# Indian Flavors Calgary - robots.txt

# ----------------------------------------------------------------------
# Default rules for all crawlers
# ----------------------------------------------------------------------
User-agent: *
Allow: /

# Block crawler-only / system paths
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/

# Block low-value query-string variants (filters, archives, format switches)
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# Keep llms.txt out of search indexes (consumed by AI agents only)
Disallow: /llms.txt

# ----------------------------------------------------------------------
# AI / LLM training crawlers
# ----------------------------------------------------------------------
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: PerplexityBot
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ----------------------------------------------------------------------
# Google Ads crawlers (allow full access for ad quality scoring)
# ----------------------------------------------------------------------
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ----------------------------------------------------------------------
# Heavy / aggressive crawlers - throttle
# ----------------------------------------------------------------------
User-agent: Baiduspider
Crawl-delay: 10

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