yt_dlp/extractor/helsinki.py

   1 from .common import InfoExtractor
   2 from ..utils import js_to_json
   3
   4
   5 class HelsinkiIE(InfoExtractor):
   6     IE_DESC = 'helsinki.fi'
   7     _VALID_URL = r'https?://video\.helsinki\.fi/Arkisto/flash\.php\?id=(?P<id>\d+)'
   8     _TEST = {
   9         'url': 'http://video.helsinki.fi/Arkisto/flash.php?id=20258',
  10         'info_dict': {
  11             'id': '20258',
  12             'ext': 'mp4',
  13             'title': 'Tietotekniikkafoorumi-iltapäivä',
  14             'description': 'md5:f5c904224d43c133225130fe156a5ee0',
  15         },
  16         'params': {
  17             'skip_download': True,  # RTMP
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         params = self._parse_json(self._html_search_regex(
  26             r'(?s)jwplayer\("player"\).setup\((\{.*?\})\);',
  27             webpage, 'player code'), video_id, transform_source=js_to_json)
  28         formats = [{
  29             'url': s['file'],
  30             'ext': 'mp4',
  31         } for s in params['sources']]
  32
  33         return {
  34             'id': video_id,
  35             'title': self._og_search_title(webpage).replace('Video: ', ''),
  36             'description': self._og_search_description(webpage),
  37             'formats': formats,
  38         }