# robots.txt — taginsight.com (site vitrine)
# Objectif : couper les crawlers IA / scrapers qui consomment de la bande passante
# sans valeur SEO. Les moteurs classiques (Google, Bing) restent autorisés.
# NB : seuls les bots "polis" respectent ce fichier. Les scrapers malveillants
# l'ignorent — pour ceux-là il faut un WAF (cf. migration Cloudflare Pages).

# --- Crawlers IA / entraînement de modèles ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# --- Tout le reste : autorisé (Googlebot, Bingbot, etc.) ---
User-agent: *
Allow: /

Sitemap: https://www.taginsight.com/sitemap.xml