# Robots.txt for ThinkCrypt - Software Development Company
# Website: https://thinkcrypt.dev

# Allow all search engines to crawl the site
User-agent: *
Allow: /

# Block access to admin and private areas
Disallow: /admin/
Disallow: /api/
Disallow: /_next/
Disallow: /private/
Disallow: /.well-known/

# Block crawling of search and filter pages to avoid duplicate content
Disallow: /search
Disallow: /*?category=*
Disallow: /*?filter=*
Disallow: /*?sort=*
Disallow: /*?page=*

# Allow crawling of specific important paths
Allow: /api/portfolio$
Allow: /api/blog$

# Sitemap location
Sitemap: https://thinkcrypt.dev/sitemap.xml

# Crawl delay (optional - helps with server load)
Crawl-delay: 1

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 0

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

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Block specific bot types that might not be useful
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /