# Robots.txt for Pirate Tic-Tac-Toe Game
# Updated: 2025-12-22
# International SEO: English content with hreflang tags for global markets

# Search Engine Crawlers
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: msnbot
Allow: /
Crawl-delay: 1

User-agent: msnbot-media
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

# Social Media Crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

# General Rule
User-agent: *
Allow: /
Crawl-delay: 1

# Disallow any duplicate/backup directories
Disallow: /project-files/
Disallow: /files/
Disallow: /*-backup/
Disallow: /*-old/

# AI / LLM Training Crawlers — block while allowing search crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

# SEO / marketing bots (optional)
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Sitemap Location
Sitemap: https://piratetictactoe.com/sitemap.xml

# Preferred Domain (HTTPS)
Host: https://piratetictactoe.com

# Note: Regional Suggestion System
# Our site suggests regional pages (/uk, /us, /ca, /au) via client-side banner
# This is NOT an automatic redirect - users choose whether to accept
# All content is accessible to everyone regardless of location
# No cloaking: crawlers see the same content as users