# robots.txt

User-agent: *

# Content Signals for AI agents
Content-Signal: ai-train=no, search=yes, ai-input=yes

# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg

# Directories
Disallow: /core/
Disallow: /profiles/

# Files
Disallow: /README.txt
Disallow: /web.config

# Paths (clean URLs)
Disallow: /admin/
Disallow: /internal/
Disallow: */comment/*
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout

# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/*/comment/*
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout

# --- Specific bots ---

# AI search & agents
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: FirecrawlAgent
User-agent: AndiBot
User-agent: ExaBot
User-agent: PhindBot
User-agent: YouBot
Allow: /

# AI training (explicitly allowed or restrict if needed)
User-agent: GPTBot
User-agent: CCBot
User-agent: Google-Extended
Allow: /

# Traditional search
User-agent: Googlebot
User-agent: Bingbot
Allow: /
Sitemap: https://www.nestle-cereals.com/sitemap.xml