# File: robots.txt — v1.00.690 (2026-08-18) WP-03 paginazione crawlable
Sitemap:  https://www.aziende.it/sitemap.xml
Sitemap: https://www.aziende.it/sitemap-blog.xml

# --- Crawler AI: accesso CONSENTITO alle pagine contenuto (valore di citazione GEO) ---
# Throttling/anti-abuso gestito a livello applicativo (rate-limit), non con blocco totale.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /search
Disallow: /*?pag=
Disallow: /admin/
Disallow: /pagina.php
Disallow: /dettagli.php
Disallow: /profiles/
Disallow: /domande/
Disallow: /accounts/
Disallow: /directory/
Disallow: /cart$
Disallow: /ordini$
Disallow: /login$
Disallow: /pay$
Disallow: /profilo$
Disallow: /fatture$
Disallow: /down_loads.php

# --- Bot AI/scraper ancora ESCLUSI (nessun valore di citazione o troppo aggressivi) ---
User-agent: Bytespider
User-agent: Applebot-Extended
User-agent: cohere-ai
User-agent: Diffbot
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: YouBot
Disallow: /

# --- Regole generali ---
User-agent: *
Allow: /
Disallow: /search
Disallow: /admin/
Disallow: /pagina.php
Disallow: /dettagli.php
Disallow: /profiles/
Disallow: /domande/
Disallow: /accounts/
Disallow: /directory/
Disallow: /cart$
Disallow: /ordini$
Disallow: /login$
Disallow: /pay$
Disallow: /profilo$
Disallow: /fatture$
Disallow: /down_loads.php