yt_dlp/extractor/acast.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     clean_podcast_url,
   5     int_or_none,
   6     parse_iso8601,
   7 )
   8
   9
  10 class ACastBaseIE(InfoExtractor):
  11     def _extract_episode(self, episode, show_info):
  12         title = episode['title']
  13         info = {
  14             'id': episode['id'],
  15             'display_id': episode.get('episodeUrl'),
  16             'url': clean_podcast_url(episode['url']),
  17             'title': title,
  18             'description': clean_html(episode.get('description') or episode.get('summary')),
  19             'thumbnail': episode.get('image'),
  20             'timestamp': parse_iso8601(episode.get('publishDate')),
  21             'duration': int_or_none(episode.get('duration')),
  22             'filesize': int_or_none(episode.get('contentLength')),
  23             'season_number': int_or_none(episode.get('season')),
  24             'episode': title,
  25             'episode_number': int_or_none(episode.get('episode')),
  26         }
  27         info.update(show_info)
  28         return info
  29
  30     def _extract_show_info(self, show):
  31         return {
  32             'creator': show.get('author'),
  33             'series': show.get('title'),
  34         }
  35
  36     def _call_api(self, path, video_id, query=None):
  37         return self._download_json(
  38             'https://feeder.acast.com/api/v1/shows/' + path, video_id, query=query)
  39
  40
  41 class ACastIE(ACastBaseIE):
  42     IE_NAME = 'acast'
  43     _VALID_URL = r'''(?x:
  44                     https?://
  45                         (?:
  46                             (?:(?:embed|www)\.)?acast\.com/|
  47                             play\.acast\.com/s/
  48                         )
  49                         (?P<channel>[^/]+)/(?P<id>[^/#?"]+)
  50                     )'''
  51     _EMBED_REGEX = [rf'(?x)<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
  52     _TESTS = [{
  53         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  54         'info_dict': {
  55             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  56             'ext': 'mp3',
  57             'title': '2. Raggarmordet - Röster ur det förflutna',
  58             'description': 'md5:013959207e05011ad14a222cf22278cc',
  59             'timestamp': 1477346700,
  60             'upload_date': '20161024',
  61             'duration': 2766,
  62             'creator': 'Third Ear Studio',
  63             'series': 'Spår',
  64             'episode': '2. Raggarmordet - Röster ur det förflutna',
  65             'thumbnail': 'https://assets.pippa.io/shows/616ebe1886d7b1398620b943/616ebe33c7e6e70013cae7da.jpg',
  66             'episode_number': 2,
  67             'display_id': '2.raggarmordet-rosterurdetforflutna',
  68             'season_number': 4,
  69             'season': 'Season 4',
  70         },
  71     }, {
  72         'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
  73         'only_matching': True,
  74     }, {
  75         'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
  76         'only_matching': True,
  77     }, {
  78         'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
  79         'only_matching': True,
  80     }]
  81     _WEBPAGE_TESTS = [{
  82         'url': 'https://ausi.anu.edu.au/news/democracy-sausage-episode-can-labor-be-long-form-government',
  83         'info_dict': {
  84             'id': '646c68fb21fbf20011e9c651',
  85             'ext': 'mp3',
  86             'creator': 'The Australian National University',
  87             'display_id': 'can-labor-be-a-long-form-government',
  88             'duration': 2618,
  89             'thumbnail': 'https://assets.pippa.io/shows/6113e8578b4903809f16f7e5/1684821529295-515b9520db9ce53275b995eb302f941c.jpeg',
  90             'title': 'Can Labor be a long-form government?',
  91             'episode': 'Can Labor be a long-form government?',
  92             'upload_date': '20230523',
  93             'series': 'Democracy Sausage with Mark Kenny',
  94             'timestamp': 1684826362,
  95             'description': 'md5:feabe1fc5004c78ee59c84a46bf4ba16',
  96         },
  97     }]
  98
  99     def _real_extract(self, url):
 100         channel, display_id = self._match_valid_url(url).groups()
 101         episode = self._call_api(
 102             f'{channel}/episodes/{display_id}',
 103             display_id, {'showInfo': 'true'})
 104         return self._extract_episode(
 105             episode, self._extract_show_info(episode.get('show') or {}))
 106
 107
 108 class ACastChannelIE(ACastBaseIE):
 109     IE_NAME = 'acast:channel'
 110     _VALID_URL = r'''(?x)
 111                     https?://
 112                         (?:
 113                             (?:www\.)?acast\.com/|
 114                             play\.acast\.com/s/
 115                         )
 116                         (?P<id>[^/#?]+)
 117                     '''
 118     _TESTS = [{
 119         'url': 'https://www.acast.com/todayinfocus',
 120         'info_dict': {
 121             'id': '4efc5294-5385-4847-98bd-519799ce5786',
 122             'title': 'Today in Focus',
 123             'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
 124         },
 125         'playlist_mincount': 200,
 126     }, {
 127         'url': 'http://play.acast.com/s/ft-banking-weekly',
 128         'only_matching': True,
 129     }]
 130
 131     @classmethod
 132     def suitable(cls, url):
 133         return False if ACastIE.suitable(url) else super().suitable(url)
 134
 135     def _real_extract(self, url):
 136         show_slug = self._match_id(url)
 137         show = self._call_api(show_slug, show_slug)
 138         show_info = self._extract_show_info(show)
 139         entries = []
 140         for episode in (show.get('episodes') or []):
 141             entries.append(self._extract_episode(episode, show_info))
 142         return self.playlist_result(
 143             entries, show.get('id'), show.get('title'), show.get('description'))