yt_dlp/extractor/iheart.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     clean_podcast_url,
   5     int_or_none,
   6     str_or_none,
   7 )
   8
   9
  10 class IHeartRadioBaseIE(InfoExtractor):
  11     def _call_api(self, path, video_id, fatal=True, query=None):
  12         return self._download_json(
  13             'https://api.iheart.com/api/v3/podcast/' + path,
  14             video_id, fatal=fatal, query=query)
  15
  16     def _extract_episode(self, episode):
  17         return {
  18             'thumbnail': episode.get('imageUrl'),
  19             'description': clean_html(episode.get('description')),
  20             'timestamp': int_or_none(episode.get('startDate'), 1000),
  21             'duration': int_or_none(episode.get('duration')),
  22         }
  23
  24
  25 class IHeartRadioIE(IHeartRadioBaseIE):
  26     IE_NAME = 'iheartradio'
  27     _VALID_URL = r'(?:https?://(?:www\.)?iheart\.com/podcast/[^/]+/episode/(?P<display_id>[^/?&#]+)-|iheartradio:)(?P<id>\d+)'
  28     _TEST = {
  29         'url': 'https://www.iheart.com/podcast/105-behind-the-bastards-29236323/episode/part-one-alexander-lukashenko-the-dictator-70346499/?embed=true',
  30         'md5': 'c8609c92c8688dcb69d8541042b8abca',
  31         'info_dict': {
  32             'id': '70346499',
  33             'ext': 'mp3',
  34             'title': 'Part One: Alexander Lukashenko: The Dictator of Belarus',
  35             'description': 'md5:96cc7297b3a5a9ebae28643801c96fae',
  36             'timestamp': 1597741200,
  37             'upload_date': '20200818',
  38         },
  39     }
  40
  41     def _real_extract(self, url):
  42         episode_id = self._match_id(url)
  43         episode = self._call_api(
  44             'episodes/' + episode_id, episode_id)['episode']
  45         info = self._extract_episode(episode)
  46         info.update({
  47             'id': episode_id,
  48             'title': episode['title'],
  49             'url': clean_podcast_url(episode['mediaUrl']),
  50         })
  51         return info
  52
  53
  54 class IHeartRadioPodcastIE(IHeartRadioBaseIE):
  55     IE_NAME = 'iheartradio:podcast'
  56     _VALID_URL = r'https?://(?:www\.)?iheart(?:podcastnetwork)?\.com/podcast/[^/?&#]+-(?P<id>\d+)/?(?:[?#&]|$)'
  57     _TESTS = [{
  58         'url': 'https://www.iheart.com/podcast/1119-it-could-happen-here-30717896/',
  59         'info_dict': {
  60             'id': '30717896',
  61             'title': 'It Could Happen Here',
  62             'description': 'md5:5842117412a967eb0b01f8088eb663e2',
  63         },
  64         'playlist_mincount': 11,
  65     }, {
  66         'url': 'https://www.iheartpodcastnetwork.com/podcast/105-stuff-you-should-know-26940277',
  67         'only_matching': True,
  68     }]
  69
  70     def _real_extract(self, url):
  71         podcast_id = self._match_id(url)
  72         path = 'podcasts/' + podcast_id
  73         episodes = self._call_api(
  74             path + '/episodes', podcast_id, query={'limit': 1000000000})['data']
  75
  76         entries = []
  77         for episode in episodes:
  78             episode_id = str_or_none(episode.get('id'))
  79             if not episode_id:
  80                 continue
  81             info = self._extract_episode(episode)
  82             info.update({
  83                 '_type': 'url',
  84                 'id': episode_id,
  85                 'title': episode.get('title'),
  86                 'url': 'iheartradio:' + episode_id,
  87                 'ie_key': IHeartRadioIE.ie_key(),
  88             })
  89             entries.append(info)
  90
  91         podcast = self._call_api(path, podcast_id, False) or {}
  92
  93         return self.playlist_result(
  94             entries, podcast_id, podcast.get('title'), podcast.get('description'))