youtube_dl/extractor/criterion.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class CriterionIE(InfoExtractor):
  10     _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
  11     _TEST = {
  12         'url': 'http://www.criterion.com/films/184-le-samourai',
  13         'md5': 'bc51beba55685509883a9a7830919ec3',
  14         'info_dict': {
  15             'id': '184',
  16             'ext': 'mp4',
  17             'title': 'Le Samouraï',
  18             'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25         webpage = self._download_webpage(url, video_id)
  26
  27         final_url = self._search_regex(
  28             r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
  29         title = self._og_search_title(webpage)
  30         description = self._html_search_regex(
  31             r'<meta name="description" content="(.+?)" />',
  32             webpage, 'video description')
  33         thumbnail = self._search_regex(
  34             r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
  35             webpage, 'thumbnail url')
  36
  37         return {
  38             'id': video_id,
  39             'url': final_url,
  40             'title': title,
  41             'description': description,
  42             'thumbnail': thumbnail,
  43         }