Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dump.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class DumpIE(InfoExtractor):
  10     _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/'
  11
  12     _TEST = {
  13         'url': 'http://www.dump.com/oneus/',
  14         'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99',
  15         'info_dict': {
  16             'id': 'oneus',
  17             'ext': 'flv',
  18             'title': "He's one of us.",
  19             'thumbnail': 're:^https?://.*\.jpg$',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         m = re.match(self._VALID_URL, url)
  25         video_id = m.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         video_url = self._search_regex(
  29             r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
  30
  31         thumb = self._og_search_thumbnail(webpage)
  32         title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
  33
  34         return {
  35             'id': video_id,
  36             'title': title,
  37             'url': video_url,
  38             'thumbnail': thumb,
  39         }