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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class KeekIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
  10     IE_NAME = 'keek'
  11     _TEST = {
  12         'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
  13         'file': 'NODfbab.mp4',
  14         'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
  15         'info_dict': {
  16             'uploader': '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         m = re.match(self._VALID_URL, url)
  23         video_id = m.group('videoID')
  24
  25         video_url = 'http://cdn.keek.com/keek/video/%s' % video_id
  26         thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
  27         webpage = self._download_webpage(url, video_id)
  28
  29         uploader = self._html_search_regex(
  30             r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
  31             webpage, 'uploader', fatal=False)
  32
  33         return {
  34             'id': video_id,
  35             'url': video_url,
  36             'ext': 'mp4',
  37             'title': self._og_search_title(webpage),
  38             'thumbnail': thumbnail,
  39             'uploader': uploader
  40         }