X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvk.py;h=3b3bec92fedd06fe4f61cea73d3e1e97c425e290;hb=ca97a56e4bd920971e02a55ee5d42fe83e25b4f9;hp=f13ba1c8e2a0b9a230cfd47da9e0998abc796eee;hpb=913f32929b36ec5d0f9685b7c80ac37855ebaf51;p=youtube-dl diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index f13ba1c8e..3b3bec92f 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -6,6 +6,9 @@ import json from .common import InfoExtractor from ..utils import ( + ExtractorError, + compat_urllib_request, + compat_urllib_parse, compat_str, unescapeHTML, ) @@ -13,32 +16,96 @@ from ..utils import ( class VKIE(InfoExtractor): IE_NAME = 'vk.com' - _VALID_URL = r'https?://vk\.com/(?:videos.*?\?.*?z=)?video(?P.*?)(?:\?|%2F|$)' - - _TESTS = [{ - 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521', - 'file': '162222515.flv', - 'md5': '0deae91935c54e00003c2a00646315f0', - 'info_dict': { - 'title': 'ProtivoGunz - Хуёвая песня', - 'uploader': 'Noize MC', + _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P\d+).*?\bid=(?P\d+)|(?:videos.*?\?.*?z=)?video(?P.*?)(?:\?|%2F|$))' + _NETRC_MACHINE = 'vk' + + _TESTS = [ + { + 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521', + 'md5': '0deae91935c54e00003c2a00646315f0', + 'info_dict': { + 'id': '162222515', + 'ext': 'flv', + 'title': 'ProtivoGunz - Хуёвая песня', + 'uploader': 'Noize MC', + 'duration': 195, + }, + }, + { + 'url': 'http://vk.com/video4643923_163339118', + 'md5': 'f79bccb5cd182b1f43502ca5685b2b36', + 'info_dict': { + 'id': '163339118', + 'ext': 'mp4', + 'uploader': 'Elvira Dzhonik', + 'title': 'Dream Theater - Hollow Years Live at Budokan 720*', + 'duration': 558, + } + }, + { + 'note': 'Embedded video', + 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1', + 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a', + 'info_dict': { + 'id': '162925554', + 'ext': 'mp4', + 'uploader': 'Vladimir Gavrin', + 'title': 'Lin Dan', + 'duration': 101, + } + }, + { + 'url': 'http://vk.com/video-8871596_164049491', + 'md5': 'a590bcaf3d543576c9bd162812387666', + 'note': 'Only available for registered users', + 'info_dict': { + 'id': '164049491', + 'ext': 'mp4', + 'uploader': 'Триллеры', + 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]\u00a0', + 'duration': 8352, + }, + 'skip': 'Requires vk account credentials', }, - }, - { - 'url': 'http://vk.com/video4643923_163339118', - 'file': '163339118.mp4', - 'md5': 'f79bccb5cd182b1f43502ca5685b2b36', - 'info_dict': { - 'uploader': 'Elvira Dzhonik', - 'title': 'Dream Theater - Hollow Years Live at Budokan 720*', + ] + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'act': 'login', + 'role': 'al_frame', + 'expire': '1', + 'email': username, + 'pass': password, } - }] + + request = compat_urllib_request.Request('https://login.vk.com/?act=login', + compat_urllib_parse.urlencode(login_form).encode('utf-8')) + login_page = self._download_webpage(request, None, note='Logging in as %s' % username) + + if re.search(r'onLoginFailed', login_page): + raise ExtractorError('Unable to login, incorrect username and/or password', expected=True) + + def _real_initialize(self): + self._login() def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.group('videoid') + + if not video_id: + video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) + info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id info_page = self._download_webpage(info_url, video_id) + + if re.search(r'Please log in or <', info_page): + raise ExtractorError('This video is only available for registered users, ' + 'use --username and --password options to provide account credentials.', expected=True) + m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page) if m_yt is not None: self.to_screen(u'Youtube video detected') @@ -60,4 +127,5 @@ class VKIE(InfoExtractor): 'title': unescapeHTML(data['md_title']), 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), + 'duration': data.get('duration') }