From 0957c1533d82479ef6a5b17f6bf3fc79374009ff Mon Sep 17 00:00:00 2001
From: MDLeom <2809763-curben@users.noreply.gitlab.com>
Date: Thu, 21 Jan 2021 04:09:23 +0000
Subject: [PATCH] fix(script): remove invalid protocol

- #32
---
 script.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/script.sh b/script.sh
index eebc478b..a423fed1 100644
--- a/script.sh
+++ b/script.sh
@@ -27,6 +27,8 @@ cut -f 6 -d '"' | \
 cut -f 3- -d "/" | \
 # Domain must have at least a 'dot'
 grep -F "." | \
+# Remove invalid protocol, see #32
+sed -E "s/^(ttps:\/\/|https:\/|http\/)//g" | \
 # Remove www.
 sed "s/^www\.//g" | \
 sort -u > "urlhaus.txt"