[ie/lrt] add fixes suggested by bashonly

yt_dlp/extractor/lrt.py

@@ -1,4 +1,3 @@
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
@@ -7,6 +6,7 @@ from ..utils import (
     traverse_obj,
     unified_timestamp,
     url_or_none,
+    urljoin,
 )
 
 
@@ -83,7 +83,7 @@ class LRTVODIE(LRTBaseIE):
     }]
 
     def _real_extract(self, url):
-        path, video_id = self._match_valid_url(url).groups()
+        path, video_id = self._match_valid_url(url).group('path', 'id')
         webpage = self._download_webpage(url, video_id)
 
         media_url = self._extract_js_var(webpage, 'main_url', path)
@@ -123,9 +123,9 @@ class LRTRadioIE(LRTBaseIE):
             'description': 'md5:5eee9a0e86a55bf547bd67596204625d',
             'timestamp': 1726143120,
             'upload_date': '20240912',
-            'tags': list,
+            'tags': 'count:5',
             'thumbnail': r're:https?://.+/.+\.jpe?g',
-            'categories': list,
+            'categories': ['Daiktiniai įrodymai'],
         },
     }, {
         'url': 'https://www.lrt.lt/radioteka/irasas/2000304654/vakaras-su-knyga-svetlana-aleksijevic-cernobylio-malda-v-dalis?season=%2Fmediateka%2Faudio%2Fvakaras-su-knyga%2F2023',
@@ -133,19 +133,18 @@ class LRTRadioIE(LRTBaseIE):
     }]
 
     def _real_extract(self, url):
-        video_id, path = self._match_valid_url(url).groups()
+        video_id, path = self._match_valid_url(url).group('id', 'path')
 
-        base_url = 'https://www.lrt.lt'
-        api_url = 'https://www.lrt.lt/radioteka/api/media'
-        media_url = f'/mediateka/irasas/{video_id}/{path}'
-        media = self._download_json(api_url, video_id, query={'url': media_url})
+        media = self._download_json(
+            'https://www.lrt.lt/radioteka/api/media', video_id,
+            query={'url': f'/mediateka/irasas/{video_id}/{path}'})
         return traverse_obj(media, {
             'id': ('id', {int}, {str_or_none}),
             'title': ('title', {str}),
-            'tags': ('tags', ..., 'name'),
-            'categories': ('playlist_item', 'category', {lambda x: [x]}),
+            'tags': ('tags', ..., 'name', {str}),
+            'categories': ('playlist_item', 'category', {str}, filter, all, filter),
             'description': ('content', {clean_html}, {str}),
             'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
-            'thumbnail': ('playlist_item', 'image', {lambda x: f'{base_url}{x}'}, {url_or_none}),
+            'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
             'formats': ('playlist_item', 'file', {lambda x: self._extract_m3u8_formats(x, video_id)}),
         })