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

   1 from __future__ import unicode_literals
   2
   3 from .twentythreevideo import TwentyThreeVideoIE
   4
   5
   6 class FilmwebIE(TwentyThreeVideoIE):
   7     IE_NAME = 'Filmweb'
   8     _VALID_URL = r'https?://(?:www\.)?filmweb\.no/trailere/article(?P<id>\d+).ece'
   9     _TEST = {
  10         'url': 'http://www.filmweb.no/trailere/article1264921.ece',
  11         'md5': 'e353f47df98e557d67edaceda9dece89',
  12         'info_dict': {
  13             'id': '1264921',
  14             'title': 'Det som en gang var',
  15             'ext': 'mp4',
  16             'description': 'Trailer: Scener fra et vennskap',
  17         }
  18     }
  19
  20     _CLIENT_NAME = 'filmweb'
  21     _CLIENT_ID = '12732917'
  22     _EMBED_BASE_URL = 'http://www.filmweb.no/template/ajax/json_trailerEmbed.jsp?articleId=%s&autoplay=true'
  23
  24     def _real_extract(self, url):
  25         article_id = self._match_id(url)
  26         webpage = self._download_webpage(url, article_id)
  27
  28         title = self._search_regex(r'var\s+jsTitle\s*=\s*escape\("([^"]+)"\);',
  29             webpage, 'title', fatal=True)
  30
  31         format_url = self._proto_relative_url(
  32             self._html_search_regex(r'"(//filmweb\.23video\.com/[^"]+)"',
  33                 self._download_json(self._EMBED_BASE_URL % article_id,
  34                     article_id)['embedCode'], 'format url'))
  35
  36         formats = self._extract_formats(format_url, self._CLIENT_ID)
  37         self._sort_formats(formats)
  38
  39         return {
  40             'id': article_id,
  41             'title': title,
  42             'alt_title': self._og_search_title(webpage),
  43             'formats': formats,
  44             'description': self._og_search_description(webpage),
  45         }