Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mofosex.py

   1 from __future__ import unicode_literals
   2
   3 import os
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse_unquote,
   9     compat_urllib_parse_urlparse,
  10 )
  11 from ..utils import sanitized_Request
  12
  13
  14 class MofosexIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
  16     _TEST = {
  17         'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
  18         'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
  19         'info_dict': {
  20             'id': '5018',
  21             'ext': 'mp4',
  22             'title': 'Japanese Teen Music Video',
  23             'age_limit': 18,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30         url = 'http://www.' + mobj.group('url')
  31
  32         req = sanitized_Request(url)
  33         req.add_header('Cookie', 'age_verified=1')
  34         webpage = self._download_webpage(req, video_id)
  35
  36         video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
  37         video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
  38         path = compat_urllib_parse_urlparse(video_url).path
  39         extension = os.path.splitext(path)[1][1:]
  40         format = path.split('/')[5].split('_')[:2]
  41         format = '-'.join(format)
  42
  43         age_limit = self._rta_search(webpage)
  44
  45         return {
  46             'id': video_id,
  47             'title': video_title,
  48             'url': video_url,
  49             'ext': extension,
  50             'format': format,
  51             'format_id': format,
  52             'age_limit': age_limit,
  53         }