_ Git - youtube-dl/blob - youtube_dl/extractor/keek.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class KeekIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P<id>\w+)'
  11     IE_NAME = 'keek'
  12     _TEST = {
  13         'url': 'https://www.keek.com/keek/NODfbab',
  14         'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
  15         'info_dict': {
  16             'id': 'NODfbab',
  17             'ext': 'mp4',
  18             'title': 'test chars: "\'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de . - Video - Videos on Keek',
  19             'description': 'md5:35d42050a3ece241d5ddd7fdcc6fd896',
  20             'uploader': 'ytdl',
  21             'uploader_id': 'eGT5bab',
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         webpage = self._download_webpage(url, video_id)
  29         uploader = uploader_id = None
  30         matches = re.search(r'data-username="(?P<uploader>[^"]+)"[^>]*data-user-id="(?P<uploader_id>[^"]+)"', webpage)
  31         if matches:
  32             uploader, uploader_id = matches.groups()
  33
  34         return {
  35             'id': video_id,
  36             'url': self._og_search_video_url(webpage),
  37             'ext': 'mp4',
  38             'title': self._og_search_title(webpage),
  39             'description': self._og_search_description(webpage),
  40             'thumbnail': self._og_search_thumbnail(webpage),
  41             'uploader': uploader,
  42             'uploader_id': uploader_id,
  43         }