yt_dlp/extractor/googlepodcasts.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_podcast_url,
   6     int_or_none,
   7     try_get,
   8     urlencode_postdata,
   9 )
  10
  11
  12 class GooglePodcastsBaseIE(InfoExtractor):
  13     _VALID_URL_BASE = r'https?://podcasts\.google\.com/feed/'
  14
  15     def _batch_execute(self, func_id, video_id, params):
  16         return json.loads(self._download_json(
  17             'https://podcasts.google.com/_/PodcastsUi/data/batchexecute',
  18             video_id, data=urlencode_postdata({
  19                 'f.req': json.dumps([[[func_id, json.dumps(params), None, '1']]]),
  20             }), transform_source=lambda x: self._search_regex(r'(?s)(\[.+\])', x, 'data'))[0][2])
  21
  22     def _extract_episode(self, episode):
  23         return {
  24             'id': episode[4][3],
  25             'title': episode[8],
  26             'url': clean_podcast_url(episode[13]),
  27             'thumbnail': episode[2],
  28             'description': episode[9],
  29             'creator': try_get(episode, lambda x: x[14]),
  30             'timestamp': int_or_none(episode[11]),
  31             'duration': int_or_none(episode[12]),
  32             'series': episode[1],
  33         }
  34
  35
  36 class GooglePodcastsIE(GooglePodcastsBaseIE):
  37     IE_NAME = 'google:podcasts'
  38     _VALID_URL = GooglePodcastsBaseIE._VALID_URL_BASE + r'(?P<feed_url>[^/]+)/episode/(?P<id>[^/?&#]+)'
  39     _TEST = {
  40         'url': 'https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkcy5ucHIub3JnLzM0NDA5ODUzOS9wb2RjYXN0LnhtbA/episode/MzBlNWRlN2UtOWE4Yy00ODcwLTk2M2MtM2JlMmUyNmViOTRh',
  41         'md5': 'fa56b2ee8bd0703e27e42d4b104c4766',
  42         'info_dict': {
  43             'id': '30e5de7e-9a8c-4870-963c-3be2e26eb94a',
  44             'ext': 'mp3',
  45             'title': 'WWDTM New Year 2021',
  46             'description': 'We say goodbye to 2020 with Christine Baranksi, Doug Jones, Jonna Mendez, and Kellee Edwards.',
  47             'upload_date': '20210102',
  48             'timestamp': 1609606800,
  49             'duration': 2901,
  50             'series': "Wait Wait... Don't Tell Me!",
  51         },
  52     }
  53
  54     def _real_extract(self, url):
  55         b64_feed_url, b64_guid = self._match_valid_url(url).groups()
  56         episode = self._batch_execute(
  57             'oNjqVe', b64_guid, [b64_feed_url, b64_guid])[1]
  58         return self._extract_episode(episode)
  59
  60
  61 class GooglePodcastsFeedIE(GooglePodcastsBaseIE):
  62     IE_NAME = 'google:podcasts:feed'
  63     _VALID_URL = GooglePodcastsBaseIE._VALID_URL_BASE + r'(?P<id>[^/?&#]+)/?(?:[?#&]|$)'
  64     _TEST = {
  65         'url': 'https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkcy5ucHIub3JnLzM0NDA5ODUzOS9wb2RjYXN0LnhtbA',
  66         'info_dict': {
  67             'title': "Wait Wait... Don't Tell Me!",
  68             'description': "NPR's weekly current events quiz. Have a laugh and test your news knowledge while figuring out what's real and what we've made up.",
  69         },
  70         'playlist_mincount': 20,
  71     }
  72
  73     def _real_extract(self, url):
  74         b64_feed_url = self._match_id(url)
  75         data = self._batch_execute('ncqJEe', b64_feed_url, [b64_feed_url])
  76
  77         entries = []
  78         for episode in (try_get(data, lambda x: x[1][0]) or []):
  79             entries.append(self._extract_episode(episode))
  80
  81         feed = try_get(data, lambda x: x[3]) or []
  82         return self.playlist_result(
  83             entries, playlist_title=try_get(feed, lambda x: x[0]),
  84             playlist_description=try_get(feed, lambda x: x[2]))