[extractor/generic] Properly extract format id from Content-Type

Fixes extraction for cases like: audio/x-mpegURL; charset=utf-8

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 8121f04a5e02cf672dc6ab0f152d21df8b98034e..b75db12521caee855e41b086e931d2e7d79a49d2 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -1249,7 +1249,7 @@ class GenericIE(InfoExtractor):
 
         # Check for direct link to a video
         content_type = head_response.headers.get('Content-Type', '')
-        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
+        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
         if m:
             upload_date = unified_strdate(
                 head_response.headers.get('Last-Modified'))