From db0461ec4efe68940e8b2d7b649219019ee88c2f Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@nicksweeting.com>
Date: Wed, 23 Jan 2019 01:06:59 -0500
Subject: [PATCH] add timeout to title fetching

---
 archivebox/util.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/archivebox/util.py b/archivebox/util.py
index 761b5380..70d7e544 100644
--- a/archivebox/util.py
+++ b/archivebox/util.py
@@ -234,7 +234,7 @@ def fetch_page_title(url, default=True):
         default = url
 
     try:
-        html_content = urllib.request.urlopen(url).read().decode('utf-8')
+        html_content = urllib.request.urlopen(url, timeout=10).read().decode('utf-8')
 
         match = re.search('<title>(.*?)</title>', html_content)
         return match.group(1) if match else default or None