diff options
| author | Yen Chi Hsuan <yan12125@gmail.com> | 2016-04-14 14:06:05 +0800 |
|---|---|---|
| committer | Yen Chi Hsuan <yan12125@gmail.com> | 2016-04-14 14:06:05 +0800 |
| commit | f141fefab73d96a6dd2c927f56d0b86253991c02 (patch) | |
| tree | 094d7b5cc636528d0ebac55acece70fdd4eab6d1 | |
| parent | 8334637f4ac4a1aeddc6f05131be1c42ea6761e1 (diff) | |
[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.
| -rw-r--r-- | youtube_dl/extractor/karrierevideos.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/youtube_dl/extractor/karrierevideos.py b/youtube_dl/extractor/karrierevideos.py index 2cb04e533..c05263e61 100644 --- 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' |