fixed some html decoding issues

lists/mhonarc.py

@@ -159,8 +159,14 @@ def archive_thread(li, base_url, parent_thread_data):
 def collect_message(url, message):
 
     response = urllib.request.urlopen(url)
-    html = response.read().decode(encoding="utf-8")
-    # html = response.read()
+
+    html = response.read()
+    try:
+        html = html.decode(encoding="utf-8")
+    except:
+        logging.warning("Error decoding(utf-8): " + url + "... Continuing (non-utf).")
+        pass
+
     soup = BeautifulSoup(html, "html5lib")    
 
     #note: this should follow an RFC header standard -- MHonArc has header info in the 1th <pre>

lists/pipermail.py

@@ -69,7 +69,13 @@ def collect_threads_from_url(url, name, base_arch_dir):
 
 
 	response = urllib.request.urlopen(url)
-	html = response.read().decode(encoding="utf-8")
+
+	html = response.read()
+	try:
+		html = html.decode(encoding="utf-8")
+	except:
+		logging.warning("Error decoding(utf-8): " + url + "... Continuing (non-utf).")
+
 	soup = BeautifulSoup(html, "html5lib")
 
 	ul = soup.find_all('ul')[1];