From 5b0d37824be42dc7bc7e82ea74ea2e06f9c27194 Mon Sep 17 00:00:00 2001
From: Alex Cabal <alex@alexcabal.com>
Date: Sat, 18 Jan 2025 17:33:00 -0600
Subject: [PATCH] Add configuration to stop rude bot crawlers using fail2ban

---
 scripts/rotate-www-logs | 5 ++++-
 templates/Header.php    | 2 ++
 www/robots.txt          | 3 +++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/scripts/rotate-www-logs b/scripts/rotate-www-logs
index aeee3fa1..40d353c3 100755
--- a/scripts/rotate-www-logs
+++ b/scripts/rotate-www-logs
@@ -61,7 +61,7 @@ for filename in ${directory}/${filenameBase}.*; do
 			# ipv6loganon is provided by the `ipv6calc` package
 			grep --extended-regexp "\[${grepString}" "${filename}" | ipv6loganon --anonymize-paranoid >> "${directory}/${logMonth}/${logFilename}"
 
-			gzip --best "${directory}/${logMonth}/${logFilename}"
+			gzip --force --best "${directory}/${logMonth}/${logFilename}"
 
 			chown --preserve-root --recursive www-data:adm "${directory}/${logMonth}"
 			chmod --preserve-root --recursive g+w "${directory}/${logMonth}"
@@ -70,3 +70,6 @@ for filename in ${directory}/${filenameBase}.*; do
 		rm "${filename}"
 	fi
 done
+
+# Set this for `fail2ban` to use.
+ln -s "$1" "${directory}"/current.log
diff --git a/templates/Header.php b/templates/Header.php
index 2c9497e3..720690c2 100644
--- a/templates/Header.php
+++ b/templates/Header.php
@@ -119,6 +119,8 @@ if(!$isXslt){
 			</div>
 		<? } ?>
 		<a href="/">Standard Ebooks</a>
+		<? /* This link is hidden to regular users, and also disallowed by `robots.txt`. If a rude bot crawls this URL, `fail2ban` bans the IP for 24 hours. See `./config/fail2ban/filter.d/se.conf`. */ ?>
+		<a href="/honeypot" hidden="hidden">Following this link will ban your IP for 24 hours</a>
 		<nav>
 			<ul>
 				<li>
diff --git a/www/robots.txt b/www/robots.txt
index 97ad664c..48211b7f 100644
--- a/www/robots.txt
+++ b/www/robots.txt
@@ -1 +1,4 @@
 Sitemap: https://standardebooks.org/sitemap
+
+User-agent: *
+Disallow: /honeypot