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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class DiggIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?digg\.com/video/(?P<id>[^/?#&]+)'
   8     _TEST = {
   9         'url': 'http://digg.com/video/sci-fi-short-jonah-daniel-kaluuya-get-out',
  10         'info_dict': {
  11             'id': 'LcqvmS0b',
  12             'ext': 'mp4',
  13             'title': "'Get Out' Star Daniel Kaluuya Goes On 'Moby Dick'-Like Journey In Sci-Fi Short 'Jonah'",
  14             'description': 'md5:541bb847648b6ee3d6514bc84b82efda',
  15             'upload_date': '20180109',
  16             'timestamp': 1515530551,
  17         },
  18         'params': {
  19             'skip_download': True,
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         display_id = self._match_id(url)
  25
  26         webpage = self._download_webpage(url, display_id)
  27
  28         jwplatform_id = self._search_regex(
  29             r'video_id\s*:\s*["\']([a-zA-Z0-9]{8})', webpage, 'jwplatform id',
  30             default=None)
  31
  32         if not jwplatform_id:
  33             return self.url_result(url, 'Generic')
  34
  35         return {
  36             '_type': 'url_transparent',
  37             'ie_key': 'JWPlatform',
  38             'url': 'jwplatform:%s' % jwplatform_id,
  39             'id': jwplatform_id,
  40             'display_id': display_id,
  41         }