lordwelch/comictagger
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

better stripping of markup tags from CV text

Browse Source 
git-svn-id: http://comictagger.googlecode.com/svn/trunk@70 6c5673fe-1810-88d6-992b-cd32ca31540c
This commit is contained in:
beville@gmail.com 2012-11-20 19:19:33 +00:00
parent 8202c97ad3
commit 2594a85783
1 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
comicvinetalker.py
View File

@ -240,14 +240,24 @@ class ComicVineTalker(QObject):
return metadata
def cleanup_html( self, string):
p = re.compile(r'<[^<]*?>')
# remove all newlines first
string = string.replace("\n", "")
#put in our own
string = string.replace("<br>", "\n")
string = string.replace("</p>", "\n\n")
string = string.replace("<h4>", "*")
string = string.replace("</h4>", "*\n")
# now strip all other tags
p = re.compile(r'<[^<]*?>')
newstring = p.sub('',string)
newstring = p.sub('',string)
newstring = newstring.replace('&nbsp;',' ')
newstring = newstring.replace('&amp;','&')
return newstring
newstring = newstring.replace('&nbsp;',' ')
newstring = newstring.replace('&amp;','&')
return newstring
def fetchIssueDate( self, issue_id ):
image_url, thumb_url, month,year = self.fetchIssueSelectDetails( issue_id )