2 from __future__ import unicode_literals
8 from .common import InfoExtractor
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 cookies = url_handle.headers.get('Set-Cookie')
56 if sys.version_info[0] >= 3:
57 cookies = cookies.encode('iso-8859-1')
58 cookies = cookies.decode('utf-8')
59 remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
61 value, domain = remixlhk.groups()
62 self._set_cookie(domain, 'remixlhk', value)
64 login_page = self._download_webpage(
65 'https://login.vk.com/?act=login', None,
66 note='Logging in as %s' % username,
67 data=urlencode_postdata(login_form))
69 if re.search(r'onLoginFailed', login_page):
71 'Unable to login, incorrect username and/or password', expected=True)
73 def _real_initialize(self):
84 (?:(?:m|new)\.)?vk\.com/video_|
87 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
89 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
90 (?:www\.)?daxab.com/embed/
92 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
97 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
98 'md5': '0deae91935c54e00003c2a00646315f0',
102 'title': 'ProtivoGunz - Хуёвая песня',
103 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
105 'upload_date': '20120212',
110 'url': 'http://vk.com/video205387401_165548505',
111 'md5': '6c0aeb2e90396ba97035b9cbde548700',
115 'uploader': 'Tom Cruise',
118 'upload_date': '20130721',
123 'note': 'Embedded video',
124 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
125 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
129 'uploader': 'Vladimir Gavrin',
132 'upload_date': '20120730',
135 'skip': 'This video has been removed from public access.',
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',
146 'uploader': 'Триллеры',
147 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
149 'upload_date': '20121218',
152 'skip': 'Requires vk account credentials',
155 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
156 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
160 'uploader': 'Киномания - лучшее из мира кино',
163 'upload_date': '20140328',
165 'skip': 'Requires vk account credentials',
168 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
169 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
170 'note': 'ivi.ru embed',
174 'title': 'Книга Илая',
176 'upload_date': '20140626',
179 'skip': 'Only works from Russia',
182 # video (removed?) only available with list id
183 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
184 'md5': '091287af5402239a1051c37ec7b92913',
188 'title': 'ТюменцевВВ_09.07.2015',
189 'uploader': 'Anton Ivanov',
191 'upload_date': '20150709',
197 'url': 'https://vk.com/video276849682_170681728',
201 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
202 'description': 'md5:d9903938abdc74c738af77f527ca0596',
204 'upload_date': '20130116',
205 'uploader': "Children's Joy Foundation",
206 'uploader_id': 'thecjf',
211 # video key is extra_data not url\d+
212 'url': 'http://vk.com/video-110305615_171782105',
213 'md5': 'e13fcda136f99764872e739d13fac1d1',
217 'title': 'S-Dance, репетиции к The way show',
218 'uploader': 'THE WAY SHOW | 17 апреля',
219 'upload_date': '20160207',
224 # removed video, just testing that we match the pattern
225 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
226 'only_matching': True,
229 # age restricted video, requires vk account credentials
230 'url': 'https://vk.com/video205387401_164765225',
231 'only_matching': True,
235 'url': 'https://vk.com/video-76116461_171554880',
236 'only_matching': True,
239 'url': 'http://new.vk.com/video205387401_165548505',
240 'only_matching': True,
244 def _real_extract(self, url):
245 mobj = re.match(self._VALID_URL, url)
246 video_id = mobj.group('videoid')
249 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
250 # Some videos (removed?) can only be downloaded with list id specified
251 list_id = mobj.group('list_id')
253 info_url += '&list=%s' % list_id
255 info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
256 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
258 info_page = self._download_webpage(info_url, video_id)
260 error_message = self._html_search_regex(
261 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
262 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
263 info_page, 'error message', default=None)
265 raise ExtractorError(error_message, expected=True)
267 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
268 raise ExtractorError(
269 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
273 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
274 'Video %s has been removed from public access due to rightholder complaint.',
276 r'<!>Please log in or <':
277 'Video %s is only available for registered users, '
278 'use --username and --password options to provide account credentials.',
281 'Video %s does not exist.',
283 r'<!>Видео временно недоступно':
284 'Video %s is temporarily unavailable.',
287 'Access denied to video %s.',
290 for error_re, error_msg in ERRORS.items():
291 if re.search(error_re, info_page):
292 raise ExtractorError(error_msg % video_id, expected=True)
294 youtube_url = self._search_regex(
295 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
296 info_page, 'youtube iframe', default=None)
298 return self.url_result(youtube_url, 'Youtube')
300 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
301 if vimeo_url is not None:
302 return self.url_result(vimeo_url)
304 pladform_url = PladformIE._extract_url(info_page)
306 return self.url_result(pladform_url)
308 m_rutube = re.search(
309 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
310 if m_rutube is not None:
311 rutube_url = self._proto_relative_url(
312 m_rutube.group(1).replace('\\', ''))
313 return self.url_result(rutube_url)
315 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
317 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
319 opts_url = m_opts_url.group(1)
320 if opts_url.startswith('//'):
321 opts_url = 'http:' + opts_url
322 return self.url_result(opts_url)
324 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
325 data = json.loads(data_json)
327 # Extract upload date
329 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
331 mobj.group(1) + ' ' + mobj.group(2)
332 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
335 views = self._html_search_regex(
336 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
337 info_page, 'view count', default=None)
339 view_count = str_to_int(self._search_regex(
340 r'([\d,.]+)', views, 'view count', fatal=False))
343 for k, v in data.items():
344 if not k.startswith('url') and not k.startswith('cache') and k != 'extra_data' or not v:
346 height = int_or_none(self._search_regex(
347 r'^(?:url|cache)(\d+)', k, 'height', default=None))
353 self._sort_formats(formats)
356 'id': compat_str(data['vid']),
358 'title': unescapeHTML(data['md_title']),
359 'thumbnail': data.get('jpg'),
360 'uploader': data.get('md_author'),
361 'duration': data.get('duration'),
362 'upload_date': upload_date,
363 'view_count': view_count,
367 class VKUserVideosIE(VKBaseIE):
368 IE_NAME = 'vk:uservideos'
369 IE_DESC = "VK - User's Videos"
370 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
371 _TEMPLATE_URL = 'https://vk.com/videos'
373 'url': 'http://vk.com/videos205387401',
376 'title': "Tom Cruise's Videos",
378 'playlist_mincount': 4,
380 'url': 'http://vk.com/videos-77521',
381 'only_matching': True,
383 'url': 'http://vk.com/videos-97664626?section=all',
384 'only_matching': True,
386 'url': 'http://m.vk.com/videos205387401',
387 'only_matching': True,
389 'url': 'http://new.vk.com/videos205387401',
390 'only_matching': True,
393 def _real_extract(self, url):
394 page_id = self._match_id(url)
396 webpage = self._download_webpage(url, page_id)
400 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
401 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
403 title = unescapeHTML(self._search_regex(
404 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
405 webpage, 'title', default=page_id))
407 return self.playlist_result(entries, page_id, title)
410 class VKWallPostIE(VKBaseIE):
411 IE_NAME = 'vk:wallpost'
412 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
414 # public page URL, audio playlist
415 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
418 'title': 'Black Shadow - Wall post 23538238_35',
419 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
422 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
424 'id': '135220665_111806521',
426 'title': 'Black Shadow - Слепое Верование',
428 'uploader': 'Black Shadow',
429 'artist': 'Black Shadow',
430 'track': 'Слепое Верование',
433 'md5': '4cc7e804579122b17ea95af7834c9233',
435 'id': '135220665_111802303',
437 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
439 'uploader': 'Black Shadow',
440 'artist': 'Black Shadow',
441 'track': 'Война - Негасимое Бездны Пламя!',
444 'skip_download': True,
447 'skip': 'Requires vk account credentials',
449 # single YouTube embed, no leading -
450 'url': 'https://vk.com/wall85155021_6319',
452 'id': '85155021_6319',
453 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
456 'skip': 'Requires vk account credentials',
459 'url': 'https://vk.com/wall-23538238_35',
460 'only_matching': True,
462 # mobile wall page URL
463 'url': 'https://m.vk.com/wall-23538238_35',
464 'only_matching': True,
467 def _real_extract(self, url):
468 post_id = self._match_id(url)
470 wall_url = 'https://vk.com/wall%s' % post_id
472 post_id = remove_start(post_id, '-')
474 webpage = self._download_webpage(wall_url, post_id)
476 error = self._html_search_regex(
477 r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
478 webpage, 'error', default=None)
480 raise ExtractorError('VK said: %s' % error, expected=True)
482 description = clean_html(get_element_by_class('wall_post_text', webpage))
483 uploader = clean_html(get_element_by_class(
484 'fw_post_author', webpage)) or self._og_search_description(webpage)
485 thumbnail = self._og_search_thumbnail(webpage)
489 for audio in re.finditer(r'''(?sx)
491 id=(?P<q1>["\'])audio_info(?P<id>\d+_\d+).*?(?P=q1)[^>]+
492 value=(?P<q2>["\'])(?P<url>http.+?)(?P=q2)
494 </table>''', webpage):
495 audio_html = audio.group(0)
496 audio_id = audio.group('id')
497 duration = parse_duration(get_element_by_class('duration', audio_html))
498 track = self._html_search_regex(
499 r'<span[^>]+id=["\']title%s[^>]*>([^<]+)' % audio_id,
500 audio_html, 'title', default=None)
501 artist = self._html_search_regex(
502 r'>([^<]+)</a></b>\s*&ndash', audio_html,
503 'artist', default=None)
506 'url': audio.group('url'),
507 'title': '%s - %s' % (artist, track) if artist and track else audio_id,
508 'thumbnail': thumbnail,
509 'duration': duration,
510 'uploader': uploader,
515 for video in re.finditer(
516 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
517 entries.append(self.url_result(
518 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
520 title = 'Wall post %s' % post_id
522 return self.playlist_result(
523 orderedSet(entries), post_id,
524 '%s - %s' % (uploader, title) if uploader else title,