2 from __future__ import unicode_literals
8 from .common import InfoExtractor
27 from .dailymotion import DailymotionIE
28 from .pladform import PladformIE
29 from .vimeo import VimeoIE
30 from .youtube import YoutubeIE
33 class VKBaseIE(InfoExtractor):
37 username, password = self._get_login_info()
41 login_page, url_handle = self._download_webpage_handle(
42 'https://vk.com', None, 'Downloading login page')
44 login_form = self._hidden_inputs(login_page)
47 'email': username.encode('cp1251'),
48 'pass': password.encode('cp1251'),
51 # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
52 # and expects the first one to be set rather than second (see
53 # https://github.com/ytdl-org/youtube-dl/issues/9841#issuecomment-227871201).
54 # As of RFC6265 the newer one cookie should be set into cookie store
55 # what actually happens.
56 # We will workaround this VK issue by resetting the remixlhk cookie to
57 # the first one manually.
58 for header, cookies in url_handle.headers.items():
59 if header.lower() != 'set-cookie':
61 if sys.version_info[0] >= 3:
62 cookies = cookies.encode('iso-8859-1')
63 cookies = cookies.decode('utf-8')
64 remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
66 value, domain = remixlhk.groups()
67 self._set_cookie(domain, 'remixlhk', value)
70 login_page = self._download_webpage(
71 'https://login.vk.com/?act=login', None,
73 data=urlencode_postdata(login_form))
75 if re.search(r'onLoginFailed', login_page):
77 'Unable to login, incorrect username and/or password', expected=True)
79 def _real_initialize(self):
90 (?:(?:m|new)\.)?vk\.com/video_|
93 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
95 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
96 (?:www\.)?daxab.com/embed/
98 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
103 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
104 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
106 'id': '-77521_162222515',
108 'title': 'ProtivoGunz - Хуёвая песня',
109 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
110 'uploader_id': '-77521',
112 'timestamp': 1329049880,
113 'upload_date': '20120212',
117 'url': 'http://vk.com/video205387401_165548505',
118 'md5': '6c0aeb2e90396ba97035b9cbde548700',
120 'id': '205387401_165548505',
123 'uploader': 'Tom Cruise',
124 'uploader_id': '205387401',
126 'timestamp': 1374364108,
127 'upload_date': '20130720',
131 'note': 'Embedded video',
132 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
133 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
135 'id': '32194266_162925554',
137 'uploader': 'Vladimir Gavrin',
140 'upload_date': '20120730',
143 'skip': 'This video has been removed from public access.',
147 # please update if you find a video whose URL follows the same pattern
148 'url': 'http://vk.com/video-8871596_164049491',
149 'md5': 'a590bcaf3d543576c9bd162812387666',
150 'note': 'Only available for registered users',
152 'id': '-8871596_164049491',
154 'uploader': 'Триллеры',
155 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
157 'upload_date': '20121218',
160 'skip': 'Requires vk account credentials',
163 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
164 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
166 'id': '-43215063_168067957',
168 'uploader': 'Киномания - лучшее из мира кино',
171 'upload_date': '20140328',
173 'skip': 'Requires vk account credentials',
176 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
177 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
178 'note': 'ivi.ru embed',
180 'id': '-43215063_169084319',
182 'title': 'Книга Илая',
184 'upload_date': '20140626',
187 'skip': 'Only works from Russia',
190 # video (removed?) only available with list id
191 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
192 'md5': '091287af5402239a1051c37ec7b92913',
194 'id': '30481095_171201961',
196 'title': 'ТюменцевВВ_09.07.2015',
197 'uploader': 'Anton Ivanov',
199 'upload_date': '20150709',
206 'url': 'https://vk.com/video276849682_170681728',
210 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
211 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
213 'upload_date': '20130116',
214 'uploader': "Children's Joy Foundation Inc.",
215 'uploader_id': 'thecjf',
221 'url': 'https://vk.com/video-37468416_456239855',
223 'id': 'k3lz2cmXyRuJQSjGHUv',
225 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
226 # TODO: fix test by fixing dailymotion description extraction
227 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
228 'uploader': 'AniLibria.Tv',
229 'upload_date': '20160914',
230 'uploader_id': 'x1p5vl5',
231 'timestamp': 1473877246,
234 'skip_download': True,
238 # video key is extra_data not url\d+
239 'url': 'http://vk.com/video-110305615_171782105',
240 'md5': 'e13fcda136f99764872e739d13fac1d1',
242 'id': '-110305615_171782105',
244 'title': 'S-Dance, репетиции к The way show',
245 'uploader': 'THE WAY SHOW | 17 апреля',
246 'uploader_id': '-110305615',
247 'timestamp': 1454859345,
248 'upload_date': '20160207',
251 'skip_download': True,
255 # finished live stream, postlive_mp4
256 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
258 'id': '-387766_456242764',
260 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
261 'uploader': 'Игромания',
263 # TODO: use act=show to extract view_count
265 'upload_date': '20160929',
266 'uploader_id': '-387766',
267 'timestamp': 1475137527,
271 # live stream, hls and rtmp links, most likely already finished live
272 # stream by the time you are reading this comment
273 'url': 'https://vk.com/video-140332_456239111',
274 'only_matching': True,
277 # removed video, just testing that we match the pattern
278 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
279 'only_matching': True,
282 # age restricted video, requires vk account credentials
283 'url': 'https://vk.com/video205387401_164765225',
284 'only_matching': True,
288 'url': 'https://vk.com/video-76116461_171554880',
289 'only_matching': True,
292 'url': 'http://new.vk.com/video205387401_165548505',
293 'only_matching': True,
296 # This video is no longer available, because its author has been blocked.
297 'url': 'https://vk.com/video-10639516_456240611',
298 'only_matching': True,
301 # The video is not available in your region.
302 'url': 'https://vk.com/video-51812607_171445436',
303 'only_matching': True,
306 def _real_extract(self, url):
307 mobj = re.match(self._VALID_URL, url)
308 video_id = mobj.group('videoid')
311 info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id
312 # Some videos (removed?) can only be downloaded with list id specified
313 list_id = mobj.group('list_id')
315 info_url += '&list=%s' % list_id
317 info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
318 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
320 info_page = self._download_webpage(info_url, video_id)
322 error_message = self._html_search_regex(
323 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
324 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
325 info_page, 'error message', default=None)
327 raise ExtractorError(error_message, expected=True)
329 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
330 raise ExtractorError(
331 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
334 ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
337 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
340 r'>The video .*? was removed from public access by request of the copyright holder.<':
343 r'<!>Please log in or <':
344 'Video %s is only available for registered users, '
345 'use --username and --password options to provide account credentials.',
348 'Video %s does not exist.',
350 r'<!>Видео временно недоступно':
351 'Video %s is temporarily unavailable.',
354 'Access denied to video %s.',
356 r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
357 'Video %s is no longer available, because its author has been blocked.',
359 r'<!>This video is no longer available, because its author has been blocked.':
360 'Video %s is no longer available, because its author has been blocked.',
362 r'<!>This video is no longer available, because it has been deleted.':
363 'Video %s is no longer available, because it has been deleted.',
365 r'<!>The video .+? is not available in your region.':
366 'Video %s is not available in your region.',
369 for error_re, error_msg in ERRORS.items():
370 if re.search(error_re, info_page):
371 raise ExtractorError(error_msg % video_id, expected=True)
373 youtube_url = YoutubeIE._extract_url(info_page)
375 return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
377 vimeo_url = VimeoIE._extract_url(url, info_page)
378 if vimeo_url is not None:
379 return self.url_result(vimeo_url)
381 pladform_url = PladformIE._extract_url(info_page)
383 return self.url_result(pladform_url)
385 m_rutube = re.search(
386 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
387 if m_rutube is not None:
388 rutube_url = self._proto_relative_url(
389 m_rutube.group(1).replace('\\', ''))
390 return self.url_result(rutube_url)
392 dailymotion_urls = DailymotionIE._extract_urls(info_page)
394 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
396 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
398 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
400 opts_url = m_opts_url.group(1)
401 if opts_url.startswith('//'):
402 opts_url = 'http:' + opts_url
403 return self.url_result(opts_url)
405 # vars does not look to be served anymore since 24.10.2016
406 data = self._parse_json(
408 r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'),
409 video_id, fatal=False)
411 # <!json> is served instead
413 data = self._parse_json(
415 [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'],
416 info_page, 'json', default='{}'),
419 data = data['player']['params'][0]
422 data = self._parse_json(
424 r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
426 video_id)['params'][0]
428 title = unescapeHTML(data['md_title'])
431 # 3 = post live (finished live)
432 is_live = data.get('live') == 2
434 title = self._live_title(title)
436 timestamp = unified_timestamp(self._html_search_regex(
437 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
438 'upload date', default=None)) or int_or_none(data.get('date'))
440 view_count = str_to_int(self._search_regex(
441 r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
442 info_page, 'view count', default=None))
445 for format_id, format_url in data.items():
446 format_url = url_or_none(format_url)
447 if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
449 if (format_id.startswith(('url', 'cache')) or
450 format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
451 height = int_or_none(self._search_regex(
452 r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
454 'format_id': format_id,
458 elif format_id == 'hls':
459 formats.extend(self._extract_m3u8_formats(
460 format_url, video_id, 'mp4', 'm3u8_native',
461 m3u8_id=format_id, fatal=False, live=is_live))
462 elif format_id == 'rtmp':
464 'format_id': format_id,
468 self._sort_formats(formats)
474 'thumbnail': data.get('jpg'),
475 'uploader': data.get('md_author'),
476 'uploader_id': str_or_none(data.get('author_id')),
477 'duration': data.get('duration'),
478 'timestamp': timestamp,
479 'view_count': view_count,
480 'like_count': int_or_none(data.get('liked')),
481 'dislike_count': int_or_none(data.get('nolikes')),
486 class VKUserVideosIE(VKBaseIE):
487 IE_NAME = 'vk:uservideos'
488 IE_DESC = "VK - User's Videos"
489 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
490 _TEMPLATE_URL = 'https://vk.com/videos'
492 'url': 'http://vk.com/videos205387401',
495 'title': "Tom Cruise's Videos",
497 'playlist_mincount': 4,
499 'url': 'http://vk.com/videos-77521',
500 'only_matching': True,
502 'url': 'http://vk.com/videos-97664626?section=all',
503 'only_matching': True,
505 'url': 'http://m.vk.com/videos205387401',
506 'only_matching': True,
508 'url': 'http://new.vk.com/videos205387401',
509 'only_matching': True,
512 def _real_extract(self, url):
513 page_id = self._match_id(url)
515 webpage = self._download_webpage(url, page_id)
519 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
520 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
522 title = unescapeHTML(self._search_regex(
523 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
524 webpage, 'title', default=page_id))
526 return self.playlist_result(entries, page_id, title)
529 class VKWallPostIE(VKBaseIE):
530 IE_NAME = 'vk:wallpost'
531 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
533 # public page URL, audio playlist
534 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
537 'title': 'Black Shadow - Wall post 23538238_35',
538 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
541 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
543 'id': '135220665_111806521',
545 'title': 'Black Shadow - Слепое Верование',
547 'uploader': 'Black Shadow',
548 'artist': 'Black Shadow',
549 'track': 'Слепое Верование',
552 'md5': '4cc7e804579122b17ea95af7834c9233',
554 'id': '135220665_111802303',
556 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
558 'uploader': 'Black Shadow',
559 'artist': 'Black Shadow',
560 'track': 'Война - Негасимое Бездны Пламя!',
563 'skip_download': True,
569 'skip': 'Requires vk account credentials',
571 # single YouTube embed, no leading -
572 'url': 'https://vk.com/wall85155021_6319',
574 'id': '85155021_6319',
575 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
581 'skip': 'Requires vk account credentials',
584 'url': 'https://vk.com/wall-23538238_35',
585 'only_matching': True,
587 # mobile wall page URL
588 'url': 'https://m.vk.com/wall-23538238_35',
589 'only_matching': True,
592 def _real_extract(self, url):
593 post_id = self._match_id(url)
595 wall_url = 'https://vk.com/wall%s' % post_id
597 post_id = remove_start(post_id, '-')
599 webpage = self._download_webpage(wall_url, post_id)
601 error = self._html_search_regex(
602 r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
603 webpage, 'error', default=None)
605 raise ExtractorError('VK said: %s' % error, expected=True)
607 description = clean_html(get_element_by_class('wall_post_text', webpage))
608 uploader = clean_html(get_element_by_class('author', webpage))
609 thumbnail = self._og_search_thumbnail(webpage)
613 audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
615 al_audio = self._download_webpage(
616 'https://vk.com/al_audio.php', post_id,
617 note='Downloading audio info', fatal=False,
618 data=urlencode_postdata({
619 'act': 'reload_audio',
621 'ids': ','.join(audio_ids)
624 Audio = collections.namedtuple(
625 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration'])
626 audios = self._parse_json(
628 r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'),
629 post_id, fatal=False, transform_source=unescapeHTML)
630 if isinstance(audios, list):
632 a = Audio._make(audio[:6])
634 'id': '%s_%s' % (a.user_id, a.id),
636 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
637 'thumbnail': thumbnail,
638 'duration': a.duration,
639 'uploader': uploader,
644 for video in re.finditer(
645 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
646 entries.append(self.url_result(
647 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
649 title = 'Wall post %s' % post_id
651 return self.playlist_result(
652 orderedSet(entries), post_id,
653 '%s - %s' % (uploader, title) if uploader else title,