 1427237531,
1342 'uploader': 'Crunch Report',
1343 'upload_date': '20150324',
1344 },
1345 'params': {
1346 # m3u8 download
1347 'skip_download': True,
1348 },
1349 },
1350 # SVT embed
1351 {
1352 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1353 'info_dict': {
1354 'id': '2900353',
1355 'ext': 'flv',
1356 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1357 'duration': 27,
1358 'age_limit': 0,
1359 },
1360 },
1361 # Crooks and Liars embed
1362 {
1363 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1364 'info_dict': {
1365 'id': '8RUoRhRi',
1366 'ext': 'mp4',
1367 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1368 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1369 'timestamp': 1428207000,
1370 'upload_date': '20150405',
1371 'uploader': 'Heather',
1372 },
1373 },
1374 # Crooks and Liars external embed
1375 {
1376 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1377 'info_dict': {
1378 'id': 'MTE3MjUtMzQ2MzA',
1379 'ext': 'mp4',
1380 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1381 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1382 'timestamp': 1265032391,
1383 'upload_date': '20100201',
1384 'uploader': 'Heather',
1385 },
1386 },
1387 # NBC Sports vplayer embed
1388 {
1389 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1390 'info_dict': {
1391 'id': 'ln7x1qSThw4k',
1392 'ext': 'flv',
1393 'title': "PFT Live: New leader in the 'new-look' defense",
1394 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1395 'uploader': 'NBCU-SPORTS',
1396 'upload_date': '20140107',
1397 'timestamp': 1389118457,
1398 },
1399 'skip': 'Invalid Page URL',
1400 },
1401 # NBC News embed
1402 {
1403 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1404 'md5': '1aa589c675898ae6d37a17913cf68d66',
1405 'info_dict': {
1406 'id': 'x_dtl_oa_LettermanliftPR_160608',
1407 'ext': 'mp4',
1408 'title': 'David Letterman: A Preview',
1409 '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.',
1410 'upload_date': '20160609',
1411 'timestamp': 1465431544,
1412 'uploader': 'NBCU-NEWS',
1413 },
1414 },
1415 # UDN embed
1416 {
1417 'url': 'https://video.udn.com/news/300346',
1418 'md5': 'fd2060e988c326991037b9aff9df21a6',
1419 'info_dict': {
1420 'id': '300346',
1421 'ext': 'mp4',
1422 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1423 'thumbnail': r're:^https?://.*\.jpg$',
1424 },
1425 'params': {
1426 # m3u8 download
1427 'skip_download': True,
1428 },
1429 'expected_warnings': ['Failed to parse JSON Expecting value'],
1430 },
1431 # Ooyala embed
1432 {
1433 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1434 'info_dict': {
1435 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1436 'ext': 'mp4',
1437 'description': 'Index/Match versus VLOOKUP.',
1438 'title': 'This is what separates the Excel masters from the wannabes',
1439 'duration': 191.933,
1440 },
1441 'params': {
1442 # m3u8 downloads
1443 'skip_download': True,
1444 }
1445 },
1446 # Brightcove URL in single quotes
1447 {
1448 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1449 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1450 'info_dict': {
1451 'id': '4255764656001',
1452 'ext': 'mp4',
1453 'title': 'SN Presents: Russell Martin, World Citizen',
1454 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1455 'uploader': 'Rogers Sportsnet',
1456 'uploader_id': '1704050871',
1457 'upload_date': '20150525',
1458 'timestamp': 1432570283,
1459 },
1460 },
1461 # Dailymotion Cloud video
1462 {
1463 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1464 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1465 'info_dict': {
1466 'id': 'x2uy8t3',
1467 'ext': 'mp4',
1468 'title': 'Sauvons les abeilles ! - Le dƩbat',
1469 'description': 'md5:d9082128b1c5277987825d684939ca26',
1470 'thumbnail': r're:^https?://.*\.jpe?g$',
1471 'timestamp': 1434970506,
1472 'upload_date': '20150622',
1473 'uploader': 'Public SĆ©nat',
1474 'uploader_id': 'xa9gza',
1475 },
1476 'skip': 'File not found.',
1477 },
1478 # OnionStudios embed
1479 {
1480 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1481 'info_dict': {
1482 'id': '2855',
1483 'ext': 'mp4',
1484 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1485 'thumbnail': r're:^https?://.*\.jpe?g$',
1486 'uploader': 'ClickHole',
1487 'uploader_id': 'clickhole',
1488 }
1489 },
1490 # SnagFilms embed
1491 {
1492 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1493 'info_dict': {
1494 'id': '74849a00-85a9-11e1-9660-123139220831',
1495 'ext': 'mp4',
1496 'title': '#whilewewatch',
1497 }
1498 },
1499 # AdobeTVVideo embed
1500 {
1501 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1502 'md5': '43662b577c018ad707a63766462b1e87',
1503 'info_dict': {
1504 'id': '2456',
1505 'ext': 'mp4',
1506 'title': 'New experience with Acrobat DC',
1507 'description': 'New experience with Acrobat DC',
1508 'duration': 248.667,
1509 },
1510 },
1511 # BrightcoveInPageEmbed embed
1512 {
1513 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1514 'info_dict': {
1515 'id': '4238694884001',
1516 'ext': 'flv',
1517 'title': 'Tabletop: Dread, Last Thoughts',
1518 'description': 'Tabletop: Dread, Last Thoughts',
1519 'duration': 51690,
1520 },
1521 },
1522 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1523 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1524 {
1525 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1526 'info_dict': {
1527 'id': '4785848093001',
1528 'ext': 'mp4',
1529 'title': 'The Cardinal Pell Interview',
1530 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1531 'uploader': 'GlobeCast Australia - GlobeStream',
1532 'uploader_id': '2733773828001',
1533 'upload_date': '20160304',
1534 'timestamp': 1457083087,
1535 },
1536 'params': {
1537 # m3u8 downloads
1538 'skip_download': True,
1539 },
1540 },
1541 {
1542 # Brightcove embed with whitespace around attribute names
1543 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1544 'info_dict': {
1545 'id': '3167554373001',
1546 'ext': 'mp4',
1547 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1548 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1549 'uploader_id': '1079349493',
1550 'upload_date': '20140207',
1551 'timestamp': 1391810548,
1552 },
1553 'params': {
1554 'skip_download': True,
1555 },
1556 },
1557 # Another form of arte.tv embed
1558 {
1559 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1560 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1561 'info_dict': {
1562 'id': '030273-562_PLUS7-F',
1563 'ext': 'mp4',
1564 'title': 'ARTE Reportage - Nulle part, en France',
1565 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1566 'upload_date': '20160409',
1567 },
1568 },
1569 # LiveLeak embed
1570 {
1571 'url': 'http://www.wykop.pl/link/3088787/',
1572 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1573 'info_dict': {
1574 'id': '874_1459135191',
1575 'ext': 'mp4',
1576 'title': 'Man shows poor quality of new apartment building',
1577 'description': 'The wall is like a sand pile.',
1578 'uploader': 'Lake8737',
1579 },
1580 'add_ie': [LiveLeakIE.ie_key()],
1581 },
1582 # Another LiveLeak embed pattern (#13336)
1583 {
1584 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1585 'info_dict': {
1586 'id': '2eb_1496309988',
1587 'ext': 'mp4',
1588 'title': 'Thief robs place where everyone was armed',
1589 'description': 'md5:694d73ee79e535953cf2488562288eee',
1590 'uploader': 'brazilwtf',
1591 },
1592 'add_ie': [LiveLeakIE.ie_key()],
1593 },
1594 # Duplicated embedded video URLs
1595 {
1596 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1597 'info_dict': {
1598 'id': '149298443_480_16c25b74_2',
1599 'ext': 'mp4',
1600 'title': 'vs. Blue Orange Spring Game',
1601 'uploader': 'www.hudl.com',
1602 },
1603 },
1604 # twitter:player:stream embed
1605 {
1606 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1607 'info_dict': {
1608 'id': 'master',
1609 'ext': 'mp4',
1610 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1611 'uploader': 'www.rtl.be',
1612 },
1613 'params': {
1614 # m3u8 downloads
1615 'skip_download': True,
1616 },
1617 },
1618 # twitter:player embed
1619 {
1620 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1621 'md5': 'a3e0df96369831de324f0778e126653c',
1622 'info_dict': {
1623 'id': '4909620399001',
1624 'ext': 'mp4',
1625 'title': 'What Do Black Holes Sound Like?',
1626 'description': 'what do black holes sound like',
1627 'upload_date': '20160524',
1628 'uploader_id': '29913724001',
1629 'timestamp': 1464107587,
1630 'uploader': 'TheAtlantic',
1631 },
1632 'add_ie': ['BrightcoveLegacy'],
1633 },
1634 # Facebook <iframe> embed
1635 {
1636 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1637 'md5': 'fbcde74f534176ecb015849146dd3aee',
1638 'info_dict': {
1639 'id': '599637780109885',
1640 'ext': 'mp4',
1641 'title': 'Facebook video #599637780109885',
1642 },
1643 },
1644 # Facebook <iframe> embed, plugin video
1645 {
1646 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1647 'info_dict': {
1648 'id': '1754168231264132',
1649 'ext': 'mp4',
1650 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1651 'uploader': 'Tariq Ramadan (official)',
1652 'timestamp': 1496758379,
1653 'upload_date': '20170606',
1654 },
1655 'params': {
1656 'skip_download': True,
1657 },
1658 },
1659 # Facebook API embed
1660 {
1661 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1662 'md5': 'a47372ee61b39a7b90287094d447d94e',
1663 'info_dict': {
1664 'id': '10153467542406923',
1665 'ext': 'mp4',
1666 'title': 'Facebook video #10153467542406923',
1667 },
1668 },
1669 # Wordpress "YouTube Video Importer" plugin
1670 {
1671 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1672 'md5': 'd16797741b560b485194eddda8121b48',
1673 'info_dict': {
1674 'id': 'HNTXWDXV9Is',
1675 'ext': 'mp4',
1676 'title': 'Blue Devils Drumline Stanford lot 2016',
1677 'upload_date': '20160627',
1678 'uploader_id': 'GENOCIDE8GENERAL10',
1679 'uploader': 'cylus cyrus',
1680 },
1681 },
1682 {
1683 # video stored on custom kaltura server
1684 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1685 'md5': '537617d06e64dfed891fa1593c4b30cc',
1686 'info_dict': {
1687 'id': '0_1iotm5bh',
1688 'ext': 'mp4',
1689 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1690 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1691 'uploader_id': 'videos.expansion@el-mundo.net',
1692 'upload_date': '20150429',
1693 'timestamp': 1430303472,
1694 },
1695 'add_ie': ['Kaltura'],
1696 },
1697 {
1698 # Non-standard Vimeo embed
1699 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1700 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1701 'info_dict': {
1702 'id': '148867247',
1703 'ext': 'mp4',
1704 'title': 'Understanding the web - Teaser',
1705 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1706 'upload_date': '20151214',
1707 'uploader': 'OpenClassrooms',
1708 'uploader_id': 'openclassrooms',
1709 },
1710 'add_ie': ['Vimeo'],
1711 },
1712 {
1713 # generic vimeo embed that requires original URL passed as Referer
1714 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1715 'only_matching': True,
1716 },
1717 {
1718 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1719 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1720 'info_dict': {
1721 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1722 'ext': 'mp4',
1723 'title': 'Big Buck Bunny',
1724 'description': 'Royalty free test video',
1725 'timestamp': 1432816365,
1726 'upload_date': '20150528',
1727 'is_live': False,
1728 },
1729 'params': {
1730 'skip_download': True,
1731 },
1732 'add_ie': [ArkenaIE.ie_key()],
1733 },
1734 {
1735 '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/',
1736 'info_dict': {
1737 'id': '1c7141f46c',
1738 'ext': 'mp4',
1739 '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',
1740 },
1741 'params': {
1742 'skip_download': True,
1743 },
1744 'add_ie': [Vbox7IE.ie_key()],
1745 },
1746 {
1747 # DBTV embeds
1748 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1749 'info_dict': {
1750 'id': '43254897',
1751 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1752 },
1753 'playlist_mincount': 3,
1754 },
1755 {
1756 # Videa embeds
1757 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1758 'info_dict': {
1759 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1760 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1761 },
1762 'playlist_mincount': 2,
1763 },
1764 {
1765 # 20 minuten embed
1766 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1767 'info_dict': {
1768 'id': '523629',
1769 'ext': 'mp4',
1770 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1771 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1772 },
1773 'params': {
1774 'skip_download': True,
1775 },
1776 'add_ie': [TwentyMinutenIE.ie_key()],
1777 },
1778 {
1779 # VideoPress embed
1780 'url': 'https://en.support.wordpress.com/videopress/',
1781 'info_dict': {
1782 'id': 'OcobLTqC',
1783 'ext': 'm4v',
1784 'title': 'IMG_5786',
1785 'timestamp': 1435711927,
1786 'upload_date': '20150701',
1787 },
1788 'params': {
1789 'skip_download': True,
1790 },
1791 'add_ie': [VideoPressIE.ie_key()],
1792 },
1793 {
1794 # Rutube embed
1795 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1796 'info_dict': {
1797 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1798 'ext': 'flv',
1799 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1800 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1801 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1802 'upload_date': '20170228',
1803 'uploader_id': '996642',
1804 },
1805 'params': {
1806 'skip_download': True,
1807 },
1808 'add_ie': [RutubeIE.ie_key()],
1809 },
1810 {
1811 # ThePlatform embedded with whitespaces in URLs
1812 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1813 'only_matching': True,
1814 },
1815 {
1816 # Senate ISVP iframe https
1817 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1818 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1819 'info_dict': {
1820 'id': 'govtaff020316',
1821 'ext': 'mp4',
1822 'title': 'Integrated Senate Video Player',
1823 },
1824 'add_ie': [SenateISVPIE.ie_key()],
1825 },
1826 {
1827 # Limelight embeds (1 channel embed + 4 media embeds)
1828 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1829 'info_dict': {
1830 'id': 'FacilitatorTraining2017',
1831 'title': 'Facilitator Training 2017',
1832 },
1833 'playlist_mincount': 5,
1834 },
1835 {
1836 # Limelight embed (LimelightPlayerUtil.embed)
1837 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1838 'info_dict': {
1839 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1840 'ext': 'mp4',
1841 'title': '07448641',
1842 'timestamp': 1499890639,
1843 'upload_date': '20170712',
1844 },
1845 'params': {
1846 'skip_download': True,
1847 },
1848 'add_ie': ['LimelightMedia'],
1849 },
1850 {
1851 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1852 'info_dict': {
1853 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1854 'title': 'Standoff with Walnut Creek murder suspect ends',
1855 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1856 },
1857 'playlist_mincount': 4,
1858 },
1859 {
1860 # WashingtonPost embed
1861 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1862 'info_dict': {
1863 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1864 'ext': 'mp4',
1865 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1866 '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.',
1867 'timestamp': 1455216756,
1868 'uploader': 'The Washington Post',
1869 'upload_date': '20160211',
1870 },
1871 'add_ie': [WashingtonPostIE.ie_key()],
1872 },
1873 {
1874 # Mediaset embed
1875 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1876 'info_dict': {
1877 'id': '720642',
1878 'ext': 'mp4',
1879 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1880 },
1881 'params': {
1882 'skip_download': True,
1883 },
1884 'add_ie': [MediasetIE.ie_key()],
1885 },
1886 {
1887 # JOJ.sk embeds
1888 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1889 'info_dict': {
1890 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1891 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1892 },
1893 'playlist_mincount': 5,
1894 'add_ie': [JojIE.ie_key()],
1895 },
1896 {
1897 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1898 'url': 'https://tvrain.ru/amp/418921/',
1899 'md5': 'cc00413936695987e8de148b67d14f1d',
1900 'info_dict': {
1901 'id': '418921',
1902 'ext': 'mp4',
1903 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1904 },
1905 },
1906 {
1907 # vzaar embed
1908 'url': 'http://help.vzaar.com/article/165-embedding-video',
1909 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1910 'info_dict': {
1911 'id': '8707641',
1912 'ext': 'mp4',
1913 'title': 'Building A Business Online: Principal Chairs Q & A',
1914 },
1915 },
1916 {
1917 # multiple HTML5 videos on one page
1918 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1919 'info_dict': {
1920 'id': 'keyscenarios',
1921 'title': 'Rescue Kit 14 Free Edition - Getting started',
1922 },
1923 'playlist_count': 4,
1924 }
1925 # {
1926 # # TODO: find another test
1927 # # http://schema.org/VideoObject
1928 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1929 # 'md5': '888dcf08b7ea671381f00fab74692755',
1930 # 'info_dict': {
1931 # 'id': 'nyvTSJMKId',
1932 # 'ext': 'mp4',
1933 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1934 # 'description': '#love for cats.',
1935 # 'timestamp': 1461244995,
1936 # 'upload_date': '20160421',
1937 # },
1938 # 'params': {
1939 # 'force_generic_extractor': True,
1940 # },
1941 # }
1942 ]
1943
1944 def report_following_redirect(self, new_url):
1945 """Report information extraction."""
1946 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1947
1948 def _extract_rss(self, url, video_id, doc):
1949 playlist_title = doc.find('./channel/title').text
1950 playlist_desc_el = doc.find('./channel/description')
1951 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1952
1953 entries = []
1954 for it in doc.findall('./channel/item'):
1955 next_url = xpath_text(it, 'link', fatal=False)
1956 if not next_url:
1957 enclosure_nodes = it.findall('./enclosure')
1958 for e in enclosure_nodes:
1959 next_url = e.attrib.get('url')
1960 if next_url:
1961 break
1962
1963 if not next_url:
1964 continue
1965
1966 entries.append({
1967 '_type': 'url_transparent',
1968 'url': next_url,
1969 'title': it.find('title').text,
1970 })
1971
1972 return {
1973 '_type': 'playlist',
1974 'id': url,
1975 'title': playlist_title,
1976 'description': playlist_desc,
1977 'entries': entries,
1978 }
1979
1980 def _extract_camtasia(self, url, video_id, webpage):
1981 """ Returns None if no camtasia video can be found. """
1982
1983 camtasia_cfg = self._search_regex(
1984 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1985 webpage, 'camtasia configuration file', default=None)
1986 if camtasia_cfg is None:
1987 return None
1988
1989 title = self._html_search_meta('DC.title', webpage, fatal=True)
1990
1991 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1992 camtasia_cfg = self._download_xml(
1993 camtasia_url, video_id,
1994 note='Downloading camtasia configuration',
1995 errnote='Failed to download camtasia configuration')
1996 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1997
1998 entries = []
1999 for n in fileset_node.getchildren():
2000 url_n = n.find('./uri')
2001 if url_n is None:
2002 continue
2003
2004 entries.append({
2005 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2006 'title': '%s - %s' % (title, n.tag),
2007 'url': compat_urlparse.urljoin(url, url_n.text),
2008 'duration': float_or_none(n.find('./duration').text),
2009 })
2010
2011 return {
2012 '_type': 'playlist',
2013 'entries': entries,
2014 'title': title,
2015 }
2016
2017 def _real_extract(self, url):
2018 if url.startswith('//'):
2019 return {
2020 '_type': 'url',
2021 'url': self.http_scheme() + url,
2022 }
2023
2024 parsed_url = compat_urlparse.urlparse(url)
2025 if not parsed_url.scheme:
2026 default_search = self._downloader.params.get('default_search')
2027 if default_search is None:
2028 default_search = 'fixup_error'
2029
2030 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2031 if '/' in url:
2032 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2033 return self.url_result('http://' + url)
2034 elif default_search != 'fixup_error':
2035 if default_search == 'auto_warning':
2036 if re.match(r'^(?:url|URL)$', url):
2037 raise ExtractorError(
2038 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2039 expected=True)
2040 else:
2041 self._downloader.report_warning(
2042 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2043 return self.url_result('ytsearch:' + url)
2044
2045 if default_search in ('error', 'fixup_error'):
2046 raise ExtractorError(
2047 '%r is not a valid URL. '
2048 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2049 % (url, url), expected=True)
2050 else:
2051 if ':' not in default_search:
2052 default_search += ':'
2053 return self.url_result(default_search + url)
2054
2055 url, smuggled_data = unsmuggle_url(url)
2056 force_videoid = None
2057 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2058 if smuggled_data and 'force_videoid' in smuggled_data:
2059 force_videoid = smuggled_data['force_videoid']
2060 video_id = force_videoid
2061 else:
2062 video_id = self._generic_id(url)
2063
2064 self.to_screen('%s: Requesting header' % video_id)
2065
2066 head_req = HEADRequest(url)
2067 head_response = self._request_webpage(
2068 head_req, video_id,
2069 note=False, errnote='Could not send HEAD request to %s' % url,
2070 fatal=False)
2071
2072 if head_response is not False:
2073 # Check for redirect
2074 new_url = compat_str(head_response.geturl())
2075 if url != new_url:
2076 self.report_following_redirect(new_url)
2077 if force_videoid:
2078 new_url = smuggle_url(
2079 new_url, {'force_videoid': force_videoid})
2080 return self.url_result(new_url)
2081
2082 full_response = None
2083 if head_response is False:
2084 request = sanitized_Request(url)
2085 request.add_header('Accept-Encoding', '*')
2086 full_response = self._request_webpage(request, video_id)
2087 head_response = full_response
2088
2089 info_dict = {
2090 'id': video_id,
2091 'title': self._generic_title(url),
2092 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2093 }
2094
2095 # Check for direct link to a video
2096 content_type = head_response.headers.get('Content-Type', '').lower()
2097 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2098 if m:
2099 format_id = compat_str(m.group('format_id'))
2100 if format_id.endswith('mpegurl'):
2101 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2102 elif format_id == 'f4m':
2103 formats = self._extract_f4m_formats(url, video_id)
2104 else:
2105 formats = [{
2106 'format_id': format_id,
2107 'url': url,
2108 'vcodec': 'none' if m.group('type') == 'audio' else None
2109 }]
2110 info_dict['direct'] = True
2111 self._sort_formats(formats)
2112 info_dict['formats'] = formats
2113 return info_dict
2114
2115 if not self._downloader.params.get('test', False) and not is_intentional:
2116 force = self._downloader.params.get('force_generic_extractor', False)
2117 self._downloader.report_warning(
2118 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2119
2120 if not full_response:
2121 request = sanitized_Request(url)
2122 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2123 # making it impossible to download only chunk of the file (yet we need only 512kB to
2124 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2125 # that will always result in downloading the whole file that is not desirable.
2126 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2127 # to accept raw bytes and being able to download only a chunk.
2128 # It may probably better to solve this by checking Content-Type for application/octet-stream
2129 # after HEAD request finishes, but not sure if we can rely on this.
2130 request.add_header('Accept-Encoding', '*')
2131 full_response = self._request_webpage(request, video_id)
2132
2133 first_bytes = full_response.read(512)
2134
2135 # Is it an M3U playlist?
2136 if first_bytes.startswith(b'#EXTM3U'):
2137 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2138 self._sort_formats(info_dict['formats'])
2139 return info_dict
2140
2141 # Maybe it's a direct link to a video?
2142 # Be careful not to download the whole thing!
2143 if not is_html(first_bytes):
2144 self._downloader.report_warning(
2145 'URL could be a direct video link, returning it as such.')
2146 info_dict.update({
2147 'direct': True,
2148 'url': url,
2149 })
2150 return info_dict
2151
2152 webpage = self._webpage_read_content(
2153 full_response, url, video_id, prefix=first_bytes)
2154
2155 self.report_extraction(video_id)
2156
2157 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2158 try:
2159 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2160 if doc.tag == 'rss':
2161 return self._extract_rss(url, video_id, doc)
2162 elif doc.tag == 'SmoothStreamingMedia':
2163 info_dict['formats'] = self._parse_ism_formats(doc, url)
2164 self._sort_formats(info_dict['formats'])
2165 return info_dict
2166 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2167 smil = self._parse_smil(doc, url, video_id)
2168 self._sort_formats(smil['formats'])
2169 return smil
2170 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2171 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2172 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2173 info_dict['formats'] = self._parse_mpd_formats(
2174 doc, video_id,
2175 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2176 mpd_url=url)
2177 self._sort_formats(info_dict['formats'])
2178 return info_dict
2179 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2180 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2181 self._sort_formats(info_dict['formats'])
2182 return info_dict
2183 except compat_xml_parse_error:
2184 pass
2185
2186 # Is it a Camtasia project?
2187 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2188 if camtasia_res is not None:
2189 return camtasia_res
2190
2191 # Sometimes embedded video player is hidden behind percent encoding
2192 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2193 # Unescaping the whole page allows to handle those cases in a generic way
2194 webpage = compat_urllib_parse_unquote(webpage)
2195
2196 # it's tempting to parse this further, but you would
2197 # have to take into account all the variations like
2198 # Video Title - Site Name
2199 # Site Name | Video Title
2200 # Video Title - Tagline | Site Name
2201 # and so on and so forth; it's just not practical
2202 video_title = self._og_search_title(
2203 webpage, default=None) or self._html_search_regex(
2204 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2205 default='video')
2206
2207 # Try to detect age limit automatically
2208 age_limit = self._rta_search(webpage)
2209 # And then there are the jokers who advertise that they use RTA,
2210 # but actually don't.
2211 AGE_LIMIT_MARKERS = [
2212 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2213 ]
2214 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2215 age_limit = 18
2216
2217 # video uploader is domain name
2218 video_uploader = self._search_regex(
2219 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2220
2221 video_description = self._og_search_description(webpage, default=None)
2222 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2223
2224 info_dict.update({
2225 'title': video_title,
2226 'description': video_description,
2227 'thumbnail': video_thumbnail,
2228 'age_limit': age_limit,
2229 })
2230
2231 # Look for Brightcove Legacy Studio embeds
2232 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2233 if bc_urls:
2234 entries = [{
2235 '_type': 'url',
2236 'url': smuggle_url(bc_url, {'Referer': url}),
2237 'ie_key': 'BrightcoveLegacy'
2238 } for bc_url in bc_urls]
2239
2240 return {
2241 '_type': 'playlist',
2242 'title': video_title,
2243 'id': video_id,
2244 'entries': entries,
2245 }
2246
2247 # Look for Brightcove New Studio embeds
2248 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2249 if bc_urls:
2250 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2251
2252 # Look for Nexx embeds
2253 nexx_urls = NexxIE._extract_urls(webpage)
2254 if nexx_urls:
2255 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2256
2257 # Look for Nexx iFrame embeds
2258 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2259 if nexx_embed_urls:
2260 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2261
2262 # Look for ThePlatform embeds
2263 tp_urls = ThePlatformIE._extract_urls(webpage)
2264 if tp_urls:
2265 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2266
2267 # Look for Vessel embeds
2268 vessel_urls = VesselIE._extract_urls(webpage)
2269 if vessel_urls:
2270 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2271
2272 # Look for embedded rtl.nl player
2273 matches = re.findall(
2274 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2275 webpage)
2276 if matches:
2277 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2278
2279 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2280 if vimeo_urls:
2281 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2282
2283 vid_me_embed_url = self._search_regex(
2284 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2285 webpage, 'vid.me embed', default=None)
2286 if vid_me_embed_url is not None:
2287 return self.url_result(vid_me_embed_url, 'Vidme')
2288
2289 # Look for YouTube embeds
2290 youtube_urls = YoutubeIE._extract_urls(webpage)
2291 if youtube_urls:
2292 return self.playlist_from_matches(
2293 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2294
2295 matches = DailymotionIE._extract_urls(webpage)
2296 if matches:
2297 return self.playlist_from_matches(matches, video_id, video_title)
2298
2299 # Look for embedded Dailymotion playlist player (#3822)
2300 m = re.search(
2301 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2302 if m:
2303 playlists = re.findall(
2304 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2305 if playlists:
2306 return self.playlist_from_matches(
2307 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2308
2309 # Look for DailyMail embeds
2310 dailymail_urls = DailyMailIE._extract_urls(webpage)
2311 if dailymail_urls:
2312 return self.playlist_from_matches(
2313 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2314
2315 # Look for embedded Wistia player
2316 wistia_url = WistiaIE._extract_url(webpage)
2317 if wistia_url:
2318 return {
2319 '_type': 'url_transparent',
2320 'url': self._proto_relative_url(wistia_url),
2321 'ie_key': WistiaIE.ie_key(),
2322 'uploader': video_uploader,
2323 }
2324
2325 # Look for SVT player
2326 svt_url = SVTIE._extract_url(webpage)
2327 if svt_url:
2328 return self.url_result(svt_url, 'SVT')
2329
2330 # Look for Bandcamp pages with custom domain
2331 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2332 if mobj is not None:
2333 burl = unescapeHTML(mobj.group(1))
2334 # Don't set the extractor because it can be a track url or an album
2335 return self.url_result(burl)
2336
2337 # Look for embedded Vevo player
2338 mobj = re.search(
2339 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2340 if mobj is not None:
2341 return self.url_result(mobj.group('url'))
2342
2343 # Look for embedded Viddler player
2344 mobj = re.search(
2345 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2346 webpage)
2347 if mobj is not None:
2348 return self.url_result(mobj.group('url'))
2349
2350 # Look for NYTimes player
2351 mobj = re.search(
2352 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2353 webpage)
2354 if mobj is not None:
2355 return self.url_result(mobj.group('url'))
2356
2357 # Look for Libsyn player
2358 mobj = re.search(
2359 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2360 if mobj is not None:
2361 return self.url_result(mobj.group('url'))
2362
2363 # Look for Ooyala videos
2364 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2365 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2366 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2367 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2368 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2369 if mobj is not None:
2370 embed_token = self._search_regex(
2371 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2372 webpage, 'ooyala embed token', default=None)
2373 return OoyalaIE._build_url_result(smuggle_url(
2374 mobj.group('ec'), {
2375 'domain': url,
2376 'embed_token': embed_token,
2377 }))
2378
2379 # Look for multiple Ooyala embeds on SBN network websites
2380 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2381 if mobj is not None:
2382 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2383 if embeds:
2384 return self.playlist_from_matches(
2385 embeds, video_id, video_title,
2386 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2387
2388 # Look for Aparat videos
2389 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2390 if mobj is not None:
2391 return self.url_result(mobj.group(1), 'Aparat')
2392
2393 # Look for MPORA videos
2394 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2395 if mobj is not None:
2396 return self.url_result(mobj.group(1), 'Mpora')
2397
2398 # Look for embedded NovaMov-based player
2399 mobj = re.search(
2400 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2401 (?P<url>http://(?:(?:embed|www)\.)?
2402 (?:novamov\.com|
2403 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2404 videoweed\.(?:es|com)|
2405 movshare\.(?:net|sx|ag)|
2406 divxstage\.(?:eu|net|ch|co|at|ag))
2407 /embed\.php.+?)\1''', webpage)
2408 if mobj is not None:
2409 return self.url_result(mobj.group('url'))
2410
2411 # Look for embedded Facebook player
2412 facebook_urls = FacebookIE._extract_urls(webpage)
2413 if facebook_urls:
2414 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2415
2416 # Look for embedded VK player
2417 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2418 if mobj is not None:
2419 return self.url_result(mobj.group('url'), 'VK')
2420
2421 # Look for embedded Odnoklassniki player
2422 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2423 if mobj is not None:
2424 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2425
2426 # Look for embedded ivi player
2427 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2428 if mobj is not None:
2429 return self.url_result(mobj.group('url'), 'Ivi')
2430
2431 # Look for embedded Huffington Post player
2432 mobj = re.search(
2433 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2434 if mobj is not None:
2435 return self.url_result(mobj.group('url'), 'HuffPost')
2436
2437 # Look for embed.ly
2438 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2439 if mobj is not None:
2440 return self.url_result(mobj.group('url'))
2441 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2442 if mobj is not None:
2443 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2444
2445 # Look for funnyordie embed
2446 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2447 if matches:
2448 return self.playlist_from_matches(
2449 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2450
2451 # Look for BBC iPlayer embed
2452 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2453 if matches:
2454 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2455
2456 # Look for embedded RUTV player
2457 rutv_url = RUTVIE._extract_url(webpage)
2458 if rutv_url:
2459 return self.url_result(rutv_url, 'RUTV')
2460
2461 # Look for embedded TVC player
2462 tvc_url = TVCIE._extract_url(webpage)
2463 if tvc_url:
2464 return self.url_result(tvc_url, 'TVC')
2465
2466 # Look for embedded SportBox player
2467 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2468 if sportbox_urls:
2469 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2470
2471 # Look for embedded XHamster player
2472 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2473 if xhamster_urls:
2474 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2475
2476 # Look for embedded TNAFlixNetwork player
2477 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2478 if tnaflix_urls:
2479 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2480
2481 # Look for embedded PornHub player
2482 pornhub_urls = PornHubIE._extract_urls(webpage)
2483 if pornhub_urls:
2484 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2485
2486 # Look for embedded DrTuber player
2487 drtuber_urls = DrTuberIE._extract_urls(webpage)
2488 if drtuber_urls:
2489 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2490
2491 # Look for embedded RedTube player
2492 redtube_urls = RedTubeIE._extract_urls(webpage)
2493 if redtube_urls:
2494 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2495
2496 # Look for embedded Tvigle player
2497 mobj = re.search(
2498 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2499 if mobj is not None:
2500 return self.url_result(mobj.group('url'), 'Tvigle')
2501
2502 # Look for embedded TED player
2503 mobj = re.search(
2504 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2505 if mobj is not None:
2506 return self.url_result(mobj.group('url'), 'TED')
2507
2508 # Look for embedded Ustream videos
2509 ustream_url = UstreamIE._extract_url(webpage)
2510 if ustream_url:
2511 return self.url_result(ustream_url, UstreamIE.ie_key())
2512
2513 # Look for embedded arte.tv player
2514 mobj = re.search(
2515 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2516 webpage)
2517 if mobj is not None:
2518 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2519
2520 # Look for embedded francetv player
2521 mobj = re.search(
2522 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2523 webpage)
2524 if mobj is not None:
2525 return self.url_result(mobj.group('url'))
2526
2527 # Look for embedded smotri.com player
2528 smotri_url = SmotriIE._extract_url(webpage)
2529 if smotri_url:
2530 return self.url_result(smotri_url, 'Smotri')
2531
2532 # Look for embedded Myvi.ru player
2533 myvi_url = MyviIE._extract_url(webpage)
2534 if myvi_url:
2535 return self.url_result(myvi_url)
2536
2537 # Look for embedded soundcloud player
2538 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2539 if soundcloud_urls:
2540 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2541
2542 # Look for tunein player
2543 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2544 if tunein_urls:
2545 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2546
2547 # Look for embedded mtvservices player
2548 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2549 if mtvservices_url:
2550 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2551
2552 # Look for embedded yahoo player
2553 mobj = re.search(
2554 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2555 webpage)
2556 if mobj is not None:
2557 return self.url_result(mobj.group('url'), 'Yahoo')
2558
2559 # Look for embedded sbs.com.au player
2560 mobj = re.search(
2561 r'''(?x)
2562 (?:
2563 <meta\s+property="og:video"\s+content=|
2564 <iframe[^>]+?src=
2565 )
2566 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2567 webpage)
2568 if mobj is not None:
2569 return self.url_result(mobj.group('url'), 'SBS')
2570
2571 # Look for embedded Cinchcast player
2572 mobj = re.search(
2573 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2574 webpage)
2575 if mobj is not None:
2576 return self.url_result(mobj.group('url'), 'Cinchcast')
2577
2578 mobj = re.search(
2579 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2580 webpage)
2581 if not mobj:
2582 mobj = re.search(
2583 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2584 webpage)
2585 if mobj is not None:
2586 return self.url_result(mobj.group('url'), 'MLB')
2587
2588 mobj = re.search(
2589 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2590 webpage)
2591 if mobj is not None:
2592 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2593
2594 mobj = re.search(
2595 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2596 webpage)
2597 if mobj is not None:
2598 return self.url_result(mobj.group('url'), 'Livestream')
2599
2600 # Look for Zapiks embed
2601 mobj = re.search(
2602 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'), 'Zapiks')
2605
2606 # Look for Kaltura embeds
2607 kaltura_url = KalturaIE._extract_url(webpage)
2608 if kaltura_url:
2609 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2610
2611 # Look for EaglePlatform embeds
2612 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2613 if eagleplatform_url:
2614 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2615
2616 # Look for ClipYou (uses EaglePlatform) embeds
2617 mobj = re.search(
2618 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2619 if mobj is not None:
2620 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2621
2622 # Look for Pladform embeds
2623 pladform_url = PladformIE._extract_url(webpage)
2624 if pladform_url:
2625 return self.url_result(pladform_url)
2626
2627 # Look for Videomore embeds
2628 videomore_url = VideomoreIE._extract_url(webpage)
2629 if videomore_url:
2630 return self.url_result(videomore_url)
2631
2632 # Look for Webcaster embeds
2633 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2634 if webcaster_url:
2635 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2636
2637 # Look for Playwire embeds
2638 mobj = re.search(
2639 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2640 if mobj is not None:
2641 return self.url_result(mobj.group('url'))
2642
2643 # Look for 5min embeds
2644 mobj = re.search(
2645 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2646 if mobj is not None:
2647 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2648
2649 # Look for Crooks and Liars embeds
2650 mobj = re.search(
2651 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2652 if mobj is not None:
2653 return self.url_result(mobj.group('url'))
2654
2655 # Look for NBC Sports VPlayer embeds
2656 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2657 if nbc_sports_url:
2658 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2659
2660 # Look for NBC News embeds
2661 nbc_news_embed_url = re.search(
2662 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2663 if nbc_news_embed_url:
2664 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2665
2666 # Look for Google Drive embeds
2667 google_drive_url = GoogleDriveIE._extract_url(webpage)
2668 if google_drive_url:
2669 return self.url_result(google_drive_url, 'GoogleDrive')
2670
2671 # Look for UDN embeds
2672 mobj = re.search(
2673 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2674 if mobj is not None:
2675 return self.url_result(
2676 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2677
2678 # Look for Senate ISVP iframe
2679 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2680 if senate_isvp_url:
2681 return self.url_result(senate_isvp_url, 'SenateISVP')
2682
2683 # Look for Dailymotion Cloud videos
2684 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2685 if dmcloud_url:
2686 return self.url_result(dmcloud_url, 'DailymotionCloud')
2687
2688 # Look for OnionStudios embeds
2689 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2690 if onionstudios_url:
2691 return self.url_result(onionstudios_url)
2692
2693 # Look for ViewLift embeds
2694 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2695 if viewlift_url:
2696 return self.url_result(viewlift_url)
2697
2698 # Look for JWPlatform embeds
2699 jwplatform_url = JWPlatformIE._extract_url(webpage)
2700 if jwplatform_url:
2701 return self.url_result(jwplatform_url, 'JWPlatform')
2702
2703 # Look for Digiteka embeds
2704 digiteka_url = DigitekaIE._extract_url(webpage)
2705 if digiteka_url:
2706 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2707
2708 # Look for Arkena embeds
2709 arkena_url = ArkenaIE._extract_url(webpage)
2710 if arkena_url:
2711 return self.url_result(arkena_url, ArkenaIE.ie_key())
2712
2713 # Look for Piksel embeds
2714 piksel_url = PikselIE._extract_url(webpage)
2715 if piksel_url:
2716 return self.url_result(piksel_url, PikselIE.ie_key())
2717
2718 # Look for Limelight embeds
2719 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2720 if limelight_urls:
2721 return self.playlist_result(
2722 limelight_urls, video_id, video_title, video_description)
2723
2724 # Look for Anvato embeds
2725 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2726 if anvato_urls:
2727 return self.playlist_result(
2728 anvato_urls, video_id, video_title, video_description)
2729
2730 # Look for AdobeTVVideo embeds
2731 mobj = re.search(
2732 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2733 webpage)
2734 if mobj is not None:
2735 return self.url_result(
2736 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2737 'AdobeTVVideo')
2738
2739 # Look for Vine embeds
2740 mobj = re.search(
2741 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2742 webpage)
2743 if mobj is not None:
2744 return self.url_result(
2745 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2746
2747 # Look for VODPlatform embeds
2748 mobj = re.search(
2749 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2750 webpage)
2751 if mobj is not None:
2752 return self.url_result(
2753 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2754
2755 # Look for Mangomolo embeds
2756 mobj = re.search(
2757 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2758 (?:
2759 video\?.*?\bid=(?P<video_id>\d+)|
2760 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2761 ).+?)\1''', webpage)
2762 if mobj is not None:
2763 info = {
2764 '_type': 'url_transparent',
2765 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2766 'title': video_title,
2767 'description': video_description,
2768 'thumbnail': video_thumbnail,
2769 'uploader': video_uploader,
2770 }
2771 video_id = mobj.group('video_id')
2772 if video_id:
2773 info.update({
2774 'ie_key': 'MangomoloVideo',
2775 'id': video_id,
2776 })
2777 else:
2778 info.update({
2779 'ie_key': 'MangomoloLive',
2780 'id': mobj.group('channel_id'),
2781 })
2782 return info
2783
2784 # Look for Instagram embeds
2785 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2786 if instagram_embed_url is not None:
2787 return self.url_result(
2788 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2789
2790 # Look for LiveLeak embeds
2791 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2792 if liveleak_urls:
2793 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2794
2795 # Look for 3Q SDN embeds
2796 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2797 if threeqsdn_url:
2798 return {
2799 '_type': 'url_transparent',
2800 'ie_key': ThreeQSDNIE.ie_key(),
2801 'url': self._proto_relative_url(threeqsdn_url),
2802 'title': video_title,
2803 'description': video_description,
2804 'thumbnail': video_thumbnail,
2805 'uploader': video_uploader,
2806 }
2807
2808 # Look for VBOX7 embeds
2809 vbox7_url = Vbox7IE._extract_url(webpage)
2810 if vbox7_url:
2811 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2812
2813 # Look for DBTV embeds
2814 dbtv_urls = DBTVIE._extract_urls(webpage)
2815 if dbtv_urls:
2816 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2817
2818 # Look for Videa embeds
2819 videa_urls = VideaIE._extract_urls(webpage)
2820 if videa_urls:
2821 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2822
2823 # Look for 20 minuten embeds
2824 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2825 if twentymin_urls:
2826 return self.playlist_from_matches(
2827 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2828
2829 # Look for Openload embeds
2830 openload_urls = OpenloadIE._extract_urls(webpage)
2831 if openload_urls:
2832 return self.playlist_from_matches(
2833 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2834
2835 # Look for VideoPress embeds
2836 videopress_urls = VideoPressIE._extract_urls(webpage)
2837 if videopress_urls:
2838 return self.playlist_from_matches(
2839 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2840
2841 # Look for Rutube embeds
2842 rutube_urls = RutubeIE._extract_urls(webpage)
2843 if rutube_urls:
2844 return self.playlist_from_matches(
2845 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2846
2847 # Look for WashingtonPost embeds
2848 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2849 if wapo_urls:
2850 return self.playlist_from_matches(
2851 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2852
2853 # Look for Mediaset embeds
2854 mediaset_urls = MediasetIE._extract_urls(webpage)
2855 if mediaset_urls:
2856 return self.playlist_from_matches(
2857 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2858
2859 # Look for JOJ.sk embeds
2860 joj_urls = JojIE._extract_urls(webpage)
2861 if joj_urls:
2862 return self.playlist_from_matches(
2863 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2864
2865 # Look for megaphone.fm embeds
2866 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2867 if mpfn_urls:
2868 return self.playlist_from_matches(
2869 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2870
2871 # Look for vzaar embeds
2872 vzaar_urls = VzaarIE._extract_urls(webpage)
2873 if vzaar_urls:
2874 return self.playlist_from_matches(
2875 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2876
2877 channel9_urls = Channel9IE._extract_urls(webpage)
2878 if channel9_urls:
2879 return self.playlist_from_matches(
2880 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2881
2882 def merge_dicts(dict1, dict2):
2883 merged = {}
2884 for k, v in dict1.items():
2885 if v is not None:
2886 merged[k] = v
2887 for k, v in dict2.items():
2888 if v is None:
2889 continue
2890 if (k not in merged or
2891 (isinstance(v, compat_str) and v and
2892 isinstance(merged[k], compat_str) and
2893 not merged[k])):
2894 merged[k] = v
2895 return merged
2896
2897 # Look for HTML5 media
2898 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2899 if entries:
2900 if len(entries) == 1:
2901 entries[0].update({
2902 'id': video_id,
2903 'title': video_title,
2904 })
2905 else:
2906 for num, entry in enumerate(entries, start=1):
2907 entry.update({
2908 'id': '%s-%s' % (video_id, num),
2909 'title': '%s (%d)' % (video_title, num),
2910 })
2911 for entry in entries:
2912 self._sort_formats(entry['formats'])
2913 return self.playlist_result(entries, video_id, video_title)
2914
2915 jwplayer_data = self._find_jwplayer_data(
2916 webpage, video_id, transform_source=js_to_json)
2917 if jwplayer_data:
2918 info = self._parse_jwplayer_data(
2919 jwplayer_data, video_id, require_title=False, base_url=url)
2920 return merge_dicts(info, info_dict)
2921
2922 # Video.js embed
2923 mobj = re.search(
2924 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2925 webpage)
2926 if mobj is not None:
2927 sources = self._parse_json(
2928 mobj.group(1), video_id, transform_source=js_to_json,
2929 fatal=False) or []
2930 if not isinstance(sources, list):
2931 sources = [sources]
2932 formats = []
2933 for source in sources:
2934 src = source.get('src')
2935 if not src or not isinstance(src, compat_str):
2936 continue
2937 src = compat_urlparse.urljoin(url, src)
2938 src_type = source.get('type')
2939 if isinstance(src_type, compat_str):
2940 src_type = src_type.lower()
2941 ext = determine_ext(src).lower()
2942 if src_type == 'video/youtube':
2943 return self.url_result(src, YoutubeIE.ie_key())
2944 if src_type == 'application/dash+xml' or ext == 'mpd':
2945 formats.extend(self._extract_mpd_formats(
2946 src, video_id, mpd_id='dash', fatal=False))
2947 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2948 formats.extend(self._extract_m3u8_formats(
2949 src, video_id, 'mp4', entry_protocol='m3u8_native',
2950 m3u8_id='hls', fatal=False))
2951 else:
2952 formats.append({
2953 'url': src,
2954 'ext': (mimetype2ext(src_type) or
2955 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2956 })
2957 if formats:
2958 self._sort_formats(formats)
2959 info_dict['formats'] = formats
2960 return info_dict
2961
2962 # Looking for http://schema.org/VideoObject
2963 json_ld = self._search_json_ld(
2964 webpage, video_id, default={}, expected_type='VideoObject')
2965 if json_ld.get('url'):
2966 return merge_dicts(json_ld, info_dict)
2967
2968 def check_video(vurl):
2969 if YoutubeIE.suitable(vurl):
2970 return True
2971 if RtmpIE.suitable(vurl):
2972 return True
2973 vpath = compat_urlparse.urlparse(vurl).path
2974 vext = determine_ext(vpath)
2975 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2976
2977 def filter_video(urls):
2978 return list(filter(check_video, urls))
2979
2980 # Start with something easy: JW Player in SWFObject
2981 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2982 if not found:
2983 # Look for gorilla-vid style embedding
2984 found = filter_video(re.findall(r'''(?sx)
2985 (?:
2986 jw_plugins|
2987 JWPlayerOptions|
2988 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2989 )
2990 .*?
2991 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2992 if not found:
2993 # Broaden the search a little bit
2994 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2995 if not found:
2996 # Broaden the findall a little bit: JWPlayer JS loader
2997 found = filter_video(re.findall(
2998 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2999 if not found:
3000 # Flow player
3001 found = filter_video(re.findall(r'''(?xs)
3002 flowplayer\("[^"]+",\s*
3003 \{[^}]+?\}\s*,
3004 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3005 ["']?url["']?\s*:\s*["']([^"']+)["']
3006 ''', webpage))
3007 if not found:
3008 # Cinerama player
3009 found = re.findall(
3010 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3011 if not found:
3012 # Try to find twitter cards info
3013 # twitter:player:stream should be checked before twitter:player since
3014 # it is expected to contain a raw stream (see
3015 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3016 found = filter_video(re.findall(
3017 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3018 if not found:
3019 # We look for Open Graph info:
3020 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3021 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3022 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3023 if m_video_type is not None:
3024 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3025 if not found:
3026 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3027 found = re.search(
3028 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3029 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3030 webpage)
3031 if not found:
3032 # Look also in Refresh HTTP header
3033 refresh_header = head_response.headers.get('Refresh')
3034 if refresh_header:
3035 # In python 2 response HTTP headers are bytestrings
3036 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3037 refresh_header = refresh_header.decode('iso-8859-1')
3038 found = re.search(REDIRECT_REGEX, refresh_header)
3039 if found:
3040 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3041 if new_url != url:
3042 self.report_following_redirect(new_url)
3043 return {
3044 '_type': 'url',
3045 'url': new_url,
3046 }
3047 else:
3048 found = None
3049
3050 if not found:
3051 # twitter:player is a https URL to iframe player that may or may not
3052 # be supported by youtube-dl thus this is checked the very last (see
3053 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3054 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3055 if embed_url and embed_url != url:
3056 return self.url_result(embed_url)
3057
3058 if not found:
3059 raise UnsupportedError(url)
3060
3061 entries = []
3062 for video_url in orderedSet(found):
3063 video_url = unescapeHTML(video_url)
3064 video_url = video_url.replace('\\/', '/')
3065 video_url = compat_urlparse.urljoin(url, video_url)
3066 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3067
3068 # Sometimes, jwplayer extraction will result in a YouTube URL
3069 if YoutubeIE.suitable(video_url):
3070 entries.append(self.url_result(video_url, 'Youtube'))
3071 continue
3072
3073 # here's a fun little line of code for you:
3074 video_id = os.path.splitext(video_id)[0]
3075
3076 entry_info_dict = {
3077 'id': video_id,
3078 'uploader': video_uploader,
3079 'title': video_title,
3080 'age_limit': age_limit,
3081 }
3082
3083 if RtmpIE.suitable(video_url):
3084 entry_info_dict.update({
3085 '_type': 'url_transparent',
3086 'ie_key': RtmpIE.ie_key(),
3087 'url': video_url,
3088 })
3089 entries.append(entry_info_dict)
3090 continue
3091
3092 ext = determine_ext(video_url)
3093 if ext == 'smil':
3094 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3095 elif ext == 'xspf':
3096 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3097 elif ext == 'm3u8':
3098 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3099 elif ext == 'mpd':
3100 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3101 elif ext == 'f4m':
3102 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3103 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3104 # Just matching .ism/manifest is not enough to be reliably sure
3105 # whether it's actually an ISM manifest or some other streaming
3106 # manifest since there are various streaming URL formats
3107 # possible (see [1]) as well as some other shenanigans like
3108 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3109 # so on.
3110 # Thus the most reasonable way to solve this is to delegate
3111 # to generic extractor in order to look into the contents of
3112 # the manifest itself.
3113 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3114 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3115 entry_info_dict = self.url_result(
3116 smuggle_url(video_url, {'to_generic': True}),
3117 GenericIE.ie_key())
3118 else:
3119 entry_info_dict['url'] = video_url
3120
3121 if entry_info_dict.get('formats'):
3122 self._sort_formats(entry_info_dict['formats'])
3123
3124 entries.append(entry_info_dict)
3125
3126 if len(entries) == 1:
3127 return entries[0]
3128 else:
3129 for num, e in enumerate(entries, start=1):
3130 # 'url' results don't have a title
3131 if e.get('title') is not None:
3132 e['title'] = '%s (%d)' % (e['title'], num)
3133 return {
3134 '_type': 'playlist',
3135 'entries': entries,
3136 }