commit: b60016e83139ace517fc823cf2b22756e64c2e63
parent 5aafe895fce2a7be9595cb2e56b7bd73a748e6b6
Author: Philipp Hagemeister <phihag@phihag.de>
Date: Tue, 21 Jan 2014 01:39:39 +0100
Deal with implicitly UTF-16 decoded webpages
These webpages don't specify an encoding and rely on the BOM
Diffstat:
1 file changed, 2 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -220,6 +220,8 @@ class InfoExtractor(object):
webpage_bytes[:1024])
if m:
encoding = m.group(1).decode('ascii')
+ elif webpage_bytes.startswith(b'\xff\xfe'):
+ encoding = 'utf-16'
else:
encoding = 'utf-8'
if self._downloader.params.get('dump_intermediate_pages', False):