commit f141fefab73d96a6dd2c927f56d0b86253991c02
parent 8334637f4ac4a1aeddc6f05131be1c42ea6761e1
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date: Thu, 14 Apr 2016 14:06:05 +0800
[karrierevideos] Fix extraction
The server serves malformed header "Content Type: text/xml" for the XML
request (it should be Content-Type but not Content Type). Python 3.x,
which uses email.feedparser rejects such headers. As a result,
Content-Encoding header is not parsed, so the returned content is kept
not decompressed, and thus XML parsing error.
Diffstat:
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/karrierevideos.py b/youtube_dl/extractor/karrierevideos.py
@@ -52,9 +52,12 @@ class KarriereVideosIE(InfoExtractor):
video_id = self._search_regex(
r'/config/video/(.+?)\.xml', webpage, 'video id')
+ # Server returns malformed headers
+ # Force Accept-Encoding: * to prevent gzipped results
playlist = self._download_xml(
'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id,
- video_id, transform_source=fix_xml_ampersands)
+ video_id, transform_source=fix_xml_ampersands,
+ headers={'Accept-Encoding': '*'})
NS_MAP = {
'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'