_ Git - youtube-dl/blob - youtube_dl/extractor/criterion.py

   1 # -*- coding: utf-8 -*-
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7 class CriterionIE(InfoExtractor):
   8     _VALID_URL = r'http://www.criterion.com/films/(.*)'
   9
  10     def _real_extract(self, url):
  11         mobj = re.match(self._VALID_URL, url)
  12         video_id = mobj.group(1).split('-')[0]
  13         webpage = self._download_webpage(url, video_id)
  14
  15         final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
  16                                 webpage, 'video url')
  17         title = self._search_regex(r'<meta content="(.+?)" property="og:title" />',
  18                                 webpage, 'video title')
  19         description = self._search_regex(r'<meta name="description" content="(.+?)" />',
  20                                 webpage, 'video description')
  21         thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
  22                                 webpage, 'thumbnail url')
  23         ext = final_url.split('.')[-1]
  24
  25         return {'id': video_id,
  26                 'url' : final_url,
  27                 'title': title,
  28                 'ext': ext,
  29                 'description': description,
  30                 'thumbnail': thumbnail,
  31                 }