From bc8d98d52386568c8cd32e3a0c5dd0fb94e8c207 Mon Sep 17 00:00:00 2001
From: helenclx <contact@helenchong.dev>
Date: Mon, 19 Aug 2024 16:23:25 +0000
Subject: [PATCH] Build: (1e3ccd5) Block bad bots

---
 .htaccess | 38 +++++++++++++++++++++++++++++++++++++-
 feed.xml  |  2 +-
 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/.htaccess b/.htaccess
index d46f75c9..0199481c 100644
--- a/.htaccess
+++ b/.htaccess
@@ -5,4 +5,40 @@ Header set Cache-Control "max-age=31536000, public"
 </FilesMatch>
 <FilesMatch "\.(css|js)$">
 Header set Cache-Control "no-cache, public"
-</FilesMatch>
\ No newline at end of file
+</FilesMatch>
+
+# Block bad bots
+RewriteCond %{HTTP_USER_AGENT} (Amazonbot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Applebot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Applebot-Extended) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Bytespider) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (CCBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (ChatGPT-User) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Claude-Web) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (ClaudeBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Diffbot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (FacebookBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (FriendlyCrawler) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (GPTBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Google-Extended) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (GoogleOther) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (GoogleOther-Image) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (GoogleOther-Video) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (ICC-Crawler) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (ImagesiftBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Meta-ExternalAgent) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Meta-ExternalFetcher) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (OAI-SearchBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (PerplexityBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (PetalBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Scrapy) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (Timpibot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (VelenPublicWebCrawler) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (YouBot) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (anthropic-ai) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (cohere-ai) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (facebookexternalhit) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (img2dataset) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (omgili) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (omgilibot) [NC]
+RewriteRule .* https://nocommercialuse.org/ [L]
\ No newline at end of file
diff --git a/feed.xml b/feed.xml
index d325ee01..a108322e 100644
--- a/feed.xml
+++ b/feed.xml
@@ -4,7 +4,7 @@
     <subtitle>Leilukin&#39;s personal website.</subtitle>
     <link href="https://leilukin.com/feed.xml" rel="self"/>
     <link href="https://leilukin.com"/>
-    <updated>2024-08-19T15:59:53Z</updated>
+    <updated>2024-08-19T16:23:22Z</updated>
     <id>https://leilukin.com/</id>
     <author>
         <name>Leilukin</name>