2 from __future__ import unicode_literals
7 from .common import InfoExtractor
11 compat_urllib_request,
22 class VKIE(InfoExtractor):
27 (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
29 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
30 (?:www\.)?biqle\.ru/watch/
32 (?P<videoid>[^s].*?)(?:\?|%2F|$)
39 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
40 'md5': '0deae91935c54e00003c2a00646315f0',
44 'title': 'ProtivoGunz - Хуёвая песня',
45 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
47 'upload_date': '20120212',
52 'url': 'http://vk.com/video205387401_165548505',
53 'md5': '6c0aeb2e90396ba97035b9cbde548700',
57 'uploader': 'Tom Cruise',
60 'upload_date': '20130721',
65 'note': 'Embedded video',
66 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
67 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
71 'uploader': 'Vladimir Gavrin',
74 'upload_date': '20120730',
80 # please update if you find a video whose URL follows the same pattern
81 'url': 'http://vk.com/video-8871596_164049491',
82 'md5': 'a590bcaf3d543576c9bd162812387666',
83 'note': 'Only available for registered users',
87 'uploader': 'Триллеры',
88 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
90 'upload_date': '20121218',
93 'skip': 'Requires vk account credentials',
96 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
97 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
101 'uploader': 'Киномания - лучшее из мира кино',
104 'upload_date': '20140328',
106 'skip': 'Requires vk account credentials',
109 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
110 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
111 'note': 'ivi.ru embed',
115 'title': 'Книга Илая',
117 'upload_date': '20140626',
120 'skip': 'Only works from Russia',
123 # removed video, just testing that we match the pattern
124 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
125 'only_matching': True,
129 'url': 'http://www.biqle.ru/watch/847655_160197695',
130 'only_matching': True,
135 (username, password) = self._get_login_info()
139 login_page = self._download_webpage(
140 'https://vk.com', None, 'Downloading login page')
142 login_form = dict(re.findall(
143 r'<input\s+type="hidden"\s+name="([^"]+)"\s+(?:id="[^"]+"\s+)?value="([^"]*)"',
147 'email': username.encode('cp1251'),
148 'pass': password.encode('cp1251'),
151 request = compat_urllib_request.Request(
152 'https://login.vk.com/?act=login',
153 compat_urllib_parse.urlencode(login_form).encode('utf-8'))
154 login_page = self._download_webpage(
155 request, None, note='Logging in as %s' % username)
157 if re.search(r'onLoginFailed', login_page):
158 raise ExtractorError(
159 'Unable to login, incorrect username and/or password', expected=True)
161 def _real_initialize(self):
164 def _real_extract(self, url):
165 mobj = re.match(self._VALID_URL, url)
166 video_id = mobj.group('videoid')
169 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
171 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
172 info_page = self._download_webpage(info_url, video_id)
174 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
175 raise ExtractorError(
176 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
180 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
181 'Video %s has been removed from public access due to rightholder complaint.',
183 r'<!>Please log in or <':
184 'Video %s is only available for registered users, '
185 'use --username and --password options to provide account credentials.',
188 'Video %s does not exist.',
190 r'<!>Видео временно недоступно':
191 'Video %s is temporarily unavailable.',
194 for error_re, error_msg in ERRORS.items():
195 if re.search(error_re, info_page):
196 raise ExtractorError(error_msg % video_id, expected=True)
198 youtube_url = self._search_regex(
199 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
200 info_page, 'youtube iframe', default=None)
202 return self.url_result(youtube_url, 'Youtube', video_id)
204 m_rutube = re.search(
205 r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
206 if m_rutube is not None:
207 self.to_screen('rutube video detected')
208 rutube_url = self._proto_relative_url(
209 m_rutube.group(1).replace('\\', ''))
210 return self.url_result(rutube_url)
212 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
214 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
216 opts_url = m_opts_url.group(1)
217 if opts_url.startswith('//'):
218 opts_url = 'http:' + opts_url
219 return self.url_result(opts_url)
221 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
222 data = json.loads(data_json)
224 # Extract upload date
226 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
228 mobj.group(1) + ' ' + mobj.group(2)
229 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
231 view_count = str_to_int(self._search_regex(
232 r'"mv_views_count_number"[^>]*>([\d,.]+) views<',
233 info_page, 'view count', fatal=False))
238 'width': int(k[len('url'):]),
239 } for k, v in data.items()
240 if k.startswith('url')]
241 self._sort_formats(formats)
244 'id': compat_str(data['vid']),
246 'title': unescapeHTML(data['md_title']),
247 'thumbnail': data.get('jpg'),
248 'uploader': data.get('md_author'),
249 'duration': data.get('duration'),
250 'upload_date': upload_date,
251 'view_count': view_count,
255 class VKUserVideosIE(InfoExtractor):
256 IE_NAME = 'vk.com:user-videos'
257 IE_DESC = 'vk.com:All of a user\'s videos'
258 _VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
259 _TEMPLATE_URL = 'https://vk.com/videos'
261 'url': 'http://vk.com/videos205387401',
265 'playlist_mincount': 4,
268 def _real_extract(self, url):
269 page_id = self._match_id(url)
270 page = self._download_webpage(url, page_id)
271 video_ids = orderedSet(
272 m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
275 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
276 for video_id in video_ids]
277 return self.playlist_result(url_entries, page_id)