yt_dlp/extractor/bild.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     unescapeHTML,
   5 )
   6
   7
   8 class BildIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
  10     IE_DESC = 'Bild.de'
  11     _TEST = {
  12         'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
  13         'md5': 'dd495cbd99f2413502a1713a1156ac8a',
  14         'info_dict': {
  15             'id': '38184146',
  16             'ext': 'mp4',
  17             'title': 'Das können die  neuen iPads',
  18             'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'duration': 196,
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26
  27         video_data = self._download_json(
  28             url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
  29
  30         return {
  31             'id': video_id,
  32             'title': unescapeHTML(video_data['title']).strip(),
  33             'description': unescapeHTML(video_data.get('description')),
  34             'url': video_data['clipList'][0]['srces'][0]['src'],
  35             'thumbnail': video_data.get('poster'),
  36             'duration': int_or_none(video_data.get('durationSec')),
  37         }