# robots.txt — Studio Legale Militare
# Generato automaticamente — 2026-05-18 (v4.30 — Politica C: Selettiva)
# Spec: https://www.rfc-editor.org/rfc/rfc9309 (Robots Exclusion Protocol)
#
# Politica adottata: opt-out training IA / opt-in search-time citation
# Riferimenti normativi: Direttiva UE 2019/790 art. 4 §3 (TDM opt-out)
#   + D.Lgs. 177/2021 art. 70-quater l. 633/1941
#   + Reg. UE 2024/1689 (AI Act)
# Informativa completa: https://www.studiolegalemilitare.it/ai-policy

# ─── Crawler generici ───────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /data/
Disallow: /includes/
Disallow: /vendor/
Disallow: /cerca?
Crawl-delay: 1

# ═══════════════════════════════════════════════════════════════════
#  SEARCH-TIME / INFERENCE-TIME crawler — ALLOW
#  (leggono il sito quando l'utente fa una query realtime,
#   NON memorizzano nei pesi del modello — visibilità AI utile)
# ═══════════════════════════════════════════════════════════════════

# ─── Search engine classici ─────────────────────────────────────────
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Yandex
Allow: /
User-agent: Baiduspider
Allow: /
User-agent: Applebot
Allow: /

# ─── AI search-time / on-demand fetchers ────────────────────────────
# Permessi: leggono il sito SOLO quando un utente fa una domanda
# realtime in ChatGPT Search, Perplexity, Claude Web, Gemini, etc.
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-CloudVertexBot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: KagiBot
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: YouBot
Allow: /
User-agent: Brave-Leo
Allow: /
User-agent: Phind
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /
User-agent: cohere-search-data-crawler
Allow: /

# ═══════════════════════════════════════════════════════════════════
#  TRAINING crawler — DISALLOW
#  (assorbono i contenuti nei dataset di addestramento LLM
#   permanenti; opt-out ex art. 4 §3 Dir. UE 2019/790)
# ═══════════════════════════════════════════════════════════════════

User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Bytespider
Disallow: /

# ─── Sitemaps ────────────────────────────────────────────────────────
Sitemap: https://www.studiolegalemilitare.it/sitemap-index.xml
Sitemap: https://www.studiolegalemilitare.it/sitemap.xml
Sitemap: https://www.studiolegalemilitare.it/sitemap-news.xml
Sitemap: https://www.studiolegalemilitare.it/sitemap-images.xml
Sitemap: https://www.studiolegalemilitare.it/sitemap-faq.xml

# ─── Risorse AI/GEO ─────────────────────────────────────────────────
# llms.txt:           https://www.studiolegalemilitare.it/llms.txt
# llms-full.txt:      https://www.studiolegalemilitare.it/llms-full.txt
# ai.txt:             https://www.studiolegalemilitare.it/ai.txt
# citations.json:     https://www.studiolegalemilitare.it/citations.json
# agents.json:        https://www.studiolegalemilitare.it/agents.json
# carbon.txt:         https://www.studiolegalemilitare.it/carbon.txt
# security.txt:       https://www.studiolegalemilitare.it/.well-known/security.txt
# ai-preferences.txt: https://www.studiolegalemilitare.it/.well-known/ai-preferences.txt
# mcp.json:           https://www.studiolegalemilitare.it/.well-known/mcp.json
# traffic-advice:     https://www.studiolegalemilitare.it/.well-known/traffic-advice
# nodeinfo:           https://www.studiolegalemilitare.it/.well-known/nodeinfo