# Robots.txt for nuovicomici.com
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /.well-known/
Disallow: /private/
Disallow: /tmp/
Disallow: /*.json$
Disallow: /*?*session*
Disallow: /*?*debug*

# Allow specific resource directories
Allow: /images/
Allow: /public/
Allow: /static/
Allow: /assets/

# Sitemap location
Sitemap: https://nuovicomici.com/sitemap.xml

# Crawl-delay for polite crawling
Crawl-delay: 1

# Allow all major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebot
Allow: /

User-agent: ia_archiver
Allow: /

# Block problematic bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Specific rules for social media crawlers
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Specific rules for image crawlers
User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot-Image
Allow: /

# Wildcard rules for specific file types
Disallow: /*.log$
Disallow: /*.bak$
Disallow: /*.tmp$
Disallow: /*.sql$