# The Builder Market - robots.txt
# https://thebuildermarket.com

# Sitemaps
Sitemap: https://thebuildermarket.com/sitemap-index.xml

# Default rules for all crawlers
User-agent: *
Allow: /
Disallow: /cdn-cgi/
Disallow: /auth/
Disallow: /account/
Disallow: /dashboard/
Disallow: /checkout/
Disallow: /payment/
Disallow: /search?
Disallow: /*?page=
Disallow: /*?sort=
Disallow: /*?filter=

# Legacy URLs - prefer new SEO-friendly URLs
# /l/* redirects to /us/*
# /pros/lists/* redirects to /us/*/*
# /pros/recommended/* redirects to /guides/cities/*/*

# Googlebot - no restrictions beyond defaults
User-agent: Googlebot
Allow: /

# Bingbot - no restrictions beyond defaults
User-agent: Bingbot
Allow: /

# Applebot - no restrictions beyond defaults
User-agent: Applebot
Allow: /

# GPTBot (OpenAI)
User-agent: GPTBot
Allow: /

# Google-Extended (Gemini training)
User-agent: Google-Extended
Allow: /

# Claude-Web (Anthropic)
User-agent: Claude-Web
Allow: /

# CCBot (Common Crawl)
User-agent: CCBot
Allow: /

# Block aggressive/unwanted crawlers
User-agent: oBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Yandexbot
Disallow: /

User-agent: Dotbot
Disallow: /

User-agent: Seznam
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AhrefsBot
Crawl-delay: 5

User-agent: SemrushBot
Crawl-delay: 5

User-agent: DataForSeoBot
Crawl-delay: 5

# Host directive (legacy, but still respected by some crawlers)
Host: https://thebuildermarket.com