From 7415707c3399ce128e073e089debeec494cf8982 Mon Sep 17 00:00:00 2001
From: Denis Kuzmenok <denis.kuzmenok@gmail.com>
Date: Thu, 13 Jan 2022 21:52:50 +0100
Subject: [PATCH] Added a try/except to catch unicode errors.

---
 burst/normalize.py | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/burst/normalize.py b/burst/normalize.py
index bc67ee35..ada2aa93 100644
--- a/burst/normalize.py
+++ b/burst/normalize.py
@@ -184,20 +184,23 @@ def normalize_string(string, charset=None, replacing=False):
             string = unicode(string, errors='ignore')
             pass
 
-    string = remove_control_chars(string)
-    string = fix_bad_unicode(string)
-    string = unquote(string)
-    string = string.replace(u'<![CDATA[', u'').replace(u']]', u'')
+    try:
+        string = remove_control_chars(string)
+        string = fix_bad_unicode(string)
+        string = unquote(string)
+        string = string.replace(u'<![CDATA[', u'').replace(u']]', u'')
 
-    if PY3:
-        string = html.unescape(string)
-    else:
-        string = HTMLParser().unescape(string)
+        if PY3:
+            string = html.unescape(string)
+        else:
+            string = HTMLParser().unescape(string)
 
-    if replacing:
-        string = string.replace(u"'", '')
+        if replacing:
+            string = string.replace(u"'", '')
 
-    string = string.lower()
+        string = string.lower()
+    except:
+        pass
 
     return string