yt_dlp/extractor/podchaser.py

   1 import functools
   2 import json
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     OnDemandPagedList,
   7     float_or_none,
   8     str_or_none,
   9     str_to_int,
  10     traverse_obj,
  11     unified_timestamp,
  12 )
  13
  14
  15 class PodchaserIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?podchaser\.com/podcasts/[\w-]+-(?P<podcast_id>\d+)(?:/episodes/[\w-]+-(?P<id>\d+))?'
  17     _PAGE_SIZE = 100
  18     _TESTS = [{
  19         'url': 'https://www.podchaser.com/podcasts/cum-town-36924/episodes/ep-285-freeze-me-off-104365585',
  20         'info_dict': {
  21             'id': '104365585',
  22             'title': 'Ep. 285 – freeze me off',
  23             'description': 'cam ahn',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'ext': 'mp3',
  26             'categories': ['Comedy'],
  27             'tags': ['comedy', 'dark humor'],
  28             'series': 'Cum Town',
  29             'duration': 3708,
  30             'timestamp': 1636531259,
  31             'upload_date': '20211110',
  32             'average_rating': 4.0
  33         }
  34     }, {
  35         'url': 'https://www.podchaser.com/podcasts/the-bone-zone-28853',
  36         'info_dict': {
  37             'id': '28853',
  38             'title': 'The Bone Zone',
  39             'description': 'Podcast by The Bone Zone',
  40         },
  41         'playlist_count': 275
  42     }, {
  43         'url': 'https://www.podchaser.com/podcasts/sean-carrolls-mindscape-scienc-699349/episodes',
  44         'info_dict': {
  45             'id': '699349',
  46             'title': 'Sean Carroll\'s Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas',
  47             'description': 'md5:2cbd8f4749891a84dc8235342e0b5ff1'
  48         },
  49         'playlist_mincount': 225
  50     }]
  51
  52     @staticmethod
  53     def _parse_episode(episode, podcast):
  54         return {
  55             'id': str(episode.get('id')),
  56             'title': episode.get('title'),
  57             'description': episode.get('description'),
  58             'url': episode.get('audio_url'),
  59             'thumbnail': episode.get('image_url'),
  60             'duration': str_to_int(episode.get('length')),
  61             'timestamp': unified_timestamp(episode.get('air_date')),
  62             'average_rating': float_or_none(episode.get('rating')),
  63             'categories': list(set(traverse_obj(podcast, (('summary', None), 'categories', ..., 'text')))),
  64             'tags': traverse_obj(podcast, ('tags', ..., 'text')),
  65             'series': podcast.get('title'),
  66         }
  67
  68     def _call_api(self, path, *args, **kwargs):
  69         return self._download_json(f'https://api.podchaser.com/{path}', *args, **kwargs)
  70
  71     def _fetch_page(self, podcast_id, podcast, page):
  72         json_response = self._call_api(
  73             'list/episode', podcast_id,
  74             headers={'Content-Type': 'application/json;charset=utf-8'},
  75             data=json.dumps({
  76                 'start': page * self._PAGE_SIZE,
  77                 'count': self._PAGE_SIZE,
  78                 'sort_order': 'SORT_ORDER_RECENT',
  79                 'filters': {
  80                     'podcast_id': podcast_id
  81                 },
  82                 'options': {}
  83             }).encode())
  84
  85         for episode in json_response['entities']:
  86             yield self._parse_episode(episode, podcast)
  87
  88     def _real_extract(self, url):
  89         podcast_id, episode_id = self._match_valid_url(url).group('podcast_id', 'id')
  90         podcast = self._call_api(f'podcasts/{podcast_id}', episode_id or podcast_id)
  91         if not episode_id:
  92             return self.playlist_result(
  93                 OnDemandPagedList(functools.partial(self._fetch_page, podcast_id, podcast), self._PAGE_SIZE),
  94                 str_or_none(podcast.get('id')), podcast.get('title'), podcast.get('description'))
  95
  96         episode = self._call_api(f'episodes/{episode_id}', episode_id)
  97         return self._parse_episode(episode, podcast)