youtube_dl/extractor/criterion.py

   1 # -*- coding: utf-8 -*-
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import determine_ext
   7
   8 class CriterionIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
  10     _TEST = {
  11         u'url': u'http://www.criterion.com/films/184-le-samourai',
  12         u'file': u'184.mp4',
  13         u'md5': u'bc51beba55685509883a9a7830919ec3',
  14         u'info_dict': {
  15             u"title": u"Le Samouraï",
  16             u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group(1)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
  26                                 webpage, 'video url')
  27         title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
  28                                 webpage, 'video title')
  29         description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
  30                                 webpage, 'video description')
  31         thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
  32                                 webpage, 'thumbnail url')
  33
  34         return {'id': video_id,
  35                 'url' : final_url,
  36                 'title': title,
  37                 'ext': determine_ext(final_url),
  38                 'description': description,
  39                 'thumbnail': thumbnail,
  40                 }