# robots.txt — realtorpeterlaw.com
# Companion to the Automated-Access clause in the Terms of Service.
# See: https://www.realtorpeterlaw.com/terms/#automated

# ---- AI / LLM training crawlers: disallowed site-wide ----
# The AI-training reservation of rights in the Terms stands independently
# of whether any given crawler honours the directives below.

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: YouBot
Disallow: /

# ---- General-purpose search crawlers: allowed (indexing, not training) ----
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# ---- Everyone else ----
User-agent: *
Allow: /
Disallow: /contact/thanks

Sitemap: https://www.realtorpeterlaw.com/sitemap-index.xml