# Clay Oven Restaurant – robots.txt
# Site: https://www.clayovenexpress.ca/
# Last Updated: 2026-05-02

# ---- Default rules for all crawlers ----
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /config/
Disallow: /search/
Disallow: /api/
Disallow: /static/
Disallow: /logs/
Disallow: /*?*
Disallow: /*&*
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
# llms.txt is intended for LLM agents only and must not be indexed.
# Disallow blocks crawl, and an X-Robots-Tag: noindex header should be set
# at the server / hosting layer for /llms.txt for full noindex enforcement.
Disallow: /llms.txt
Noindex: /llms.txt

# ---- AI / LLM training & crawler bots ----
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /llms.txt
Noindex: /llms.txt

# ---- 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: Yandex
Crawl-delay: 10

# ---- Sitemap ----
Sitemap: https://www.clayovenexpress.ca/sitemap.xml