# ===============================
# robots.txt - ImperiaPost.it
# Ultimo aggiornamento: 07/11/2025
# Ottimizzato per SEO Google 2025
# ===============================

# --- Regole per tutti i crawler ---
User-agent: *

# WordPress - blocco cartelle di sistema
Disallow: /cgi-bin/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/

# Consenti risorse critiche per rendering (Core Web Vitals)
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/themes/*.css
Allow: /wp-content/themes/*.js
Allow: /wp-content/plugins/*.css
Allow: /wp-content/plugins/*.js

# Pagine di ricerca e contenuto duplicato
Disallow: /search/
Disallow: /?s=
Disallow: /page/
Disallow: */feed/
Disallow: */trackback/
Disallow: */attachment/
Disallow: /author/*/page/

# Parametri URL da evitare (tracking e duplicati)
Disallow: /*?replytocom
Disallow: /*?utm_*
Disallow: /*?fbclid=
Disallow: /*&

# File e pagine WordPress sensibili
Disallow: /wp-*.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt

# --- Google Bot (massima priorità) ---
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /wp-content/uploads/

User-agent: Googlebot-News
Allow: /

User-agent: Mediapartners-Google
Allow: /

User-agent: AdsBot-Google
Allow: /
# --- FACEBOOK - tutti gli user-agent (obbligatorio 2026) ---
User-agent: facebookexternalhit
Allow: /


User-agent: facebot
Allow: /

User-agent: FacebookExternalHit
Allow: /

User-agent: Facebook App
Allow: /
# --- Bing ---
User-agent: Bingbot
Allow: /
Crawl-delay: 5

# --- Archivi web (importante per giornali) ---
User-agent: ia_archiver
Allow: /

# --- Bot aggressivi e AI scraper da bloccare ---
User-agent: AhrefsBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SEMrushBot
Disallow: /

User-agent: SemrushBot-SA
Disallow: /

User-agent: MegaIndex.ru
Disallow: /

User-agent: megaindex.com
Disallow: /

User-agent: SEOkicks-Robot
Disallow: /

User-agent: SISTRIX
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Wget
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: YoudaoBot
Disallow: /

User-agent: Yeti
Disallow: /

User-agent: pimonster
Disallow: /

User-agent: pricepi
Disallow: /

User-agent: Cuam
Disallow: /

User-agent: Pixray-Seeker
Disallow: /

User-agent: UptimeRobot
Disallow: /

User-agent: SimplePie
Disallow: /

User-agent: Heritrix
Disallow: /

User-agent: Vagabondo
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Applebot-Extended
Disallow: /


User-agent: omgili
Disallow: /

User-agent: Diffbot
Disallow: /

# --- Sitemap XML ---
Sitemap: https://imperiapost.it/sitemap_index.xml

# ===============================
# Note tecniche novembre 2025:
# - CSS/JS consentiti per Core Web Vitals
# - Parametri URL bloccati contro duplicati
# - AI bot bloccati (GPTBot, CCBot, Claude, Applebot-Extended)
# - Archive.org consentito per storico articoli
# - Crawl-delay solo per Bing (Google lo ignora)
# - NO duplicati bot SEO (rimossi Allow conflittuali)
# ===============================