User-agent: *
Allow: /

# Pages HTML systeme: ne pas bloquer ici. Elles portent deja une meta noindex,
# que Google doit pouvoir crawler pour les sortir proprement de l'index.
Disallow: /api/
Disallow: /wp-json/
Disallow: /wp-content/
Disallow: /.well-known/captcha/
Disallow: /.well-known/sgcaptcha/
Disallow: /cdn-cgi/

# AI / LLM crawlers — explicitly allowed (we want to be cited by AI answer engines).
# See /llms.txt and /llms-full.txt for AI-oriented context.
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: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

Sitemap: https://formateur-pro.fr/sitemap-index.xml

# LLM resources
# https://formateur-pro.fr/llms.txt
# https://formateur-pro.fr/llms-full.txt