projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[sohu] Handle encoding, and fix tests
[youtube-dl]
/
youtube_dl
/
extractor
/
common.py
diff --git
a/youtube_dl/extractor/common.py
b/youtube_dl/extractor/common.py
index 77a13aea533d17aa57f17e01929ca3a276787844..a2986cebe5db15d54fbbdf90e87669982ce08aec 100644
(file)
--- a/
youtube_dl/extractor/common.py
+++ b/
youtube_dl/extractor/common.py
@@
-145,12
+145,17
@@
class InfoExtractor(object):
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
+ webpage_bytes = urlh.read()
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
else:
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
else:
- encoding = 'utf-8'
- webpage_bytes = urlh.read()
+ m = re.search(br'<meta[^>]+charset="?([^"]+)[ /">]',
+ webpage_bytes[:1024])
+ if m:
+ encoding = m.group(1).decode('ascii')
+ else:
+ encoding = 'utf-8'
if self._downloader.params.get('dump_intermediate_pages', False):
try:
url = url_or_request.get_full_url()
if self._downloader.params.get('dump_intermediate_pages', False):
try:
url = url_or_request.get_full_url()