From db97d3dcfa497c6865399351fa8702b92a940459 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 19 May 2020 10:58:43 -0700
Subject: handle UnboundLocalError in HTML parsing

---
 python/sandcrawler/html.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py
index 3eadc7b..88ea41b 100644
--- a/python/sandcrawler/html.py
+++ b/python/sandcrawler/html.py
@@ -42,7 +42,10 @@ def extract_fulltext_url(html_url, html_body):
     try:
         soup = BeautifulSoup(html_body, 'html.parser')
     except TypeError as te:
-        print("{} (url={})".format(te, html_url, file=sys.stderr))
+        print(f"{te} (url={html_url})", file=sys.stderr)
+        return dict()
+    except UnboundLocalError as ule:
+        print(f"{ule} (url={html_url})", file=sys.stderr)
         return dict()
 
     ### General Tricks ###
-- 
cgit v1.2.3