# Malabar Kitchen Peterborough - robots.txt
# https://www.malabarkitchenpeterborough.ca

# ----------------------------------------------------------------------------
# Default directives 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=*

# ----------------------------------------------------------------------------
# AI / LLM crawlers
# Allow site content for AI grounding & answer attribution.
# Legal pages are excluded from AI training to limit liability.
# ----------------------------------------------------------------------------
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: PerplexityBot
User-agent: Applebot-Extended
User-agent: cohere-ai
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

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

# ----------------------------------------------------------------------------
# Throttle heavy crawlers
# ----------------------------------------------------------------------------
User-agent: Baiduspider
Crawl-delay: 10

# ----------------------------------------------------------------------------
# Noindex for /llms.txt
# robots.txt does not support a `Noindex:` directive (deprecated by Google in
# 2019). The correct mechanism for non-HTML files is the X-Robots-Tag HTTP
# header, which is configured in /_headers as:
#     /llms.txt
#       X-Robots-Tag: noindex
# This keeps /llms.txt readable by AI agents while preventing search indexing.
# ----------------------------------------------------------------------------

# ----------------------------------------------------------------------------
# Sitemap location
# ----------------------------------------------------------------------------
Sitemap: https://www.malabarkitchenpeterborough.ca/sitemap.xml