User-agent: Clickagy Intelligence Bot
Disallow: /

User-agent: Clickagy Intelligence Bot v2
Disallow: /

User-agent: *
Disallow: /admin/

User-agent: Seekport Crawler
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: Dotbot
Disallow:/

User-agent: barkrowler
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: dotbot
Disallow: /

# disable MauiBot (crawler.feedback+wc@gmail.com)
User-agent: MauiBot
Disallow: /

# disable http://law.di.unimi.it/BUbiNG.html
User-agent: BUbiNG
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: ltx71 - (http://ltx71.com/)
Disallow: /

# http://www.majestic12.co.uk/projects/dsearch/mj12bot.php
User-agent: MJ12bot
Disallow: /

# Backlink Analysis
user-agent: AhrefsBot
disallow: /

# https://megaindex.com/crawler
User-agent: MegaIndex.ru
Disallow: /

User-agent: megaindex.com
Disallow: /

# https://www.qwant.com/
User-agent: Qwantify
Disallow: /

User-agent: bingbot
Crawl-delay: 5

User-agent: Yandex
Crawl-delay: 5

User-agent: PetalBot
Crawl-delay: 5

User-agent: SemrushBot
Disallow: /

User-agent: Amazonbot
Crawl-delay: 5

# --- Assistenti AI: recupero in tempo reale, citano la pagina con il link. Ammessi. ---

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Crawler di solo addestramento: nessuna attribuzione, nessun traffico di ritorno.
#     Riuso dei contenuti per training soggetto a licenza, vedi /note_legali. ---

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

Sitemap: https://blog.fogliettoillustrativo.net/sitemap.xml