# Calzone Corner Takeout & Tiffin Service - robots.txt # https://calzonecorner.com # Default rules for all bots User-agent: * Allow: / Disallow: /components/ Disallow: /config/ Disallow: /search/ Disallow: /account/ Disallow: /api/ Disallow: /static/ Disallow: /*?*author=* Disallow: /*?*tag=* Disallow: /*?*month=* Disallow: /*?*view=* Disallow: /*?*format=* # Block legal pages from all crawlers Disallow: /privacy-policy.html Disallow: /terms-of-use.html # Block llms.txt from being indexed by search engines # (AI bots are explicitly allowed below) Disallow: /llms.txt # --------------------------------------------------------------- # Search engine bots (explicit block for /llms.txt and legal pages) # --------------------------------------------------------------- User-agent: Googlebot Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /llms.txt User-agent: Googlebot-Image Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /llms.txt User-agent: Bingbot Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /llms.txt User-agent: Yandex Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /llms.txt User-agent: DuckDuckBot Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /llms.txt # --------------------------------------------------------------- # AI crawlers - allow access to llms.txt but block legal pages # --------------------------------------------------------------- User-agent: GPTBot Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: ChatGPT-User Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: OAI-SearchBot Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: CCBot Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: anthropic-ai Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: ClaudeBot Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: Claude-Web Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: cohere-ai Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: Google-Extended Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: PerplexityBot Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: Applebot-Extended Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ User-agent: meta-externalagent Allow: /llms.txt Allow: / Disallow: /privacy-policy.html Disallow: /terms-of-use.html Disallow: /components/ # --------------------------------------------------------------- # Google Ads bots # --------------------------------------------------------------- User-agent: AdsBot-Google User-agent: AdsBot-Google-Mobile User-agent: AdsBot-Google-Mobile-Apps Allow: / # Crawl delay for heavy bots User-agent: Baiduspider Crawl-delay: 10 User-agent: Sogou Crawl-delay: 10 # --------------------------------------------------------------- # Sitemap # --------------------------------------------------------------- Sitemap: https://calzonecorner.com/sitemap.xml # Note: To reinforce noindex for /llms.txt at the HTTP level, # configure the server to send this response header for /llms.txt: # X-Robots-Tag: noindex