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

Fixes extraction for cases like: audio/x-mpegURL; charset=utf-8
This commit is contained in:
Sergey M․ 2016-03-18 21:50:10 +06:00
parent cae21032ab
commit 263eff9537

View File

@ -1249,7 +1249,7 @@ def _real_extract(self, url):
# 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'))