# WebConforme — robots.txt
# Politique : autorisation explicite des crawlers IA pour maximiser
# la citation dans ChatGPT, Claude, Perplexity, Gemini, Grok, etc.
# Référence llms.txt : https://webconforme.fr/llms.txt
# Référence llms-full.txt : https://webconforme.fr/llms-full.txt

# --- Règle générique ---
User-agent: *
Allow: /
Disallow: /dashboard/
Disallow: /admin/
Disallow: /api/
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /pdf-envoye

# --- Crawlers OpenAI / ChatGPT ---
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# --- Crawlers Anthropic / Claude ---
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# --- Crawlers Perplexity ---
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Crawlers Google (Gemini / Bard) ---
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# --- Crawlers Apple Intelligence ---
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Crawlers Meta (Llama / Meta AI) ---
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# --- Crawlers Amazon (Alexa / Q) ---
User-agent: Amazonbot
Allow: /

# --- Common Crawl (datasets entrainement modèles) ---
User-agent: CCBot
Allow: /

# --- Crawlers ByteDance / Doubao ---
User-agent: Bytespider
Allow: /

# --- Crawlers Cohere ---
User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# --- Crawlers Diffbot (Knowledge Graph commercial) ---
User-agent: Diffbot
Allow: /

# --- Crawlers Mistral ---
User-agent: MistralAI-User
Allow: /

# --- Crawlers DuckDuckGo ---
User-agent: DuckAssistBot
Allow: /

# --- Crawlers You.com ---
User-agent: YouBot
Allow: /

# --- Sitemap & ressources LLM ---
Sitemap: https://webconforme.fr/sitemap.xml