From 1b7fdad6a88cd7f7857d2436149db2467014473e Mon Sep 17 00:00:00 2001
From: pictuga <contact@pictuga.com>
Date: Sun, 8 Sep 2013 15:48:34 +0200
Subject: [PATCH] Improve broken XML support

TPB feed is a good example <http://rss.thepiratebay.sx/blog>. Now supports ampersand in feed, using the "recover" mode in etree.parse. Broken utf-8 strings in feed are now also supported.
---
 feeds.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/feeds.py b/feeds.py
index eb11b4d..8127e67 100644
--- a/feeds.py
+++ b/feeds.py
@@ -42,7 +42,10 @@ class FeedException(Exception):
 	pass
 
 def parse(data):
-	doc = etree.fromstring(data)
+	data = data.decode('utf-8', 'replace').encode('utf-8')
+	parser = etree.XMLParser(recover=True)
+	doc = etree.fromstring(data, parser)
+
 	match = doc.xpath("//atom03:feed|//atom:feed|//channel|//rdf:rdf|//rdf:RDF", namespaces=NSMAP)
 	if len(match):
 		mtable = {	'rdf:rdf': FeedParserRSS, 'channel': FeedParserRSS,