# robots.txt — Dil Tak Indian Cuisine and Bar
# https://www.dil-tak.ca/

# ==========================================
# All crawlers
# ==========================================
User-agent: *
Allow: /

# Static site — no app directories to crawl
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/

# Block tracking / faceted URL parameters (duplicate content)
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*
Disallow: /*?*utm_*
Disallow: /*?*fbclid=*
Disallow: /*?*gclid=*

# llms.txt must stay crawlable for AI agents, but should not
# appear as a search result. Mirror this with an
# X-Robots-Tag: noindex response header at the server if possible.
Noindex: /llms.txt

# ==========================================
# AI / LLM crawlers — full content access
# ==========================================
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: Bytespider
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ==========================================
# 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: YandexBot
Crawl-delay: 10

# ==========================================
# Sitemap
# ==========================================
Sitemap: https://www.dil-tak.ca/sitemap.xml