From 3ac0efb6195757b46474eddb934c64117fc2f482 Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@nicksweeting.com>
Date: Mon, 4 Feb 2019 18:54:02 -0800
Subject: [PATCH] dont parse quotes as part of urls

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

diff --git a/archivebox/util.py b/archivebox/util.py
index 1dbb9f21..f708a4bf 100644
--- a/archivebox/util.py
+++ b/archivebox/util.py
@@ -43,7 +43,7 @@ base_url = lambda url: without_scheme(url)  # uniq base url used to dedupe links
 
 short_ts = lambda ts: ts.split('.')[0]
 
-URL_REGEX = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))[^<]+'
+URL_REGEX = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))[^<\""]+'
 
 
 def check_dependencies():