From 2594a857832c16cac24076e4823f01482603fafb Mon Sep 17 00:00:00 2001
From: "beville@gmail.com"
 <beville@gmail.com@6c5673fe-1810-88d6-992b-cd32ca31540c>
Date: Tue, 20 Nov 2012 19:19:33 +0000
Subject: [PATCH] better stripping of markup tags from CV text

git-svn-id: http://comictagger.googlecode.com/svn/trunk@70 6c5673fe-1810-88d6-992b-cd32ca31540c
---
 comicvinetalker.py | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/comicvinetalker.py b/comicvinetalker.py
index 08003d5..770c16a 100644
--- a/comicvinetalker.py
+++ b/comicvinetalker.py
@@ -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 )