yt_dlp/extractor/yle_areena.py

   1 from .common import InfoExtractor
   2 from .kaltura import KalturaIE
   3 from ..utils import int_or_none, traverse_obj, url_or_none
   4
   5
   6 class YleAreenaIE(InfoExtractor):
   7     _VALID_URL = r'https?://areena\.yle\.fi/(?P<id>[\d-]+)'
   8     _TESTS = [{
   9         'url': 'https://areena.yle.fi/1-4371942',
  10         'md5': '932edda0ecf5dfd6423804182d32f8ac',
  11         'info_dict': {
  12             'id': '0_a3tjk92c',
  13             'ext': 'mp4',
  14             'title': 'Pouchit',
  15             'description': 'md5:d487309c3abbe5650265bbd1742d2f82',
  16             'series': 'Modernit miehet',
  17             'season': 'Season 1',
  18             'season_number': 1,
  19             'episode': 'Episode 2',
  20             'episode_number': 2,
  21             'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/0_a3tjk92c/version/100061',
  22             'uploader_id': 'ovp@yle.fi',
  23             'duration': 1435,
  24             'view_count': int,
  25             'upload_date': '20181204',
  26             'timestamp': 1543916210,
  27             'subtitles': {'fin': [{'url': r're:^https?://', 'ext': 'srt'}]},
  28             'age_limit': 7,
  29         }
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         info = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
  35         video_data = self._download_json(
  36             f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b',
  37             video_id)
  38
  39         # Example title: 'K1, J2: Pouchit | Modernit miehet'
  40         series, season_number, episode_number, episode = self._search_regex(
  41             r'K(?P<season_no>[\d]+),\s*J(?P<episode_no>[\d]+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
  42             info.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
  43             default=(None, None, None, None))
  44         description = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'description', 'fin'), expected_type=str)
  45
  46         subtitles = {}
  47         for sub in traverse_obj(video_data, ('data', 'ongoing_ondemand', 'subtitles', ...)):
  48             if url_or_none(sub.get('uri')):
  49                 subtitles.setdefault(sub.get('language') or 'und', []).append({
  50                     'url': sub['uri'],
  51                     'ext': 'srt',
  52                     'name': sub.get('kind'),
  53                 })
  54
  55         return {
  56             '_type': 'url_transparent',
  57             'url': 'kaltura:1955031:%s' % traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id')),
  58             'ie_key': KalturaIE.ie_key(),
  59             'title': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'title', 'fin'), expected_type=str)
  60                       or episode or info.get('title')),
  61             'description': description,
  62             'series': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'series', 'title', 'fin'), expected_type=str)
  63                        or series),
  64             'season_number': (int_or_none(self._search_regex(r'Kausi (\d+)', description, 'season number', default=None))
  65                               or int(season_number)),
  66             'episode_number': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'episode_number'), expected_type=int_or_none)
  67                                or int(episode_number)),
  68             'thumbnails': traverse_obj(info, ('thumbnails', ..., {'url': 'url'})),
  69             'age_limit': traverse_obj(video_data, ('data', 'ongoing_ondemand', 'content_rating', 'age_restriction'), expected_type=int_or_none),
  70             'subtitles': subtitles,
  71         }