# robots.txt per exxagon.it
# Ultima modifica: 2026

# Regole generali per tutti i crawler
User-agent: *
Allow: /

# Blocca directory comuni che non dovrebbero essere indicizzate
Disallow: /admin/
Disallow: /private/
Disallow: /tmp/
Disallow: /cache/
Disallow: /backup/
Disallow: /logs/
Disallow: /includes/
Disallow: /config/
Disallow: /database/
Disallow: /cgi-bin/
Disallow: /.git/
Disallow: /node_modules/

# Blocca file comuni (NON i .txt: necessari per llms.txt e robots.txt)
Disallow: /*.log$
Disallow: /*.zip$
Disallow: /*.sql$
Disallow: /*.bak$

# Consenti esplicitamente file importanti
Allow: /robots.txt
Allow: /llms.txt
Allow: /sitemap.xml
Allow: /sitemap*.xml
Allow: /*.css$
Allow: /*.js$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$
Allow: /*.ico$
Allow: /*.pdf$

# Regole specifiche per bot comuni
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 2

User-agent: Slurp
Allow: /
Crawl-delay: 2

# Crawler AI — accesso esplicito consentito
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Googlebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Applebot-Extended
Allow: /

# Blocca bot indesiderati
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# Riferimento alla sitemap
Sitemap: https://www.exxagon.it/sitemap.xml