youtube_dl/extractor/empflix.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class EmpflixIE(InfoExtractor):
   9     _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
  10     _TEST = {
  11         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
  12         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
  13         'info_dict': {
  14             'id': '33051',
  15             'ext': 'mp4',
  16             'title': 'Amateur Finger Fuck',
  17             'description': 'Amateur solo finger fucking.',
  18             'age_limit': 18,
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27         age_limit = self._rta_search(webpage)
  28
  29         video_title = self._html_search_regex(
  30             r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
  31         video_description = self._html_search_regex(
  32             r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
  33
  34         cfg_url = self._html_search_regex(
  35             r'flashvars\.config = escape\("([^"]+)"',
  36             webpage, 'flashvars.config')
  37
  38         cfg_xml = self._download_xml(
  39             cfg_url, video_id, note='Downloading metadata')
  40
  41         formats = [
  42             {
  43                 'url': item.find('videoLink').text,
  44                 'format_id': item.find('res').text,
  45             } for item in cfg_xml.findall('./quality/item')
  46         ]
  47
  48         return {
  49             'id': video_id,
  50             'title': video_title,
  51             'description': video_description,
  52             'formats': formats,
  53             'age_limit': age_limit,
  54         }