youtube_dl/extractor/empflix.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8 )
   9
  10
  11 class EmpflixIE(InfoExtractor):
  12     _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
  13     _TEST = {
  14         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
  15         'md5': '5e5cc160f38ca9857f318eb97146e13e',
  16         'info_dict': {
  17             'id': '33051',
  18             'ext': 'flv',
  19             'title': 'Amateur Finger Fuck',
  20             'age_limit': 18,
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27
  28         webpage = self._download_webpage(url, video_id)
  29         age_limit = self._rta_search(webpage)
  30
  31         video_title = self._html_search_regex(
  32             r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
  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         video_url = cfg_xml.find('videoLink').text
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'ext': 'flv',
  46             'title': video_title,
  47             'age_limit': age_limit,
  48         }