fix for html numeric entities in descriptions
git-svn-id: svn://svn.berlios.de/gpodder/trunk@287 b0d088ad-0a06-0410-aad2-9ed5178a7e87
This commit is contained in:
parent
571c20d03c
commit
a366ea1582
|
@ -1,3 +1,9 @@
|
|||
Wed, 21 Mar 2007 21:32:43 +0100 <thp@perli.net>
|
||||
* src/gpodder/libpodcasts.py: Convert numeric HTML entities to
|
||||
symbolic entities so these will be replaced with the right unicode
|
||||
character (for podcast descriptions); thanks to Gerrit Sangel
|
||||
(newsletter sangel.eu) for reporting this bug on gpodder-devel
|
||||
|
||||
Tue, 20 Mar 2007 19:47:14 +0100 <thp@perli.net>
|
||||
* data/po/nl.po: Added Dutch translation from Pieter De Decker
|
||||
(pdedecker gmail com)
|
||||
|
|
|
@ -554,10 +554,14 @@ def channelsToModel( channels):
|
|||
|
||||
def stripHtml( html):
|
||||
# strips html from a string (fix for <description> tags containing html)
|
||||
dict = htmlentitydefs.entitydefs
|
||||
rexp = re.compile( "<[^>]*>")
|
||||
stripstr = rexp.sub( "", html)
|
||||
# replaces numeric entities with entity names
|
||||
dict = htmlentitydefs.codepoint2name
|
||||
for key in dict.keys():
|
||||
stripstr = stripstr.replace( '&#'+str(key)+';', '&'+unicode( dict[key], 'iso-8859-1')+';')
|
||||
# strips html entities
|
||||
dict = htmlentitydefs.entitydefs
|
||||
for key in dict.keys():
|
||||
stripstr = stripstr.replace( '&'+unicode(key,'iso-8859-1')+';', unicode(dict[key], 'iso-8859-1'))
|
||||
return stripstr
|
||||
|
|
Loading…
Reference in New Issue