youtube_dl/extractor/mofosex.py

   1 import os
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urllib_parse_urlparse,
   7     compat_urllib_request,
   8     compat_urllib_parse,
   9 )
  10
  11 class MofosexIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
  13     _TEST = {
  14         u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
  15         u'file': u'5018.mp4',
  16         u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a',
  17         u'info_dict': {
  18             u"title": u"Japanese Teen Music Video",
  19             u"age_limit": 18,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('videoid')
  26         url = 'http://www.' + mobj.group('url')
  27
  28         req = compat_urllib_request.Request(url)
  29         req.add_header('Cookie', 'age_verified=1')
  30         webpage = self._download_webpage(req, video_id)
  31
  32         video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title')
  33         video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url'))
  34         path = compat_urllib_parse_urlparse(video_url).path
  35         extension = os.path.splitext(path)[1][1:]
  36         format = path.split('/')[5].split('_')[:2]
  37         format = "-".join(format)
  38
  39         age_limit = self._rta_search(webpage)
  40
  41         return {
  42             'id': video_id,
  43             'title': video_title,
  44             'url': video_url,
  45             'ext': extension,
  46             'format': format,
  47             'format_id': format,
  48             'age_limit': age_limit,
  49         }