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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class KeekIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<id>\w+)'
   8     IE_NAME = 'keek'
   9     _TEST = {
  10         'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
  11         'md5': '09c5c109067536c1cec8bac8c21fea05',
  12         'info_dict': {
  13             'id': 'NODfbab',
  14             'ext': 'mp4',
  15             'uploader': 'youtube-dl project',
  16             'uploader_id': 'ytdl',
  17             'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23
  24         video_url = 'http://cdn.keek.com/keek/video/%s' % video_id
  25         thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
  26         webpage = self._download_webpage(url, video_id)
  27
  28         raw_desc = self._html_search_meta('description', webpage)
  29         if raw_desc:
  30             uploader = self._html_search_regex(
  31                 r'Watch (.*?)\s+\(', raw_desc, 'uploader', fatal=False)
  32             uploader_id = self._html_search_regex(
  33                 r'Watch .*?\(@(.+?)\)', raw_desc, 'uploader_id', fatal=False)
  34         else:
  35             uploader = None
  36             uploader_id = None
  37
  38         return {
  39             'id': video_id,
  40             'url': video_url,
  41             'ext': 'mp4',
  42             'title': self._og_search_title(webpage),
  43             'thumbnail': thumbnail,
  44             'uploader': uploader,
  45             'uploader_id': uploader_id,
  46         }