]>
Commit | Line | Data |
---|---|---|
cfe50f04 JMF |
1 | # encoding: utf-8 |
2 | ||
79649588 PH |
3 | from __future__ import unicode_literals |
4 | ||
9b122384 PH |
5 | import os |
6 | import re | |
7 | ||
8 | from .common import InfoExtractor | |
fc9713a1 | 9 | from .youtube import YoutubeIE |
9b122384 | 10 | from ..utils import ( |
9b122384 | 11 | compat_urllib_parse, |
a5caba1e | 12 | compat_urlparse, |
f7300c5c | 13 | compat_xml_parse_error, |
9b122384 | 14 | |
b759a0d4 | 15 | determine_ext, |
9b122384 | 16 | ExtractorError, |
c8e9a235 | 17 | float_or_none, |
aa94a6d3 | 18 | HEADRequest, |
ed2d6a19 | 19 | orderedSet, |
bcf89ce6 | 20 | parse_xml, |
9d4660ca PH |
21 | smuggle_url, |
22 | unescapeHTML, | |
42393ce2 | 23 | unified_strdate, |
4d54ef20 | 24 | unsmuggle_url, |
42393ce2 | 25 | url_basename, |
9b122384 | 26 | ) |
cfe50f04 | 27 | from .brightcove import BrightcoveIE |
c0d0b01f | 28 | from .ooyala import OoyalaIE |
93d020dd | 29 | from .rutv import RUTVIE |
cb3ac1c6 | 30 | from .smotri import SmotriIE |
1419fafd | 31 | from .condenast import CondeNastIE |
9b122384 | 32 | |
0838239e | 33 | |
9b122384 | 34 | class GenericIE(InfoExtractor): |
79649588 | 35 | IE_DESC = 'Generic downloader that works on some sites' |
9b122384 | 36 | _VALID_URL = r'.*' |
79649588 | 37 | IE_NAME = 'generic' |
cfe50f04 JMF |
38 | _TESTS = [ |
39 | { | |
79649588 | 40 | 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', |
d360a146 | 41 | 'md5': '85b90ccc9d73b4acd9138d3af4c27f89', |
79649588 | 42 | 'info_dict': { |
d360a146 S |
43 | 'id': '13601338388002', |
44 | 'ext': 'mp4', | |
79649588 PH |
45 | 'uploader': 'www.hodiho.fr', |
46 | 'title': 'R\u00e9gis plante sa Jeep', | |
cfe50f04 JMF |
47 | } |
48 | }, | |
c19f7764 JMF |
49 | # bandcamp page with custom domain |
50 | { | |
79649588 PH |
51 | 'add_ie': ['Bandcamp'], |
52 | 'url': 'http://bronyrock.com/track/the-pony-mash', | |
79649588 | 53 | 'info_dict': { |
fd50bf62 S |
54 | 'id': '3235767654', |
55 | 'ext': 'mp3', | |
79649588 PH |
56 | 'title': 'The Pony Mash', |
57 | 'uploader': 'M_Pallante', | |
c19f7764 | 58 | }, |
79649588 | 59 | 'skip': 'There is a limit of 200 free downloads / month for the test song', |
c19f7764 | 60 | }, |
eeb165e6 | 61 | # embedded brightcove video |
dd5bcdc4 JMF |
62 | # it also tests brightcove videos that need to set the 'Referer' in the |
63 | # http requests | |
eeb165e6 | 64 | { |
79649588 PH |
65 | 'add_ie': ['Brightcove'], |
66 | 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', | |
67 | 'info_dict': { | |
68 | 'id': '2765128793001', | |
69 | 'ext': 'mp4', | |
70 | 'title': 'Le cours de bourse : l’analyse technique', | |
71 | 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9', | |
72 | 'uploader': 'BFM BUSINESS', | |
eeb165e6 | 73 | }, |
79649588 PH |
74 | 'params': { |
75 | 'skip_download': True, | |
eeb165e6 JMF |
76 | }, |
77 | }, | |
17ab4d3b PH |
78 | { |
79 | # https://github.com/rg3/youtube-dl/issues/2253 | |
80 | 'url': 'http://bcove.me/i6nfkrc3', | |
17ab4d3b PH |
81 | 'md5': '0ba9446db037002366bab3b3eb30c88c', |
82 | 'info_dict': { | |
fd50bf62 S |
83 | 'id': '3101154703001', |
84 | 'ext': 'mp4', | |
17ab4d3b PH |
85 | 'title': 'Still no power', |
86 | 'uploader': 'thestar.com', | |
87 | '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.', | |
88 | }, | |
89 | 'add_ie': ['Brightcove'], | |
90 | }, | |
0479c625 S |
91 | { |
92 | 'url': 'http://www.championat.com/video/football/v/87/87499.html', | |
93 | 'md5': 'fb973ecf6e4a78a67453647444222983', | |
94 | 'info_dict': { | |
95 | 'id': '3414141473001', | |
96 | 'ext': 'mp4', | |
97 | 'title': 'Видео. Удаление Дзагоева (ЦСКА)', | |
98 | 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"', | |
99 | 'uploader': 'Championat', | |
100 | }, | |
101 | }, | |
42393ce2 PH |
102 | # Direct link to a video |
103 | { | |
79649588 | 104 | 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', |
79649588 PH |
105 | 'md5': '67d406c2bcb6af27fa886f31aa934bbe', |
106 | 'info_dict': { | |
107 | 'id': 'trailer', | |
89ef304b | 108 | 'ext': 'mp4', |
79649588 PH |
109 | 'title': 'trailer', |
110 | 'upload_date': '20100513', | |
42393ce2 | 111 | } |
c0d0b01f JMF |
112 | }, |
113 | # ooyala video | |
114 | { | |
79649588 PH |
115 | 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', |
116 | 'md5': '5644c6ca5d5782c1d0d350dad9bd840c', | |
117 | 'info_dict': { | |
118 | 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', | |
119 | 'ext': 'mp4', | |
3486df38 | 120 | 'title': '2cc213299525360.mov', # that's what we get |
c0d0b01f JMF |
121 | }, |
122 | }, | |
89ef304b PH |
123 | # google redirect |
124 | { | |
125 | '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', | |
126 | 'info_dict': { | |
127 | 'id': 'cmQHVoWB5FY', | |
128 | 'ext': 'mp4', | |
129 | 'upload_date': '20130224', | |
130 | 'uploader_id': 'TheVerge', | |
131 | 'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.', | |
132 | 'uploader': 'The Verge', | |
133 | 'title': 'First Firefox OS phones side-by-side', | |
134 | }, | |
135 | 'params': { | |
136 | 'skip_download': False, | |
137 | } | |
f55a1f0a | 138 | }, |
1b86cc41 | 139 | # embed.ly video |
140 | { | |
141 | 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/', | |
142 | 'info_dict': { | |
143 | 'id': '9ODmcdjQcHQ', | |
144 | 'ext': 'mp4', | |
0a5bce56 PH |
145 | 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second', |
146 | 'upload_date': '20140225', | |
147 | 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff', | |
148 | 'uploader': 'Tested', | |
149 | 'uploader_id': 'testedcom', | |
1b86cc41 | 150 | }, |
151 | # No need to test YoutubeIE here | |
152 | 'params': { | |
153 | 'skip_download': True, | |
154 | }, | |
155 | }, | |
60cc4dc4 PH |
156 | # funnyordie embed |
157 | { | |
158 | 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns', | |
60cc4dc4 PH |
159 | 'info_dict': { |
160 | 'id': '18e820ec3f', | |
161 | 'ext': 'mp4', | |
162 | 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama', | |
163 | 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', | |
93d020dd | 164 | }, |
60cc4dc4 | 165 | }, |
93d020dd S |
166 | # RUTV embed |
167 | { | |
168 | 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', | |
169 | 'info_dict': { | |
170 | 'id': '776940', | |
171 | 'ext': 'mp4', | |
172 | 'title': 'Охотское море стало целиком российским', | |
173 | 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43', | |
174 | }, | |
175 | 'params': { | |
176 | # m3u8 download | |
177 | 'skip_download': True, | |
178 | }, | |
aab74fa1 PH |
179 | }, |
180 | # Embedded TED video | |
181 | { | |
182 | 'url': 'http://en.support.wordpress.com/videos/ted-talks/', | |
a8eb5a8e | 183 | 'md5': '65fdff94098e4a607385a60c5177c638', |
aab74fa1 | 184 | 'info_dict': { |
a8eb5a8e | 185 | 'id': '1969', |
aab74fa1 | 186 | 'ext': 'mp4', |
a8eb5a8e PH |
187 | 'title': 'Hidden miracles of the natural world', |
188 | 'uploader': 'Louie Schwartzberg', | |
189 | 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', | |
aab74fa1 | 190 | } |
60cc4dc4 | 191 | }, |
5c386252 | 192 | # Embeded Ustream video |
193 | { | |
194 | 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm', | |
195 | 'md5': '27b99cdb639c9b12a79bca876a073417', | |
196 | 'info_dict': { | |
ca6aada4 | 197 | 'id': '45734260', |
198 | 'ext': 'flv', | |
199 | 'uploader': 'AU SPA: The NSA and Privacy', | |
5c386252 | 200 | 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman' |
201 | } | |
202 | }, | |
d95e35d6 S |
203 | # nowvideo embed hidden behind percent encoding |
204 | { | |
205 | 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/', | |
206 | 'md5': '2baf4ddd70f697d94b1c18cf796d5107', | |
207 | 'info_dict': { | |
208 | 'id': '06e53103ca9aa', | |
209 | 'ext': 'flv', | |
210 | 'title': 'Macross Episode 001 Watch Macross Episode 001 onl', | |
211 | 'description': 'No description', | |
212 | }, | |
0f2a2ba1 | 213 | }, |
893f8832 PH |
214 | # arte embed |
215 | { | |
216 | 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html', | |
217 | 'md5': '7653032cbb25bf6c80d80f217055fa43', | |
218 | 'info_dict': { | |
219 | 'id': '048195-004_PLUS7-F', | |
220 | 'ext': 'flv', | |
221 | 'title': 'X:enius', | |
222 | 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168', | |
223 | 'upload_date': '20140320', | |
224 | }, | |
225 | 'params': { | |
226 | 'skip_download': 'Requires rtmpdump' | |
227 | } | |
228 | }, | |
fa35cdad PH |
229 | # Condé Nast embed |
230 | { | |
231 | 'url': 'http://www.wired.com/2014/04/honda-asimo/', | |
232 | 'md5': 'ba0dfe966fa007657bd1443ee672db0f', | |
233 | 'info_dict': { | |
234 | 'id': '53501be369702d3275860000', | |
235 | 'ext': 'mp4', | |
236 | 'title': 'Honda’s New Asimo Robot Is More Human Than Ever', | |
237 | } | |
ebd3c7b3 PH |
238 | }, |
239 | # Dailymotion embed | |
240 | { | |
241 | 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/', | |
242 | 'md5': '441aeeb82eb72c422c7f14ec533999cd', | |
243 | 'info_dict': { | |
244 | 'id': 'k2mm4bCdJ6CQ2i7c8o2', | |
245 | 'ext': 'mp4', | |
246 | 'title': 'Le Zap de Spi0n n°216 - Zapping du Web', | |
247 | 'uploader': 'Spi0n', | |
248 | }, | |
249 | 'add_ie': ['Dailymotion'], | |
2b88feed PH |
250 | }, |
251 | # YouTube embed | |
252 | { | |
253 | 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html', | |
254 | 'info_dict': { | |
255 | 'id': 'FXRb4ykk4S0', | |
256 | 'ext': 'mp4', | |
257 | 'title': 'The NBL Auction 2014', | |
258 | 'uploader': 'BADMINTON England', | |
259 | 'uploader_id': 'BADMINTONEvents', | |
260 | 'upload_date': '20140603', | |
261 | 'description': 'md5:9ef128a69f1e262a700ed83edb163a73', | |
262 | }, | |
263 | 'add_ie': ['Youtube'], | |
264 | 'params': { | |
265 | 'skip_download': True, | |
266 | } | |
267 | }, | |
c5cd249e JMF |
268 | # MTVSercices embed |
269 | { | |
270 | 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too', | |
271 | 'md5': '35727f82f58c76d996fc188f9755b0d5', | |
272 | 'info_dict': { | |
273 | 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9', | |
274 | 'ext': 'mp4', | |
275 | 'title': 'Review', | |
276 | 'description': 'Mario\'s life in the fast lane has never looked so good.', | |
277 | }, | |
278 | }, | |
61013473 | 279 | # YouTube embed via <data-embed-url=""> |
280 | { | |
281 | 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', | |
61013473 | 282 | 'info_dict': { |
a8eb5a8e | 283 | 'id': '4vAffPZIT44', |
61013473 | 284 | 'ext': 'mp4', |
a8eb5a8e | 285 | 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!', |
ed2d6a19 PH |
286 | 'uploader': 'Gameloft', |
287 | 'uploader_id': 'gameloft', | |
a8eb5a8e PH |
288 | 'upload_date': '20140828', |
289 | 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4', | |
ed2d6a19 PH |
290 | }, |
291 | 'params': { | |
292 | 'skip_download': True, | |
61013473 | 293 | } |
c8e9a235 PH |
294 | }, |
295 | # Camtasia studio | |
296 | { | |
297 | 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/', | |
298 | 'playlist': [{ | |
299 | 'md5': '0c5e352edabf715d762b0ad4e6d9ee67', | |
300 | 'info_dict': { | |
301 | 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', | |
302 | 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1', | |
303 | 'ext': 'flv', | |
304 | 'duration': 2235.90, | |
305 | } | |
306 | }, { | |
307 | 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63', | |
308 | 'info_dict': { | |
309 | 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP', | |
310 | 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip', | |
311 | 'ext': 'flv', | |
312 | 'duration': 2235.93, | |
313 | } | |
314 | }], | |
315 | 'info_dict': { | |
316 | 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', | |
317 | } | |
4d805e06 PH |
318 | }, |
319 | # Flowplayer | |
320 | { | |
321 | 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html', | |
322 | 'md5': '9d65602bf31c6e20014319c7d07fba27', | |
323 | 'info_dict': { | |
324 | 'id': '5123ea6d5e5a7', | |
325 | 'ext': 'mp4', | |
326 | 'age_limit': 18, | |
327 | 'uploader': 'www.handjobhub.com', | |
d6d9186f | 328 | 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', |
4d805e06 | 329 | } |
0990305d PH |
330 | }, |
331 | # RSS feed | |
332 | { | |
333 | 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', | |
334 | 'info_dict': { | |
335 | 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', | |
336 | 'title': 'Zero Punctuation', | |
337 | 'description': 're:' | |
338 | }, | |
339 | 'playlist_mincount': 11, | |
22a6f150 PH |
340 | }, |
341 | # Multiple brightcove videos | |
342 | # https://github.com/rg3/youtube-dl/issues/2283 | |
343 | { | |
344 | 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', | |
345 | 'info_dict': { | |
346 | 'id': 'always-never', | |
347 | 'title': 'Always / Never - The New Yorker', | |
348 | }, | |
349 | 'playlist_count': 3, | |
350 | 'params': { | |
351 | 'extract_flat': False, | |
352 | 'skip_download': True, | |
353 | } | |
1a94ff68 S |
354 | }, |
355 | # MLB embed | |
356 | { | |
357 | 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/', | |
358 | 'md5': '96f09a37e44da40dd083e12d9a683327', | |
359 | 'info_dict': { | |
360 | 'id': '33322633', | |
361 | 'ext': 'mp4', | |
362 | 'title': 'Ump changes call to ball', | |
363 | 'description': 'md5:71c11215384298a172a6dcb4c2e20685', | |
364 | 'duration': 48, | |
365 | 'timestamp': 1401537900, | |
366 | 'upload_date': '20140531', | |
367 | 'thumbnail': 're:^https?://.*\.jpg$', | |
368 | }, | |
369 | }, | |
746c67d7 NJ |
370 | # Wistia embed |
371 | { | |
372 | 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', | |
373 | 'md5': '8788b683c777a5cf25621eaf286d0c23', | |
374 | 'info_dict': { | |
375 | 'id': '1cfaf6b7ea', | |
376 | 'ext': 'mov', | |
377 | 'title': 'md5:51364a8d3d009997ba99656004b5e20d', | |
378 | 'duration': 643.0, | |
379 | 'filesize': 182808282, | |
380 | 'uploader': 'education-portal.com', | |
381 | }, | |
382 | }, | |
52cffcb1 | 383 | { |
384 | 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz', | |
385 | 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4', | |
386 | 'info_dict': { | |
387 | 'id': 'uxjb0lwrcz', | |
388 | 'ext': 'mp4', | |
85d7b765 | 389 | 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', |
52cffcb1 | 390 | 'duration': 1715.0, |
85d7b765 | 391 | 'uploader': 'thoughtworks.wistia.com', |
70b7e3fb | 392 | }, |
52cffcb1 | 393 | }, |
70b7e3fb PH |
394 | # Direct download with broken HEAD |
395 | { | |
396 | 'url': 'http://ai-radio.org:8000/radio.opus', | |
397 | 'info_dict': { | |
398 | 'id': 'radio', | |
399 | 'ext': 'opus', | |
400 | 'title': 'radio', | |
401 | }, | |
402 | 'params': { | |
403 | 'skip_download': True, # infinite live stream | |
404 | }, | |
405 | 'expected_warnings': [ | |
406 | r'501.*Not Implemented' | |
407 | ], | |
408 | } | |
cfe50f04 | 409 | ] |
9b122384 | 410 | |
9b122384 PH |
411 | def report_following_redirect(self, new_url): |
412 | """Report information extraction.""" | |
79649588 | 413 | self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) |
9b122384 | 414 | |
4fc946b5 PH |
415 | def _extract_rss(self, url, video_id, doc): |
416 | playlist_title = doc.find('./channel/title').text | |
417 | playlist_desc_el = doc.find('./channel/description') | |
418 | playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text | |
419 | ||
420 | entries = [{ | |
421 | '_type': 'url', | |
422 | 'url': e.find('link').text, | |
423 | 'title': e.find('title').text, | |
424 | } for e in doc.findall('./channel/item')] | |
425 | ||
426 | return { | |
427 | '_type': 'playlist', | |
428 | 'id': url, | |
429 | 'title': playlist_title, | |
430 | 'description': playlist_desc, | |
431 | 'entries': entries, | |
432 | } | |
433 | ||
c8e9a235 PH |
434 | def _extract_camtasia(self, url, video_id, webpage): |
435 | """ Returns None if no camtasia video can be found. """ | |
436 | ||
437 | camtasia_cfg = self._search_regex( | |
438 | r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);', | |
439 | webpage, 'camtasia configuration file', default=None) | |
440 | if camtasia_cfg is None: | |
441 | return None | |
442 | ||
443 | title = self._html_search_meta('DC.title', webpage, fatal=True) | |
444 | ||
445 | camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg) | |
446 | camtasia_cfg = self._download_xml( | |
447 | camtasia_url, video_id, | |
448 | note='Downloading camtasia configuration', | |
449 | errnote='Failed to download camtasia configuration') | |
450 | fileset_node = camtasia_cfg.find('./playlist/array/fileset') | |
451 | ||
452 | entries = [] | |
453 | for n in fileset_node.getchildren(): | |
454 | url_n = n.find('./uri') | |
455 | if url_n is None: | |
456 | continue | |
457 | ||
458 | entries.append({ | |
459 | 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0], | |
460 | 'title': '%s - %s' % (title, n.tag), | |
461 | 'url': compat_urlparse.urljoin(url, url_n.text), | |
462 | 'duration': float_or_none(n.find('./duration').text), | |
463 | }) | |
464 | ||
465 | return { | |
466 | '_type': 'playlist', | |
467 | 'entries': entries, | |
468 | 'title': title, | |
469 | } | |
470 | ||
9b122384 | 471 | def _real_extract(self, url): |
ebd3c7b3 PH |
472 | if url.startswith('//'): |
473 | return { | |
474 | '_type': 'url', | |
20991253 | 475 | 'url': self.http_scheme() + url, |
ebd3c7b3 PH |
476 | } |
477 | ||
a7130543 JMF |
478 | parsed_url = compat_urlparse.urlparse(url) |
479 | if not parsed_url.scheme: | |
04b4d394 PH |
480 | default_search = self._downloader.params.get('default_search') |
481 | if default_search is None: | |
1f7ccb90 | 482 | default_search = 'fixup_error' |
04b4d394 | 483 | |
1f7ccb90 | 484 | if default_search in ('auto', 'auto_warning', 'fixup_error'): |
04b4d394 PH |
485 | if '/' in url: |
486 | self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') | |
487 | return self.url_result('http://' + url) | |
1f7ccb90 | 488 | elif default_search != 'fixup_error': |
9c1fc022 | 489 | if default_search == 'auto_warning': |
0e67ab0d PH |
490 | if re.match(r'^(?:url|URL)$', url): |
491 | raise ExtractorError( | |
492 | 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url, | |
493 | expected=True) | |
494 | else: | |
495 | self._downloader.report_warning( | |
7571c02c | 496 | 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url) |
04b4d394 | 497 | return self.url_result('ytsearch:' + url) |
1f7ccb90 PH |
498 | |
499 | if default_search in ('error', 'fixup_error'): | |
7571c02c PH |
500 | raise ExtractorError( |
501 | ('%r is not a valid URL. ' | |
eef4a7a3 | 502 | 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' |
7571c02c | 503 | ) % (url, url), expected=True) |
04b4d394 | 504 | else: |
f2f2c0c2 PH |
505 | if ':' not in default_search: |
506 | default_search += ':' | |
04b4d394 | 507 | return self.url_result(default_search + url) |
4d54ef20 PH |
508 | |
509 | url, smuggled_data = unsmuggle_url(url) | |
510 | force_videoid = None | |
d6e6a422 | 511 | is_intentional = smuggled_data and smuggled_data.get('to_generic') |
4d54ef20 PH |
512 | if smuggled_data and 'force_videoid' in smuggled_data: |
513 | force_videoid = smuggled_data['force_videoid'] | |
514 | video_id = force_videoid | |
515 | else: | |
516 | video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] | |
a7130543 | 517 | |
79649588 | 518 | self.to_screen('%s: Requesting header' % video_id) |
c1d1facd | 519 | |
ebab4520 | 520 | head_req = HEADRequest(url) |
23be51d8 | 521 | head_response = self._request_webpage( |
ebab4520 PH |
522 | head_req, video_id, |
523 | note=False, errnote='Could not send HEAD request to %s' % url, | |
524 | fatal=False) | |
42393ce2 | 525 | |
23be51d8 | 526 | if head_response is not False: |
42393ce2 | 527 | # Check for redirect |
23be51d8 | 528 | new_url = head_response.geturl() |
42393ce2 PH |
529 | if url != new_url: |
530 | self.report_following_redirect(new_url) | |
4d54ef20 PH |
531 | if force_videoid: |
532 | new_url = smuggle_url( | |
533 | new_url, {'force_videoid': force_videoid}) | |
cecaaf3f | 534 | return self.url_result(new_url) |
42393ce2 | 535 | |
23be51d8 PH |
536 | full_response = None |
537 | if head_response is False: | |
538 | full_response = self._request_webpage(url, video_id) | |
539 | head_response = full_response | |
540 | ||
541 | # Check for direct link to a video | |
542 | content_type = head_response.headers.get('Content-Type', '') | |
543 | m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) | |
544 | if m: | |
545 | upload_date = unified_strdate( | |
546 | head_response.headers.get('Last-Modified')) | |
547 | return { | |
548 | 'id': video_id, | |
549 | 'title': os.path.splitext(url_basename(url))[0], | |
550 | 'formats': [{ | |
551 | 'format_id': m.group('format_id'), | |
552 | 'url': url, | |
553 | 'vcodec': 'none' if m.group('type') == 'audio' else None | |
554 | }], | |
555 | 'upload_date': upload_date, | |
556 | } | |
42393ce2 | 557 | |
d6e6a422 PH |
558 | if not self._downloader.params.get('test', False) and not is_intentional: |
559 | self._downloader.report_warning('Falling back on generic information extractor.') | |
560 | ||
23be51d8 | 561 | if full_response: |
37d66e7f | 562 | webpage = self._webpage_read_content(full_response, url, video_id) |
23be51d8 | 563 | else: |
9b122384 | 564 | webpage = self._download_webpage(url, video_id) |
9b122384 | 565 | self.report_extraction(video_id) |
887c6acd | 566 | |
4fc946b5 PH |
567 | # Is it an RSS feed? |
568 | try: | |
bcf89ce6 | 569 | doc = parse_xml(webpage) |
4fc946b5 PH |
570 | if doc.tag == 'rss': |
571 | return self._extract_rss(url, video_id, doc) | |
f7300c5c | 572 | except compat_xml_parse_error: |
4fc946b5 PH |
573 | pass |
574 | ||
c8e9a235 PH |
575 | # Is it a Camtasia project? |
576 | camtasia_res = self._extract_camtasia(url, video_id, webpage) | |
577 | if camtasia_res is not None: | |
578 | return camtasia_res | |
579 | ||
14390730 S |
580 | # Sometimes embedded video player is hidden behind percent encoding |
581 | # (e.g. https://github.com/rg3/youtube-dl/issues/2448) | |
582 | # Unescaping the whole page allows to handle those cases in a generic way | |
1f7659db S |
583 | webpage = compat_urllib_parse.unquote(webpage) |
584 | ||
887c6acd PH |
585 | # it's tempting to parse this further, but you would |
586 | # have to take into account all the variations like | |
587 | # Video Title - Site Name | |
588 | # Site Name | Video Title | |
589 | # Video Title - Tagline | Site Name | |
590 | # and so on and so forth; it's just not practical | |
ef4fd848 | 591 | video_title = self._html_search_regex( |
79649588 PH |
592 | r'(?s)<title>(.*?)</title>', webpage, 'video title', |
593 | default='video') | |
ef4fd848 | 594 | |
4d805e06 PH |
595 | # Try to detect age limit automatically |
596 | age_limit = self._rta_search(webpage) | |
597 | # And then there are the jokers who advertise that they use RTA, | |
598 | # but actually don't. | |
599 | AGE_LIMIT_MARKERS = [ | |
600 | r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>', | |
601 | ] | |
602 | if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): | |
603 | age_limit = 18 | |
604 | ||
ef4fd848 PH |
605 | # video uploader is domain name |
606 | video_uploader = self._search_regex( | |
79649588 | 607 | r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') |
887c6acd | 608 | |
ed2d6a19 PH |
609 | # Helper method |
610 | def _playlist_from_matches(matches, getter, ie=None): | |
3b2f933b PH |
611 | urlrs = orderedSet( |
612 | self.url_result(self._proto_relative_url(getter(m)), ie) | |
613 | for m in matches) | |
ed2d6a19 PH |
614 | return self.playlist_result( |
615 | urlrs, playlist_id=video_id, playlist_title=video_title) | |
616 | ||
627a91a9 | 617 | # Look for BrightCove: |
99877772 PH |
618 | bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) |
619 | if bc_urls: | |
79649588 | 620 | self.to_screen('Brightcove video detected.') |
99877772 PH |
621 | entries = [{ |
622 | '_type': 'url', | |
623 | 'url': smuggle_url(bc_url, {'Referer': url}), | |
624 | 'ie_key': 'Brightcove' | |
625 | } for bc_url in bc_urls] | |
626 | ||
627 | return { | |
628 | '_type': 'playlist', | |
629 | 'title': video_title, | |
630 | 'id': video_id, | |
631 | 'entries': entries, | |
632 | } | |
cfe50f04 | 633 | |
7115ca84 | 634 | # Look for embedded (iframe) Vimeo player |
9d4660ca | 635 | mobj = re.search( |
15fd51b3 | 636 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage) |
9d4660ca | 637 | if mobj: |
15fd51b3 | 638 | player_url = unescapeHTML(mobj.group('url')) |
9d4660ca | 639 | surl = smuggle_url(player_url, {'Referer': url}) |
09a42738 | 640 | return self.url_result(surl) |
9d4660ca | 641 | |
7115ca84 PH |
642 | # Look for embedded (swf embed) Vimeo player |
643 | mobj = re.search( | |
09a42738 | 644 | r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) |
7115ca84 | 645 | if mobj: |
09a42738 | 646 | return self.url_result(mobj.group(1)) |
7115ca84 | 647 | |
53c1d3ef | 648 | # Look for embedded YouTube player |
1f9da904 | 649 | matches = re.findall(r'''(?x) |
2b88feed PH |
650 | (?: |
651 | <iframe[^>]+?src=| | |
c71dfccc | 652 | data-video-url=| |
2b88feed | 653 | <embed[^>]+?src=| |
a7e97f6d PH |
654 | embedSWF\(?:\s*| |
655 | new\s+SWFObject\( | |
2b88feed PH |
656 | ) |
657 | (["\']) | |
1bf5423e | 658 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ |
6b08cdf6 | 659 | (?:embed|v|p)/.+?) |
1f9da904 | 660 | \1''', webpage) |
887c6acd | 661 | if matches: |
ed2d6a19 | 662 | return _playlist_from_matches( |
3b2f933b | 663 | matches, lambda m: unescapeHTML(m[1])) |
53c1d3ef | 664 | |
355e4fd0 PH |
665 | # Look for embedded Dailymotion player |
666 | matches = re.findall( | |
ef4fd848 | 667 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) |
355e4fd0 | 668 | if matches: |
ed2d6a19 PH |
669 | return _playlist_from_matches( |
670 | matches, lambda m: unescapeHTML(m[1])) | |
355e4fd0 | 671 | |
8489578d NJ |
672 | # Look for embedded Dailymotion playlist player (#3822) |
673 | m = re.search( | |
674 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage) | |
675 | if m: | |
676 | playlists = re.findall( | |
677 | r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url'))) | |
678 | if playlists: | |
679 | return _playlist_from_matches( | |
680 | playlists, lambda p: '//dailymotion.com/playlist/%s' % p) | |
681 | ||
ef4fd848 PH |
682 | # Look for embedded Wistia player |
683 | match = re.search( | |
281d3f1d | 684 | r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) |
ef4fd848 | 685 | if match: |
9471c444 NJ |
686 | embed_url = self._proto_relative_url( |
687 | unescapeHTML(match.group('url'))) | |
ef4fd848 PH |
688 | return { |
689 | '_type': 'url_transparent', | |
9471c444 | 690 | 'url': embed_url, |
ef4fd848 PH |
691 | 'ie_key': 'Wistia', |
692 | 'uploader': video_uploader, | |
693 | 'title': video_title, | |
694 | 'id': video_id, | |
695 | } | |
52cffcb1 | 696 | |
9471c444 | 697 | match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) |
746c67d7 NJ |
698 | if match: |
699 | return { | |
700 | '_type': 'url_transparent', | |
701 | 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), | |
702 | 'ie_key': 'Wistia', | |
703 | 'uploader': video_uploader, | |
704 | 'title': video_title, | |
705 | 'id': match.group('id') | |
706 | } | |
ef4fd848 | 707 | |
ee3e63e4 | 708 | # Look for embedded blip.tv player |
19dab5e6 | 709 | mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) |
ee3e63e4 | 710 | if mobj: |
19dab5e6 | 711 | return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') |
1f8b6af7 | 712 | mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) |
ee3e63e4 | 713 | if mobj: |
19dab5e6 | 714 | return self.url_result(mobj.group(1), 'BlipTV') |
ee3e63e4 | 715 | |
fa35cdad PH |
716 | # Look for embedded condenast player |
717 | matches = re.findall( | |
718 | r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")', | |
719 | webpage) | |
720 | if matches: | |
721 | return { | |
722 | '_type': 'playlist', | |
723 | 'entries': [{ | |
724 | '_type': 'url', | |
725 | 'ie_key': 'CondeNast', | |
726 | 'url': ma, | |
727 | } for ma in matches], | |
728 | 'title': video_title, | |
729 | 'id': video_id, | |
730 | } | |
731 | ||
c19f7764 JMF |
732 | # Look for Bandcamp pages with custom domain |
733 | mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) | |
734 | if mobj is not None: | |
735 | burl = unescapeHTML(mobj.group(1)) | |
09804265 JMF |
736 | # Don't set the extractor because it can be a track url or an album |
737 | return self.url_result(burl) | |
c19f7764 | 738 | |
f25571ff PH |
739 | # Look for embedded Vevo player |
740 | mobj = re.search( | |
741 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage) | |
742 | if mobj is not None: | |
743 | return self.url_result(mobj.group('url')) | |
744 | ||
c0d0b01f | 745 | # Look for Ooyala videos |
750f9020 JMF |
746 | mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or |
747 | re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)) | |
c0d0b01f | 748 | if mobj is not None: |
750f9020 | 749 | return OoyalaIE._build_url_result(mobj.group('ec')) |
c0d0b01f | 750 | |
aa94a6d3 | 751 | # Look for Aparat videos |
48099643 | 752 | mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage) |
aa94a6d3 PH |
753 | if mobj is not None: |
754 | return self.url_result(mobj.group(1), 'Aparat') | |
755 | ||
c93c2ab1 | 756 | # Look for MPORA videos |
c3f51436 | 757 | mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage) |
c93c2ab1 PH |
758 | if mobj is not None: |
759 | return self.url_result(mobj.group(1), 'Mpora') | |
5f59ee79 | 760 | |
15c0e8e7 | 761 | # Look for embedded NovaMov-based player |
8f89e687 | 762 | mobj = re.search( |
8dfa187b | 763 | r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\']) |
15c0e8e7 S |
764 | (?P<url>http://(?:(?:embed|www)\.)? |
765 | (?:novamov\.com| | |
766 | nowvideo\.(?:ch|sx|eu|at|ag|co)| | |
767 | videoweed\.(?:es|com)| | |
768 | movshare\.(?:net|sx|ag)| | |
769 | divxstage\.(?:eu|net|ch|co|at|ag)) | |
770 | /embed\.php.+?)\1''', webpage) | |
8f89e687 | 771 | if mobj is not None: |
15c0e8e7 | 772 | return self.url_result(mobj.group('url')) |
50f56607 | 773 | |
9834872b PH |
774 | # Look for embedded Facebook player |
775 | mobj = re.search( | |
db1f3888 | 776 | r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) |
9834872b PH |
777 | if mobj is not None: |
778 | return self.url_result(mobj.group('url'), 'Facebook') | |
779 | ||
ca97a56e S |
780 | # Look for embedded VK player |
781 | mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage) | |
782 | if mobj is not None: | |
783 | return self.url_result(mobj.group('url'), 'VK') | |
784 | ||
0364fa8b S |
785 | # Look for embedded ivi player |
786 | mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) | |
787 | if mobj is not None: | |
788 | return self.url_result(mobj.group('url'), 'Ivi') | |
789 | ||
db1f3888 PH |
790 | # Look for embedded Huffington Post player |
791 | mobj = re.search( | |
c3f51436 | 792 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage) |
db1f3888 PH |
793 | if mobj is not None: |
794 | return self.url_result(mobj.group('url'), 'HuffPost') | |
795 | ||
1b86cc41 | 796 | # Look for embed.ly |
797 | mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage) | |
798 | if mobj is not None: | |
799 | return self.url_result(mobj.group('url')) | |
800 | mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage) | |
801 | if mobj is not None: | |
802 | return self.url_result(compat_urllib_parse.unquote(mobj.group('url'))) | |
803 | ||
60cc4dc4 PH |
804 | # Look for funnyordie embed |
805 | matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) | |
806 | if matches: | |
ed2d6a19 PH |
807 | return _playlist_from_matches( |
808 | matches, getter=unescapeHTML, ie='FunnyOrDie') | |
60cc4dc4 | 809 | |
93d020dd S |
810 | # Look for embedded RUTV player |
811 | rutv_url = RUTVIE._extract_url(webpage) | |
812 | if rutv_url: | |
813 | return self.url_result(rutv_url, 'RUTV') | |
814 | ||
7e2ede98 JMF |
815 | # Look for embedded TED player |
816 | mobj = re.search( | |
817 | r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage) | |
818 | if mobj is not None: | |
819 | return self.url_result(mobj.group('url'), 'TED') | |
820 | ||
5c386252 | 821 | # Look for embedded Ustream videos |
822 | mobj = re.search( | |
823 | r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage) | |
824 | if mobj is not None: | |
825 | return self.url_result(mobj.group('url'), 'Ustream') | |
826 | ||
893f8832 PH |
827 | # Look for embedded arte.tv player |
828 | mobj = re.search( | |
829 | r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"', | |
830 | webpage) | |
831 | if mobj is not None: | |
832 | return self.url_result(mobj.group('url'), 'ArteTVEmbed') | |
833 | ||
cb3ac1c6 S |
834 | # Look for embedded smotri.com player |
835 | smotri_url = SmotriIE._extract_url(webpage) | |
836 | if smotri_url: | |
837 | return self.url_result(smotri_url, 'Smotri') | |
838 | ||
20991253 PH |
839 | # Look for embeded soundcloud player |
840 | mobj = re.search( | |
841 | r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', | |
842 | webpage) | |
843 | if mobj is not None: | |
844 | url = unescapeHTML(mobj.group('url')) | |
845 | return self.url_result(url) | |
846 | ||
826ec77f PH |
847 | # Look for embedded vulture.com player |
848 | mobj = re.search( | |
849 | r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"', | |
850 | webpage) | |
851 | if mobj is not None: | |
852 | url = unescapeHTML(mobj.group('url')) | |
853 | return self.url_result(url, ie='Vulture') | |
854 | ||
c5cd249e JMF |
855 | # Look for embedded mtvservices player |
856 | mobj = re.search( | |
857 | r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"', | |
858 | webpage) | |
859 | if mobj is not None: | |
860 | url = unescapeHTML(mobj.group('url')) | |
861 | return self.url_result(url, ie='MTVServicesEmbedded') | |
862 | ||
49807b4a S |
863 | # Look for embedded yahoo player |
864 | mobj = re.search( | |
865 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', | |
866 | webpage) | |
867 | if mobj is not None: | |
868 | return self.url_result(mobj.group('url'), 'Yahoo') | |
869 | ||
2ef6fcb5 PH |
870 | # Look for embedded sbs.com.au player |
871 | mobj = re.search( | |
872 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1', | |
873 | webpage) | |
874 | if mobj is not None: | |
875 | return self.url_result(mobj.group('url'), 'SBS') | |
876 | ||
1a94ff68 S |
877 | mobj = re.search( |
878 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', | |
879 | webpage) | |
880 | if mobj is not None: | |
881 | return self.url_result(mobj.group('url'), 'MLB') | |
882 | ||
1419fafd S |
883 | mobj = re.search( |
884 | r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL, | |
885 | webpage) | |
886 | if mobj is not None: | |
887 | return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast') | |
888 | ||
ced659bb S |
889 | def check_video(vurl): |
890 | vpath = compat_urlparse.urlparse(vurl).path | |
891 | vext = determine_ext(vpath) | |
892 | return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') | |
893 | ||
894 | def filter_video(urls): | |
895 | return list(filter(check_video, urls)) | |
896 | ||
9b122384 | 897 | # Start with something easy: JW Player in SWFObject |
ced659bb | 898 | found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)) |
b30b8698 | 899 | if not found: |
d981cef6 | 900 | # Look for gorilla-vid style embedding |
ced659bb | 901 | found = filter_video(re.findall(r'''(?sx) |
c0292e8a PH |
902 | (?: |
903 | jw_plugins| | |
904 | JWPlayerOptions| | |
905 | jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup | |
906 | ) | |
ced659bb | 907 | .*?file\s*:\s*["\'](.*?)["\']''', webpage)) |
b30b8698 | 908 | if not found: |
9b122384 | 909 | # Broaden the search a little bit |
ced659bb | 910 | found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)) |
b30b8698 PH |
911 | if not found: |
912 | # Broaden the findall a little bit: JWPlayer JS loader | |
ced659bb S |
913 | found = filter_video(re.findall( |
914 | r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)) | |
4d805e06 PH |
915 | if not found: |
916 | # Flow player | |
ced659bb | 917 | found = filter_video(re.findall(r'''(?xs) |
4d805e06 PH |
918 | flowplayer\("[^"]+",\s* |
919 | \{[^}]+?\}\s*, | |
920 | \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s* | |
921 | ["']?url["']?\s*:\s*["']([^"']+)["'] | |
ced659bb | 922 | ''', webpage)) |
b30b8698 | 923 | if not found: |
9b122384 | 924 | # Try to find twitter cards info |
ced659bb S |
925 | found = filter_video(re.findall( |
926 | r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)) | |
b30b8698 | 927 | if not found: |
9b122384 PH |
928 | # We look for Open Graph info: |
929 | # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am) | |
b30b8698 | 930 | m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage) |
9b122384 PH |
931 | # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: |
932 | if m_video_type is not None: | |
ced659bb | 933 | found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)) |
b30b8698 | 934 | if not found: |
7fea7156 | 935 | # HTML5 video |
48a24ab7 | 936 | found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src="([^"]+)"', webpage) |
b30b8698 | 937 | if not found: |
a5a45015 | 938 | found = re.search( |
89ef304b | 939 | r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' |
a04aa7a9 | 940 | r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)', |
89ef304b | 941 | webpage) |
b30b8698 PH |
942 | if found: |
943 | new_url = found.group(1) | |
89ef304b PH |
944 | self.report_following_redirect(new_url) |
945 | return { | |
946 | '_type': 'url', | |
947 | 'url': new_url, | |
948 | } | |
b30b8698 | 949 | if not found: |
79649588 | 950 | raise ExtractorError('Unsupported URL: %s' % url) |
9b122384 | 951 | |
b30b8698 PH |
952 | entries = [] |
953 | for video_url in found: | |
954 | video_url = compat_urlparse.urljoin(url, video_url) | |
955 | video_id = compat_urllib_parse.unquote(os.path.basename(video_url)) | |
9b122384 | 956 | |
b30b8698 PH |
957 | # Sometimes, jwplayer extraction will result in a YouTube URL |
958 | if YoutubeIE.suitable(video_url): | |
959 | entries.append(self.url_result(video_url, 'Youtube')) | |
960 | continue | |
9b122384 | 961 | |
b30b8698 PH |
962 | # here's a fun little line of code for you: |
963 | video_id = os.path.splitext(video_id)[0] | |
fc9713a1 | 964 | |
b30b8698 PH |
965 | entries.append({ |
966 | 'id': video_id, | |
967 | 'url': video_url, | |
968 | 'uploader': video_uploader, | |
969 | 'title': video_title, | |
4d805e06 | 970 | 'age_limit': age_limit, |
b30b8698 PH |
971 | }) |
972 | ||
973 | if len(entries) == 1: | |
669f0e7c | 974 | return entries[0] |
b30b8698 PH |
975 | else: |
976 | for num, e in enumerate(entries, start=1): | |
977 | e['title'] = '%s (%d)' % (e['title'], num) | |
978 | return { | |
979 | '_type': 'playlist', | |
980 | 'entries': entries, | |
981 | } | |
9b122384 | 982 |