# Robots.txt for Cursis (https://www.cursis.in/)
# Protection from Automated Data Scraping & AI Model Harvesting

# AI & LLM Scraping Bots Protection
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

# General Search Engines & Crawlers
User-agent: *
Disallow: /api/
Disallow: /dashboard/
Disallow: /dashboard/*
Allow: /
Allow: /privacy
Allow: /terms
Allow: /login
Allow: /signup

# Host & Sitemap
Host: https://www.cursis.in
Sitemap: https://www.cursis.in/sitemap.xml