# Robots.txt for RULLino - Patente B Simulator
# Allow all legitimate crawlers

User-agent: *
Allow: /

# Sitemap location
Sitemap: https://www.rullino.it.com/sitemap.xml

# Crawl delay for respectful crawling
Crawl-delay: 1

# Allow access to all static assets
Allow: *.css
Allow: *.js
Allow: *.png
Allow: *.jpg
Allow: *.jpeg
Allow: *.gif
Allow: *.svg
Allow: *.ico
Allow: *.woff
Allow: *.woff2
Allow: *.webp
Allow: *.avif

# Allow access to essential pages
Allow: /
Allow: /ru
Allow: /it
Allow: /sitemap.xml
Allow: /robots.txt
Allow: /favicon.ico

# Disallow admin areas and sensitive content
Disallow: /admin/
Disallow: /api/
Disallow: /private/
Disallow: /temp/
Disallow: /.git/
Disallow: /node_modules/
Disallow: /*.json$
Disallow: /*?*
Disallow: /*.log$
Disallow: /*.tmp$
Disallow: /seo-info.html
Disallow: /test-sitemap.html
Disallow: /debug-sitemap.html

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

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

User-agent: Slurp
Allow: /
Crawl-delay: 1

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

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

# Mobile crawlers
User-agent: Googlebot-Mobile
Allow: /

User-agent: Googlebot-Image
Allow: /

# Block unwanted and aggressive bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# Allow social media crawlers
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Allow important SEO tools
User-agent: Screaming Frog SEO Spider
Allow: /
Crawl-delay: 5

# Host directive for international sites
Host: https://www.rullino.it.com