From 1a36d3b675866ff4933258812a8b7ca671e25839 Mon Sep 17 00:00:00 2001
From: Mikhail Sandakov <msandakov@plesk.com>
Date: Wed, 14 Feb 2024 09:07:09 +0200
Subject: [PATCH] Get the list of malicious bots from the
 mitchellkrogza/nginx-ultimate-bad-bot-blocker repository

---
 files/gen_badbots | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/files/gen_badbots b/files/gen_badbots
index d9936257..dfcb6725 100755
--- a/files/gen_badbots
+++ b/files/gen_badbots
@@ -34,16 +34,12 @@
 #
 #-----------------\____________________________________/------------------
 
-url=http://www.user-agents.org/index.shtml
+url=https://raw.githubusercontent.com/mitchellkrogza/nginx-ultimate-bad-bot-blocker/master/_generator_lists/bad-user-agents.list
 badbots=$(
-for f in "" "?g_m" "?moz" "?n_s" "?t_z"; do
-	wget -q -O- $url$f;
-done \
-| grep -h -B4 '<td class="smallcell" nowrap>S&nbsp;</td>'\
-| sed -e 's/&nbsp;//g' \
-| awk '/^--/{getline; gsub("  ",""); print $0}' \
-| sed -e 's/\([.\:|()+]\)/\\\1/g' \
+curl -sS $url \
 | uniq \
+| sed -e 's/\\ / /g' \
+| sed -e 's/\([.\:|()+]\)/\\\1/g' \
 | tr '\n' '|' \
 | sed -e 's/|$//g'
 )