Strip html in RSS description tags fixes problems with certain feeds (Thanks to Leo Gomez)

git-svn-id: svn://svn.berlios.de/gpodder@34 b0d088ad-0a06-0410-aad2-9ed5178a7e87

ChangeLog

@@ -1,3 +1,8 @@
+Sun, 26 Feb 2006 00:11:28 +0100 <thp@perli.net>
+	* Bumped version number and date in bin/gpodder
+	* Updated TODO-List
+	* Strip html inside <description> tags (Reported by Leo Gomez)
+
 Sat, 04 Feb 2006 19:07:33 +0100 <thp@perli.net> 
 	* ** gPodder version 0.5 is here! **
 	+ Added "downloaded episodes" tab

README

@@ -45,7 +45,7 @@
 
  Debian/Ubuntu users can install the dependencies with:
  
-   apt-get install python python-glade2 python-gtk2 wget
+   apt-get install python python-glade2 python-gtk2 wget python-xml
 
  Other users: Please install the above packages somehow ;)
  If you want to install gPodder from source, you have to 

TODO

@@ -30,4 +30,5 @@
  * maybe save date with downloads
  * maybe a "all channels view"
 
+ ** UTILIZE PYTHON-FEEDPARSER
 

bin/gpodder

@@ -6,8 +6,8 @@
 # PLEASE DO NOT CHANGE FORMAT OF __version__ LINE (Makefile reads this)
 
 __author__    = "Thomas Perl <thp@perli.net>"
-__version__   = "0.5"
-__date__      = "2006-02-04"
+__version__   = "0.6-svn"
+__date__      = "2006-02-26"
 __copyright__ = "Copyright (c) 2005-2006 %s. All rights reserved." % __author__
 __licence__   = "GPL"
 

src/gpodder/libpodcasts.py

@@ -19,6 +19,8 @@ import libgpodder
 from liblocdbwriter import writeLocalDB
 from liblocdbreader import readLocalDB
 
+import re
+
 
 # podcastChannel: holds data for a complete channel
 class podcastChannel(object):
@@ -35,7 +37,7 @@ class podcastChannel(object):
         self.url = url
         self.title = title
         self.link = link
-        self.description = description
+        self.description = stripHtml( description)
         self.items = []
     
     def addItem( self, item):
@@ -111,7 +113,7 @@ class podcastItem(object):
         self.length = length
         self.mimetype = mimetype
         self.guid = guid
-        self.description = description
+        self.description = stripHtml( description)
         self.link = ""
     
     def getSize( self):
@@ -169,3 +171,8 @@ def channelsToModel( channels):
     return new_model
 
 
+def stripHtml( html):
+    # strips html from a string (fix for <description> tags containing html)
+    rexp = re.compile( "<[^>]*>")
+    return rexp.sub( "", html)
+

src/gpodder/librssreader.py

@@ -18,6 +18,7 @@ from string import strip
 
 from libpodcasts import podcastChannel
 from libpodcasts import podcastItem
+from libpodcasts import stripHtml
 
 class rssErrorHandler( ErrorHandler):
     def __init__( self):
@@ -72,7 +73,7 @@ class rssReader( DefaultHandler):
             if name == "link":
                 self.channel.link = self.current_element_data
             if name == "description":
-                self.channel.description = self.current_element_data
+                self.channel.description = stripHtml( self.current_element_data)
         
         if self.current_item != None:
             if name == "title":
@@ -80,7 +81,7 @@ class rssReader( DefaultHandler):
             if name == "link":
                 self.current_item.link = self.current_element_data
             if name == "description":
-                self.current_item.description = self.current_element_data
+                self.current_item.description = stripHtml( self.current_element_data)
             if name == "guid":
                 self.current_item.guid = self.current_element_data
             if name == "item":