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/keek/(?P<id>\w+)'
  10     IE_NAME = 'keek'
  11     _TEST = {
  12         'url': 'https://www.keek.com/keek/NODfbab',
  13         'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
  14         'info_dict': {
  15             'id': 'NODfbab',
  16             'ext': 'mp4',
  17             'title': 'test chars: "\'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de . - Video - Videos on Keek',
  18             'description': 'test chars: "\'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
  19             'uploader': 'ytdl',
  20             'uploader_id': 'eGT5bab',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26
  27         webpage = self._download_webpage(url, video_id)
  28         uploader = uploader_id = None
  29         matches = re.search(r'data-username="(?P<uploader>[^"]+)"[^>]*data-user-id="(?P<uploader_id>[^"]+)"', webpage)
  30         if matches:
  31             uploader, uploader_id = matches.groups()
  32
  33         return {
  34             'id': video_id,
  35             'url': self._og_search_video_url(webpage),
  36             'ext': 'mp4',
  37             'title': self._og_search_title(webpage),
  38             'description': self._og_search_description(webpage),
  39             'thumbnail': self._og_search_thumbnail(webpage),
  40             'uploader': uploader,
  41             'uploader_id': uploader_id,
  42         }