2 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from ..compat import compat_str
20 from .vimeo import VimeoIE
21 from .pladform import PladformIE
24 class VKIE(InfoExtractor):
31 (?:m\.)?vk\.com/video_|
34 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
36 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
37 (?:www\.)?daxab.com/embed/
39 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
46 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
47 'md5': '0deae91935c54e00003c2a00646315f0',
51 'title': 'ProtivoGunz - Хуёвая песня',
52 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
54 'upload_date': '20120212',
59 'url': 'http://vk.com/video205387401_165548505',
60 'md5': '6c0aeb2e90396ba97035b9cbde548700',
64 'uploader': 'Tom Cruise',
67 'upload_date': '20130721',
72 'note': 'Embedded video',
73 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
74 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
78 'uploader': 'Vladimir Gavrin',
81 'upload_date': '20120730',
84 'skip': 'This video has been removed from public access.',
88 # please update if you find a video whose URL follows the same pattern
89 'url': 'http://vk.com/video-8871596_164049491',
90 'md5': 'a590bcaf3d543576c9bd162812387666',
91 'note': 'Only available for registered users',
95 'uploader': 'Триллеры',
96 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
98 'upload_date': '20121218',
101 'skip': 'Requires vk account credentials',
104 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
105 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
109 'uploader': 'Киномания - лучшее из мира кино',
112 'upload_date': '20140328',
114 'skip': 'Requires vk account credentials',
117 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
118 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
119 'note': 'ivi.ru embed',
123 'title': 'Книга Илая',
125 'upload_date': '20140626',
128 'skip': 'Only works from Russia',
131 # video (removed?) only available with list id
132 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
133 'md5': '091287af5402239a1051c37ec7b92913',
137 'title': 'ТюменцевВВ_09.07.2015',
138 'uploader': 'Anton Ivanov',
140 'upload_date': '20150709',
146 'url': 'https://vk.com/video276849682_170681728',
150 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
151 'description': 'md5:d9903938abdc74c738af77f527ca0596',
153 'upload_date': '20130116',
154 'uploader': "Children's Joy Foundation",
155 'uploader_id': 'thecjf',
160 # video key is extra_data not url\d+
161 'url': 'http://vk.com/video-110305615_171782105',
162 'md5': 'e13fcda136f99764872e739d13fac1d1',
166 'title': 'S-Dance, репетиции к The way show',
167 'uploader': 'THE WAY SHOW | 17 апреля',
168 'upload_date': '20160207',
173 # removed video, just testing that we match the pattern
174 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
175 'only_matching': True,
178 # age restricted video, requires vk account credentials
179 'url': 'https://vk.com/video205387401_164765225',
180 'only_matching': True,
184 'url': 'https://vk.com/video-76116461_171554880',
185 'only_matching': True,
190 (username, password) = self._get_login_info()
194 login_page, url_handle = self._download_webpage_handle(
195 'https://vk.com', None, 'Downloading login page')
197 login_form = self._hidden_inputs(login_page)
200 'email': username.encode('cp1251'),
201 'pass': password.encode('cp1251'),
204 # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
205 # and expects the first one to be set rather than second (see
206 # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
207 # As of RFC6265 the newer one cookie should be set into cookie store
208 # what actually happens.
209 # We will workaround this VK issue by resetting the remixlhk cookie to
210 # the first one manually.
211 cookies = url_handle.headers.get('Set-Cookie')
212 if sys.version_info[0] >= 3:
213 cookies = cookies.encode('iso-8859-1')
214 cookies = cookies.decode('utf-8')
215 remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
217 value, domain = remixlhk.groups()
218 self._set_cookie(domain, 'remixlhk', value)
220 login_page = self._download_webpage(
221 'https://login.vk.com/?act=login', None,
222 note='Logging in as %s' % username,
223 data=urlencode_postdata(login_form))
225 if re.search(r'onLoginFailed', login_page):
226 raise ExtractorError(
227 'Unable to login, incorrect username and/or password', expected=True)
229 def _real_initialize(self):
232 def _real_extract(self, url):
233 mobj = re.match(self._VALID_URL, url)
234 video_id = mobj.group('videoid')
237 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
238 # Some videos (removed?) can only be downloaded with list id specified
239 list_id = mobj.group('list_id')
241 info_url += '&list=%s' % list_id
243 info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
244 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
246 info_page = self._download_webpage(info_url, video_id)
248 error_message = self._html_search_regex(
249 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
250 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
251 info_page, 'error message', default=None)
253 raise ExtractorError(error_message, expected=True)
255 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
256 raise ExtractorError(
257 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
261 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
262 'Video %s has been removed from public access due to rightholder complaint.',
264 r'<!>Please log in or <':
265 'Video %s is only available for registered users, '
266 'use --username and --password options to provide account credentials.',
269 'Video %s does not exist.',
271 r'<!>Видео временно недоступно':
272 'Video %s is temporarily unavailable.',
275 'Access denied to video %s.',
278 for error_re, error_msg in ERRORS.items():
279 if re.search(error_re, info_page):
280 raise ExtractorError(error_msg % video_id, expected=True)
282 youtube_url = self._search_regex(
283 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
284 info_page, 'youtube iframe', default=None)
286 return self.url_result(youtube_url, 'Youtube')
288 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
289 if vimeo_url is not None:
290 return self.url_result(vimeo_url)
292 pladform_url = PladformIE._extract_url(info_page)
294 return self.url_result(pladform_url)
296 m_rutube = re.search(
297 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
298 if m_rutube is not None:
299 rutube_url = self._proto_relative_url(
300 m_rutube.group(1).replace('\\', ''))
301 return self.url_result(rutube_url)
303 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
305 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
307 opts_url = m_opts_url.group(1)
308 if opts_url.startswith('//'):
309 opts_url = 'http:' + opts_url
310 return self.url_result(opts_url)
312 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
313 data = json.loads(data_json)
315 # Extract upload date
317 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
319 mobj.group(1) + ' ' + mobj.group(2)
320 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
323 views = self._html_search_regex(
324 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
325 info_page, 'view count', default=None)
327 view_count = str_to_int(self._search_regex(
328 r'([\d,.]+)', views, 'view count', fatal=False))
331 for k, v in data.items():
332 if not k.startswith('url') and not k.startswith('cache') and k != 'extra_data' or not v:
334 height = int_or_none(self._search_regex(
335 r'^(?:url|cache)(\d+)', k, 'height', default=None))
341 self._sort_formats(formats)
344 'id': compat_str(data['vid']),
346 'title': unescapeHTML(data['md_title']),
347 'thumbnail': data.get('jpg'),
348 'uploader': data.get('md_author'),
349 'duration': data.get('duration'),
350 'upload_date': upload_date,
351 'view_count': view_count,
355 class VKUserVideosIE(InfoExtractor):
356 IE_NAME = 'vk:uservideos'
357 IE_DESC = "VK - User's Videos"
358 _VALID_URL = r'https?://vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
359 _TEMPLATE_URL = 'https://vk.com/videos'
361 'url': 'http://vk.com/videos205387401',
364 'title': "Tom Cruise's Videos",
366 'playlist_mincount': 4,
368 'url': 'http://vk.com/videos-77521',
369 'only_matching': True,
371 'url': 'http://vk.com/videos-97664626?section=all',
372 'only_matching': True,
375 def _real_extract(self, url):
376 page_id = self._match_id(url)
378 webpage = self._download_webpage(url, page_id)
382 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
383 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
385 title = unescapeHTML(self._search_regex(
386 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
387 webpage, 'title', default=page_id))
389 return self.playlist_result(entries, page_id, title)