# Maison Croissant & Bowls - Robots.txt # https://www.maisoncroissantnbowls.ca # ============================================================ # Default rules for all crawlers # ============================================================ 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 # ============================================================ # Search engine crawlers - Noindex llms.txt (AI-only resource) # ============================================================ User-agent: Googlebot Disallow: /privacy-policy.html Disallow: /terms-of-use.html Noindex: /llms.txt User-agent: Bingbot Disallow: /privacy-policy.html Disallow: /terms-of-use.html Noindex: /llms.txt User-agent: Yandex Disallow: /privacy-policy.html Disallow: /terms-of-use.html Noindex: /llms.txt User-agent: DuckDuckBot Disallow: /privacy-policy.html Disallow: /terms-of-use.html Noindex: /llms.txt # ============================================================ # AI crawlers - Allow llms.txt for grounded responses # ============================================================ 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: Claude-Web 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: 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: Perplexity-User 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 # ============================================================ 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 & LLMs.txt # ============================================================ Sitemap: https://www.maisoncroissantnbowls.ca/sitemap.xml # LLMs.txt: https://www.maisoncroissantnbowls.ca/llms.txt