From 0c6cb0c7f9faad6c34fba1aeca9189b8af3d7033 Mon Sep 17 00:00:00 2001
From: Ronald Schaten <ronald@schatenseite.de>
Date: Sat, 6 Apr 2013 00:12:20 +0200
Subject: [PATCH] decode html entities

---
 atomstrom.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/atomstrom.py b/atomstrom.py
index dcc0916..4f58d15 100755
--- a/atomstrom.py
+++ b/atomstrom.py
@@ -14,6 +14,7 @@ import codecs
 import urllib2
 #import hn
 import html2text
+import HTMLParser
 import ConfigParser
 from argparse import ArgumentParser
 from email.header import Header
@@ -165,6 +166,15 @@ def process_feed_entry(session, feed, entry):
                 thisentry.fullpage = h2t.handle(thisentry.fullpage)
             elif feed.contentcolumn == 'readability':
                 thisentry.readability = h2t.handle(thisentry.readability)
+        hp = HTMLParser.HTMLParser()
+        if thisentry.summary:
+            thisentry.summary = hp.unescape(thisentry.summary)
+        if thisentry.content:
+            thisentry.content = hp.unescape(thisentry.content)
+        if thisentry.fullpage:
+            thisentry.fullpage = hp.unescape(thisentry.fullpage)
+        if thisentry.readability:
+            thisentry.readability = hp.unescape(thisentry.readability)
         feed.entry.append(thisentry)
         session.commit()
         return 1