2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_urlparse
22 from .dailymotion
import DailymotionIE
23 from .odnoklassniki
import OdnoklassnikiIE
24 from .pladform
import PladformIE
25 from .vimeo
import VimeoIE
26 from .youtube
import YoutubeIE
29 class VKBaseIE(InfoExtractor
):
33 username
, password
= self
._get
_login
_info
()
37 login_page
, url_handle
= self
._download
_webpage
_handle
(
38 'https://vk.com', None, 'Downloading login page')
40 login_form
= self
._hidden
_inputs
(login_page
)
43 'email': username
.encode('cp1251'),
44 'pass': password
.encode('cp1251'),
47 # vk serves two same remixlhk cookies in Set-Cookie header and expects
48 # first one to be actually set
49 self
._apply
_first
_set
_cookie
_header
(url_handle
, 'remixlhk')
51 login_page
= self
._download
_webpage
(
52 'https://vk.com/login', None,
54 data
=urlencode_postdata(login_form
))
56 if re
.search(r
'onLoginFailed', login_page
):
58 'Unable to login, incorrect username and/or password', expected
=True)
60 def _real_initialize(self
):
63 def _download_payload(self
, path
, video_id
, data
, fatal
=True):
65 code
, payload
= self
._download
_json
(
66 'https://vk.com/%s.php' % path
, video_id
,
67 data
=urlencode_postdata(data
), fatal
=fatal
,
68 headers
={'X-Requested-With': 'XMLHttpRequest'}
)['payload']
70 self
.raise_login_required()
72 raise ExtractorError(clean_html(payload
[0][1:-1]), expected
=True)
83 (?:(?:m|new)\.)?vk\.com/video_|
86 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
88 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
89 (?:www\.)?daxab.com/embed/
91 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
96 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
97 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
99 'id': '-77521_162222515',
101 'title': 'ProtivoGunz - Хуёвая песня',
102 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
103 'uploader_id': '-77521',
105 'timestamp': 1329049880,
106 'upload_date': '20120212',
110 'url': 'http://vk.com/video205387401_165548505',
112 'id': '205387401_165548505',
115 'uploader': 'Tom Cruise',
116 'uploader_id': '205387401',
118 'timestamp': 1374364108,
119 'upload_date': '20130720',
123 'note': 'Embedded video',
124 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
125 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
127 'id': '-77521_162222515',
129 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
130 'title': 'ProtivoGunz - Хуёвая песня',
132 'upload_date': '20120212',
133 'timestamp': 1329049880,
134 'uploader_id': '-77521',
139 # please update if you find a video whose URL follows the same pattern
140 'url': 'http://vk.com/video-8871596_164049491',
141 'md5': 'a590bcaf3d543576c9bd162812387666',
142 'note': 'Only available for registered users',
144 'id': '-8871596_164049491',
146 'uploader': 'Триллеры',
147 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
149 'upload_date': '20121218',
155 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
157 'id': '-43215063_168067957',
159 'uploader': 'Bro Mazter',
162 'upload_date': '20140328',
163 'uploader_id': '223413403',
164 'timestamp': 1396018030,
166 'skip': 'Requires vk account credentials',
169 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
170 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
171 'note': 'ivi.ru embed',
173 'id': '-43215063_169084319',
175 'title': 'Книга Илая',
177 'upload_date': '20140626',
183 'url': 'https://vk.com/video-93049196_456239755?list=ln-cBjJ7S4jYYx3ADnmDT',
185 'id': '-93049196_456239755',
187 'title': '8 серия (озвучка)',
189 'upload_date': '20211222',
194 # video (removed?) only available with list id
195 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
196 'md5': '091287af5402239a1051c37ec7b92913',
198 'id': '30481095_171201961',
200 'title': 'ТюменцевВВ_09.07.2015',
201 'uploader': 'Anton Ivanov',
203 'upload_date': '20150709',
210 'url': 'https://vk.com/video276849682_170681728',
214 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
215 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
217 'upload_date': '20130116',
218 'uploader': "Children's Joy Foundation Inc.",
219 'uploader_id': 'thecjf',
225 'url': 'https://vk.com/video-37468416_456239855',
227 'id': 'k3lz2cmXyRuJQSjGHUv',
229 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
230 'description': 'md5:424b8e88cc873217f520e582ba28bb36',
231 'uploader': 'AniLibria.Tv',
232 'upload_date': '20160914',
233 'uploader_id': 'x1p5vl5',
234 'timestamp': 1473877246,
237 'skip_download': True,
241 # video key is extra_data not url\d+
242 'url': 'http://vk.com/video-110305615_171782105',
243 'md5': 'e13fcda136f99764872e739d13fac1d1',
245 'id': '-110305615_171782105',
247 'title': 'S-Dance, репетиции к The way show',
248 'uploader': 'THE WAY SHOW | 17 апреля',
249 'uploader_id': '-110305615',
250 'timestamp': 1454859345,
251 'upload_date': '20160207',
254 'skip_download': True,
258 # finished live stream, postlive_mp4
259 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
261 'id': '-387766_456242764',
263 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
264 'uploader': 'Игромания',
266 # TODO: use act=show to extract view_count
268 'upload_date': '20160929',
269 'uploader_id': '-387766',
270 'timestamp': 1475137527,
273 'skip_download': True,
277 # live stream, hls and rtmp links, most likely already finished live
278 # stream by the time you are reading this comment
279 'url': 'https://vk.com/video-140332_456239111',
280 'only_matching': True,
283 # removed video, just testing that we match the pattern
284 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
285 'only_matching': True,
288 # age restricted video, requires vk account credentials
289 'url': 'https://vk.com/video205387401_164765225',
290 'only_matching': True,
294 'url': 'https://vk.com/video-76116461_171554880',
295 'only_matching': True,
298 'url': 'http://new.vk.com/video205387401_165548505',
299 'only_matching': True,
302 # This video is no longer available, because its author has been blocked.
303 'url': 'https://vk.com/video-10639516_456240611',
304 'only_matching': True,
307 # The video is not available in your region.
308 'url': 'https://vk.com/video-51812607_171445436',
309 'only_matching': True,
312 'url': 'https://vk.com/clip30014565_456240946',
313 'only_matching': True,
317 def _extract_sibnet_urls(webpage
):
318 # https://help.sibnet.ru/?sibnet_video_embed
319 return [unescapeHTML(mobj
.group('url')) for mobj
in re
.finditer(
320 r
'<iframe\b[^>]+\bsrc=(["\'])(?P
<url
>(?
:https?
:)?
//video\
.sibnet\
.ru
/shell\
.php
\?.*?
\bvideoid
=\d
+.*?
)\
1',
323 def _real_extract(self, url):
324 mobj = self._match_valid_url(url)
325 video_id = mobj.group('videoid
')
330 'act
': 'show_inline
',
333 # Some videos (removed?) can only be downloaded with list id specified
334 list_id = mobj.group('list_id
')
336 data['list'] = list_id
338 payload = self._download_payload('al_video
', video_id, data)
339 info_page = payload[1]
341 mv_data = opts.get('mvData
') or {}
342 player = opts.get('player
') or {}
344 video_id = '%s_%s' % (mobj.group('oid
'), mobj.group('id'))
346 info_page = self._download_webpage(
347 'http
://vk
.com
/video_ext
.php?
' + mobj.group('embed_query
'), video_id)
349 error_message = self._html_search_regex(
350 [r'(?s
)<!><div
[^
>]+class="video_layer_message"[^
>]*>(.+?
)</div
>',
351 r'(?s
)<div
[^
>]+id="video_ext_msg"[^
>]*>(.+?
)</div
>'],
352 info_page, 'error message
', default=None)
354 raise ExtractorError(error_message, expected=True)
356 if re.search(r'<!>/login\
.php
\?.*\bact
=security_check
', info_page):
357 raise ExtractorError(
358 'You are trying to log
in from an unusual location
. You should confirm ownership at vk
.com to log
in with this IP
.',
361 ERROR_COPYRIGHT = 'Video
%s has been removed
from public access due to rightholder complaint
.'
364 r'>Видеозапись
.*? была изъята из публичного доступа в связи с обращением правообладателя
.<':
367 r'>The video
.*? was removed
from public access by request of the copyright holder
.<':
370 r'<!>Please log
in or <':
371 'Video
%s is only available
for registered users
, '
372 'use
--username
and --password options to provide account credentials
.',
375 'Video
%s does
not exist
.',
377 r'<!>Видео временно недоступно
':
378 'Video
%s is temporarily unavailable
.',
381 'Access denied to video
%s.',
383 r'<!>Видеозапись недоступна
, так как её автор был заблокирован
.':
384 'Video
%s is no longer available
, because its author has been blocked
.',
386 r'<!>This video
is no longer available
, because its author has been blocked
.':
387 'Video
%s is no longer available
, because its author has been blocked
.',
389 r'<!>This video
is no longer available
, because it has been deleted
.':
390 'Video
%s is no longer available
, because it has been deleted
.',
392 r'<!>The video
.+?
is not available
in your region
.':
393 'Video
%s is not available
in your region
.',
396 for error_re, error_msg in ERRORS.items():
397 if re.search(error_re, info_page):
398 raise ExtractorError(error_msg % video_id, expected=True)
400 player = self._parse_json(self._search_regex(
401 r'var\s
+playerParams\s
*=\s
*({.+?}
)\s
*;\s
*\n',
402 info_page, 'player params
'), video_id)
404 youtube_url = YoutubeIE._extract_url(info_page)
406 return self.url_result(youtube_url, YoutubeIE.ie_key())
408 vimeo_url = VimeoIE._extract_url(url, info_page)
409 if vimeo_url is not None:
410 return self.url_result(vimeo_url, VimeoIE.ie_key())
412 pladform_url = PladformIE._extract_url(info_page)
414 return self.url_result(pladform_url, PladformIE.ie_key())
416 m_rutube = re.search(
417 r'\ssrc
="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
418 if m_rutube is not None:
419 rutube_url = self._proto_relative_url(
420 m_rutube.group(1).replace('\\', ''))
421 return self.url_result(rutube_url)
423 dailymotion_urls = DailymotionIE._extract_urls(info_page)
425 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
427 odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
428 if odnoklassniki_url:
429 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
431 sibnet_urls = self._extract_sibnet_urls(info_page)
433 return self.url_result(sibnet_urls[0])
435 m_opts = re.search(r'(?s
)var\s
+opts\s
*=\s
*({.+?}
);', info_page)
437 m_opts_url = re.search(r"url\s*:\s*'((?
!/\b)[^
']+)", m_opts.group(1))
439 opts_url = m_opts_url.group(1)
440 if opts_url.startswith('//'):
441 opts_url = 'http
:' + opts_url
442 return self.url_result(opts_url)
444 data = player['params
'][0]
445 title = unescapeHTML(data['md_title
'])
448 # 3 = post live (finished live)
449 is_live = data.get('live
') == 2
451 timestamp = unified_timestamp(self._html_search_regex(
452 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
453 'upload date', default=None)) or int_or_none(data.get('date'))
455 view_count = str_to_int(self._search_regex(
456 r'class=["\']mv_views_count
[^
>]+>\s
*([\d
,.]+)',
457 info_page, 'view count
', default=None))
460 for format_id, format_url in data.items():
461 format_url = url_or_none(format_url)
462 if not format_url or not format_url.startswith(('http
', '//', 'rtmp
')):
464 if (format_id.startswith(('url
', 'cache
'))
465 or format_id in ('extra_data
', 'live_mp4
', 'postlive_mp4
')):
466 height = int_or_none(self._search_regex(
467 r'^
(?
:url|cache
)(\d
+)', format_id, 'height
', default=None))
469 'format_id
': format_id,
473 elif format_id == 'hls
':
474 formats.extend(self._extract_m3u8_formats(
475 format_url, video_id, 'mp4
', 'm3u8_native
',
476 m3u8_id=format_id, fatal=False, live=is_live))
477 elif format_id == 'rtmp
':
479 'format_id
': format_id,
483 self._sort_formats(formats)
486 for sub in data.get('subs
') or {}:
487 subtitles.setdefault(sub.get('lang
', 'en
'), []).append({
488 'ext
': sub.get('title
', '.srt
').split('.')[-1],
489 'url
': url_or_none(sub.get('url
')),
496 'thumbnail
': data.get('jpg
'),
497 'uploader
': data.get('md_author
'),
498 'uploader_id
': str_or_none(data.get('author_id
') or mv_data.get('authorId
')),
499 'duration
': int_or_none(data.get('duration
') or mv_data.get('duration
')),
500 'timestamp
': timestamp,
501 'view_count
': view_count,
502 'like_count
': int_or_none(mv_data.get('likes
')),
503 'comment_count
': int_or_none(mv_data.get('commcount
')),
505 'subtitles
': subtitles,
509 class VKUserVideosIE(VKBaseIE):
510 IE_NAME = 'vk
:uservideos
'
511 IE_DESC = "VK - User's Videos
"
512 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/@(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
513 _TEMPLATE_URL = 'https://vk.com/videos'
515 'url': 'https://vk.com/video/@mobidevices',
517 'id': '-17892518_all',
519 'playlist_mincount': 1355,
521 'url': 'https://vk.com/video/@mobidevices?section=uploaded',
523 'id': '-17892518_uploaded',
525 'playlist_mincount': 182,
527 _VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
529 def _entries(self, page_id, section):
530 video_list_json = self._download_payload('al_video', page_id, {
531 'act': 'load_videos_silent',
536 count = video_list_json['count']
537 total = video_list_json['total']
538 video_list = video_list_json['list']
541 for video in video_list:
542 v = self._VIDEO._make(video[:2])
543 video_id = '%d_%d' % (v.owner_id, v.id)
544 yield self.url_result(
545 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id)
548 video_list_json = self._download_payload('al_video', page_id, {
549 'act': 'load_videos_silent',
554 count += video_list_json['count']
555 video_list = video_list_json['list']
557 def _real_extract(self, url):
558 u_id, section = self._match_valid_url(url).groups()
559 webpage = self._download_webpage(url, u_id)
560 page_id = self._search_regex(r'data-owner-id\s?=\s?"([^
"]+)"', webpage, 'page_id
')
564 return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section))
567 class VKWallPostIE(VKBaseIE):
568 IE_NAME = 'vk
:wallpost
'
569 _VALID_URL = r'https?
://(?
:(?
:(?
:(?
:m|new
)\
.)?vk\
.com
/(?
:[^?
]+\?.*\bw
=)?
wall(?P
<id>-?\d
+_\d
+)))'
571 # public page URL, audio playlist
572 'url
': 'https
://vk
.com
/bs
.official?w
=wall
-23538238_35',
574 'id': '-23538238_35',
575 'title
': 'Black Shadow
- Wall post
-23538238_35',
576 'description
': 'md5
:3f84b9c4f9ef499731cf1ced9998cc0c
',
579 'md5
': '5ba93864ec5b85f7ce19a9af4af080f6
',
581 'id': '135220665_111806521',
583 'title
': 'Black Shadow
- Слепое Верование
',
585 'uploader
': 'Black Shadow
',
586 'artist
': 'Black Shadow
',
587 'track
': 'Слепое Верование
',
590 'md5
': '4cc7e804579122b17ea95af7834c9233
',
592 'id': '135220665_111802303',
594 'title
': 'Black Shadow
- Война
- Негасимое Бездны Пламя
!',
596 'uploader
': 'Black Shadow
',
597 'artist
': 'Black Shadow
',
598 'track
': 'Война
- Негасимое Бездны Пламя
!',
602 'skip_download
': True,
605 'skip
': 'Requires vk account credentials
',
607 # single YouTube embed, no leading -
608 'url
': 'https
://vk
.com
/wall85155021_6319
',
610 'id': '85155021_6319',
611 'title
': 'Сергей Горбунов
- Wall post
85155021_6319',
617 'skip
': 'Requires vk account credentials
',
620 'url
': 'https
://vk
.com
/wall
-23538238_35',
621 'only_matching
': True,
623 # mobile wall page URL
624 'url
': 'https
://m
.vk
.com
/wall
-23538238_35',
625 'only_matching
': True,
627 _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789
+/='
628 _AUDIO = collections.namedtuple('Audio
', ['id', 'owner_id
', 'url
', 'title
', 'performer
', 'duration
', 'album_id
', 'unk
', 'author_link
', 'lyrics
', 'flags
', 'context
', 'extra
', 'hashes
', 'cover_url
', 'ads
'])
630 def _decode(self, enc):
634 r = self._BASE64_CHARS.index(c)
636 e = 64 * e + r if cond else r
639 dec += chr(255 & e >> (-2 * n & 6))
642 def _unmask_url(self, mask_url, vk_id):
643 if 'audio_api_unavailable
' in mask_url:
644 extra = mask_url.split('?extra
=')[1].split('#')
645 func
, base
= self
._decode
(extra
[1]).split(chr(11))
646 mask_url
= list(self
._decode
(extra
[0]))
647 url_len
= len(mask_url
)
648 indexes
= [None] * url_len
649 index
= int(base
) ^ vk_id
650 for n
in range(url_len
- 1, -1, -1):
651 index
= (url_len
* (n
+ 1) ^ index
+ n
) % url_len
653 for n
in range(1, url_len
):
655 index
= indexes
[url_len
- 1 - n
]
656 mask_url
[n
] = mask_url
[index
]
658 mask_url
= ''.join(mask_url
)
661 def _real_extract(self
, url
):
662 post_id
= self
._match
_id
(url
)
664 webpage
= self
._download
_payload
('wkview', post_id
, {
666 'w': 'wall' + post_id
,
669 description
= clean_html(get_element_by_class('wall_post_text', webpage
))
670 uploader
= clean_html(get_element_by_class('author', webpage
))
674 for audio
in re
.findall(r
'data-audio="([^"]+)', webpage
):
675 audio
= self
._parse
_json
(unescapeHTML(audio
), post_id
)
676 a
= self
._AUDIO
._make
(audio
[:16])
679 title
= unescapeHTML(a
.title
)
680 performer
= unescapeHTML(a
.performer
)
682 'id': '%s_%s' % (a
.owner_id
, a
.id),
683 'url': self
._unmask
_url
(a
.url
, a
.ads
['vk_id']),
684 'title': '%s - %s' % (performer
, title
) if performer
else title
,
685 'thumbnails': [{'url': c_url}
for c_url
in a
.cover_url
.split(',')] if a
.cover_url
else None,
686 'duration': int_or_none(a
.duration
),
687 'uploader': uploader
,
691 'protocol': 'm3u8_native',
694 for video
in re
.finditer(
695 r
'<a[^>]+href=(["\'])(?P
<url
>/video(?
:-?
[\d_
]+).*?
)\
1', webpage):
696 entries.append(self.url_result(
697 compat_urlparse.urljoin(url, video.group('url
')), VKIE.ie_key()))
699 title = 'Wall post
%s' % post_id
701 return self.playlist_result(
702 orderedSet(entries), post_id,
703 '%s - %s' % (uploader, title) if uploader else title,