From e68268f50612b8689962e593c8d50ca948c4bc45 Mon Sep 17 00:00:00 2001 From: MDLeom <2809763-curben@users.noreply.gitlab.com> Date: Tue, 27 Sep 2022 09:43:30 +0000 Subject: [PATCH] fix: remove mitchellkrogza/Phishing.Database source - close #35 --- README.md | 4 +--- src/script.sh | 12 ++---------- 2 files changed, 3 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index f73a1451..d7334acb 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # Phishing URL Blocklist -A blocklist of phishing websites, curated from [PhishTank](https://www.phishtank.com/), [OpenPhish](https://openphish.com/), [phishunt.io](https://phishunt.io/) and [mitchellkrogza/Phishing.Database](https://github.com/mitchellkrogza/Phishing.Database/blob/master/phishing-domains-ACTIVE.txt). Blocklist is updated twice a day. +A blocklist of phishing websites, curated from [PhishTank](https://www.phishtank.com/), [OpenPhish](https://openphish.com/), [phishunt.io](https://phishunt.io/). Blocklist is updated twice a day. There are multiple formats available, refer to the appropriate section according to the program used: @@ -485,6 +485,4 @@ _PhishTank is either trademark or registered trademark of Cisco Systems, Inc._ [phishunt.io](https://phishunt.io/): All rights reserved by [Daniel López](https://twitter.com/0xDanielLopez) -[mitchellkrogza/Phishing.Database](https://github.com/mitchellkrogza/Phishing.Database): MIT License - This repository is not endorsed by PhishTank/OpenDNS and OpenPhish. diff --git a/src/script.sh b/src/script.sh index a2b9d1a8..e67c3a8f 100644 --- a/src/script.sh +++ b/src/script.sh @@ -39,7 +39,6 @@ cd "tmp/" curl -L "https://data.phishtank.com/data/$PHISHTANK_API/online-valid.csv.bz2" -o "phishtank.bz2" curl -L "https://openphish.com/feed.txt" -o "openphish-raw.txt" curl -L "https://phishunt.io/feed.txt" -o "phishunt-raw.txt" -curl -L "https://github.com/mitchellkrogza/Phishing.Database/raw/master/phishing-links-ACTIVE.txt" -o "phishing.db-raw.txt" curl -L "https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m.csv.zip" -o "top-1m-umbrella.zip" curl -L "https://tranco-list.eu/top-1m.csv.zip" -o "top-1m-tranco.zip" @@ -76,15 +75,8 @@ grep -F "." | \ sed "s/^www\.//g" | \ sed "s/ /%20/g" > "phishunt.txt" -cat "phishing.db-raw.txt" | \ -tr "[:upper:]" "[:lower:]" | \ -cut -f 3- -d "/" | \ -grep -F "." | \ -sed "s/^www\.//g" | \ -sed "s/ /%20/g" > "phishing.db.txt" - ## Combine all sources -cat "phishtank.txt" "openphish.txt" "phishunt.txt" "phishing.db.txt" | \ +cat "phishtank.txt" "openphish.txt" "phishunt.txt" | \ sort -u > "phishing.txt" ## Parse domain and IP address only @@ -181,7 +173,7 @@ SECOND_LINE="! Updated: $CURRENT_TIME" THIRD_LINE="! Expires: 1 day (update frequency)" FOURTH_LINE="! Homepage: https://gitlab.com/malware-filter/phishing-filter" FIFTH_LINE="! License: https://gitlab.com/malware-filter/phishing-filter#license" -SIXTH_LINE="! Sources: phishtank.com, openphish.com, phishunt.io, github.com/mitchellkrogza/Phishing.Database" +SIXTH_LINE="! Sources: phishtank.com, openphish.com, phishunt.io" COMMENT_UBO="$FIRST_LINE\n$SECOND_LINE\n$THIRD_LINE\n$FOURTH_LINE\n$FIFTH_LINE\n$SIXTH_LINE" mkdir -p "../public/"