# robots.txt - nosmagazine.it
# Aggiornato: Aprile 2026

# -----------------------------------------------
# Facebook Scraper - Accesso completo consentito
# -----------------------------------------------
User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

# -----------------------------------------------
# Altri crawler social e SEO - Accesso consentito
# -----------------------------------------------
User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Slackbot
Allow: /

# -----------------------------------------------
# Bot SEO principali - Accesso consentito
# -----------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: bingbot
Allow: /

# -----------------------------------------------
# Bot malevoli e scraper indesiderati - Bloccati
# -----------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# -----------------------------------------------
# Regola generale per tutti gli altri crawler
# -----------------------------------------------
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /tmp/
Disallow: /include/
Disallow: /config/

# -----------------------------------------------
# Sitemap
# -----------------------------------------------
Sitemap: https://www.nosmagazine.it/sitemap.xml