# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ========================================
# Robots.txt ottimizzato per WordPress + Yoast + AdSense
# Dominio: www.economia-italia.com
# Aggiornato: Giugno 2026 (Versione 9.5+)
# ========================================

# ✅ Permetti esplicitamente ad AdSense di analizzare il sito per i banner
User-agent: Mediapartners-Google
Allow: /

# ========================================
# 🤖 Configurazione bilanciata per Network Economia Italiacom
# ========================================================
User-agent: AhrefsBot
Crawl-delay: 10
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /*/trackback/
Disallow: /*/feed/

# 🚫 Blocca scraper e crawler SEO aggressivi
User-agent: MJ12bot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Rogerbot
Disallow: /

# 🚫 Blocca motori di ricerca esteri invasivi (Sintassi Corretta)
User-agent: Baiduspider
Disallow: /

User-agent: Yandex
User-agent: YandexBot
Disallow: /

User-agent: Sogou spider
User-agent: Sogou web spider
Disallow: /

# 🚫 Blocca il training AI e i motori di ricerca AI (Preservando il traffico diretto)
User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Anthropic-ai
User-agent: ClaudeBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /


User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: CCBot
Disallow: /

# 🌍 Regole generali per tutti gli altri crawler (incluso Googlebot standard e ChatGPT-User)
User-agent: *

# 🚫 Blocca l'accesso alle cartelle di sistema e log-in
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/

# 🚫 Blocca query di ricerca, parametri inutili e stringhe tracciamento
Disallow: /?s=
Disallow: /search/
Disallow: /?rest_route=
Disallow: /*blackhole
Disallow: /?blackhole
Disallow: /*?replytocom
Disallow: /*?utm_*
Disallow: /*?fbclid=*

# ✅ Consenti esplicitamente le risorse necessarie al rendering delle pagine
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/

# 🗺️ Indica la sitemap principale per l'indicizzazione
Sitemap: https://www.economia-italia.com/sitemap_index.xml