# robots.txt – erikamaugeri.com
# Ultimo aggiornamento: 2025

# ------------------------------------
# CRAWLER STANDARD
# ------------------------------------

User-agent: *
Disallow: /assets/
Disallow: /privacy-policy.html
Disallow: /cookie-policy.html

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


# ------------------------------------
# AI – CONSENTITI (indicizzazione e risposte AI)
# ------------------------------------

# OpenAI – ChatGPT / GPT
User-agent: GPTBot
Allow: /

# OpenAI – ChatGPT browsing
User-agent: ChatGPT-User
Allow: /

# Anthropic – Claude
User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

# Google – Gemini / AI Overviews / SGE
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

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

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

# Mistral AI (LeChat)
User-agent: MistralAI-User
Allow: /


# ------------------------------------
# AI – BLOCCATI (scraper aggressivi o data broker)
# ------------------------------------

# Common Crawl (dataset grezzo, usato per training non selettivo)
User-agent: CCBot
Disallow: /

# ByteDance / TikTok AI (non trasparente sull'uso dei dati)
User-agent: Bytespider
Disallow: /

# Diffbot (estrazione dati commerciale)
User-agent: Diffbot
Disallow: /

# Omgili / Webz.io (data broker)
User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# PetalBot (Huawei, utilizzo non chiaro)
User-agent: PetalBot
Disallow: /

# Scrapy generico
User-agent: Scrapy
Disallow: /