# ==============================================
# ROBOTS.TXT - motomag.com
# Mise à jour : 15/02/2026
# Protection anti-scraping IA + règles WordPress
# ==============================================

# --- RÈGLES GÉNÉRALES (existantes) ---
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ==============================================
# BLOCAGE DES BOTS IA - SCRAPING / ENTRAINEMENT
# ==============================================

# OpenAI (ChatGPT, GPT)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Common Crawl (dataset utilisé par les IA)
User-agent: CCBot
Disallow: /

# Google AI (Gemini, Bard) - distinct de Googlebot search
User-agent: Google-Extended
Disallow: /

# Anthropic (Claude)
User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

# Perplexity AI
User-agent: PerplexityBot
Disallow: /

# Amazon AI
User-agent: Amazonbot
Disallow: /

# Meta AI (Facebook)
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Apple AI (Siri, Apple Intelligence)
User-agent: Applebot-Extended
Disallow: /

# Cohere AI
User-agent: cohere-ai
Disallow: /

# Bytedance / TikTok AI
User-agent: Bytespider
Disallow: /

# AI divers
User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: omgili
Disallow: /

User-agent: YouBot
Disallow: /

# Scrapers agressifs connus
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# ==============================================
# SITEMAP
# ==============================================
Sitemap: https://www.motomag.com/sitemap_index.xml