]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Rapsys Git / youtubedl / blob
? search:
summary | shortlog | log | commit | commitdiff | tree
history | raw | HEAD
New upstream version 2017.02.24.1
[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_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 js_to_json,
24 orderedSet,
25 sanitized_Request,
26 smuggle_url,
27 unescapeHTML,
28 unified_strdate,
29 unsmuggle_url,
30 UnsupportedError,
31 xpath_text,
32 )
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
35 BrightcoveLegacyIE,
36 BrightcoveNewIE,
37 )
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
56 DailymotionIE,
57 DailymotionCloudIE,
58 )
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87
88
89 class GenericIE(InfoExtractor):
90 IE_DESC = 'Generic downloader that works on some sites'
91 _VALID_URL = r'.*'
92 IE_NAME = 'generic'
93 _TESTS = [
94 # Direct link to a video
95 {
96 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
97 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
98 'info_dict': {
99 'id': 'trailer',
100 'ext': 'mp4',
101 'title': 'trailer',
102 'upload_date': '20100513',
103 }
104 },
105 # Direct link to media delivered compressed (until Accept-Encoding is *)
106 {
107 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
108 'md5': '128c42e68b13950268b648275386fc74',
109 'info_dict': {
110 'id': 'FictionJunction-Parallel_Hearts',
111 'ext': 'flac',
112 'title': 'FictionJunction-Parallel_Hearts',
113 'upload_date': '20140522',
114 },
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
117 ],
118 'skip': 'URL invalid',
119 },
120 # Direct download with broken HEAD
121 {
122 'url': 'http://ai-radio.org:8000/radio.opus',
123 'info_dict': {
124 'id': 'radio',
125 'ext': 'opus',
126 'title': 'radio',
127 },
128 'params': {
129 'skip_download': True, # infinite live stream
130 },
131 'expected_warnings': [
132 r'501.*Not Implemented',
133 r'400.*Bad Request',
134 ],
135 },
136 # Direct link with incorrect MIME type
137 {
138 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
139 'md5': '4ccbebe5f36706d85221f204d7eb5913',
140 'info_dict': {
141 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
142 'id': '5_Lennart_Poettering_-_Systemd',
143 'ext': 'webm',
144 'title': '5_Lennart_Poettering_-_Systemd',
145 'upload_date': '20141120',
146 },
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
149 ]
150 },
151 # RSS feed
152 {
153 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
154 'info_dict': {
155 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
156 'title': 'Zero Punctuation',
157 'description': 're:.*groundbreaking video review series.*'
158 },
159 'playlist_mincount': 11,
160 },
161 # RSS feed with enclosure
162 {
163 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
164 'info_dict': {
165 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
166 'ext': 'm4v',
167 'upload_date': '20150228',
168 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
169 }
170 },
171 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
172 {
173 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
174 'info_dict': {
175 'id': 'smil',
176 'ext': 'mp4',
177 'title': 'Automatics, robotics and biocybernetics',
178 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
179 'upload_date': '20130627',
180 'formats': 'mincount:16',
181 'subtitles': 'mincount:1',
182 },
183 'params': {
184 'force_generic_extractor': True,
185 'skip_download': True,
186 },
187 },
188 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
189 {
190 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
191 'info_dict': {
192 'id': 'hds',
193 'ext': 'flv',
194 'title': 'hds',
195 'formats': 'mincount:1',
196 },
197 'params': {
198 'skip_download': True,
199 },
200 },
201 # SMIL from https://www.restudy.dk/video/play/id/1637
202 {
203 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
204 'info_dict': {
205 'id': 'video_1637',
206 'ext': 'flv',
207 'title': 'video_1637',
208 'formats': 'mincount:3',
209 },
210 'params': {
211 'skip_download': True,
212 },
213 },
214 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
215 {
216 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
217 'info_dict': {
218 'id': 'smil-service',
219 'ext': 'flv',
220 'title': 'smil-service',
221 'formats': 'mincount:1',
222 },
223 'params': {
224 'skip_download': True,
225 },
226 },
227 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
228 {
229 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
230 'info_dict': {
231 'id': '4719370',
232 'ext': 'mp4',
233 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
234 'formats': 'mincount:3',
235 },
236 'params': {
237 'skip_download': True,
238 },
239 },
240 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
241 {
242 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
243 'info_dict': {
244 'id': 'mZlp2ctYIUEB',
245 'ext': 'mp4',
246 'title': 'Tikibad ontruimd wegens brand',
247 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
248 'thumbnail': r're:^https?://.*\.jpg$',
249 'duration': 33,
250 },
251 'params': {
252 'skip_download': True,
253 },
254 },
255 # MPD from http://dash-mse-test.appspot.com/media.html
256 {
257 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
258 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
259 'info_dict': {
260 'id': 'car-20120827-manifest',
261 'ext': 'mp4',
262 'title': 'car-20120827-manifest',
263 'formats': 'mincount:9',
264 'upload_date': '20130904',
265 },
266 'params': {
267 'format': 'bestvideo',
268 },
269 },
270 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
271 {
272 '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',
273 'info_dict': {
274 'id': 'content',
275 'ext': 'mp4',
276 'title': 'content',
277 'formats': 'mincount:8',
278 },
279 'params': {
280 # m3u8 downloads
281 'skip_download': True,
282 },
283 'skip': 'video gone',
284 },
285 # m3u8 served with Content-Type: text/plain
286 {
287 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
288 'info_dict': {
289 'id': 'index',
290 'ext': 'mp4',
291 'title': 'index',
292 'upload_date': '20140720',
293 'formats': 'mincount:11',
294 },
295 'params': {
296 # m3u8 downloads
297 'skip_download': True,
298 },
299 'skip': 'video gone',
300 },
301 # google redirect
302 {
303 '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',
304 'info_dict': {
305 'id': 'cmQHVoWB5FY',
306 'ext': 'mp4',
307 'upload_date': '20130224',
308 'uploader_id': 'TheVerge',
309 'description': r're:^Chris Ziegler takes a look at the\.*',
310 'uploader': 'The Verge',
311 'title': 'First Firefox OS phones side-by-side',
312 },
313 'params': {
314 'skip_download': False,
315 }
316 },
317 {
318 # redirect in Refresh HTTP header
319 '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',
320 'info_dict': {
321 'id': 'pO8h3EaFRdo',
322 'ext': 'mp4',
323 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
324 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
325 'upload_date': '20150917',
326 'uploader_id': 'brtvofficial',
327 'uploader': 'Boiler Room',
328 },
329 'params': {
330 'skip_download': False,
331 },
332 },
333 {
334 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
335 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
336 'info_dict': {
337 'id': '13601338388002',
338 'ext': 'mp4',
339 'uploader': 'www.hodiho.fr',
340 'title': 'R\u00e9gis plante sa Jeep',
341 }
342 },
343 # bandcamp page with custom domain
344 {
345 'add_ie': ['Bandcamp'],
346 'url': 'http://bronyrock.com/track/the-pony-mash',
347 'info_dict': {
348 'id': '3235767654',
349 'ext': 'mp3',
350 'title': 'The Pony Mash',
351 'uploader': 'M_Pallante',
352 },
353 'skip': 'There is a limit of 200 free downloads / month for the test song',
354 },
355 {
356 # embedded brightcove video
357 # it also tests brightcove videos that need to set the 'Referer'
358 # in the http requests
359 'add_ie': ['BrightcoveLegacy'],
360 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
361 'info_dict': {
362 'id': '2765128793001',
363 'ext': 'mp4',
364 'title': 'Le cours de bourse : lā€™analyse technique',
365 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
366 'uploader': 'BFM BUSINESS',
367 },
368 'params': {
369 'skip_download': True,
370 },
371 },
372 {
373 # embedded with itemprop embedURL and video id spelled as `idVideo`
374 'add_id': ['BrightcoveLegacy'],
375 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
376 'info_dict': {
377 'id': '5255628253001',
378 'ext': 'mp4',
379 'title': 'md5:37c519b1128915607601e75a87995fc0',
380 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
381 'uploader': 'BFM BUSINESS',
382 'uploader_id': '876450612001',
383 'timestamp': 1482255315,
384 'upload_date': '20161220',
385 },
386 'params': {
387 'skip_download': True,
388 },
389 },
390 {
391 # https://github.com/rg3/youtube-dl/issues/2253
392 'url': 'http://bcove.me/i6nfkrc3',
393 'md5': '0ba9446db037002366bab3b3eb30c88c',
394 'info_dict': {
395 'id': '3101154703001',
396 'ext': 'mp4',
397 'title': 'Still no power',
398 'uploader': 'thestar.com',
399 '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.',
400 },
401 'add_ie': ['BrightcoveLegacy'],
402 'skip': 'video gone',
403 },
404 {
405 'url': 'http://www.championat.com/video/football/v/87/87499.html',
406 'md5': 'fb973ecf6e4a78a67453647444222983',
407 'info_dict': {
408 'id': '3414141473001',
409 'ext': 'mp4',
410 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
411 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
412 'uploader': 'Championat',
413 },
414 },
415 {
416 # https://github.com/rg3/youtube-dl/issues/3541
417 'add_ie': ['BrightcoveLegacy'],
418 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
419 'info_dict': {
420 'id': '3866516442001',
421 'ext': 'mp4',
422 'title': 'Leer mij vrouwen kennen: Aflevering 1',
423 'description': 'Leer mij vrouwen kennen: Aflevering 1',
424 'uploader': 'SBS Broadcasting',
425 },
426 'skip': 'Restricted to Netherlands',
427 'params': {
428 'skip_download': True, # m3u8 download
429 },
430 },
431 {
432 # Brightcove with alternative playerID key
433 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
434 'info_dict': {
435 'id': 'nmeth.2062_SV1',
436 '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',
437 },
438 'playlist': [{
439 'info_dict': {
440 'id': '2228375078001',
441 'ext': 'mp4',
442 'title': 'nmeth.2062-sv1',
443 'description': 'nmeth.2062-sv1',
444 'timestamp': 1363357591,
445 'upload_date': '20130315',
446 'uploader': 'Nature Publishing Group',
447 'uploader_id': '1964492299001',
448 },
449 }],
450 },
451 # ooyala video
452 {
453 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
454 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
455 'info_dict': {
456 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
457 'ext': 'mp4',
458 'title': '2cc213299525360.mov', # that's what we get
459 'duration': 238.231,
460 },
461 'add_ie': ['Ooyala'],
462 },
463 {
464 # ooyala video embedded with http://player.ooyala.com/iframe.js
465 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
466 'info_dict': {
467 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
468 'ext': 'mp4',
469 'title': '"Steve Jobs: Man in the Machine" trailer',
470 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
471 'duration': 135.427,
472 },
473 'params': {
474 'skip_download': True,
475 },
476 'skip': 'movie expired',
477 },
478 # embed.ly video
479 {
480 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
481 'info_dict': {
482 'id': '9ODmcdjQcHQ',
483 'ext': 'mp4',
484 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
485 'upload_date': '20140225',
486 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
487 'uploader': 'Tested',
488 'uploader_id': 'testedcom',
489 },
490 # No need to test YoutubeIE here
491 'params': {
492 'skip_download': True,
493 },
494 },
495 # funnyordie embed
496 {
497 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
498 'info_dict': {
499 'id': '18e820ec3f',
500 'ext': 'mp4',
501 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
502 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
503 },
504 # HEAD requests lead to endless 301, while GET is OK
505 'expected_warnings': ['301'],
506 },
507 # RUTV embed
508 {
509 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
510 'info_dict': {
511 'id': '776940',
512 'ext': 'mp4',
513 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
514 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
515 },
516 'params': {
517 # m3u8 download
518 'skip_download': True,
519 },
520 },
521 # TVC embed
522 {
523 '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/',
524 'info_dict': {
525 'id': '55304',
526 'ext': 'mp4',
527 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
528 },
529 },
530 # SportBox embed
531 {
532 'url': 'http://www.vestifinance.ru/articles/25753',
533 'info_dict': {
534 'id': '25753',
535 '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"',
536 },
537 'playlist': [{
538 'info_dict': {
539 'id': '370908',
540 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
541 'ext': 'mp4',
542 }
543 }, {
544 'info_dict': {
545 'id': '370905',
546 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
547 'ext': 'mp4',
548 }
549 }, {
550 'info_dict': {
551 'id': '370902',
552 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
553 'ext': 'mp4',
554 }
555 }],
556 'params': {
557 # m3u8 download
558 'skip_download': True,
559 },
560 },
561 # Myvi.ru embed
562 {
563 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
564 'info_dict': {
565 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
566 'ext': 'mp4',
567 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
568 'thumbnail': r're:^https?://.*\.jpg$',
569 'duration': 153,
570 }
571 },
572 # XHamster embed
573 {
574 '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',
575 'info_dict': {
576 'id': 'showthread',
577 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
578 },
579 'playlist_mincount': 7,
580 # This forum does not allow <iframe> syntaxes anymore
581 # Now HTML tags are displayed as-is
582 'skip': 'No videos on this page',
583 },
584 # Embedded TED video
585 {
586 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
587 'md5': '65fdff94098e4a607385a60c5177c638',
588 'info_dict': {
589 'id': '1969',
590 'ext': 'mp4',
591 'title': 'Hidden miracles of the natural world',
592 'uploader': 'Louie Schwartzberg',
593 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
594 }
595 },
596 # nowvideo embed hidden behind percent encoding
597 {
598 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
599 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
600 'info_dict': {
601 'id': '06e53103ca9aa',
602 'ext': 'flv',
603 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
604 'description': 'No description',
605 },
606 },
607 # arte embed
608 {
609 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
610 'md5': '7653032cbb25bf6c80d80f217055fa43',
611 'info_dict': {
612 'id': '048195-004_PLUS7-F',
613 'ext': 'flv',
614 'title': 'X:enius',
615 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
616 'upload_date': '20140320',
617 },
618 'params': {
619 'skip_download': 'Requires rtmpdump'
620 },
621 'skip': 'video gone',
622 },
623 # francetv embed
624 {
625 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
626 'info_dict': {
627 'id': 'EV_30231',
628 'ext': 'mp4',
629 'title': 'Alcaline, le concert avec Calogero',
630 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
631 'upload_date': '20150226',
632 'timestamp': 1424989860,
633 'duration': 5400,
634 },
635 'params': {
636 # m3u8 downloads
637 'skip_download': True,
638 },
639 'expected_warnings': [
640 'Forbidden'
641 ]
642 },
643 # CondƩ Nast embed
644 {
645 'url': 'http://www.wired.com/2014/04/honda-asimo/',
646 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
647 'info_dict': {
648 'id': '53501be369702d3275860000',
649 'ext': 'mp4',
650 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
651 }
652 },
653 # Dailymotion embed
654 {
655 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
656 'md5': '441aeeb82eb72c422c7f14ec533999cd',
657 'info_dict': {
658 'id': 'k2mm4bCdJ6CQ2i7c8o2',
659 'ext': 'mp4',
660 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
661 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
662 'uploader': 'Spi0n',
663 'uploader_id': 'xgditw',
664 'upload_date': '20140425',
665 'timestamp': 1398441542,
666 },
667 'add_ie': ['Dailymotion'],
668 },
669 # YouTube embed
670 {
671 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
672 'info_dict': {
673 'id': 'FXRb4ykk4S0',
674 'ext': 'mp4',
675 'title': 'The NBL Auction 2014',
676 'uploader': 'BADMINTON England',
677 'uploader_id': 'BADMINTONEvents',
678 'upload_date': '20140603',
679 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
680 },
681 'add_ie': ['Youtube'],
682 'params': {
683 'skip_download': True,
684 }
685 },
686 # MTVSercices embed
687 {
688 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
689 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
690 'info_dict': {
691 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
692 'ext': 'mp4',
693 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
694 'description': 'Two valets share their love for movie star Liam Neesons.',
695 'timestamp': 1349922600,
696 'upload_date': '20121011',
697 },
698 },
699 # YouTube embed via <data-embed-url="">
700 {
701 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
702 'info_dict': {
703 'id': '4vAffPZIT44',
704 'ext': 'mp4',
705 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
706 'uploader': 'Gameloft',
707 'uploader_id': 'gameloft',
708 'upload_date': '20140828',
709 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
710 },
711 'params': {
712 'skip_download': True,
713 }
714 },
715 # Camtasia studio
716 {
717 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
718 'playlist': [{
719 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
720 'info_dict': {
721 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
722 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
723 'ext': 'flv',
724 'duration': 2235.90,
725 }
726 }, {
727 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
728 'info_dict': {
729 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
730 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
731 'ext': 'flv',
732 'duration': 2235.93,
733 }
734 }],
735 'info_dict': {
736 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
737 }
738 },
739 # Flowplayer
740 {
741 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
742 'md5': '9d65602bf31c6e20014319c7d07fba27',
743 'info_dict': {
744 'id': '5123ea6d5e5a7',
745 'ext': 'mp4',
746 'age_limit': 18,
747 'uploader': 'www.handjobhub.com',
748 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
749 }
750 },
751 # Multiple brightcove videos
752 # https://github.com/rg3/youtube-dl/issues/2283
753 {
754 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
755 'info_dict': {
756 'id': 'always-never',
757 'title': 'Always / Never - The New Yorker',
758 },
759 'playlist_count': 3,
760 'params': {
761 'extract_flat': False,
762 'skip_download': True,
763 }
764 },
765 # MLB embed
766 {
767 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
768 'md5': '96f09a37e44da40dd083e12d9a683327',
769 'info_dict': {
770 'id': '33322633',
771 'ext': 'mp4',
772 'title': 'Ump changes call to ball',
773 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
774 'duration': 48,
775 'timestamp': 1401537900,
776 'upload_date': '20140531',
777 'thumbnail': r're:^https?://.*\.jpg$',
778 },
779 },
780 # Wistia embed
781 {
782 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
783 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
784 'info_dict': {
785 'id': '6e2wtrbdaf',
786 'ext': 'mov',
787 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
788 'description': 'a Paywall Videos video from Remilon',
789 'duration': 644.072,
790 'uploader': 'study.com',
791 'timestamp': 1459678540,
792 'upload_date': '20160403',
793 'filesize': 24687186,
794 },
795 },
796 {
797 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
798 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
799 'info_dict': {
800 'id': 'uxjb0lwrcz',
801 'ext': 'mp4',
802 'title': 'Conversation about Hexagonal Rails Part 1',
803 'description': 'a Martin Fowler video from ThoughtWorks',
804 'duration': 1715.0,
805 'uploader': 'thoughtworks.wistia.com',
806 'timestamp': 1401832161,
807 'upload_date': '20140603',
808 },
809 },
810 # Wistia standard embed (async)
811 {
812 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
813 'info_dict': {
814 'id': '807fafadvk',
815 'ext': 'mp4',
816 'title': 'Drip Brennan Dunn Workshop',
817 'description': 'a JV Webinars video from getdrip-1',
818 'duration': 4986.95,
819 'timestamp': 1463607249,
820 'upload_date': '20160518',
821 },
822 'params': {
823 'skip_download': True,
824 }
825 },
826 # Soundcloud embed
827 {
828 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
829 'info_dict': {
830 'id': '174391317',
831 'ext': 'mp3',
832 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
833 'uploader': 'Sophos Security',
834 'title': 'Chet Chat 171 - Oct 29, 2014',
835 'upload_date': '20141029',
836 }
837 },
838 # Soundcloud multiple embeds
839 {
840 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
841 'info_dict': {
842 'id': '52809',
843 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
844 },
845 'playlist_mincount': 7,
846 },
847 # TuneIn station embed
848 {
849 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
850 'info_dict': {
851 'id': '204146',
852 'ext': 'mp3',
853 'title': 'CNRV',
854 'location': 'Paris, France',
855 'is_live': True,
856 },
857 'params': {
858 # Live stream
859 'skip_download': True,
860 },
861 },
862 # Livestream embed
863 {
864 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
865 'info_dict': {
866 'id': '67864563',
867 'ext': 'flv',
868 'upload_date': '20141112',
869 'title': 'Rosetta #CometLanding webcast HL 10',
870 }
871 },
872 # Another Livestream embed, without 'new.' in URL
873 {
874 'url': 'https://www.freespeech.org/',
875 'info_dict': {
876 'id': '123537347',
877 'ext': 'mp4',
878 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
879 },
880 'params': {
881 # Live stream
882 'skip_download': True,
883 },
884 },
885 # LazyYT
886 {
887 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
888 'info_dict': {
889 'id': '1986',
890 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
891 },
892 'playlist_mincount': 2,
893 },
894 # Cinchcast embed
895 {
896 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
897 'info_dict': {
898 'id': '7141703',
899 'ext': 'mp3',
900 'upload_date': '20141126',
901 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
902 }
903 },
904 # Cinerama player
905 {
906 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
907 'info_dict': {
908 'id': '730m_DandD_1901_512k',
909 'ext': 'mp4',
910 'uploader': 'www.abc.net.au',
911 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
912 }
913 },
914 # embedded viddler video
915 {
916 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
917 'info_dict': {
918 'id': '4d03aad9',
919 'ext': 'mp4',
920 'uploader': 'deadspin',
921 'title': 'WALL-TO-GORTAT',
922 'timestamp': 1422285291,
923 'upload_date': '20150126',
924 },
925 'add_ie': ['Viddler'],
926 },
927 # Libsyn embed
928 {
929 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
930 'info_dict': {
931 'id': '3377616',
932 'ext': 'mp3',
933 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
934 'description': 'md5:601cb790edd05908957dae8aaa866465',
935 'upload_date': '20150220',
936 },
937 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
938 },
939 # jwplayer YouTube
940 {
941 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
942 'info_dict': {
943 'id': 'Mrj4DVp2zeA',
944 'ext': 'mp4',
945 'upload_date': '20150212',
946 'uploader': 'The National Archives UK',
947 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
948 'uploader_id': 'NationalArchives08',
949 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
950 },
951 },
952 # jwplayer rtmp
953 {
954 'url': 'http://www.suffolk.edu/sjc/',
955 'info_dict': {
956 'id': 'sjclive',
957 'ext': 'flv',
958 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
959 'uploader': 'www.suffolk.edu',
960 },
961 'params': {
962 'skip_download': True,
963 }
964 },
965 # Complex jwplayer
966 {
967 'url': 'http://www.indiedb.com/games/king-machine/videos',
968 'info_dict': {
969 'id': 'videos',
970 'ext': 'mp4',
971 'title': 'king machine trailer 1',
972 'thumbnail': r're:^https?://.*\.jpg$',
973 },
974 },
975 # rtl.nl embed
976 {
977 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
978 'playlist_mincount': 5,
979 'info_dict': {
980 'id': 'aanslagen-kopenhagen',
981 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
982 }
983 },
984 # Zapiks embed
985 {
986 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
987 'info_dict': {
988 'id': '118046',
989 'ext': 'mp4',
990 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
991 }
992 },
993 # Kaltura embed (different embed code)
994 {
995 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
996 'info_dict': {
997 'id': '1_a52wc67y',
998 'ext': 'flv',
999 'upload_date': '20150127',
1000 'uploader_id': 'PremierMedia',
1001 'timestamp': int,
1002 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1003 },
1004 },
1005 # Kaltura embed with single quotes
1006 {
1007 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1008 'info_dict': {
1009 'id': '0_izeg5utt',
1010 'ext': 'mp4',
1011 'title': '35871',
1012 'timestamp': 1355743100,
1013 'upload_date': '20121217',
1014 'uploader_id': 'batchUser',
1015 },
1016 'add_ie': ['Kaltura'],
1017 },
1018 {
1019 # Kaltura embedded via quoted entry_id
1020 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1021 'info_dict': {
1022 'id': '0_utuok90b',
1023 'ext': 'mp4',
1024 'title': '06_matthew_brender_raj_dutt',
1025 'timestamp': 1466638791,
1026 'upload_date': '20160622',
1027 },
1028 'add_ie': ['Kaltura'],
1029 'expected_warnings': [
1030 'Could not send HEAD request'
1031 ],
1032 'params': {
1033 'skip_download': True,
1034 }
1035 },
1036 {
1037 # Kaltura embedded, some fileExt broken (#11480)
1038 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1039 'info_dict': {
1040 'id': '1_sgtvehim',
1041 'ext': 'mp4',
1042 'title': 'Our "Standard Models" of particle physics and cosmology',
1043 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1044 'timestamp': 1321158993,
1045 'upload_date': '20111113',
1046 'uploader_id': 'kps1',
1047 },
1048 'add_ie': ['Kaltura'],
1049 },
1050 # Eagle.Platform embed (generic URL)
1051 {
1052 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1053 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1054 'info_dict': {
1055 'id': '227304',
1056 'ext': 'mp4',
1057 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1058 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1059 'thumbnail': r're:^https?://.*\.jpg$',
1060 'duration': 87,
1061 'view_count': int,
1062 'age_limit': 0,
1063 },
1064 },
1065 # ClipYou (Eagle.Platform) embed (custom URL)
1066 {
1067 'url': 'http://muz-tv.ru/play/7129/',
1068 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1069 'info_dict': {
1070 'id': '12820',
1071 'ext': 'mp4',
1072 'title': "'O Sole Mio",
1073 'thumbnail': r're:^https?://.*\.jpg$',
1074 'duration': 216,
1075 'view_count': int,
1076 },
1077 },
1078 # Pladform embed
1079 {
1080 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1081 'info_dict': {
1082 'id': '100183293',
1083 'ext': 'mp4',
1084 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1085 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1086 'thumbnail': r're:^https?://.*\.jpg$',
1087 'duration': 694,
1088 'age_limit': 0,
1089 },
1090 },
1091 # Playwire embed
1092 {
1093 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1094 'info_dict': {
1095 'id': '3519514',
1096 'ext': 'mp4',
1097 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1098 'thumbnail': r're:^https?://.*\.png$',
1099 'duration': 45.115,
1100 },
1101 },
1102 # 5min embed
1103 {
1104 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1105 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1106 'info_dict': {
1107 'id': '518726732',
1108 'ext': 'mp4',
1109 'title': 'Facebook Creates "On This Day" | Crunch Report',
1110 },
1111 },
1112 # SVT embed
1113 {
1114 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1115 'info_dict': {
1116 'id': '2900353',
1117 'ext': 'flv',
1118 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1119 'duration': 27,
1120 'age_limit': 0,
1121 },
1122 },
1123 # Crooks and Liars embed
1124 {
1125 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1126 'info_dict': {
1127 'id': '8RUoRhRi',
1128 'ext': 'mp4',
1129 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1130 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1131 'timestamp': 1428207000,
1132 'upload_date': '20150405',
1133 'uploader': 'Heather',
1134 },
1135 },
1136 # Crooks and Liars external embed
1137 {
1138 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1139 'info_dict': {
1140 'id': 'MTE3MjUtMzQ2MzA',
1141 'ext': 'mp4',
1142 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1143 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1144 'timestamp': 1265032391,
1145 'upload_date': '20100201',
1146 'uploader': 'Heather',
1147 },
1148 },
1149 # NBC Sports vplayer embed
1150 {
1151 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1152 'info_dict': {
1153 'id': 'ln7x1qSThw4k',
1154 'ext': 'flv',
1155 'title': "PFT Live: New leader in the 'new-look' defense",
1156 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1157 'uploader': 'NBCU-SPORTS',
1158 'upload_date': '20140107',
1159 'timestamp': 1389118457,
1160 },
1161 },
1162 # NBC News embed
1163 {
1164 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1165 'md5': '1aa589c675898ae6d37a17913cf68d66',
1166 'info_dict': {
1167 'id': '701714499682',
1168 'ext': 'mp4',
1169 'title': 'PREVIEW: On Assignment: David Letterman',
1170 '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.',
1171 },
1172 },
1173 # UDN embed
1174 {
1175 'url': 'https://video.udn.com/news/300346',
1176 'md5': 'fd2060e988c326991037b9aff9df21a6',
1177 'info_dict': {
1178 'id': '300346',
1179 'ext': 'mp4',
1180 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1181 'thumbnail': r're:^https?://.*\.jpg$',
1182 },
1183 'params': {
1184 # m3u8 download
1185 'skip_download': True,
1186 },
1187 },
1188 # Ooyala embed
1189 {
1190 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1191 'info_dict': {
1192 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1193 'ext': 'mp4',
1194 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1195 'title': 'This is what separates the Excel masters from the wannabes',
1196 'duration': 191.933,
1197 },
1198 'params': {
1199 # m3u8 downloads
1200 'skip_download': True,
1201 }
1202 },
1203 # Brightcove URL in single quotes
1204 {
1205 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1206 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1207 'info_dict': {
1208 'id': '4255764656001',
1209 'ext': 'mp4',
1210 'title': 'SN Presents: Russell Martin, World Citizen',
1211 '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.',
1212 'uploader': 'Rogers Sportsnet',
1213 'uploader_id': '1704050871',
1214 'upload_date': '20150525',
1215 'timestamp': 1432570283,
1216 },
1217 },
1218 # Dailymotion Cloud video
1219 {
1220 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1221 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1222 'info_dict': {
1223 'id': 'x2uy8t3',
1224 'ext': 'mp4',
1225 'title': 'Sauvons les abeilles ! - Le dƩbat',
1226 'description': 'md5:d9082128b1c5277987825d684939ca26',
1227 'thumbnail': r're:^https?://.*\.jpe?g$',
1228 'timestamp': 1434970506,
1229 'upload_date': '20150622',
1230 'uploader': 'Public SĆ©nat',
1231 'uploader_id': 'xa9gza',
1232 }
1233 },
1234 # OnionStudios embed
1235 {
1236 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1237 'info_dict': {
1238 'id': '2855',
1239 'ext': 'mp4',
1240 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1241 'thumbnail': r're:^https?://.*\.jpe?g$',
1242 'uploader': 'ClickHole',
1243 'uploader_id': 'clickhole',
1244 }
1245 },
1246 # SnagFilms embed
1247 {
1248 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1249 'info_dict': {
1250 'id': '74849a00-85a9-11e1-9660-123139220831',
1251 'ext': 'mp4',
1252 'title': '#whilewewatch',
1253 }
1254 },
1255 # AdobeTVVideo embed
1256 {
1257 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1258 'md5': '43662b577c018ad707a63766462b1e87',
1259 'info_dict': {
1260 'id': '2456',
1261 'ext': 'mp4',
1262 'title': 'New experience with Acrobat DC',
1263 'description': 'New experience with Acrobat DC',
1264 'duration': 248.667,
1265 },
1266 },
1267 # BrightcoveInPageEmbed embed
1268 {
1269 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1270 'info_dict': {
1271 'id': '4238694884001',
1272 'ext': 'flv',
1273 'title': 'Tabletop: Dread, Last Thoughts',
1274 'description': 'Tabletop: Dread, Last Thoughts',
1275 'duration': 51690,
1276 },
1277 },
1278 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1279 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1280 {
1281 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1282 'info_dict': {
1283 'id': '4785848093001',
1284 'ext': 'mp4',
1285 'title': 'The Cardinal Pell Interview',
1286 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1287 'uploader': 'GlobeCast Australia - GlobeStream',
1288 'uploader_id': '2733773828001',
1289 'upload_date': '20160304',
1290 'timestamp': 1457083087,
1291 },
1292 'params': {
1293 # m3u8 downloads
1294 'skip_download': True,
1295 },
1296 },
1297 # Another form of arte.tv embed
1298 {
1299 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1300 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1301 'info_dict': {
1302 'id': '030273-562_PLUS7-F',
1303 'ext': 'mp4',
1304 'title': 'ARTE Reportage - Nulle part, en France',
1305 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1306 'upload_date': '20160409',
1307 },
1308 },
1309 # LiveLeak embed
1310 {
1311 'url': 'http://www.wykop.pl/link/3088787/',
1312 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1313 'info_dict': {
1314 'id': '874_1459135191',
1315 'ext': 'mp4',
1316 'title': 'Man shows poor quality of new apartment building',
1317 'description': 'The wall is like a sand pile.',
1318 'uploader': 'Lake8737',
1319 }
1320 },
1321 # Duplicated embedded video URLs
1322 {
1323 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1324 'info_dict': {
1325 'id': '149298443_480_16c25b74_2',
1326 'ext': 'mp4',
1327 'title': 'vs. Blue Orange Spring Game',
1328 'uploader': 'www.hudl.com',
1329 },
1330 },
1331 # twitter:player:stream embed
1332 {
1333 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1334 'info_dict': {
1335 'id': 'master',
1336 'ext': 'mp4',
1337 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1338 'uploader': 'www.rtl.be',
1339 },
1340 'params': {
1341 # m3u8 downloads
1342 'skip_download': True,
1343 },
1344 },
1345 # twitter:player embed
1346 {
1347 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1348 'md5': 'a3e0df96369831de324f0778e126653c',
1349 'info_dict': {
1350 'id': '4909620399001',
1351 'ext': 'mp4',
1352 'title': 'What Do Black Holes Sound Like?',
1353 'description': 'what do black holes sound like',
1354 'upload_date': '20160524',
1355 'uploader_id': '29913724001',
1356 'timestamp': 1464107587,
1357 'uploader': 'TheAtlantic',
1358 },
1359 'add_ie': ['BrightcoveLegacy'],
1360 },
1361 # Facebook <iframe> embed
1362 {
1363 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1364 'md5': 'fbcde74f534176ecb015849146dd3aee',
1365 'info_dict': {
1366 'id': '599637780109885',
1367 'ext': 'mp4',
1368 'title': 'Facebook video #599637780109885',
1369 },
1370 },
1371 # Facebook API embed
1372 {
1373 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1374 'md5': 'a47372ee61b39a7b90287094d447d94e',
1375 'info_dict': {
1376 'id': '10153467542406923',
1377 'ext': 'mp4',
1378 'title': 'Facebook video #10153467542406923',
1379 },
1380 },
1381 # Wordpress "YouTube Video Importer" plugin
1382 {
1383 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1384 'md5': 'd16797741b560b485194eddda8121b48',
1385 'info_dict': {
1386 'id': 'HNTXWDXV9Is',
1387 'ext': 'mp4',
1388 'title': 'Blue Devils Drumline Stanford lot 2016',
1389 'upload_date': '20160627',
1390 'uploader_id': 'GENOCIDE8GENERAL10',
1391 'uploader': 'cylus cyrus',
1392 },
1393 },
1394 {
1395 # video stored on custom kaltura server
1396 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1397 'md5': '537617d06e64dfed891fa1593c4b30cc',
1398 'info_dict': {
1399 'id': '0_1iotm5bh',
1400 'ext': 'mp4',
1401 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1402 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1403 'uploader_id': 'videos.expansion@el-mundo.net',
1404 'upload_date': '20150429',
1405 'timestamp': 1430303472,
1406 },
1407 'add_ie': ['Kaltura'],
1408 },
1409 {
1410 # Non-standard Vimeo embed
1411 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1412 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1413 'info_dict': {
1414 'id': '148867247',
1415 'ext': 'mp4',
1416 'title': 'Understanding the web - Teaser',
1417 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1418 'upload_date': '20151214',
1419 'uploader': 'OpenClassrooms',
1420 'uploader_id': 'openclassrooms',
1421 },
1422 'add_ie': ['Vimeo'],
1423 },
1424 {
1425 # generic vimeo embed that requires original URL passed as Referer
1426 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1427 'only_matching': True,
1428 },
1429 {
1430 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1431 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1432 'info_dict': {
1433 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1434 'ext': 'mp4',
1435 'title': 'Big Buck Bunny',
1436 'description': 'Royalty free test video',
1437 'timestamp': 1432816365,
1438 'upload_date': '20150528',
1439 'is_live': False,
1440 },
1441 'params': {
1442 'skip_download': True,
1443 },
1444 'add_ie': [ArkenaIE.ie_key()],
1445 },
1446 {
1447 '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/',
1448 'info_dict': {
1449 'id': '1c7141f46c',
1450 'ext': 'mp4',
1451 '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',
1452 },
1453 'params': {
1454 'skip_download': True,
1455 },
1456 'add_ie': [Vbox7IE.ie_key()],
1457 },
1458 {
1459 # DBTV embeds
1460 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1461 'info_dict': {
1462 'id': '43254897',
1463 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1464 },
1465 'playlist_mincount': 3,
1466 },
1467 {
1468 # Videa embeds
1469 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1470 'info_dict': {
1471 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1472 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1473 },
1474 'playlist_mincount': 2,
1475 },
1476 {
1477 # 20 minuten embed
1478 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1479 'info_dict': {
1480 'id': '523629',
1481 'ext': 'mp4',
1482 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1483 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1484 },
1485 'params': {
1486 'skip_download': True,
1487 },
1488 'add_ie': [TwentyMinutenIE.ie_key()],
1489 },
1490 {
1491 # VideoPress embed
1492 'url': 'https://en.support.wordpress.com/videopress/',
1493 'info_dict': {
1494 'id': 'OcobLTqC',
1495 'ext': 'm4v',
1496 'title': 'IMG_5786',
1497 'timestamp': 1435711927,
1498 'upload_date': '20150701',
1499 },
1500 'params': {
1501 'skip_download': True,
1502 },
1503 'add_ie': [VideoPressIE.ie_key()],
1504 },
1505 {
1506 # ThePlatform embedded with whitespaces in URLs
1507 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1508 'only_matching': True,
1509 },
1510 # {
1511 # # TODO: find another test
1512 # # http://schema.org/VideoObject
1513 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1514 # 'md5': '888dcf08b7ea671381f00fab74692755',
1515 # 'info_dict': {
1516 # 'id': 'nyvTSJMKId',
1517 # 'ext': 'mp4',
1518 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1519 # 'description': '#love for cats.',
1520 # 'timestamp': 1461244995,
1521 # 'upload_date': '20160421',
1522 # },
1523 # 'params': {
1524 # 'force_generic_extractor': True,
1525 # },
1526 # }
1527 ]
1528
1529 def report_following_redirect(self, new_url):
1530 """Report information extraction."""
1531 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1532
1533 def _extract_rss(self, url, video_id, doc):
1534 playlist_title = doc.find('./channel/title').text
1535 playlist_desc_el = doc.find('./channel/description')
1536 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1537
1538 entries = []
1539 for it in doc.findall('./channel/item'):
1540 next_url = xpath_text(it, 'link', fatal=False)
1541 if not next_url:
1542 enclosure_nodes = it.findall('./enclosure')
1543 for e in enclosure_nodes:
1544 next_url = e.attrib.get('url')
1545 if next_url:
1546 break
1547
1548 if not next_url:
1549 continue
1550
1551 entries.append({
1552 '_type': 'url',
1553 'url': next_url,
1554 'title': it.find('title').text,
1555 })
1556
1557 return {
1558 '_type': 'playlist',
1559 'id': url,
1560 'title': playlist_title,
1561 'description': playlist_desc,
1562 'entries': entries,
1563 }
1564
1565 def _extract_camtasia(self, url, video_id, webpage):
1566 """ Returns None if no camtasia video can be found. """
1567
1568 camtasia_cfg = self._search_regex(
1569 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1570 webpage, 'camtasia configuration file', default=None)
1571 if camtasia_cfg is None:
1572 return None
1573
1574 title = self._html_search_meta('DC.title', webpage, fatal=True)
1575
1576 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1577 camtasia_cfg = self._download_xml(
1578 camtasia_url, video_id,
1579 note='Downloading camtasia configuration',
1580 errnote='Failed to download camtasia configuration')
1581 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1582
1583 entries = []
1584 for n in fileset_node.getchildren():
1585 url_n = n.find('./uri')
1586 if url_n is None:
1587 continue
1588
1589 entries.append({
1590 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1591 'title': '%s - %s' % (title, n.tag),
1592 'url': compat_urlparse.urljoin(url, url_n.text),
1593 'duration': float_or_none(n.find('./duration').text),
1594 })
1595
1596 return {
1597 '_type': 'playlist',
1598 'entries': entries,
1599 'title': title,
1600 }
1601
1602 def _real_extract(self, url):
1603 if url.startswith('//'):
1604 return {
1605 '_type': 'url',
1606 'url': self.http_scheme() + url,
1607 }
1608
1609 parsed_url = compat_urlparse.urlparse(url)
1610 if not parsed_url.scheme:
1611 default_search = self._downloader.params.get('default_search')
1612 if default_search is None:
1613 default_search = 'fixup_error'
1614
1615 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1616 if '/' in url:
1617 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1618 return self.url_result('http://' + url)
1619 elif default_search != 'fixup_error':
1620 if default_search == 'auto_warning':
1621 if re.match(r'^(?:url|URL)$', url):
1622 raise ExtractorError(
1623 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1624 expected=True)
1625 else:
1626 self._downloader.report_warning(
1627 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1628 return self.url_result('ytsearch:' + url)
1629
1630 if default_search in ('error', 'fixup_error'):
1631 raise ExtractorError(
1632 '%r is not a valid URL. '
1633 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1634 % (url, url), expected=True)
1635 else:
1636 if ':' not in default_search:
1637 default_search += ':'
1638 return self.url_result(default_search + url)
1639
1640 url, smuggled_data = unsmuggle_url(url)
1641 force_videoid = None
1642 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1643 if smuggled_data and 'force_videoid' in smuggled_data:
1644 force_videoid = smuggled_data['force_videoid']
1645 video_id = force_videoid
1646 else:
1647 video_id = self._generic_id(url)
1648
1649 self.to_screen('%s: Requesting header' % video_id)
1650
1651 head_req = HEADRequest(url)
1652 head_response = self._request_webpage(
1653 head_req, video_id,
1654 note=False, errnote='Could not send HEAD request to %s' % url,
1655 fatal=False)
1656
1657 if head_response is not False:
1658 # Check for redirect
1659 new_url = head_response.geturl()
1660 if url != new_url:
1661 self.report_following_redirect(new_url)
1662 if force_videoid:
1663 new_url = smuggle_url(
1664 new_url, {'force_videoid': force_videoid})
1665 return self.url_result(new_url)
1666
1667 full_response = None
1668 if head_response is False:
1669 request = sanitized_Request(url)
1670 request.add_header('Accept-Encoding', '*')
1671 full_response = self._request_webpage(request, video_id)
1672 head_response = full_response
1673
1674 info_dict = {
1675 'id': video_id,
1676 'title': self._generic_title(url),
1677 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1678 }
1679
1680 # Check for direct link to a video
1681 content_type = head_response.headers.get('Content-Type', '').lower()
1682 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1683 if m:
1684 format_id = m.group('format_id')
1685 if format_id.endswith('mpegurl'):
1686 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1687 elif format_id == 'f4m':
1688 formats = self._extract_f4m_formats(url, video_id)
1689 else:
1690 formats = [{
1691 'format_id': m.group('format_id'),
1692 'url': url,
1693 'vcodec': 'none' if m.group('type') == 'audio' else None
1694 }]
1695 info_dict['direct'] = True
1696 self._sort_formats(formats)
1697 info_dict['formats'] = formats
1698 return info_dict
1699
1700 if not self._downloader.params.get('test', False) and not is_intentional:
1701 force = self._downloader.params.get('force_generic_extractor', False)
1702 self._downloader.report_warning(
1703 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1704
1705 if not full_response:
1706 request = sanitized_Request(url)
1707 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1708 # making it impossible to download only chunk of the file (yet we need only 512kB to
1709 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1710 # that will always result in downloading the whole file that is not desirable.
1711 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1712 # to accept raw bytes and being able to download only a chunk.
1713 # It may probably better to solve this by checking Content-Type for application/octet-stream
1714 # after HEAD request finishes, but not sure if we can rely on this.
1715 request.add_header('Accept-Encoding', '*')
1716 full_response = self._request_webpage(request, video_id)
1717
1718 first_bytes = full_response.read(512)
1719
1720 # Is it an M3U playlist?
1721 if first_bytes.startswith(b'#EXTM3U'):
1722 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1723 self._sort_formats(info_dict['formats'])
1724 return info_dict
1725
1726 # Maybe it's a direct link to a video?
1727 # Be careful not to download the whole thing!
1728 if not is_html(first_bytes):
1729 self._downloader.report_warning(
1730 'URL could be a direct video link, returning it as such.')
1731 info_dict.update({
1732 'direct': True,
1733 'url': url,
1734 })
1735 return info_dict
1736
1737 webpage = self._webpage_read_content(
1738 full_response, url, video_id, prefix=first_bytes)
1739
1740 self.report_extraction(video_id)
1741
1742 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1743 try:
1744 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1745 if doc.tag == 'rss':
1746 return self._extract_rss(url, video_id, doc)
1747 elif doc.tag == 'SmoothStreamingMedia':
1748 info_dict['formats'] = self._parse_ism_formats(doc, url)
1749 self._sort_formats(info_dict['formats'])
1750 return info_dict
1751 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1752 smil = self._parse_smil(doc, url, video_id)
1753 self._sort_formats(smil['formats'])
1754 return smil
1755 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1756 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1757 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1758 info_dict['formats'] = self._parse_mpd_formats(
1759 doc, video_id,
1760 mpd_base_url=full_response.geturl().rpartition('/')[0],
1761 mpd_url=url)
1762 self._sort_formats(info_dict['formats'])
1763 return info_dict
1764 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1765 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1766 self._sort_formats(info_dict['formats'])
1767 return info_dict
1768 except compat_xml_parse_error:
1769 pass
1770
1771 # Is it a Camtasia project?
1772 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1773 if camtasia_res is not None:
1774 return camtasia_res
1775
1776 # Sometimes embedded video player is hidden behind percent encoding
1777 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1778 # Unescaping the whole page allows to handle those cases in a generic way
1779 webpage = compat_urllib_parse_unquote(webpage)
1780
1781 # it's tempting to parse this further, but you would
1782 # have to take into account all the variations like
1783 # Video Title - Site Name
1784 # Site Name | Video Title
1785 # Video Title - Tagline | Site Name
1786 # and so on and so forth; it's just not practical
1787 video_title = self._og_search_title(
1788 webpage, default=None) or self._html_search_regex(
1789 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1790 default='video')
1791
1792 # Try to detect age limit automatically
1793 age_limit = self._rta_search(webpage)
1794 # And then there are the jokers who advertise that they use RTA,
1795 # but actually don't.
1796 AGE_LIMIT_MARKERS = [
1797 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1798 ]
1799 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1800 age_limit = 18
1801
1802 # video uploader is domain name
1803 video_uploader = self._search_regex(
1804 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1805
1806 video_description = self._og_search_description(webpage, default=None)
1807 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1808
1809 # Helper method
1810 def _playlist_from_matches(matches, getter=None, ie=None):
1811 urlrs = orderedSet(
1812 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1813 for m in matches)
1814 return self.playlist_result(
1815 urlrs, playlist_id=video_id, playlist_title=video_title)
1816
1817 # Look for Brightcove Legacy Studio embeds
1818 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1819 if bc_urls:
1820 self.to_screen('Brightcove video detected.')
1821 entries = [{
1822 '_type': 'url',
1823 'url': smuggle_url(bc_url, {'Referer': url}),
1824 'ie_key': 'BrightcoveLegacy'
1825 } for bc_url in bc_urls]
1826
1827 return {
1828 '_type': 'playlist',
1829 'title': video_title,
1830 'id': video_id,
1831 'entries': entries,
1832 }
1833
1834 # Look for Brightcove New Studio embeds
1835 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1836 if bc_urls:
1837 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1838
1839 # Look for ThePlatform embeds
1840 tp_urls = ThePlatformIE._extract_urls(webpage)
1841 if tp_urls:
1842 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1843
1844 # Look for Vessel embeds
1845 vessel_urls = VesselIE._extract_urls(webpage)
1846 if vessel_urls:
1847 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1848
1849 # Look for embedded rtl.nl player
1850 matches = re.findall(
1851 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1852 webpage)
1853 if matches:
1854 return _playlist_from_matches(matches, ie='RtlNl')
1855
1856 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1857 if vimeo_urls:
1858 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1859
1860 vid_me_embed_url = self._search_regex(
1861 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1862 webpage, 'vid.me embed', default=None)
1863 if vid_me_embed_url is not None:
1864 return self.url_result(vid_me_embed_url, 'Vidme')
1865
1866 # Look for embedded YouTube player
1867 matches = re.findall(r'''(?x)
1868 (?:
1869 <iframe[^>]+?src=|
1870 data-video-url=|
1871 <embed[^>]+?src=|
1872 embedSWF\(?:\s*|
1873 new\s+SWFObject\(
1874 )
1875 (["\'])
1876 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1877 (?:embed|v|p)/.+?)
1878 \1''', webpage)
1879 if matches:
1880 return _playlist_from_matches(
1881 matches, lambda m: unescapeHTML(m[1]))
1882
1883 # Look for lazyYT YouTube embed
1884 matches = re.findall(
1885 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1886 if matches:
1887 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1888
1889 # Look for Wordpress "YouTube Video Importer" plugin
1890 matches = re.findall(r'''(?x)<div[^>]+
1891 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1892 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1893 if matches:
1894 return _playlist_from_matches(matches, lambda m: m[-1])
1895
1896 matches = DailymotionIE._extract_urls(webpage)
1897 if matches:
1898 return _playlist_from_matches(matches)
1899
1900 # Look for embedded Dailymotion playlist player (#3822)
1901 m = re.search(
1902 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1903 if m:
1904 playlists = re.findall(
1905 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1906 if playlists:
1907 return _playlist_from_matches(
1908 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1909
1910 # Look for embedded Wistia player
1911 match = re.search(
1912 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1913 if match:
1914 embed_url = self._proto_relative_url(
1915 unescapeHTML(match.group('url')))
1916 return {
1917 '_type': 'url_transparent',
1918 'url': embed_url,
1919 'ie_key': 'Wistia',
1920 'uploader': video_uploader,
1921 }
1922
1923 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1924 if match:
1925 return {
1926 '_type': 'url_transparent',
1927 'url': 'wistia:%s' % match.group('id'),
1928 'ie_key': 'Wistia',
1929 'uploader': video_uploader,
1930 }
1931
1932 match = re.search(
1933 r'''(?sx)
1934 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1935 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1936 ''', webpage)
1937 if match:
1938 return self.url_result(self._proto_relative_url(
1939 'wistia:%s' % match.group('id')), 'Wistia')
1940
1941 # Look for SVT player
1942 svt_url = SVTIE._extract_url(webpage)
1943 if svt_url:
1944 return self.url_result(svt_url, 'SVT')
1945
1946 # Look for embedded condenast player
1947 matches = re.findall(
1948 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1949 webpage)
1950 if matches:
1951 return {
1952 '_type': 'playlist',
1953 'entries': [{
1954 '_type': 'url',
1955 'ie_key': 'CondeNast',
1956 'url': ma,
1957 } for ma in matches],
1958 'title': video_title,
1959 'id': video_id,
1960 }
1961
1962 # Look for Bandcamp pages with custom domain
1963 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1964 if mobj is not None:
1965 burl = unescapeHTML(mobj.group(1))
1966 # Don't set the extractor because it can be a track url or an album
1967 return self.url_result(burl)
1968
1969 # Look for embedded Vevo player
1970 mobj = re.search(
1971 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1972 if mobj is not None:
1973 return self.url_result(mobj.group('url'))
1974
1975 # Look for embedded Viddler player
1976 mobj = re.search(
1977 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1978 webpage)
1979 if mobj is not None:
1980 return self.url_result(mobj.group('url'))
1981
1982 # Look for NYTimes player
1983 mobj = re.search(
1984 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1985 webpage)
1986 if mobj is not None:
1987 return self.url_result(mobj.group('url'))
1988
1989 # Look for Libsyn player
1990 mobj = re.search(
1991 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1992 if mobj is not None:
1993 return self.url_result(mobj.group('url'))
1994
1995 # Look for Ooyala videos
1996 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1997 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1998 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1999 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2000 if mobj is not None:
2001 embed_token = self._search_regex(
2002 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2003 webpage, 'ooyala embed token', default=None)
2004 return OoyalaIE._build_url_result(smuggle_url(
2005 mobj.group('ec'), {
2006 'domain': url,
2007 'embed_token': embed_token,
2008 }))
2009
2010 # Look for multiple Ooyala embeds on SBN network websites
2011 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2012 if mobj is not None:
2013 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2014 if embeds:
2015 return _playlist_from_matches(
2016 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2017
2018 # Look for Aparat videos
2019 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2020 if mobj is not None:
2021 return self.url_result(mobj.group(1), 'Aparat')
2022
2023 # Look for MPORA videos
2024 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2025 if mobj is not None:
2026 return self.url_result(mobj.group(1), 'Mpora')
2027
2028 # Look for embedded NovaMov-based player
2029 mobj = re.search(
2030 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2031 (?P<url>http://(?:(?:embed|www)\.)?
2032 (?:novamov\.com|
2033 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2034 videoweed\.(?:es|com)|
2035 movshare\.(?:net|sx|ag)|
2036 divxstage\.(?:eu|net|ch|co|at|ag))
2037 /embed\.php.+?)\1''', webpage)
2038 if mobj is not None:
2039 return self.url_result(mobj.group('url'))
2040
2041 # Look for embedded Facebook player
2042 facebook_url = FacebookIE._extract_url(webpage)
2043 if facebook_url is not None:
2044 return self.url_result(facebook_url, 'Facebook')
2045
2046 # Look for embedded VK player
2047 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2048 if mobj is not None:
2049 return self.url_result(mobj.group('url'), 'VK')
2050
2051 # Look for embedded Odnoklassniki player
2052 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2053 if mobj is not None:
2054 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2055
2056 # Look for embedded ivi player
2057 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2058 if mobj is not None:
2059 return self.url_result(mobj.group('url'), 'Ivi')
2060
2061 # Look for embedded Huffington Post player
2062 mobj = re.search(
2063 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2064 if mobj is not None:
2065 return self.url_result(mobj.group('url'), 'HuffPost')
2066
2067 # Look for embed.ly
2068 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2069 if mobj is not None:
2070 return self.url_result(mobj.group('url'))
2071 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2072 if mobj is not None:
2073 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2074
2075 # Look for funnyordie embed
2076 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2077 if matches:
2078 return _playlist_from_matches(
2079 matches, getter=unescapeHTML, ie='FunnyOrDie')
2080
2081 # Look for BBC iPlayer embed
2082 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2083 if matches:
2084 return _playlist_from_matches(matches, ie='BBCCoUk')
2085
2086 # Look for embedded RUTV player
2087 rutv_url = RUTVIE._extract_url(webpage)
2088 if rutv_url:
2089 return self.url_result(rutv_url, 'RUTV')
2090
2091 # Look for embedded TVC player
2092 tvc_url = TVCIE._extract_url(webpage)
2093 if tvc_url:
2094 return self.url_result(tvc_url, 'TVC')
2095
2096 # Look for embedded SportBox player
2097 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2098 if sportbox_urls:
2099 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2100
2101 # Look for embedded XHamster player
2102 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2103 if xhamster_urls:
2104 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2105
2106 # Look for embedded TNAFlixNetwork player
2107 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2108 if tnaflix_urls:
2109 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2110
2111 # Look for embedded PornHub player
2112 pornhub_urls = PornHubIE._extract_urls(webpage)
2113 if pornhub_urls:
2114 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2115
2116 # Look for embedded DrTuber player
2117 drtuber_urls = DrTuberIE._extract_urls(webpage)
2118 if drtuber_urls:
2119 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2120
2121 # Look for embedded RedTube player
2122 redtube_urls = RedTubeIE._extract_urls(webpage)
2123 if redtube_urls:
2124 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2125
2126 # Look for embedded Tvigle player
2127 mobj = re.search(
2128 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2129 if mobj is not None:
2130 return self.url_result(mobj.group('url'), 'Tvigle')
2131
2132 # Look for embedded TED player
2133 mobj = re.search(
2134 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2135 if mobj is not None:
2136 return self.url_result(mobj.group('url'), 'TED')
2137
2138 # Look for embedded Ustream videos
2139 ustream_url = UstreamIE._extract_url(webpage)
2140 if ustream_url:
2141 return self.url_result(ustream_url, UstreamIE.ie_key())
2142
2143 # Look for embedded arte.tv player
2144 mobj = re.search(
2145 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2146 webpage)
2147 if mobj is not None:
2148 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2149
2150 # Look for embedded francetv player
2151 mobj = re.search(
2152 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2153 webpage)
2154 if mobj is not None:
2155 return self.url_result(mobj.group('url'))
2156
2157 # Look for embedded smotri.com player
2158 smotri_url = SmotriIE._extract_url(webpage)
2159 if smotri_url:
2160 return self.url_result(smotri_url, 'Smotri')
2161
2162 # Look for embedded Myvi.ru player
2163 myvi_url = MyviIE._extract_url(webpage)
2164 if myvi_url:
2165 return self.url_result(myvi_url)
2166
2167 # Look for embedded soundcloud player
2168 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2169 if soundcloud_urls:
2170 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2171
2172 # Look for tunein player
2173 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2174 if tunein_urls:
2175 return _playlist_from_matches(tunein_urls)
2176
2177 # Look for embedded mtvservices player
2178 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2179 if mtvservices_url:
2180 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2181
2182 # Look for embedded yahoo player
2183 mobj = re.search(
2184 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2185 webpage)
2186 if mobj is not None:
2187 return self.url_result(mobj.group('url'), 'Yahoo')
2188
2189 # Look for embedded sbs.com.au player
2190 mobj = re.search(
2191 r'''(?x)
2192 (?:
2193 <meta\s+property="og:video"\s+content=|
2194 <iframe[^>]+?src=
2195 )
2196 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2197 webpage)
2198 if mobj is not None:
2199 return self.url_result(mobj.group('url'), 'SBS')
2200
2201 # Look for embedded Cinchcast player
2202 mobj = re.search(
2203 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2204 webpage)
2205 if mobj is not None:
2206 return self.url_result(mobj.group('url'), 'Cinchcast')
2207
2208 mobj = re.search(
2209 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2210 webpage)
2211 if not mobj:
2212 mobj = re.search(
2213 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2214 webpage)
2215 if mobj is not None:
2216 return self.url_result(mobj.group('url'), 'MLB')
2217
2218 mobj = re.search(
2219 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2220 webpage)
2221 if mobj is not None:
2222 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2223
2224 mobj = re.search(
2225 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2226 webpage)
2227 if mobj is not None:
2228 return self.url_result(mobj.group('url'), 'Livestream')
2229
2230 # Look for Zapiks embed
2231 mobj = re.search(
2232 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2233 if mobj is not None:
2234 return self.url_result(mobj.group('url'), 'Zapiks')
2235
2236 # Look for Kaltura embeds
2237 kaltura_url = KalturaIE._extract_url(webpage)
2238 if kaltura_url:
2239 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2240
2241 # Look for Eagle.Platform embeds
2242 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2243 if eagleplatform_url:
2244 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2245
2246 # Look for ClipYou (uses Eagle.Platform) embeds
2247 mobj = re.search(
2248 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2249 if mobj is not None:
2250 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2251
2252 # Look for Pladform embeds
2253 pladform_url = PladformIE._extract_url(webpage)
2254 if pladform_url:
2255 return self.url_result(pladform_url)
2256
2257 # Look for Videomore embeds
2258 videomore_url = VideomoreIE._extract_url(webpage)
2259 if videomore_url:
2260 return self.url_result(videomore_url)
2261
2262 # Look for Webcaster embeds
2263 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2264 if webcaster_url:
2265 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2266
2267 # Look for Playwire embeds
2268 mobj = re.search(
2269 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2270 if mobj is not None:
2271 return self.url_result(mobj.group('url'))
2272
2273 # Look for 5min embeds
2274 mobj = re.search(
2275 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2276 if mobj is not None:
2277 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2278
2279 # Look for Crooks and Liars embeds
2280 mobj = re.search(
2281 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2282 if mobj is not None:
2283 return self.url_result(mobj.group('url'))
2284
2285 # Look for NBC Sports VPlayer embeds
2286 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2287 if nbc_sports_url:
2288 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2289
2290 # Look for NBC News embeds
2291 nbc_news_embed_url = re.search(
2292 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2293 if nbc_news_embed_url:
2294 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2295
2296 # Look for Google Drive embeds
2297 google_drive_url = GoogleDriveIE._extract_url(webpage)
2298 if google_drive_url:
2299 return self.url_result(google_drive_url, 'GoogleDrive')
2300
2301 # Look for UDN embeds
2302 mobj = re.search(
2303 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2304 if mobj is not None:
2305 return self.url_result(
2306 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2307
2308 # Look for Senate ISVP iframe
2309 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2310 if senate_isvp_url:
2311 return self.url_result(senate_isvp_url, 'SenateISVP')
2312
2313 # Look for Dailymotion Cloud videos
2314 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2315 if dmcloud_url:
2316 return self.url_result(dmcloud_url, 'DailymotionCloud')
2317
2318 # Look for OnionStudios embeds
2319 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2320 if onionstudios_url:
2321 return self.url_result(onionstudios_url)
2322
2323 # Look for ViewLift embeds
2324 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2325 if viewlift_url:
2326 return self.url_result(viewlift_url)
2327
2328 # Look for JWPlatform embeds
2329 jwplatform_url = JWPlatformIE._extract_url(webpage)
2330 if jwplatform_url:
2331 return self.url_result(jwplatform_url, 'JWPlatform')
2332
2333 # Look for Digiteka embeds
2334 digiteka_url = DigitekaIE._extract_url(webpage)
2335 if digiteka_url:
2336 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2337
2338 # Look for Arkena embeds
2339 arkena_url = ArkenaIE._extract_url(webpage)
2340 if arkena_url:
2341 return self.url_result(arkena_url, ArkenaIE.ie_key())
2342
2343 # Look for Piksel embeds
2344 piksel_url = PikselIE._extract_url(webpage)
2345 if piksel_url:
2346 return self.url_result(piksel_url, PikselIE.ie_key())
2347
2348 # Look for Limelight embeds
2349 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2350 if mobj:
2351 lm = {
2352 'Media': 'media',
2353 'Channel': 'channel',
2354 'ChannelList': 'channel_list',
2355 }
2356 return self.url_result(smuggle_url('limelight:%s:%s' % (
2357 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2358 'Limelight%s' % mobj.group(1), mobj.group(2))
2359
2360 mobj = re.search(
2361 r'''(?sx)
2362 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2363 <param[^>]+
2364 name=(["\'])flashVars\2[^>]+
2365 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2366 ''', webpage)
2367 if mobj:
2368 return self.url_result(smuggle_url(
2369 'limelight:media:%s' % mobj.group('id'),
2370 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2371
2372 # Look for AdobeTVVideo embeds
2373 mobj = re.search(
2374 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2375 webpage)
2376 if mobj is not None:
2377 return self.url_result(
2378 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2379 'AdobeTVVideo')
2380
2381 # Look for Vine embeds
2382 mobj = re.search(
2383 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2384 webpage)
2385 if mobj is not None:
2386 return self.url_result(
2387 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2388
2389 # Look for VODPlatform embeds
2390 mobj = re.search(
2391 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2392 webpage)
2393 if mobj is not None:
2394 return self.url_result(
2395 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2396
2397 # Look for Mangomolo embeds
2398 mobj = re.search(
2399 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2400 (?:
2401 video\?.*?\bid=(?P<video_id>\d+)|
2402 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2403 ).+?)\1''', webpage)
2404 if mobj is not None:
2405 info = {
2406 '_type': 'url_transparent',
2407 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2408 'title': video_title,
2409 'description': video_description,
2410 'thumbnail': video_thumbnail,
2411 'uploader': video_uploader,
2412 }
2413 video_id = mobj.group('video_id')
2414 if video_id:
2415 info.update({
2416 'ie_key': 'MangomoloVideo',
2417 'id': video_id,
2418 })
2419 else:
2420 info.update({
2421 'ie_key': 'MangomoloLive',
2422 'id': mobj.group('channel_id'),
2423 })
2424 return info
2425
2426 # Look for Instagram embeds
2427 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2428 if instagram_embed_url is not None:
2429 return self.url_result(
2430 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2431
2432 # Look for LiveLeak embeds
2433 liveleak_url = LiveLeakIE._extract_url(webpage)
2434 if liveleak_url:
2435 return self.url_result(liveleak_url, 'LiveLeak')
2436
2437 # Look for 3Q SDN embeds
2438 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2439 if threeqsdn_url:
2440 return {
2441 '_type': 'url_transparent',
2442 'ie_key': ThreeQSDNIE.ie_key(),
2443 'url': self._proto_relative_url(threeqsdn_url),
2444 'title': video_title,
2445 'description': video_description,
2446 'thumbnail': video_thumbnail,
2447 'uploader': video_uploader,
2448 }
2449
2450 # Look for VBOX7 embeds
2451 vbox7_url = Vbox7IE._extract_url(webpage)
2452 if vbox7_url:
2453 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2454
2455 # Look for DBTV embeds
2456 dbtv_urls = DBTVIE._extract_urls(webpage)
2457 if dbtv_urls:
2458 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2459
2460 # Look for Videa embeds
2461 videa_urls = VideaIE._extract_urls(webpage)
2462 if videa_urls:
2463 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2464
2465 # Look for 20 minuten embeds
2466 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2467 if twentymin_urls:
2468 return _playlist_from_matches(
2469 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2470
2471 # Look for Openload embeds
2472 openload_urls = OpenloadIE._extract_urls(webpage)
2473 if openload_urls:
2474 return _playlist_from_matches(
2475 openload_urls, ie=OpenloadIE.ie_key())
2476
2477 # Look for VideoPress embeds
2478 videopress_urls = VideoPressIE._extract_urls(webpage)
2479 if videopress_urls:
2480 return _playlist_from_matches(
2481 videopress_urls, ie=VideoPressIE.ie_key())
2482
2483 # Looking for http://schema.org/VideoObject
2484 json_ld = self._search_json_ld(
2485 webpage, video_id, default={}, expected_type='VideoObject')
2486 if json_ld.get('url'):
2487 info_dict.update({
2488 'title': video_title or info_dict['title'],
2489 'description': video_description,
2490 'thumbnail': video_thumbnail,
2491 'age_limit': age_limit
2492 })
2493 info_dict.update(json_ld)
2494 return info_dict
2495
2496 # Look for HTML5 media
2497 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2498 if entries:
2499 for entry in entries:
2500 entry.update({
2501 'id': video_id,
2502 'title': video_title,
2503 })
2504 self._sort_formats(entry['formats'])
2505 return self.playlist_result(entries)
2506
2507 jwplayer_data_str = self._find_jwplayer_data(webpage)
2508 if jwplayer_data_str:
2509 try:
2510 jwplayer_data = self._parse_json(
2511 jwplayer_data_str, video_id, transform_source=js_to_json)
2512 return self._parse_jwplayer_data(jwplayer_data, video_id)
2513 except ExtractorError:
2514 pass
2515
2516 def check_video(vurl):
2517 if YoutubeIE.suitable(vurl):
2518 return True
2519 if RtmpIE.suitable(vurl):
2520 return True
2521 vpath = compat_urlparse.urlparse(vurl).path
2522 vext = determine_ext(vpath)
2523 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2524
2525 def filter_video(urls):
2526 return list(filter(check_video, urls))
2527
2528 # Start with something easy: JW Player in SWFObject
2529 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2530 if not found:
2531 # Look for gorilla-vid style embedding
2532 found = filter_video(re.findall(r'''(?sx)
2533 (?:
2534 jw_plugins|
2535 JWPlayerOptions|
2536 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2537 )
2538 .*?
2539 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2540 if not found:
2541 # Broaden the search a little bit
2542 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2543 if not found:
2544 # Broaden the findall a little bit: JWPlayer JS loader
2545 found = filter_video(re.findall(
2546 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2547 if not found:
2548 # Flow player
2549 found = filter_video(re.findall(r'''(?xs)
2550 flowplayer\("[^"]+",\s*
2551 \{[^}]+?\}\s*,
2552 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2553 ["']?url["']?\s*:\s*["']([^"']+)["']
2554 ''', webpage))
2555 if not found:
2556 # Cinerama player
2557 found = re.findall(
2558 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2559 if not found:
2560 # Try to find twitter cards info
2561 # twitter:player:stream should be checked before twitter:player since
2562 # it is expected to contain a raw stream (see
2563 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2564 found = filter_video(re.findall(
2565 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2566 if not found:
2567 # We look for Open Graph info:
2568 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2569 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2570 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2571 if m_video_type is not None:
2572 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2573 if not found:
2574 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2575 found = re.search(
2576 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2577 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2578 webpage)
2579 if not found:
2580 # Look also in Refresh HTTP header
2581 refresh_header = head_response.headers.get('Refresh')
2582 if refresh_header:
2583 # In python 2 response HTTP headers are bytestrings
2584 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2585 refresh_header = refresh_header.decode('iso-8859-1')
2586 found = re.search(REDIRECT_REGEX, refresh_header)
2587 if found:
2588 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2589 self.report_following_redirect(new_url)
2590 return {
2591 '_type': 'url',
2592 'url': new_url,
2593 }
2594
2595 if not found:
2596 # twitter:player is a https URL to iframe player that may or may not
2597 # be supported by youtube-dl thus this is checked the very last (see
2598 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2599 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2600 if embed_url:
2601 return self.url_result(embed_url)
2602
2603 if not found:
2604 raise UnsupportedError(url)
2605
2606 entries = []
2607 for video_url in orderedSet(found):
2608 video_url = unescapeHTML(video_url)
2609 video_url = video_url.replace('\\/', '/')
2610 video_url = compat_urlparse.urljoin(url, video_url)
2611 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2612
2613 # Sometimes, jwplayer extraction will result in a YouTube URL
2614 if YoutubeIE.suitable(video_url):
2615 entries.append(self.url_result(video_url, 'Youtube'))
2616 continue
2617
2618 # here's a fun little line of code for you:
2619 video_id = os.path.splitext(video_id)[0]
2620
2621 entry_info_dict = {
2622 'id': video_id,
2623 'uploader': video_uploader,
2624 'title': video_title,
2625 'age_limit': age_limit,
2626 }
2627
2628 if RtmpIE.suitable(video_url):
2629 entry_info_dict.update({
2630 '_type': 'url_transparent',
2631 'ie_key': RtmpIE.ie_key(),
2632 'url': video_url,
2633 })
2634 entries.append(entry_info_dict)
2635 continue
2636
2637 ext = determine_ext(video_url)
2638 if ext == 'smil':
2639 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2640 elif ext == 'xspf':
2641 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2642 elif ext == 'm3u8':
2643 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2644 elif ext == 'mpd':
2645 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2646 elif ext == 'f4m':
2647 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2648 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2649 # Just matching .ism/manifest is not enough to be reliably sure
2650 # whether it's actually an ISM manifest or some other streaming
2651 # manifest since there are various streaming URL formats
2652 # possible (see [1]) as well as some other shenanigans like
2653 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2654 # so on.
2655 # Thus the most reasonable way to solve this is to delegate
2656 # to generic extractor in order to look into the contents of
2657 # the manifest itself.
2658 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2659 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2660 entry_info_dict = self.url_result(
2661 smuggle_url(video_url, {'to_generic': True}),
2662 GenericIE.ie_key())
2663 else:
2664 entry_info_dict['url'] = video_url
2665
2666 if entry_info_dict.get('formats'):
2667 self._sort_formats(entry_info_dict['formats'])
2668
2669 entries.append(entry_info_dict)
2670
2671 if len(entries) == 1:
2672 return entries[0]
2673 else:
2674 for num, e in enumerate(entries, start=1):
2675 # 'url' results don't have a title
2676 if e.get('title') is not None:
2677 e['title'] = '%s (%d)' % (e['title'], num)
2678 return {
2679 '_type': 'playlist',
2680 'entries': entries,
2681 }
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...