yt_dlp/extractor/art19.py

@@ -11,7 +11,7 @@ class Art19IE(InfoExtractor):
         rf'https?://(?:www\.)?art19\.com/shows/[^/#?]+/episodes/(?P<id>{_UUID_REGEX})',
         rf'https?://rss\.art19\.com/episodes/(?P<id>{_UUID_REGEX})\.mp3',
     ]
-    _EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL[0]})']
+    _EMBED_REGEX = [rf'(?x)<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL[0]})']
 
     _TESTS = [{
         'url': 'https://rss.art19.com/episodes/5ba1413c-48b8-472b-9cc3-cfd952340bdb.mp3',
@@ -121,12 +121,7 @@ class Art19IE(InfoExtractor):
             f'https://rss.art19.com/episodes/{episode_id}.json', episode_id, fatal=False,
             note='Downloading RSS metadata')
 
-        formats = [{
-            'format_id': 'direct',
-            'url': f'https://rss.art19.com/episodes/{episode_id}.mp3',
-            'vcodec': 'none',
-            'acodec': 'mp3',
-        }]
+        formats = []
         for fmt_id, fmt_data in traverse_obj(rss_metadata, ('content', 'media', {dict.items}, ...)):
             if fmt_id == 'waveform_bin':
                 continue
@@ -140,6 +135,12 @@ class Art19IE(InfoExtractor):
                 'acodec': fmt_id,
                 'quality': -2 if fmt_id == 'ogg' else -1,
             })
+        formats.append({
+            'format_id': 'direct',
+            'url': f'https://rss.art19.com/episodes/{episode_id}.mp3',
+            'vcodec': 'none',
+            'acodec': 'mp3',
+        })
 
         return {
             'id': episode_id,
@@ -177,7 +178,7 @@ class Art19ShowIE(InfoExtractor):
         rf'{_VALID_URL_BASE}(?:$|[#?])',
         r'https?://rss\.art19\.com/(?P<id>[\w-]+)/?(?:$|[#?])',
     ]
-    _EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL_BASE}[^\'"])']
+    _EMBED_REGEX = [rf'(?x)<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL_BASE}[^\'"])']
 
     _TESTS = [{
         'url': 'https://www.art19.com/shows/5898c087-a14f-48dc-b6fc-a2280a1ff6e0/',