yt_dlp/extractor/rinsefm.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     MEDIA_EXTENSIONS,
   4     determine_ext,
   5     parse_iso8601,
   6     traverse_obj,
   7     url_or_none,
   8 )
   9
  10
  11 class RinseFMBaseIE(InfoExtractor):
  12     @staticmethod
  13     def _parse_entry(entry):
  14         return {
  15             **traverse_obj(entry, {
  16                 'id': ('id', {str}),
  17                 'title': ('title', {str}),
  18                 'url': ('fileUrl', {url_or_none}),
  19                 'release_timestamp': ('episodeDate', {parse_iso8601}),
  20                 'thumbnail': ('featuredImage', 0, 'filename', {str},
  21                               {lambda x: x and f'https://rinse.imgix.net/media/{x}'}),
  22                 'webpage_url': ('slug', {str},
  23                                 {lambda x: x and f'https://rinse.fm/episodes/{x}'}),
  24             }),
  25             'vcodec': 'none',
  26             'extractor_key': RinseFMIE.ie_key(),
  27             'extractor': RinseFMIE.IE_NAME,
  28         }
  29
  30
  31 class RinseFMIE(RinseFMBaseIE):
  32     _VALID_URL = r'https?://(?:www\.)?rinse\.fm/episodes/(?P<id>[^/?#]+)'
  33     _TESTS = [{
  34         'url': 'https://rinse.fm/episodes/club-glow-15-12-2023-2000/',
  35         'md5': '76ee0b719315617df42e15e710f46c7b',
  36         'info_dict': {
  37             'id': '1536535',
  38             'ext': 'mp3',
  39             'title': 'Club Glow - 15/12/2023 - 20:00',
  40             'thumbnail': r're:^https://.+\.(?:jpg|JPG)$',
  41             'release_timestamp': 1702598400,
  42             'release_date': '20231215',
  43         },
  44     }]
  45
  46     def _real_extract(self, url):
  47         display_id = self._match_id(url)
  48         webpage = self._download_webpage(url, display_id)
  49         entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
  50
  51         return self._parse_entry(entry)
  52
  53
  54 class RinseFMArtistPlaylistIE(RinseFMBaseIE):
  55     _VALID_URL = r'https?://(?:www\.)?rinse\.fm/shows/(?P<id>[^/?#]+)'
  56     _TESTS = [{
  57         'url': 'https://rinse.fm/shows/resources/',
  58         'info_dict': {
  59             'id': 'resources',
  60             'title': '[re]sources',
  61             'description': '[re]sources est un label parisien piloté par le DJ et producteur Tommy Kid.',
  62         },
  63         'playlist_mincount': 40,
  64     }, {
  65         'url': 'https://rinse.fm/shows/ivy/',
  66         'info_dict': {
  67             'id': 'ivy',
  68             'title': '[IVY]',
  69             'description': 'A dedicated space for DNB/Turbo House and 4x4.',
  70         },
  71         'playlist_mincount': 7,
  72     }]
  73
  74     def _entries(self, data):
  75         for episode in traverse_obj(data, (
  76             'props', 'pageProps', 'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
  77         ):
  78             yield self._parse_entry(episode)
  79
  80     def _real_extract(self, url):
  81         playlist_id = self._match_id(url)
  82         webpage = self._download_webpage(url, playlist_id)
  83         title = self._og_search_title(webpage) or self._html_search_meta('title', webpage)
  84         description = self._og_search_description(webpage) or self._html_search_meta(
  85             'description', webpage)
  86         data = self._search_nextjs_data(webpage, playlist_id)
  87
  88         return self.playlist_result(
  89             self._entries(data), playlist_id, title, description=description)