2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
9 from ..compat
import compat_urlparse
24 from .dailymotion
import DailymotionIE
25 from .odnoklassniki
import OdnoklassnikiIE
26 from .pladform
import PladformIE
27 from .vimeo
import VimeoIE
28 from .youtube
import YoutubeIE
31 class VKBaseIE(InfoExtractor
):
35 username
, password
= self
._get
_login
_info
()
39 login_page
, url_handle
= self
._download
_webpage
_handle
(
40 'https://vk.com', None, 'Downloading login page')
42 login_form
= self
._hidden
_inputs
(login_page
)
45 'email': username
.encode('cp1251'),
46 'pass': password
.encode('cp1251'),
49 # vk serves two same remixlhk cookies in Set-Cookie header and expects
50 # first one to be actually set
51 self
._apply
_first
_set
_cookie
_header
(url_handle
, 'remixlhk')
53 login_page
= self
._download
_webpage
(
54 'https://vk.com/login', None,
56 data
=urlencode_postdata(login_form
))
58 if re
.search(r
'onLoginFailed', login_page
):
60 'Unable to login, incorrect username and/or password', expected
=True)
62 def _real_initialize(self
):
65 def _download_payload(self
, path
, video_id
, data
, fatal
=True):
67 code
, payload
= self
._download
_json
(
68 'https://vk.com/%s.php' % path
, video_id
,
69 data
=urlencode_postdata(data
), fatal
=fatal
,
70 headers
={'X-Requested-With': 'XMLHttpRequest'}
)['payload']
72 self
.raise_login_required()
74 raise ExtractorError(clean_html(payload
[0][1:-1]), expected
=True)
85 (?:(?:m|new)\.)?vk\.com/video_|
88 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
90 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
91 (?:www\.)?daxab.com/embed/
93 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
98 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
99 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
101 'id': '-77521_162222515',
103 'title': 'ProtivoGunz - Хуёвая песня',
104 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
105 'uploader_id': '-77521',
107 'timestamp': 1329049880,
108 'upload_date': '20120212',
112 'url': 'http://vk.com/video205387401_165548505',
114 'id': '205387401_165548505',
117 'uploader': 'Tom Cruise',
118 'uploader_id': '205387401',
120 'timestamp': 1374364108,
121 'upload_date': '20130720',
125 'note': 'Embedded video',
126 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
127 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
129 'id': '-77521_162222515',
131 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
132 'title': 'ProtivoGunz - Хуёвая песня',
134 'upload_date': '20120212',
135 'timestamp': 1329049880,
136 'uploader_id': '-77521',
141 # please update if you find a video whose URL follows the same pattern
142 'url': 'http://vk.com/video-8871596_164049491',
143 'md5': 'a590bcaf3d543576c9bd162812387666',
144 'note': 'Only available for registered users',
146 'id': '-8871596_164049491',
148 'uploader': 'Триллеры',
149 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
151 'upload_date': '20121218',
157 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
159 'id': '-43215063_168067957',
161 'uploader': 'Bro Mazter',
164 'upload_date': '20140328',
165 'uploader_id': '223413403',
166 'timestamp': 1396018030,
168 'skip': 'Requires vk account credentials',
171 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
172 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
173 'note': 'ivi.ru embed',
175 'id': '-43215063_169084319',
177 'title': 'Книга Илая',
179 'upload_date': '20140626',
185 'url': 'https://vk.com/video-93049196_456239755?list=ln-cBjJ7S4jYYx3ADnmDT',
187 'id': '-93049196_456239755',
189 'title': '8 серия (озвучка)',
191 'upload_date': '20211222',
196 # video (removed?) only available with list id
197 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
198 'md5': '091287af5402239a1051c37ec7b92913',
200 'id': '30481095_171201961',
202 'title': 'ТюменцевВВ_09.07.2015',
203 'uploader': 'Anton Ivanov',
205 'upload_date': '20150709',
212 'url': 'https://vk.com/video276849682_170681728',
216 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
217 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
219 'upload_date': '20130116',
220 'uploader': "Children's Joy Foundation Inc.",
221 'uploader_id': 'thecjf',
227 'url': 'https://vk.com/video-37468416_456239855',
229 'id': 'k3lz2cmXyRuJQSjGHUv',
231 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
232 'description': 'md5:424b8e88cc873217f520e582ba28bb36',
233 'uploader': 'AniLibria.Tv',
234 'upload_date': '20160914',
235 'uploader_id': 'x1p5vl5',
236 'timestamp': 1473877246,
239 'skip_download': True,
243 # video key is extra_data not url\d+
244 'url': 'http://vk.com/video-110305615_171782105',
245 'md5': 'e13fcda136f99764872e739d13fac1d1',
247 'id': '-110305615_171782105',
249 'title': 'S-Dance, репетиции к The way show',
250 'uploader': 'THE WAY SHOW | 17 апреля',
251 'uploader_id': '-110305615',
252 'timestamp': 1454859345,
253 'upload_date': '20160207',
256 'skip_download': True,
260 # finished live stream, postlive_mp4
261 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
263 'id': '-387766_456242764',
265 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
266 'uploader': 'Игромания',
268 # TODO: use act=show to extract view_count
270 'upload_date': '20160929',
271 'uploader_id': '-387766',
272 'timestamp': 1475137527,
275 'skip_download': True,
279 # live stream, hls and rtmp links, most likely already finished live
280 # stream by the time you are reading this comment
281 'url': 'https://vk.com/video-140332_456239111',
282 'only_matching': True,
285 # removed video, just testing that we match the pattern
286 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
287 'only_matching': True,
290 # age restricted video, requires vk account credentials
291 'url': 'https://vk.com/video205387401_164765225',
292 'only_matching': True,
296 'url': 'https://vk.com/video-76116461_171554880',
297 'only_matching': True,
300 'url': 'http://new.vk.com/video205387401_165548505',
301 'only_matching': True,
304 # This video is no longer available, because its author has been blocked.
305 'url': 'https://vk.com/video-10639516_456240611',
306 'only_matching': True,
309 # The video is not available in your region.
310 'url': 'https://vk.com/video-51812607_171445436',
311 'only_matching': True,
314 'url': 'https://vk.com/clip30014565_456240946',
315 'only_matching': True,
319 def _extract_sibnet_urls(webpage
):
320 # https://help.sibnet.ru/?sibnet_video_embed
321 return [unescapeHTML(mobj
.group('url')) for mobj
in re
.finditer(
322 r
'<iframe\b[^>]+\bsrc=(["\'])(?P
<url
>(?
:https?
:)?
//video\
.sibnet\
.ru
/shell\
.php
\?.*?
\bvideoid
=\d
+.*?
)\
1',
325 def _real_extract(self, url):
326 mobj = self._match_valid_url(url)
327 video_id = mobj.group('videoid
')
332 'act
': 'show_inline
',
335 # Some videos (removed?) can only be downloaded with list id specified
336 list_id = mobj.group('list_id
')
338 data['list'] = list_id
340 payload = self._download_payload('al_video
', video_id, data)
341 info_page = payload[1]
343 mv_data = opts.get('mvData
') or {}
344 player = opts.get('player
') or {}
346 video_id = '%s_%s' % (mobj.group('oid
'), mobj.group('id'))
348 info_page = self._download_webpage(
349 'http
://vk
.com
/video_ext
.php?
' + mobj.group('embed_query
'), video_id)
351 error_message = self._html_search_regex(
352 [r'(?s
)<!><div
[^
>]+class="video_layer_message"[^
>]*>(.+?
)</div
>',
353 r'(?s
)<div
[^
>]+id="video_ext_msg"[^
>]*>(.+?
)</div
>'],
354 info_page, 'error message
', default=None)
356 raise ExtractorError(error_message, expected=True)
358 if re.search(r'<!>/login\
.php
\?.*\bact
=security_check
', info_page):
359 raise ExtractorError(
360 'You are trying to log
in from an unusual location
. You should confirm ownership at vk
.com to log
in with this IP
.',
363 ERROR_COPYRIGHT = 'Video
%s has been removed
from public access due to rightholder complaint
.'
366 r'>Видеозапись
.*? была изъята из публичного доступа в связи с обращением правообладателя
.<':
369 r'>The video
.*? was removed
from public access by request of the copyright holder
.<':
372 r'<!>Please log
in or <':
373 'Video
%s is only available
for registered users
, '
374 'use
--username
and --password options to provide account credentials
.',
377 'Video
%s does
not exist
.',
379 r'<!>Видео временно недоступно
':
380 'Video
%s is temporarily unavailable
.',
383 'Access denied to video
%s.',
385 r'<!>Видеозапись недоступна
, так как её автор был заблокирован
.':
386 'Video
%s is no longer available
, because its author has been blocked
.',
388 r'<!>This video
is no longer available
, because its author has been blocked
.':
389 'Video
%s is no longer available
, because its author has been blocked
.',
391 r'<!>This video
is no longer available
, because it has been deleted
.':
392 'Video
%s is no longer available
, because it has been deleted
.',
394 r'<!>The video
.+?
is not available
in your region
.':
395 'Video
%s is not available
in your region
.',
398 for error_re, error_msg in ERRORS.items():
399 if re.search(error_re, info_page):
400 raise ExtractorError(error_msg % video_id, expected=True)
402 player = self._parse_json(self._search_regex(
403 r'var\s
+playerParams\s
*=\s
*({.+?}
)\s
*;\s
*\n',
404 info_page, 'player params
'), video_id)
406 youtube_url = YoutubeIE._extract_url(info_page)
408 return self.url_result(youtube_url, YoutubeIE.ie_key())
410 vimeo_url = VimeoIE._extract_url(url, info_page)
411 if vimeo_url is not None:
412 return self.url_result(vimeo_url, VimeoIE.ie_key())
414 pladform_url = PladformIE._extract_url(info_page)
416 return self.url_result(pladform_url, PladformIE.ie_key())
418 m_rutube = re.search(
419 r'\ssrc
="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
420 if m_rutube is not None:
421 rutube_url = self._proto_relative_url(
422 m_rutube.group(1).replace('\\', ''))
423 return self.url_result(rutube_url)
425 dailymotion_urls = DailymotionIE._extract_urls(info_page)
427 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
429 odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
430 if odnoklassniki_url:
431 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
433 sibnet_urls = self._extract_sibnet_urls(info_page)
435 return self.url_result(sibnet_urls[0])
437 m_opts = re.search(r'(?s
)var\s
+opts\s
*=\s
*({.+?}
);', info_page)
439 m_opts_url = re.search(r"url\s*:\s*'((?
!/\b)[^
']+)", m_opts.group(1))
441 opts_url = m_opts_url.group(1)
442 if opts_url.startswith('//'):
443 opts_url = 'http
:' + opts_url
444 return self.url_result(opts_url)
446 data = player['params
'][0]
447 title = unescapeHTML(data['md_title
'])
450 # 3 = post live (finished live)
451 is_live = data.get('live
') == 2
453 timestamp = unified_timestamp(self._html_search_regex(
454 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
455 'upload date', default=None)) or int_or_none(data.get('date'))
457 view_count = str_to_int(self._search_regex(
458 r'class=["\']mv_views_count
[^
>]+>\s
*([\d
,.]+)',
459 info_page, 'view count
', default=None))
462 for format_id, format_url in data.items():
463 format_url = url_or_none(format_url)
464 if not format_url or not format_url.startswith(('http
', '//', 'rtmp
')):
466 if (format_id.startswith(('url
', 'cache
'))
467 or format_id in ('extra_data
', 'live_mp4
', 'postlive_mp4
')):
468 height = int_or_none(self._search_regex(
469 r'^
(?
:url|cache
)(\d
+)', format_id, 'height
', default=None))
471 'format_id
': format_id,
475 elif format_id == 'hls
':
476 formats.extend(self._extract_m3u8_formats(
477 format_url, video_id, 'mp4
', 'm3u8_native
',
478 m3u8_id=format_id, fatal=False, live=is_live))
479 elif format_id == 'rtmp
':
481 'format_id
': format_id,
485 self._sort_formats(formats)
488 for sub in data.get('subs
') or {}:
489 subtitles.setdefault(sub.get('lang
', 'en
'), []).append({
490 'ext
': sub.get('title
', '.srt
').split('.')[-1],
491 'url
': url_or_none(sub.get('url
')),
498 'thumbnail
': data.get('jpg
'),
499 'uploader
': data.get('md_author
'),
500 'uploader_id
': str_or_none(data.get('author_id
') or mv_data.get('authorId
')),
501 'duration
': int_or_none(data.get('duration
') or mv_data.get('duration
')),
502 'timestamp
': timestamp,
503 'view_count
': view_count,
504 'like_count
': int_or_none(mv_data.get('likes
')),
505 'comment_count
': int_or_none(mv_data.get('commcount
')),
507 'subtitles
': subtitles,
511 class VKUserVideosIE(VKBaseIE):
512 IE_NAME = 'vk
:uservideos
'
513 IE_DESC = "VK - User's Videos
"
514 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
515 _TEMPLATE_URL = 'https://vk.com/videos'
517 'url': 'https://vk.com/videos-767561',
521 'playlist_mincount': 1150,
523 'url': 'https://vk.com/videos-767561?section=uploaded',
525 'id': '-767561_uploaded',
527 'playlist_mincount': 425,
529 'url': 'http://vk.com/videos205387401',
530 'only_matching': True,
532 'url': 'http://vk.com/videos-77521',
533 'only_matching': True,
535 'url': 'http://vk.com/videos-97664626?section=all',
536 'only_matching': True,
538 'url': 'http://m.vk.com/videos205387401',
539 'only_matching': True,
541 'url': 'http://new.vk.com/videos205387401',
542 'only_matching': True,
545 _VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
547 def _fetch_page(self, page_id, section, page):
548 l = self._download_payload('al_video', page_id, {
549 'act': 'load_videos_silent',
550 'offset': page * self._PAGE_SIZE,
553 })[0][section]['list']
556 v = self._VIDEO._make(video[:2])
557 video_id = '%d_%d' % (v.owner_id, v.id)
558 yield self.url_result(
559 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id)
561 def _real_extract(self, url):
562 page_id, section = self._match_valid_url(url).groups()
566 entries = OnDemandPagedList(
567 functools.partial(self._fetch_page, page_id, section),
570 return self.playlist_result(entries, '%s_%s' % (page_id, section))
573 class VKWallPostIE(VKBaseIE):
574 IE_NAME = 'vk:wallpost'
575 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
577 # public page URL, audio playlist
578 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
580 'id': '-23538238_35',
581 'title': 'Black Shadow - Wall post -23538238_35',
582 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
585 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
587 'id': '135220665_111806521',
589 'title': 'Black Shadow - Слепое Верование',
591 'uploader': 'Black Shadow',
592 'artist': 'Black Shadow',
593 'track': 'Слепое Верование',
596 'md5': '4cc7e804579122b17ea95af7834c9233',
598 'id': '135220665_111802303',
600 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
602 'uploader': 'Black Shadow',
603 'artist': 'Black Shadow',
604 'track': 'Война - Негасимое Бездны Пламя!',
608 'skip_download': True,
611 'skip': 'Requires vk account credentials',
613 # single YouTube embed, no leading -
614 'url': 'https://vk.com/wall85155021_6319',
616 'id': '85155021_6319',
617 'title': 'Сергей Горбунов - Wall post 85155021_6319',
623 'skip': 'Requires vk account credentials',
626 'url': 'https://vk.com/wall-23538238_35',
627 'only_matching': True,
629 # mobile wall page URL
630 'url': 'https://m.vk.com/wall-23538238_35',
631 'only_matching': True,
633 _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/='
634 _AUDIO = collections.namedtuple('Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads'])
636 def _decode(self, enc):
640 r = self._BASE64_CHARS.index(c)
642 e = 64 * e + r if cond else r
645 dec += chr(255 & e >> (-2 * n & 6))
648 def _unmask_url(self, mask_url, vk_id):
649 if 'audio_api_unavailable' in mask_url:
650 extra = mask_url.split('?extra=')[1].split('#')
651 func, base = self._decode(extra[1]).split(chr(11))
652 mask_url = list(self._decode(extra[0]))
653 url_len = len(mask_url)
654 indexes = [None] * url_len
655 index = int(base) ^ vk_id
656 for n in range(url_len - 1, -1, -1):
657 index = (url_len * (n + 1) ^ index + n) % url_len
659 for n in range(1, url_len):
661 index = indexes[url_len - 1 - n]
662 mask_url[n] = mask_url[index]
664 mask_url = ''.join(mask_url)
667 def _real_extract(self, url):
668 post_id = self._match_id(url)
670 webpage = self._download_payload('wkview', post_id, {
672 'w': 'wall' + post_id,
675 description = clean_html(get_element_by_class('wall_post_text', webpage))
676 uploader = clean_html(get_element_by_class('author', webpage))
680 for audio in re.findall(r'data-audio="([^
"]+)', webpage):
681 audio = self._parse_json(unescapeHTML(audio), post_id)
682 a = self._AUDIO._make(audio[:16])
685 title = unescapeHTML(a.title)
686 performer = unescapeHTML(a.performer)
688 'id': '%s_%s' % (a.owner_id, a.id),
689 'url': self._unmask_url(a.url, a.ads['vk_id']),
690 'title': '%s - %s' % (performer, title) if performer else title,
691 'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None,
692 'duration': int_or_none(a.duration),
693 'uploader': uploader,
700 for video in re.finditer(
701 r'<a[^>]+href=(["\'])(?P
<url
>/video(?
:-?
[\d_
]+).*?
)\
1', webpage):
702 entries.append(self.url_result(
703 compat_urlparse.urljoin(url, video.group('url
')), VKIE.ie_key()))
705 title = 'Wall post
%s' % post_id
707 return self.playlist_result(
708 orderedSet(entries), post_id,
709 '%s - %s' % (uploader, title) if uploader else title,