# Haydar Pasha Pizza — robots.txt
# https://haydarpashapizza.ca/

# ==========================================
# Default rules for all crawlers
# ==========================================
User-agent: *
Allow: /
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*
Disallow: /llms.txt

# Keep llms.txt out of search indexes (non-standard but honoured by some crawlers).
# Production should also serve llms.txt with the HTTP header: X-Robots-Tag: noindex
Noindex: /llms.txt

# ==========================================
# AI / LLM crawlers
# ==========================================
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: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: Applebot-Extended
User-agent: Bytespider
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /llms.txt
Noindex: /llms.txt

# ==========================================
# Google Ads
# ==========================================
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ==========================================
# Heavy / aggressive bots — throttle
# ==========================================
User-agent: Baiduspider
Crawl-delay: 10

User-agent: YandexBot
Crawl-delay: 10

# ==========================================
# Sitemap
# ==========================================
Sitemap: https://haydarpashapizza.ca/sitemap.xml