yt_dlp/extractor/elonet.py

   1 from .common import InfoExtractor
   2 from ..utils import determine_ext
   3
   4
   5 class ElonetIE(InfoExtractor):
   6     _VALID_URL = r'https?://elonet\.finna\.fi/Record/kavi\.elonet_elokuva_(?P<id>[0-9]+)'
   7     _TESTS = [{
   8         'url': 'https://elonet.finna.fi/Record/kavi.elonet_elokuva_107867',
   9         'info_dict': {
  10             'id': '107867',
  11             'ext': 'mp4',
  12             'title': 'Valkoinen peura',
  13             'thumbnail': r're:^https?://elonet\.finna\.fi/Cover/Show\?id=kavi\.elonet_elokuva_107867.+',
  14             'description': 'md5:bded4201c9677fab10854884fe8f7312',
  15         },
  16         'params': {'skip_download': 'dash'},
  17     }, {
  18         # DASH with subtitles
  19         'url': 'https://elonet.finna.fi/Record/kavi.elonet_elokuva_116539',
  20         'info_dict': {
  21             'id': '116539',
  22             'ext': 'mp4',
  23             'title': 'Minulla on tiikeri',
  24             'thumbnail': r're:^https?://elonet\.finna\.fi/Cover/Show\?id=kavi\.elonet_elokuva_116539.+',
  25             'description': 'md5:5ab72b3fe76d3414e46cc8f277104419',
  26         },
  27         'params': {'skip_download': 'dash'},
  28     }, {
  29         # Page with multiple videos, download the main one
  30         'url': 'https://elonet.finna.fi/Record/kavi.elonet_elokuva_117396',
  31         'info_dict': {
  32             'id': '117396',
  33             'ext': 'mp4',
  34             'title': 'Sampo',
  35             'thumbnail': r're:^https?://elonet\.finna\.fi/Cover/Show\?id=kavi\.elonet_elokuva_117396.+',
  36             'description': 'md5:ec69572a5b054d0ecafe8086b1fa96f7',
  37         },
  38         'params': {'skip_download': 'dash'},
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(url, video_id)
  44
  45         src = self._parse_json(self._html_search_regex(
  46             r'id=\'video-data\'[^>]+data-video-sources="([^"]+)"', webpage, 'json'), video_id)[0]['src']
  47         ext = determine_ext(src)
  48
  49         if ext == 'm3u8':
  50             formats, subtitles = self._extract_m3u8_formats_and_subtitles(src, video_id, fatal=False)
  51         elif ext == 'mpd':
  52             formats, subtitles = self._extract_mpd_formats_and_subtitles(src, video_id, fatal=False)
  53         else:
  54             formats, subtitles = [], {}
  55             self.raise_no_formats(f'Unknown streaming format {ext}')
  56
  57         return {
  58             'id': video_id,
  59             'title': self._og_search_title(webpage),
  60             'description': self._og_search_description(webpage),
  61             'thumbnail': self._og_search_thumbnail(webpage),
  62             'formats': formats,
  63             'subtitles': subtitles,
  64         }