# robots.txt for https://squeakycleanturf.com/
# Purpose: Maximize visibility in AI/answer engines (AEO) while keeping admin and quote-form areas private.

# --- Global defaults (most search engines & bots) ---
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Additional private paths:
Disallow: /wp-login.php
Disallow: /?s=
Disallow: /search/
Disallow: /thank-you/
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/

# --- Explicit ALLOW for important AI/answer-engine crawlers ---

# OpenAI (ChatGPT browsing / training)
User-agent: GPTBot
Allow: /

# OpenAI search crawler (powers ChatGPT search results)
User-agent: OAI-SearchBot
Allow: /

# ChatGPT user-triggered fetcher (link previews & browsing)
User-agent: ChatGPT-User
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (used by multiple LLMs)
User-agent: CCBot
Allow: /

# Google AI access (Gemini, Vertex AI) — uses this opt-in token
User-agent: Google-Extended
Allow: /

# Google's non-search fetcher and standard crawlers
User-agent: GoogleOther
Allow: /

User-agent: Googlebot
Allow: /

# Microsoft Bing / Copilot
User-agent: Bingbot
Allow: /

User-agent: BingPreview
Allow: /

# Apple (Siri/Spotlight) + AI extension
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta AI (Llama training & Meta AI assistants)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Mistral AI
User-agent: MistralAI-User
Allow: /

# You.com
User-agent: YouBot
Allow: /

# (Optional) Social link previewers
User-agent: FacebookExternalHit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

# --- Sitemaps ---
Sitemap: https://squeakycleanturf.com/sitemap_index.xml