Merge b6059b8b9c into b83ca24eb7

yt_dlp/extractor/_extractors.py

@@ -1938,9 +1938,7 @@ from .spotify import (
     SpotifyShowIE,
 )
 from .spreaker import (
-    SpreakerEpisodeIE,
     SpreakerIE,
-    SpreakerPageIE,
     SpreakerShowIE,
     SpreakerShowPageIE,
 )

yt_dlp/extractor/spreaker.py

@@ -4,11 +4,13 @@ from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     int_or_none,
+    parse_qs,
     str_or_none,
     try_get,
     unified_timestamp,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 def _extract_episode(data, episode_id=None):
@@ -58,15 +60,18 @@ def _extract_episode(data, episode_id=None):
 
 
 class SpreakerIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
+    _VALID_URL = [
-                    https?://
+        r'''(?x)
-                        api\.spreaker\.com/
+        https?://
-                        (?:
+            api\.spreaker\.com/
-                            (?:download/)?episode|
+            (?:
-                            v2/episodes
+                (?:download/)?episode|
-                        )/
+                v2/episodes
-                        (?P<id>\d+)
+            )/
-                    '''
+            (?P<id>\d+)
+        ''',
+        r'https?://(?:www\.)?spreaker\.com/episode/[^#?/]*?(?P<id>\d+)/?(?:[?#]|$)',
+    ]
     _TESTS = [{
         'url': 'https://api.spreaker.com/episode/12534508',
         'info_dict': {
@@ -91,34 +96,38 @@ class SpreakerIE(InfoExtractor):
     }, {
         'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
         'only_matching': True,
+    }, {
+        'note': 'episode',
+        'url': 'https://www.spreaker.com/episode/grunge-music-origins-the-raw-sound-that-defined-a-generation--60269615',
+        'info_dict': {
+            'id': '60269615',
+            'display_id': 'grunge-music-origins-the-raw-sound-that-',
+            'ext': 'mp3',
+            'title': 'Grunge Music Origins - The Raw Sound that Defined a Generation',
+            'description': str,
+            'timestamp': 1717468905,
+            'upload_date': '20170809',
+            'uploader': 'Katie Brown 2',
+            'uploader_id': '17733249',
+            'duration': 1063.42,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'series': '90s Grunge',
+        },
     }]
 
     def _real_extract(self, url):
         episode_id = self._match_id(url)
+        query = {}
+        if key := traverse_obj(url, ({parse_qs}, 'key', 0)):
+            query = {'key': key}
         data = self._download_json(
             f'https://api.spreaker.com/v2/episodes/{episode_id}',
-            episode_id)['response']['episode']
+            episode_id, query=query)['response']['episode']
         return _extract_episode(data, episode_id)
 
 
-class SpreakerPageIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        episode_id = self._search_regex(
-            (r'data-episode_id=["\'](?P<id>\d+)',
-             r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
-        return self.url_result(
-            f'https://api.spreaker.com/episode/{episode_id}',
-            ie=SpreakerIE.ie_key(), video_id=episode_id)
-
-
 class SpreakerShowIE(InfoExtractor):
     _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
     _TESTS = [{
@@ -170,23 +179,3 @@ class SpreakerShowPageIE(InfoExtractor):
         return self.url_result(
             f'https://api.spreaker.com/show/{show_id}',
             ie=SpreakerShowIE.ie_key(), video_id=show_id)
-
-
-class SpreakerEpisodeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/episode/(?P<title>[^/?#]+)-(?P<id>\d+)(?:\?key=(?P<key>[^&]+))?'
-    _TESTS = [{
-        'url': 'https://www.spreaker.com/episode/ep-15-music-marketing-likes-part-2--12534508',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        episode_id, key = self._match_valid_url(url).group(
-            'id', 'key')
-        result = f'https://api.spreaker.com/episode/{episode_id}'
-        if key is not None:
-            access_key = f'?key={key}'
-            result = f'https://api.spreaker.com/episode/{episode_id}{access_key}'
-        data = self._download_json(
-            result,
-            episode_id)['response']['episode']
-        return _extract_episode(data, episode_id)