ErrorDocument 404 /404.html
Header set Cache-Control "max-age=31536000, public"
Header set Cache-Control "no-cache, public"
RewriteEngine on
# Block bad bots
RewriteCond %{HTTP_USER_AGENT} (AI2Bot) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (Ai2Bot-Dolma) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (Amazonbot) [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} (ISSCyberRiskCrawler) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (ImagesiftBot) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (Kangaroo.*Bot) [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} (Sidetrade.*indexer.*bot) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (Timpibot) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (VelenPublicWebCrawler) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} (Webzio-Extended) [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} (iaskspider/2.0) [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]