# PolskiAngielski.eu — robots.txt
# Dwujęzyczne Kompendium Gramatyki — polskiangielski.eu
# Last updated: Wrzesień 2026

# Allow all standard search engines
User-agent: *
Allow: /
Disallow: /404

# Sitemaps
Sitemap: https://polskiangielski.eu/sitemap-index.xml
Sitemap: https://polskiangielski.eu/sitemap.xml

# AI/LLM Crawlers — Selectively Permitted (Attribution-capable)
User-agent: GPTBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

# Blocked AI Crawlers (no attribution, aggressive scraping)
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

# References
# LLMs-Full: https://polskiangielski.eu/llms-full.txt
# LLMs: https://polskiangielski.eu/llms.txt