# Robots.txt pour DocxGen
# https://docxgen.fr

# ─── Default crawler policy ───────────────────────────────────────────────────
User-agent: *
Allow: /

# Pages publiques accessibles
Allow: /
Allow: /features
Allow: /pricing
Allow: /contact
Allow: /secteurs/

# Pages d'authentification : non-indexables (faible valeur SEO)
Disallow: /login
Disallow: /signup

# Bloquer l'accès aux ressources internes
Disallow: /api/
Disallow: /onlyoffice/
Disallow: /cache/
Disallow: /coauthoring/
Disallow: /doc/

# Bloquer les pages d'application authentifiées
Disallow: /dashboard
Disallow: /documents
Disallow: /templates
Disallow: /settings
Disallow: /editor

# ─── AI / LLM crawlers — explicitly allowed ──────────────────────────────────
# Explicit Allow rules signal intent to AI search platforms (citation eligibility).

User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /dashboard
Disallow: /editor
Crawl-delay: 2

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /dashboard
Disallow: /editor
Crawl-delay: 2

User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: Claude-Web
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/
Disallow: /dashboard
Disallow: /editor

User-agent: CCBot
Allow: /
Disallow: /api/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

User-agent: Bytespider
Disallow: /

# Sitemap
Sitemap: https://docxgen.fr/sitemap.xml