# ============================================================
# robots.txt — thinkai.it
# Ultimo aggiornamento: luglio 2026
# Strategia: accesso pieno a ricerca tradizionale e AI retrieval
#            via User-agent: *; blocco esplicito per training puro,
#            agenti Google, scraper e SEO crawler
# ============================================================

Sitemap: https://www.thinkai.it/sitemap_index.xml

# --------------------------------------------------
# REGOLE GENERALI
# Lette da tutti i bot non elencati nei blocchi
# successivi: motori di ricerca tradizionali, bot AI
# di retrieval (PerplexityBot, OAI-SearchBot,
# ChatGPT-User, ClaudeBot, GPTBot, Claude-Web,
# Claude-SearchBot, YouBot, PhindBot, DuckAssistBot,
# Bravebot, Applebot, facebookexternalhit).
# --------------------------------------------------
User-agent: *
Allow: /wp-admin/admin-ajax.php
Allow: /wp-includes/*.css
Allow: /wp-includes/*.js
Allow: /wp-content/themes/*.css
Allow: /wp-content/themes/*.js
Allow: /wp-content/plugins/*.css
Allow: /wp-content/plugins/*.js
Allow: /wp-content/uploads/
Allow: /llms.txt
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /*?s=
Disallow: /search/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /*/embed/
Disallow: /*?attachment_id=
Disallow: /*?replytocom=
Disallow: /*?p=
Disallow: /*&p=
Disallow: /*?paged=
Disallow: /*?preview=
Disallow: /*?filtering=

# --------------------------------------------------
# SCRAPER, AD-TECH E BOT INUTILI
# --------------------------------------------------
User-agent: Amazonbot
Disallow: /

User-agent: Yandex
Disallow: /

User-agent: YandexAdditional
Disallow: /

User-agent: YandexAdditionalBot
Disallow: /

User-agent: proximic
Disallow: /

User-agent: captify-crawler
Disallow: /

User-agent: SentiBot
Disallow: /

User-agent: Friendica
Disallow: /

User-agent: PostGooBot
Disallow: /

User-agent: SeltzSitemapFetcher
Disallow: /

User-agent: AudigentAdBot
Disallow: /

User-agent: weborama-fetcher
Disallow: /

User-agent: SleepBot
Disallow: /

User-agent: IbouBot
Disallow: /

User-agent: Sogou
Disallow: /

# --------------------------------------------------
# TOOL E LIBRERIE DI SCRAPING
# --------------------------------------------------
User-agent: Scrapy
Disallow: /

User-agent: python-requests
Disallow: /

User-agent: curl
Disallow: /

User-agent: wget
Disallow: /

User-agent: libwww-perl
Disallow: /

User-agent: Go-http-client
Disallow: /

User-agent: Apache-HttpClient
Disallow: /

User-agent: Java
Disallow: /

User-agent: Sidetrade indexer
Disallow: /

User-agent: webz.io
Disallow: /

# --------------------------------------------------
# ESTENSIONI NON STANDARD
# Non appartengono al protocollo robots.txt ufficiale.
# Incluse come segnale verso i sistemi che le supportano.
# --------------------------------------------------
LLMs: https://www.thinkai.it/llms.txt
LLMs-full: https://www.thinkai.it/llms-full.txt

# VigIA LLMs
# llms.txt: https://www.thinkai.it/llms.txt