import os import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, ) class MofosexIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pmofosex\.com/videos/(?P[0-9]+)/.*?\.html)' _TEST = { u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', u'file': u'5018.mp4', u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a', u'info_dict': { u"title": u"Japanese Teen Music Video", u"age_limit": 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) video_title = self._html_search_regex(r'

(.+?)<', webpage, u'title') video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url')) path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] format = "-".join(format) age_limit = self._rta_search(webpage) return { 'id': video_id, 'title': video_title, 'url': video_url, 'ext': extension, 'format': format, 'format_id': format, 'age_limit': age_limit, }