# The Syrian House — robots.txt
# https://www.thesyrianhouse.ca

# Default: allow all crawlers across the site
User-agent: *
Allow: /

# AI assistants & LLM crawlers — allowed to read the site, including
# /llms.txt, but keep legal boilerplate out of training/answer data
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
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Search engines — keep /llms.txt out of Google/Bing search results.
# (The AI crawlers above are unaffected and may still read this file.)
User-agent: Googlebot
User-agent: Bingbot
Allow: /
Disallow: /llms.txt

# Google Ads Bot
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
Allow: /

# Sitemap location
Sitemap: https://www.thesyrianhouse.ca/sitemap.xml