[ie/RinseFMArtistPlaylist] Add extractor (#8794)

Authored by: SirElderling

yt_dlp/extractor/_extractors.py

@@ -1604,7 +1604,10 @@ from .restudy import RestudyIE
 from .reuters import ReutersIE
 from .reverbnation import ReverbNationIE
 from .rheinmaintv import RheinMainTVIE
-from .rinsefm import RinseFMIE
+from .rinsefm import (
+    RinseFMIE,
+    RinseFMArtistPlaylistIE,
+)
 from .rmcdecouverte import RMCDecouverteIE
 from .rockstargames import RockstarGamesIE
 from .rokfin import (

yt_dlp/extractor/rinsefm.py

@@ -1,8 +1,34 @@
 from .common import InfoExtractor
-from ..utils import format_field, parse_iso8601
+from ..utils import (
+    MEDIA_EXTENSIONS,
+    determine_ext,
+    parse_iso8601,
+    traverse_obj,
+    url_or_none,
+)
 
 
-class RinseFMIE(InfoExtractor):
+class RinseFMBaseIE(InfoExtractor):
+    @staticmethod
+    def _parse_entry(entry):
+        return {
+            **traverse_obj(entry, {
+                'id': ('id', {str}),
+                'title': ('title', {str}),
+                'url': ('fileUrl', {url_or_none}),
+                'release_timestamp': ('episodeDate', {parse_iso8601}),
+                'thumbnail': ('featuredImage', 0, 'filename', {str},
+                              {lambda x: x and f'https://rinse.imgix.net/media/{x}'}),
+                'webpage_url': ('slug', {str},
+                                {lambda x: x and f'https://rinse.fm/episodes/{x}'}),
+            }),
+            'vcodec': 'none',
+            'extractor_key': RinseFMIE.ie_key(),
+            'extractor': RinseFMIE.IE_NAME,
+        }
+
+
+class RinseFMIE(RinseFMBaseIE):
     _VALID_URL = r'https?://(?:www\.)?rinse\.fm/episodes/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://rinse.fm/episodes/club-glow-15-12-2023-2000/',
@@ -22,12 +48,42 @@ class RinseFMIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
         entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
 
-        return {
-            'id': entry['id'],
-            'title': entry.get('title'),
-            'url': entry['fileUrl'],
-            'vcodec': 'none',
-            'release_timestamp': parse_iso8601(entry.get('episodeDate')),
-            'thumbnail': format_field(
-                entry, [('featuredImage', 0, 'filename')], 'https://rinse.imgix.net/media/%s', default=None),
-        }
+        return self._parse_entry(entry)
+
+
+class RinseFMArtistPlaylistIE(RinseFMBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?rinse\.fm/shows/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://rinse.fm/shows/resources/',
+        'info_dict': {
+            'id': 'resources',
+            'title': '[re]sources',
+            'description': '[re]sources est un label parisien piloté par le DJ et producteur Tommy Kid.'
+        },
+        'playlist_mincount': 40
+    }, {
+        'url': 'https://rinse.fm/shows/ivy/',
+        'info_dict': {
+            'id': 'ivy',
+            'title': '[IVY]',
+            'description': 'A dedicated space for DNB/Turbo House and 4x4.'
+        },
+        'playlist_mincount': 7
+    }]
+
+    def _entries(self, data):
+        for episode in traverse_obj(data, (
+            'props', 'pageProps', 'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio)
+        ):
+            yield self._parse_entry(episode)
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        title = self._og_search_title(webpage) or self._html_search_meta('title', webpage)
+        description = self._og_search_description(webpage) or self._html_search_meta(
+            'description', webpage)
+        data = self._search_nextjs_data(webpage, playlist_id)
+
+        return self.playlist_result(
+            self._entries(data), playlist_id, title, description=description)