yt_dlp/extractor/filmweb.py

   1 from .common import InfoExtractor
   2
   3
   4 class FilmwebIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?filmweb\.no/(?P<type>trailere|filmnytt)/article(?P<id>\d+)\.ece'
   6     _TEST = {
   7         'url': 'http://www.filmweb.no/trailere/article1264921.ece',
   8         'md5': 'e353f47df98e557d67edaceda9dece89',
   9         'info_dict': {
  10             'id': '13033574',
  11             'ext': 'mp4',
  12             'title': 'Det som en gang var',
  13             'upload_date': '20160316',
  14             'timestamp': 1458140101,
  15             'uploader_id': '12639966',
  16             'uploader': 'Live Roaldset',
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         article_type, article_id = self._match_valid_url(url).groups()
  22         if article_type == 'filmnytt':
  23             webpage = self._download_webpage(url, article_id)
  24             article_id = self._search_regex(r'data-videoid="(\d+)"', webpage, 'article id')
  25         embed_code = self._download_json(
  26             'https://www.filmweb.no/template_v2/ajax/json_trailerEmbed.jsp',
  27             article_id, query={
  28                 'articleId': article_id,
  29             })['embedCode']
  30         iframe_url = self._proto_relative_url(self._search_regex(
  31             r'<iframe[^>]+src="([^"]+)', embed_code, 'iframe url'))
  32
  33         return {
  34             '_type': 'url_transparent',
  35             'id': article_id,
  36             'url': iframe_url,
  37             'ie_key': 'TwentyThreeVideo',
  38         }