# =====================================================
# ROBOTS.TXT - aeometrix.it
# Ottimizzato per SEO tradizionale + AI Crawlers (2026)
# =====================================================

User-agent: *
Allow: /
Allow: /sitemap.xml
Allow: /llms.txt
Allow: /.well-known/
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/
Disallow: /private/
Disallow: /*?sessionid=
Disallow: /*?utm_

# Crawl-delay per bot generici (opzionale)
Crawl-delay: 10

# =====================================================
# GOOGLE
# =====================================================
User-agent: Googlebot
Allow: /
Allow: /static/
Allow: /assets/
Disallow: /admin/
Disallow: /dashboard/

# =====================================================
# BING
# =====================================================
User-agent: Bingbot
Allow: /
Disallow: /admin/
Disallow: /dashboard/

# =====================================================
# AI / LLM CRAWLERS - Politiche di accesso
# =====================================================

# ✅ OpenAI GPTBot - Consentito per indicizzazione AEO
User-agent: GPTBot
Allow: /
Allow: /llms.txt
Disallow: /dashboard/
Disallow: /admin/
Disallow: /api/internal/

# ✅ Anthropic Claude-Web - Consentito con limitazioni
User-agent: Claude-Web
User-agent: ClaudeBot
Allow: /
Allow: /llms.txt
Disallow: /dashboard/
Disallow: /admin/

# ✅ Google Extended (Gemini, AI Overview)
User-agent: Google-Extended
Allow: /
Allow: /llms.txt
Disallow: /dashboard/

# ✅ PerplexityBot - Consentito per visibilità GEO
User-agent: PerplexityBot
Allow: /
Allow: /llms.txt
Disallow: /dashboard/

# ✅ Common Crawl - Consentito per ricerca accademica
User-agent: CCBot
Allow: /
Allow: /llms.txt
Disallow: /dashboard/
Disallow: /api/

# ❌ Crawler non desiderati (blocco totale)
User-agent: Bytespider
User-agent: DotBot
User-agent: AhrefsBot
User-agent: SemrushBot
Disallow: /

# =====================================================
# SITEMAP
# =====================================================
Sitemap: https://www.aeometrix.it/sitemap.xml