User-agent: *
# Directories
Disallow: /add-items/*
Disallow: /faq-page/*
Disallow: /es/faq-page/*
Disallow: /es/faq-ss-info-page-sp/*

# Paths (clean URLs)
Disallow: /account/password/
Disallow: /user/logout/
Disallow: /user/login/token/*
Disallow: */undefined/*

# ============================================================
# AI CRAWLERS — SEARCHING AND CRAWLING ALLOWED, TRAINING IS BLOCKED
# ============================================================

# ------------------------------
# Allow AI search/chat crawlers
# ------------------------------

# OpenAI Search crawler (ChatGPT Search / SearchGPT)
User-agent: OAI-SearchBot
Allow: /

# OpenAI real-time browsing when users ask ChatGPT to open your site
User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude search crawlers
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /

# Perplexity search bot
User-agent: PerplexityBot
Allow: /

# AI search engines
User-agent: YouBot
Allow: /
User-agent: PhindBot
Allow: /
User-agent: ExaBot
Allow: /
User-agent: AndiBot
Allow: /
User-agent: FirecrawlAgent
Allow: /


# ------------------------------
# Blocking AI training crawlers
# ------------------------------

# OpenAI GPT model training crawler
# (Blocking our content for GPT model training)
User-agent: GPTBot
Disallow: /

# Google Gemini training crawler (not used for Google Search)
User-agent: Google-Extended
Disallow: /

# Common Crawl (feeds many AI training datasets)
User-agent: CCBot
Disallow: /

# ByteDance/TikTok training bot
User-agent: Bytespider
Disallow: /

# Amazon training & research AI crawler
User-agent: Amazonbot
Disallow: /


# ============================================================
# SITEMAPS
# ============================================================
Sitemap: https://www.enfamil.com/sitemap.xml
Sitemap: https://www.enfamil.com/es/sitemap.xml
Sitemap: https://www.enfamil.com/video_sitemap.xml
Sitemap: https://www.enfamil.com/es/video_sitemap.xml