2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
26 from .vimeo import VimeoIE
27 from .pladform import PladformIE
30 class VKBaseIE(InfoExtractor):
34 (username, password) = self._get_login_info()
38 login_page, url_handle = self._download_webpage_handle(
39 'https://vk.com', None, 'Downloading login page')
41 login_form = self._hidden_inputs(login_page)
44 'email': username.encode('cp1251'),
45 'pass': password.encode('cp1251'),
48 # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
49 # and expects the first one to be set rather than second (see
50 # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
51 # As of RFC6265 the newer one cookie should be set into cookie store
52 # what actually happens.
53 # We will workaround this VK issue by resetting the remixlhk cookie to
54 # the first one manually.
55 for header, cookies in url_handle.headers.items():
56 if header.lower() != 'set-cookie':
58 if sys.version_info[0] >= 3:
59 cookies = cookies.encode('iso-8859-1')
60 cookies = cookies.decode('utf-8')
61 remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
63 value, domain = remixlhk.groups()
64 self._set_cookie(domain, 'remixlhk', value)
67 login_page = self._download_webpage(
68 'https://login.vk.com/?act=login', None,
69 note='Logging in as %s' % username,
70 data=urlencode_postdata(login_form))
72 if re.search(r'onLoginFailed', login_page):
74 'Unable to login, incorrect username and/or password', expected=True)
76 def _real_initialize(self):
87 (?:(?:m|new)\.)?vk\.com/video_|
90 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
92 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
93 (?:www\.)?daxab.com/embed/
95 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
100 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
101 'md5': '0deae91935c54e00003c2a00646315f0',
105 'title': 'ProtivoGunz - Хуёвая песня',
106 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
108 'upload_date': '20120212',
113 'url': 'http://vk.com/video205387401_165548505',
114 'md5': '6c0aeb2e90396ba97035b9cbde548700',
118 'uploader': 'Tom Cruise',
121 'upload_date': '20130721',
126 'note': 'Embedded video',
127 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
128 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
132 'uploader': 'Vladimir Gavrin',
135 'upload_date': '20120730',
138 'skip': 'This video has been removed from public access.',
142 # please update if you find a video whose URL follows the same pattern
143 'url': 'http://vk.com/video-8871596_164049491',
144 'md5': 'a590bcaf3d543576c9bd162812387666',
145 'note': 'Only available for registered users',
149 'uploader': 'Триллеры',
150 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
152 'upload_date': '20121218',
155 'skip': 'Requires vk account credentials',
158 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
159 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
163 'uploader': 'Киномания - лучшее из мира кино',
166 'upload_date': '20140328',
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',
177 'title': 'Книга Илая',
179 'upload_date': '20140626',
182 'skip': 'Only works from Russia',
185 # video (removed?) only available with list id
186 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
187 'md5': '091287af5402239a1051c37ec7b92913',
191 'title': 'ТюменцевВВ_09.07.2015',
192 'uploader': 'Anton Ivanov',
194 'upload_date': '20150709',
200 'url': 'https://vk.com/video276849682_170681728',
204 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
205 'description': 'md5:d9903938abdc74c738af77f527ca0596',
207 'upload_date': '20130116',
208 'uploader': "Children's Joy Foundation",
209 'uploader_id': 'thecjf',
214 # video key is extra_data not url\d+
215 'url': 'http://vk.com/video-110305615_171782105',
216 'md5': 'e13fcda136f99764872e739d13fac1d1',
220 'title': 'S-Dance, репетиции к The way show',
221 'uploader': 'THE WAY SHOW | 17 апреля',
222 'upload_date': '20160207',
227 # removed video, just testing that we match the pattern
228 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
229 'only_matching': True,
232 # age restricted video, requires vk account credentials
233 'url': 'https://vk.com/video205387401_164765225',
234 'only_matching': True,
238 'url': 'https://vk.com/video-76116461_171554880',
239 'only_matching': True,
242 'url': 'http://new.vk.com/video205387401_165548505',
243 'only_matching': True,
247 def _real_extract(self, url):
248 mobj = re.match(self._VALID_URL, url)
249 video_id = mobj.group('videoid')
252 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
253 # Some videos (removed?) can only be downloaded with list id specified
254 list_id = mobj.group('list_id')
256 info_url += '&list=%s' % list_id
258 info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
259 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
261 info_page = self._download_webpage(info_url, video_id)
263 error_message = self._html_search_regex(
264 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
265 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
266 info_page, 'error message', default=None)
268 raise ExtractorError(error_message, expected=True)
270 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
271 raise ExtractorError(
272 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
276 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
277 'Video %s has been removed from public access due to rightholder complaint.',
279 r'<!>Please log in or <':
280 'Video %s is only available for registered users, '
281 'use --username and --password options to provide account credentials.',
284 'Video %s does not exist.',
286 r'<!>Видео временно недоступно':
287 'Video %s is temporarily unavailable.',
290 'Access denied to video %s.',
293 for error_re, error_msg in ERRORS.items():
294 if re.search(error_re, info_page):
295 raise ExtractorError(error_msg % video_id, expected=True)
297 youtube_url = self._search_regex(
298 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
299 info_page, 'youtube iframe', default=None)
301 return self.url_result(youtube_url, 'Youtube')
303 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
304 if vimeo_url is not None:
305 return self.url_result(vimeo_url)
307 pladform_url = PladformIE._extract_url(info_page)
309 return self.url_result(pladform_url)
311 m_rutube = re.search(
312 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
313 if m_rutube is not None:
314 rutube_url = self._proto_relative_url(
315 m_rutube.group(1).replace('\\', ''))
316 return self.url_result(rutube_url)
318 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
320 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
322 opts_url = m_opts_url.group(1)
323 if opts_url.startswith('//'):
324 opts_url = 'http:' + opts_url
325 return self.url_result(opts_url)
327 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
328 data = json.loads(data_json)
330 # Extract upload date
332 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
334 mobj.group(1) + ' ' + mobj.group(2)
335 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
338 views = self._html_search_regex(
339 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
340 info_page, 'view count', default=None)
342 view_count = str_to_int(self._search_regex(
343 r'([\d,.]+)', views, 'view count', fatal=False))
346 for k, v in data.items():
347 if not k.startswith('url') and not k.startswith('cache') and k != 'extra_data' or not v:
349 height = int_or_none(self._search_regex(
350 r'^(?:url|cache)(\d+)', k, 'height', default=None))
356 self._sort_formats(formats)
359 'id': compat_str(data['vid']),
361 'title': unescapeHTML(data['md_title']),
362 'thumbnail': data.get('jpg'),
363 'uploader': data.get('md_author'),
364 'duration': data.get('duration'),
365 'upload_date': upload_date,
366 'view_count': view_count,
370 class VKUserVideosIE(VKBaseIE):
371 IE_NAME = 'vk:uservideos'
372 IE_DESC = "VK - User's Videos"
373 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
374 _TEMPLATE_URL = 'https://vk.com/videos'
376 'url': 'http://vk.com/videos205387401',
379 'title': "Tom Cruise's Videos",
381 'playlist_mincount': 4,
383 'url': 'http://vk.com/videos-77521',
384 'only_matching': True,
386 'url': 'http://vk.com/videos-97664626?section=all',
387 'only_matching': True,
389 'url': 'http://m.vk.com/videos205387401',
390 'only_matching': True,
392 'url': 'http://new.vk.com/videos205387401',
393 'only_matching': True,
396 def _real_extract(self, url):
397 page_id = self._match_id(url)
399 webpage = self._download_webpage(url, page_id)
403 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
404 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
406 title = unescapeHTML(self._search_regex(
407 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
408 webpage, 'title', default=page_id))
410 return self.playlist_result(entries, page_id, title)
413 class VKWallPostIE(VKBaseIE):
414 IE_NAME = 'vk:wallpost'
415 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
417 # public page URL, audio playlist
418 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
421 'title': 'Black Shadow - Wall post 23538238_35',
422 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
425 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
427 'id': '135220665_111806521',
429 'title': 'Black Shadow - Слепое Верование',
431 'uploader': 'Black Shadow',
432 'artist': 'Black Shadow',
433 'track': 'Слепое Верование',
436 'md5': '4cc7e804579122b17ea95af7834c9233',
438 'id': '135220665_111802303',
440 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
442 'uploader': 'Black Shadow',
443 'artist': 'Black Shadow',
444 'track': 'Война - Негасимое Бездны Пламя!',
447 'skip_download': True,
453 'skip': 'Requires vk account credentials',
455 # single YouTube embed, no leading -
456 'url': 'https://vk.com/wall85155021_6319',
458 'id': '85155021_6319',
459 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
465 'skip': 'Requires vk account credentials',
468 'url': 'https://vk.com/wall-23538238_35',
469 'only_matching': True,
471 # mobile wall page URL
472 'url': 'https://m.vk.com/wall-23538238_35',
473 'only_matching': True,
476 def _real_extract(self, url):
477 post_id = self._match_id(url)
479 wall_url = 'https://vk.com/wall%s' % post_id
481 post_id = remove_start(post_id, '-')
483 webpage = self._download_webpage(wall_url, post_id)
485 error = self._html_search_regex(
486 r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
487 webpage, 'error', default=None)
489 raise ExtractorError('VK said: %s' % error, expected=True)
491 description = clean_html(get_element_by_class('wall_post_text', webpage))
492 uploader = clean_html(get_element_by_class('author', webpage))
493 thumbnail = self._og_search_thumbnail(webpage)
497 audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
499 al_audio = self._download_webpage(
500 'https://vk.com/al_audio.php', post_id,
501 note='Downloading audio info', fatal=False,
502 data=urlencode_postdata({
503 'act': 'reload_audio',
505 'ids': ','.join(audio_ids)
508 Audio = collections.namedtuple(
509 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration'])
510 audios = self._parse_json(
512 r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'),
513 post_id, fatal=False, transform_source=unescapeHTML)
514 if isinstance(audios, list):
516 a = Audio._make(audio[:6])
518 'id': '%s_%s' % (a.user_id, a.id),
520 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
521 'thumbnail': thumbnail,
522 'duration': a.duration,
523 'uploader': uploader,
528 for video in re.finditer(
529 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
530 entries.append(self.url_result(
531 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
533 title = 'Wall post %s' % post_id
535 return self.playlist_result(
536 orderedSet(entries), post_id,
537 '%s - %s' % (uploader, title) if uploader else title,