[iheart] clean HTML tags from episode description
authorRemita Amine <remitamine@gmail.com>
Mon, 4 Jan 2021 08:59:20 +0000 (09:59 +0100)
committerRemita Amine <remitamine@gmail.com>
Mon, 4 Jan 2021 08:59:20 +0000 (09:59 +0100)
youtube_dl/extractor/iheart.py

index 7a7295ff48efee119279fe838d640c74446aa68d..266c67a76e40eac8668b20f597523c01e53a42df 100644 (file)
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
     clean_podcast_url,
     int_or_none,
     str_or_none,
@@ -18,7 +19,7 @@ class IHeartRadioBaseIE(InfoExtractor):
     def _extract_episode(self, episode):
         return {
             'thumbnail': episode.get('imageUrl'),
-            'description': episode.get('description'),
+            'description': clean_html(episode.get('description')),
             'timestamp': int_or_none(episode.get('startDate'), 1000),
             'duration': int_or_none(episode.get('duration')),
         }