# NEVO Content - Robots.txt optimisé SEO 2025
# Dernière mise à jour: 2025-01-27

# === RÈGLES GÉNÉRALES ===
User-agent: *
Allow: /

# 🚀 Pages stratégiques à crawler en PRIORITÉ
Allow: /blog/
Allow: /seo-tools
Allow: /pricing
Allow: /facturation
Allow: /contact
Allow: /lexique/


# 🌍 Support multilingue complet
Allow: /en/
Allow: /es/
Allow: /de/
Allow: /it/

# 📱 PWA et assets critiques
Allow: /manifest.json
Allow: /sw.js
Allow: /favicon.ico
Allow: /images/
Allow: /css/
Allow: /js/

# 🚫 Blocage intelligent et sécurisé
Disallow: /admin
Disallow: /api/
Disallow: /mes-articles
Disallow: /admin-blog-dashboard
Disallow: /admin-lexique-dashboard
Disallow: /login
Disallow: /auth
Disallow: /private/
Disallow: /_next/
Disallow: /.well-known/

# 🚫 Paramètres tracking et sessions
Disallow: /*?*utm_
Disallow: /*?*fbclid
Disallow: /*?*gclid
Disallow: /*?*ref=
Disallow: /*?*source=
Disallow: /*?*campaign=
Disallow: /*?session
Disallow: /*?token
Disallow: /*?auth

# 🚫 Formats non-SEO
Disallow: /*.pdf$
Disallow: /*.zip$
Disallow: /*.exe$
Disallow: /*.dmg$

# 🚫 Versions de test et staging
Disallow: /test/
Disallow: /staging/
Disallow: /dev/
Disallow: /beta/

# === BOTS SPÉCIALISÉS 2025 ===

# 🤖 Google - Configuration premium
User-agent: Googlebot
Allow: /
Crawl-delay: 1

# 🤖 Bing - Optimisation Microsoft
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# 🤖 ChatGPT/OpenAI - Content IA (important 2025)
User-agent: GPTBot
Allow: /blog/
Allow: /seo-tools
Disallow: /api/
Disallow: /admin

# 🤖 Claude AI (Anthropic)
User-agent: Claude-Web
Allow: /blog/
Allow: /
Disallow: /api/
Disallow: /admin

# 🤖 Bard/Gemini (Google AI)
User-agent: Google-Extended
Allow: /blog/
Allow: /
Disallow: /api/

# 🤖 Meta AI
User-agent: Meta-ExternalAgent
Allow: /blog/
Allow: /
Disallow: /admin

# 🚫 Bots malveillants et scrapers
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: YandexBot
Crawl-delay: 2

# 🚫 IA bots training non autorisés
User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

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

# === SITEMAPS ET INDEXATION ===
# 🗺️ Sitemaps principaux
Sitemap: https://nevo-content.com/sitemap.xml

# 🗺️ Sitemaps spécialisés (si créés)
# Sitemap: https://nevo-content.com/sitemap-blog.xml
# Sitemap: https://nevo-content.com/sitemap-images.xml

# === OPTIMISATIONS PERFORMANCE 2025 ===
# ⚡ Crawl optimal pour gros sites
Crawl-delay: 1

# 📊 Heure de crawl préférée (optionnel)
# Visit-time: 0200-0400

# === REDIRECTIONS ET CANONICAL ===
# 🔄 Host canonique (évite les duplicatas)
Host: nevo-content.com

# === CLEAN URLs POLICY ===
# ✨ URLs propres seulement
Disallow: /*?
Allow: /blog/*
Allow: /en/blog/*
Allow: /es/blog/*
Allow: /de/blog/*
Allow: /it/blog/*

# === COMMENTAIRES ET CONTACT ===
# 📧 Contact pour questions robots.txt
# Contact: romain@nevo-content.com

# 🏢 Informations légales
# Legal: https://nevo-content.com/mentions-legales