[BBC Sounds] Tracklist Extraction

yt_dlp/extractor/bbc.py

@@ -15,11 +15,13 @@
     float_or_none,
     get_element_by_class,
     int_or_none,
+    join_nonempty,
     js_to_json,
     parse_duration,
     parse_iso8601,
     parse_qs,
     strip_or_none,
+    traverse_obj,
     try_get,
     unescapeHTML,
     unified_timestamp,
@@ -41,7 +43,6 @@ class BBCCoUkIE(InfoExtractor):
                             iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
                             music/(?:clips|audiovideo/popular)[/#]|
                             radio/player/|
-                            sounds/play/|
                             events/[^/]+/play/[^/]+/
                         )
                         (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
@@ -218,20 +219,6 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
-        }, {
-            'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb',
-            'note': 'Audio',
-            'info_dict': {
-                'id': 'm0007jz9',
-                'ext': 'mp4',
-                'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra',
-                'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.",
-                'duration': 9840,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
@@ -844,6 +831,20 @@ class BBCIE(BBCCoUkIE):  # XXX: Do not subclass from concrete IE
             'upload_date': '20190604',
             'categories': ['Psychology'],
         },
+    }, {
+        # BBC Sounds
+        'url': 'https://www.bbc.co.uk/sounds/play/m001p2jp',
+        'info_dict': {
+            'id': 'm001p2jn',
+            'ext': 'mp4',
+            'title': 'Late Junction - Bonjo Iyabinghi Noah and GAIKA in session',
+            'thumbnail': 'https://ichef.bbci.co.uk/images/ic/raw/p0cgqwnb.jpg',
+            'duration': 7200,
+            'chapters': 'count:24',
+            'description': 'md5:36f16179df6ee9992e80fea912d97ea8',
+            'uploader': 'Radio 3',
+            'uploader_id': 'bbc_radio_three',
+        },
     }, {  # onion routes
         'url': 'https://www.bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd.onion/news/av/world-europe-63208576',
         'only_matching': True,
@@ -1118,6 +1119,15 @@ def _real_extract(self, url):
                 image_url = current_programme.get('image_url')
                 if image_url:
                     thumbnail = image_url.replace('{recipe}', 'raw')
+                tracklist = []
+                for track in traverse_obj(preload_state, ("tracklist", "tracks")):
+                    tracklist.append({
+                        "title": join_nonempty("primary", "secondary", "tertiary", delim=" - ", from_dict=track.get("titles")),
+                        **traverse_obj(track, {
+                            "start_time": ("offset", "start"),
+                            "end_time": ("offset", "end"),
+                        }),
+                    })
                 return {
                     'id': programme_id,
                     'title': title,
@@ -1128,6 +1138,7 @@ def _real_extract(self, url):
                     'uploader_id': network.get('id'),
                     'formats': formats,
                     'subtitles': subtitles,
+                    'chapters': tracklist,
                 }
 
         bbc3_config = self._parse_json(