X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvk.py;h=90557fa61d53f356dd430f698df028a842617e5d;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=c0292095bab55d792249fedd03a7d927a98763e5;hpb=a5839317aa5b41e7bc99ecae7405459bbcbff8a7;p=youtube-dl diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index c0292095b..90557fa61 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -8,19 +8,22 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, ) from ..utils import ( ExtractorError, orderedSet, + sanitized_Request, str_to_int, unescapeHTML, unified_strdate, ) +from .vimeo import VimeoIE +from .pladform import PladformIE class VKIE(InfoExtractor): - IE_NAME = 'vk.com' + IE_NAME = 'vk' + IE_DESC = 'VK' _VALID_URL = r'''(?x) https?:// (?: @@ -29,7 +32,7 @@ class VKIE(InfoExtractor): (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video| (?:www\.)?biqle\.ru/watch/ ) - (?P[^s].*?)(?:\?|%2F|$) + (?P[^s].*?)(?:\?(?:.*\blist=(?P[\da-f]+))?|%2F|$) ) ''' _NETRC_MACHINE = 'vk' @@ -119,6 +122,20 @@ class VKIE(InfoExtractor): }, 'skip': 'Only works from Russia', }, + { + # video (removed?) only available with list id + 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4', + 'md5': '091287af5402239a1051c37ec7b92913', + 'info_dict': { + 'id': '171201961', + 'ext': 'mp4', + 'title': 'ТюменцевВВ_09.07.2015', + 'uploader': 'Anton Ivanov', + 'duration': 109, + 'upload_date': '20150709', + 'view_count': int, + }, + }, { # youtube embed 'url': 'https://vk.com/video276849682_170681728', @@ -139,10 +156,20 @@ class VKIE(InfoExtractor): 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', 'only_matching': True, }, + { + # age restricted video, requires vk account credentials + 'url': 'https://vk.com/video205387401_164765225', + 'only_matching': True, + }, { # vk wrapper 'url': 'http://www.biqle.ru/watch/847655_160197695', 'only_matching': True, + }, + { + # pladform embed + 'url': 'https://vk.com/video-76116461_171554880', + 'only_matching': True, } ] @@ -154,14 +181,14 @@ class VKIE(InfoExtractor): login_page = self._download_webpage( 'https://vk.com', None, 'Downloading login page') - login_form = self._form_hidden_inputs(login_page) + login_form = self._hidden_inputs(login_page) login_form.update({ 'email': username.encode('cp1251'), 'pass': password.encode('cp1251'), }) - request = compat_urllib_request.Request( + request = sanitized_Request( 'https://login.vk.com/?act=login', compat_urllib_parse.urlencode(login_form).encode('utf-8')) login_page = self._download_webpage( @@ -182,8 +209,20 @@ class VKIE(InfoExtractor): video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id + + # Some videos (removed?) can only be downloaded with list id specified + list_id = mobj.group('list_id') + if list_id: + info_url += '&list=%s' % list_id + info_page = self._download_webpage(info_url, video_id) + error_message = self._html_search_regex( + r'(?s)]+class="video_layer_message"[^>]*>(.+?)', + info_page, 'error message', default=None) + if error_message: + raise ExtractorError(error_message, expected=True) + if re.search(r'/login\.php\?.*\bact=security_check', info_page): raise ExtractorError( 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', @@ -202,6 +241,9 @@ class VKIE(InfoExtractor): r'Видео временно недоступно': 'Video %s is temporarily unavailable.', + + r'Access denied': + 'Access denied to video %s.', } for error_re, error_msg in ERRORS.items(): @@ -214,10 +256,17 @@ class VKIE(InfoExtractor): if youtube_url: return self.url_result(youtube_url, 'Youtube') + vimeo_url = VimeoIE._extract_vimeo_url(url, info_page) + if vimeo_url is not None: + return self.url_result(vimeo_url) + + pladform_url = PladformIE._extract_url(info_page) + if pladform_url: + return self.url_result(pladform_url) + m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) if m_rutube is not None: - self.to_screen('rutube video detected') rutube_url = self._proto_relative_url( m_rutube.group(1).replace('\\', '')) return self.url_result(rutube_url) @@ -241,9 +290,13 @@ class VKIE(InfoExtractor): mobj.group(1) + ' ' + mobj.group(2) upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2)) - view_count = str_to_int(self._search_regex( - r'"mv_views_count_number"[^>]*>([\d,.]+) views<', - info_page, 'view count', fatal=False)) + view_count = None + views = self._html_search_regex( + r'"mv_views_count_number"[^>]*>(.+?\bviews?)<', + info_page, 'view count', fatal=False) + if views: + view_count = str_to_int(self._search_regex( + r'([\d,.]+)', views, 'view count', fatal=False)) formats = [{ 'format_id': k, @@ -266,25 +319,34 @@ class VKIE(InfoExtractor): class VKUserVideosIE(InfoExtractor): - IE_NAME = 'vk.com:user-videos' - IE_DESC = 'vk.com:All of a user\'s videos' - _VALID_URL = r'https?://vk\.com/videos(?P[0-9]+)(?:m\?.*)?' + IE_NAME = 'vk:uservideos' + IE_DESC = "VK - User's Videos" + _VALID_URL = r'https?://vk\.com/videos(?P-?[0-9]+)$' _TEMPLATE_URL = 'https://vk.com/videos' - _TEST = { + _TESTS = [{ 'url': 'http://vk.com/videos205387401', 'info_dict': { 'id': '205387401', + 'title': "Tom Cruise's Videos", }, 'playlist_mincount': 4, - } + }, { + 'url': 'http://vk.com/videos-77521', + 'only_matching': True, + }] def _real_extract(self, url): page_id = self._match_id(url) - page = self._download_webpage(url, page_id) - video_ids = orderedSet( - m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page)) - url_entries = [ + + webpage = self._download_webpage(url, page_id) + + entries = [ self.url_result( 'http://vk.com/video' + video_id, 'VK', video_id=video_id) - for video_id in video_ids] - return self.playlist_result(url_entries, page_id) + for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))] + + title = unescapeHTML(self._search_regex( + r'\s*([^<]+?)\s+\|\s+\d+\s+videos', + webpage, 'title', default=page_id)) + + return self.playlist_result(entries, page_id, title)