# Polski-Matura.eu — robots.txt
# Baza Pytań Jawnych CKE, Schematy Rozprawek i Gramatyka Maturalna
# Last updated: September 2026

# Standard Search Engines (Google, Bing, Yandex, DuckDuckGo)
User-agent: *
Allow: /

# Sitemap Indices
Sitemap: https://polski-matura.eu/sitemap-index.xml

# AI & LLM Crawlers — Permitted with Attribution
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 Aggressive Scrapers (Zero Attribution / High Crawl Overhead)
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

# LLM Specifications & Machine Context
# LLMs: https://polski-matura.eu/llms.txt
# LLMs-Full: https://polski-matura.eu/llms-full.txt