only attempt to read html

utils/helpers.py

@@ -61,7 +61,9 @@ class WebPage(object):
 
         request = urllib.request.Request(self.url, headers=self.headers)
         page = urllib.request.urlopen(request, timeout=5)
-        self.source = page.read()
+        headers = page.info()
+        if headers['content-type'] == "text/html":
+            self.source = page.read()
 
 
     def find_links(self):