# 855TREEMAN robots.txt
# Last updated: April 2026

# ----- Default rules for all bots -----
User-agent: *
Allow: /

# Block WordPress admin and system paths
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/themes/slyfox-astra/

# Block search, filter, and parameter URLs (wasted crawl budget)
Disallow: /?s=
Disallow: /*?replytocom=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Block RSS feed URLs (they were flagged as soft 404s)
Disallow: /*/feed/
Disallow: /feed/
Disallow: /comments/feed/

# Block WordPress API endpoints that return 404
Disallow: /wp-json/pys-facebook/
Disallow: /wp-json/hostinger-reach/

# Block duplicate pagination
Disallow: /page/*/page/

# Block trackback URLs
Disallow: /trackback/
Disallow: /*/trackback/

# Allow important files
Allow: /wp-content/uploads/
Allow: /*.css
Allow: /*.js
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.webp
Allow: /*.svg
Allow: /*.gif

# ----- AI Search Crawlers (ALLOW - for GEO/AI visibility) -----

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

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Google (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /

# Anthropic (Claude)
User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Common Crawl (feeds many AI models)
User-agent: CCBot
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Microsoft (Bing Copilot / Bing Chat)
User-agent: Bingbot
Allow: /

# Meta (Meta AI)
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

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

# Cohere
User-agent: cohere-ai
Allow: /

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

# ----- Bad bots / scrapers (BLOCK) -----
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ----- Sitemap -----
Sitemap: https://855treeman.com/sitemap_index.xml
Sitemap: https://855treeman.com/sitemap.xml