2 from __future__ import unicode_literals
7 from .common import InfoExtractor
20 from .vimeo import VimeoIE
21 from .pladform import PladformIE
24 class VKIE(InfoExtractor):
30 (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
32 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
33 (?:www\.)?biqle\.ru/watch/
35 (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
42 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
43 'md5': '0deae91935c54e00003c2a00646315f0',
47 'title': 'ProtivoGunz - Хуёвая песня',
48 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
50 'upload_date': '20120212',
55 'url': 'http://vk.com/video205387401_165548505',
56 'md5': '6c0aeb2e90396ba97035b9cbde548700',
60 'uploader': 'Tom Cruise',
63 'upload_date': '20130721',
68 'note': 'Embedded video',
69 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
70 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
74 'uploader': 'Vladimir Gavrin',
77 'upload_date': '20120730',
83 # please update if you find a video whose URL follows the same pattern
84 'url': 'http://vk.com/video-8871596_164049491',
85 'md5': 'a590bcaf3d543576c9bd162812387666',
86 'note': 'Only available for registered users',
90 'uploader': 'Триллеры',
91 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
93 'upload_date': '20121218',
96 'skip': 'Requires vk account credentials',
99 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
100 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
104 'uploader': 'Киномания - лучшее из мира кино',
107 'upload_date': '20140328',
109 'skip': 'Requires vk account credentials',
112 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
113 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
114 'note': 'ivi.ru embed',
118 'title': 'Книга Илая',
120 'upload_date': '20140626',
123 'skip': 'Only works from Russia',
126 # video (removed?) only available with list id
127 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
128 'md5': '091287af5402239a1051c37ec7b92913',
132 'title': 'ТюменцевВВ_09.07.2015',
133 'uploader': 'Anton Ivanov',
135 'upload_date': '20150709',
141 'url': 'https://vk.com/video276849682_170681728',
145 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
146 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
148 'upload_date': '20130116',
149 'uploader': "Children's Joy Foundation",
150 'uploader_id': 'thecjf',
155 # removed video, just testing that we match the pattern
156 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
157 'only_matching': True,
160 # age restricted video, requires vk account credentials
161 'url': 'https://vk.com/video205387401_164765225',
162 'only_matching': True,
166 'url': 'http://www.biqle.ru/watch/847655_160197695',
167 'only_matching': True,
172 (username, password) = self._get_login_info()
176 login_page = self._download_webpage(
177 'https://vk.com', None, 'Downloading login page')
179 login_form = self._hidden_inputs(login_page)
182 'email': username.encode('cp1251'),
183 'pass': password.encode('cp1251'),
186 request = sanitized_Request(
187 'https://login.vk.com/?act=login',
188 compat_urllib_parse.urlencode(login_form).encode('utf-8'))
189 login_page = self._download_webpage(
190 request, None, note='Logging in as %s' % username)
192 if re.search(r'onLoginFailed', login_page):
193 raise ExtractorError(
194 'Unable to login, incorrect username and/or password', expected=True)
196 def _real_initialize(self):
199 def _real_extract(self, url):
200 mobj = re.match(self._VALID_URL, url)
201 video_id = mobj.group('videoid')
204 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
206 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
208 # Some videos (removed?) can only be downloaded with list id specified
209 list_id = mobj.group('list_id')
211 info_url += '&list=%s' % list_id
213 info_page = self._download_webpage(info_url, video_id)
215 error_message = self._html_search_regex(
216 r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
217 info_page, 'error message', default=None)
219 raise ExtractorError(error_message, expected=True)
221 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
222 raise ExtractorError(
223 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
227 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
228 'Video %s has been removed from public access due to rightholder complaint.',
230 r'<!>Please log in or <':
231 'Video %s is only available for registered users, '
232 'use --username and --password options to provide account credentials.',
235 'Video %s does not exist.',
237 r'<!>Видео временно недоступно':
238 'Video %s is temporarily unavailable.',
241 'Access denied to video %s.',
244 for error_re, error_msg in ERRORS.items():
245 if re.search(error_re, info_page):
246 raise ExtractorError(error_msg % video_id, expected=True)
248 youtube_url = self._search_regex(
249 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
250 info_page, 'youtube iframe', default=None)
252 return self.url_result(youtube_url, 'Youtube')
254 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
255 if vimeo_url is not None:
256 return self.url_result(vimeo_url)
258 pladform_url = PladformIE._extract_url(info_page)
260 return self.url_result(pladform_url)
262 m_rutube = re.search(
263 r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
264 if m_rutube is not None:
265 self.to_screen('rutube video detected')
266 rutube_url = self._proto_relative_url(
267 m_rutube.group(1).replace('\\', ''))
268 return self.url_result(rutube_url)
270 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
272 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
274 opts_url = m_opts_url.group(1)
275 if opts_url.startswith('//'):
276 opts_url = 'http:' + opts_url
277 return self.url_result(opts_url)
279 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
280 data = json.loads(data_json)
282 # Extract upload date
284 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
286 mobj.group(1) + ' ' + mobj.group(2)
287 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
290 views = self._html_search_regex(
291 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
292 info_page, 'view count', fatal=False)
294 view_count = str_to_int(self._search_regex(
295 r'([\d,.]+)', views, 'view count', fatal=False))
300 'width': int(k[len('url'):]),
301 } for k, v in data.items()
302 if k.startswith('url')]
303 self._sort_formats(formats)
306 'id': compat_str(data['vid']),
308 'title': unescapeHTML(data['md_title']),
309 'thumbnail': data.get('jpg'),
310 'uploader': data.get('md_author'),
311 'duration': data.get('duration'),
312 'upload_date': upload_date,
313 'view_count': view_count,
317 class VKUserVideosIE(InfoExtractor):
318 IE_NAME = 'vk:uservideos'
319 IE_DESC = "VK - User's Videos"
320 _VALID_URL = r'https?://vk\.com/videos(?P<id>-?[0-9]+)$'
321 _TEMPLATE_URL = 'https://vk.com/videos'
323 'url': 'http://vk.com/videos205387401',
326 'title': "Tom Cruise's Videos",
328 'playlist_mincount': 4,
330 'url': 'http://vk.com/videos-77521',
331 'only_matching': True,
334 def _real_extract(self, url):
335 page_id = self._match_id(url)
337 webpage = self._download_webpage(url, page_id)
341 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
342 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
344 title = unescapeHTML(self._search_regex(
345 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
346 webpage, 'title', default=page_id))
348 return self.playlist_result(entries, page_id, title)