# RankX SEO - robots.txt
# Updated: 2026-02-18

# Default: allow all crawlers
User-agent: *
Allow: /
Crawl-delay: 1

# Google (no delay)
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: Googlebot-Image
Allow: /lovable-uploads/
Allow: /assets/
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.webp$
Allow: /*.svg$

# Bing
User-agent: bingbot
Allow: /
Crawl-delay: 1

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

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# AI / LLM crawlers — full access for citation visibility
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /


# Block aggressive SEO scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Disallow internal/sensitive paths
Disallow: /admin/
Disallow: /api/
Disallow: /private/
Disallow: /src/
Disallow: /node_modules/
Disallow: /.git/

# Block query parameter duplicates
Disallow: /*?utm_*
Disallow: /*?search=*
Disallow: /*?s=*
Disallow: /*?filter=*
Disallow: /*?sort=*

# Sitemap declarations
Sitemap: https://rankx.co/sitemap-index.xml
Sitemap: https://rankx.co/sitemap.xml

# Host
Host: https://rankx.co