# Happily Hosted - robots.txt
# Last updated: November 2025

# Default rules for all crawlers
User-agent: *
Allow: /
Crawl-delay: 1

# Block admin and system directories
Disallow: /dashboard/
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /temp/
Disallow: /email/
Disallow: /*.sql$
Disallow: /*.log$

# Block order API endpoints (but allow order pages)
Disallow: /order/api/

# Allow important pages
Allow: /packages/
Allow: /dedicated-servers/
Allow: /hosting-reseller/
Allow: /about/
Allow: /contact/
Allow: /faq/
Allow: /order/

# ============================================
# AI Crawler Permissions (Explicitly Allow)
# ============================================

# OpenAI GPT crawlers
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Google AI (Bard/Gemini training)
User-agent: Google-Extended
Allow: /

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

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Common Crawl (used by many AI systems)
User-agent: CCBot
Allow: /

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

# Meta AI
User-agent: FacebookBot
Allow: /

# Microsoft/Bing AI
User-agent: bingbot
Allow: /

# ============================================
# Sitemap Location
# ============================================
Sitemap: https://www.happilyhosted.com/sitemap.xml