From aaab4b82fb01615704a849f1d997a0b6e8438c75 Mon Sep 17 00:00:00 2001
From: MDLeom <2809763-curben@users.noreply.gitlab.com>
Date: Sun, 2 Jan 2022 01:15:46 +0000
Subject: [PATCH] refactor: url encode space on the source

---
 src/script.sh | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/src/script.sh b/src/script.sh
index 15b94fae..7b476d68 100644
--- a/src/script.sh
+++ b/src/script.sh
@@ -39,14 +39,17 @@ sed 's/"//g' | \
 cut -f 3- -d "/" | \
 # Domain must have at least a 'dot'
 grep -F "." | \
-sed "s/^www\.//g" > "phishtank.txt"
+sed "s/^www\.//g" | \
+# url encode space #11
+sed "s/ /%20/g" > "phishtank.txt"
 
 cat "openphish-raw.txt" | \
 dos2unix | \
 tr "[:upper:]" "[:lower:]" | \
 cut -f 3- -d "/" | \
 grep -F "." | \
-sed "s/^www\.//g" > "openphish.txt"
+sed "s/^www\.//g" | \
+sed "s/ /%20/g" > "openphish.txt"
 
 ## Combine PhishTank and OpenPhish
 cat "phishtank.txt" "openphish.txt" | \
@@ -109,9 +112,7 @@ cat "phishing-domains.txt" | \
 grep -F -vf "phishing-top-domains.txt" > "phishing-notop-domains-temp.txt"
 
 cat "phishing.txt" | \
-grep -F -f "phishing-top-domains.txt" | \
-# url encode space #11
-sed "s/ /%20/g" > "phishing-url-top-domains-temp.txt"
+grep -F -f "phishing-top-domains.txt" > "phishing-url-top-domains-temp.txt"
 
 rm -f "phishing-url-top-domains.txt" "phishing-url-top-domains-raw.txt"