# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( parse_iso8601, int_or_none, ) class TwentyFourVideoIE(InfoExtractor): IE_NAME = '24video' _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P\d+)' _TESTS = [ { 'url': 'http://www.24video.net/video/view/1044982', 'md5': '48dd7646775690a80447a8dca6a2df76', 'info_dict': { 'id': '1044982', 'ext': 'mp4', 'title': 'Эротика каменного века', 'description': 'Как смотрели порно в каменном веке.', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'SUPERTELO', 'duration': 31, 'timestamp': 1275937857, 'upload_date': '20100607', 'age_limit': 18, 'like_count': int, 'dislike_count': int, }, }, { 'url': 'http://www.24video.net/player/new24_play.swf?id=1044982', 'only_matching': True, } ] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage( 'http://www.24video.net/video/view/%s' % video_id, video_id) title = self._og_search_title(webpage) description = self._html_search_regex( r'([^<]+)', webpage, 'description', fatal=False) thumbnail = self._og_search_thumbnail(webpage) duration = int_or_none(self._og_search_property( 'duration', webpage, 'duration', fatal=False)) timestamp = parse_iso8601(self._search_regex( r'