yt_dlp/extractor/filmweb.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5
   6
   7 class FilmwebIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?filmweb\.no/(?P<type>trailere|filmnytt)/article(?P<id>\d+)\.ece'
   9     _TEST = {
  10         'url': 'http://www.filmweb.no/trailere/article1264921.ece',
  11         'md5': 'e353f47df98e557d67edaceda9dece89',
  12         'info_dict': {
  13             'id': '13033574',
  14             'ext': 'mp4',
  15             'title': 'Det som en gang var',
  16             'upload_date': '20160316',
  17             'timestamp': 1458140101,
  18             'uploader_id': '12639966',
  19             'uploader': 'Live Roaldset',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         article_type, article_id = self._match_valid_url(url).groups()
  25         if article_type == 'filmnytt':
  26             webpage = self._download_webpage(url, article_id)
  27             article_id = self._search_regex(r'data-videoid="(\d+)"', webpage, 'article id')
  28         embed_code = self._download_json(
  29             'https://www.filmweb.no/template_v2/ajax/json_trailerEmbed.jsp',
  30             article_id, query={
  31                 'articleId': article_id,
  32             })['embedCode']
  33         iframe_url = self._proto_relative_url(self._search_regex(
  34             r'<iframe[^>]+src="([^"]+)', embed_code, 'iframe url'))
  35
  36         return {
  37             '_type': 'url_transparent',
  38             'id': article_id,
  39             'url': iframe_url,
  40             'ie_key': 'TwentyThreeVideo',
  41         }