# robots.txt
# Goal: allow broad crawling (for SEO & AI) while protecting admin endpoints.

# --- Global defaults ---
User-agent: *
Allow: /

# --- Major search engines (explicit allow just for clarity) ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

# --- International bots you may want indexed by ---
User-agent: Baiduspider
Allow: /
User-agent: Yandex
Allow: /

# --- Common LLM / AI crawlers (explicitly allowed) ---
# OpenAI
User-agent: GPTBot
Allow: /
User-agent: GPTBot-Image
Allow: /

# Google’s data-use extension (controls Gemini’s training access)
User-agent: Google-Extended
Allow: /

# Apple’s data-use extension (for Apple Intelligence training)
User-agent: Applebot-Extended
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Common Crawl (foundation for many AI datasets)
User-agent: CCBot
Allow: /

# Amazon, ByteDance, LinkedIn, Facebook (previews / AI)
User-agent: Amazonbot
Allow: /
User-agent: Bytespider
Allow: /
User-agent: LinkedInBot
Allow: /
User-agent: FacebookBot
Allow: /

# --- Sitemaps (crucial for discovery) ---
Sitemap: https://shamrockheatingandcooling.com/sitemap-index.xml

# Note: Avoid Crawl-delay