_ 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     _TEST = {
  10         u'url': u'http://www.criterion.com/films/184-le-samourai',
  11         u'file': u'184.mp4',
  12         u'md5': u'bc51beba55685509883a9a7830919ec3',
  13         u'info_dict': {
  14             u"title": u"Le Samouraï",
  15             u"description" : u"In a career-defining performance, Alain Delon plays a contract killer with samurai instincts. A razor-sharp cocktail of 1940s American gangster cinema and 1960s French pop culture, maverick director Jean-Pierre Melville&#x27;s masterpiece _Le Samouraï_ defines cool. "
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         mobj = re.match(self._VALID_URL, url)
  21         video_id = mobj.group(1).split('-')[0]
  22         webpage = self._download_webpage(url, video_id)
  23
  24         final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
  25                                 webpage, 'video url')
  26         title = self._search_regex(r'<meta content="(.+?)" property="og:title" />',
  27                                 webpage, 'video title')
  28         description = self._search_regex(r'<meta name="description" content="(.+?)" />',
  29                                 webpage, 'video description')
  30         thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
  31                                 webpage, 'thumbnail url')
  32         ext = final_url.split('.')[-1]
  33
  34         return {'id': video_id,
  35                 'url' : final_url,
  36                 'title': title,
  37                 'ext': ext,
  38                 'description': description,
  39                 'thumbnail': thumbnail,
  40                 }