# Faytech North America Robots.txt
# Last Updated: 2025
# Purpose: Welcome AI/LLM crawlers for SEO/GSO/AEO while securing WordPress directories

# ============================================
# SITEMAP DECLARATION
# ============================================
Sitemap: https://www.faytech.us/sitemap_index.xml

# ============================================
# AI/LLM CRAWLERS - FULL ACCESS GRANTED
# ============================================
# These bots are explicitly welcomed for AI search optimization

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

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

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

User-agent: Claude-Web
Allow: /

# Google (Bard/Gemini & Traditional Search)
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Googlebot-Image
Allow: /

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

User-agent: MSNBot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

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

# Meta AI (Facebook/Instagram)
User-agent: facebookexternalhit
Allow: /

User-agent: meta-externalagent
Allow: /

# Apple (Siri & Spotlight)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Amazon Alexa
User-agent: Amazonbot
Allow: /

# Neeva AI Search
User-agent: Neevabot
Allow: /

# Yandex
User-agent: YandexBot
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# ============================================
# LLM TRAINING CONTENT - EXPLICIT ALLOW
# ============================================
# Make sure LLMs can access our specially crafted content

User-agent: *
Allow: /llms.txt
Allow: /wp-content/uploads/
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$
Allow: /*.woff$
Allow: /*.woff2$
Allow: /*.ttf$
Allow: /*.eot$

# ============================================
# WORDPRESS SECURITY - BLOCKED DIRECTORIES
# ============================================
# Protect sensitive WordPress directories and files

User-agent: *
# Core WordPress directories to block
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/themes/

# WordPress files to block
Disallow: /wp-login.php
Disallow: /wp-signup.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php

# Configuration and system files
Disallow: /wp-config.php
Disallow: /.htaccess
Disallow: /readme.html
Disallow: /license.txt

# ============================================
# COMMON SECURITY & PERFORMANCE BLOCKS
# ============================================
# Additional paths commonly blocked for security and performance

User-agent: *
# Search and filter pages (prevent duplicate content)
Disallow: /search/
Disallow: /filter/
Disallow: /*?s=
Disallow: /*?p=
Disallow: /*?attachment_id=
Disallow: /*?replytocom=

# Session and tracking parameters
Disallow: /*?session
Disallow: /*?sid=
Disallow: /*?utm_
Disallow: /*?ref=

# Archive and pagination issues
Disallow: /tag/
Disallow: /author/
Disallow: /feed/
Disallow: /rss/
Disallow: /embed/
Disallow: */trackback/
Disallow: */comment-page-

# Cart and checkout (if e-commerce)
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/

# AJAX and API endpoints
Disallow: /wp-json/
Disallow: /ajax/

# Temporary and private directories
Disallow: /tmp/
Disallow: /temp/
Disallow: /private/
Disallow: /draft/
Disallow: /staging/

# ============================================
# BLOCK MALICIOUS & UNWANTED BOTS
# ============================================
# Known bad actors and resource-wasting crawlers

User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: SEOkicks-Robot
Disallow: /

User-agent: Nuclei
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SiteAuditBot
Disallow: /

# ============================================
# DEFAULT RULE FOR UNKNOWN BOTS
# ============================================
# General access with security restrictions maintained

User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/