# Allow crawlers from the Internet Archive
User-agent: archive.org_bot	# Internet Archive
User-agent: ia_archiver		# Internet Archive
Allow: /

# Allow legit crawlers and fetchers
User-agent: AhrefsBot			# Ahrefs / Yep
User-agent: Applebot			# Apple
User-agent: Baiduspider			# Baidu
User-agent: Bingbot			# Bing
User-agent: DuckDuckBot			# DuckDuckGo
User-agent: EcosiaBot			# Ecosia
User-agent: facebookexternalhit		# Facebook
User-agent: Googlebot			# Google
User-agent: Googlebot-Image		# Google
User-agent: Googlebot-Video		# Google
User-agent: IbouBot			# Ibou
User-agent: Kagibot			# Kagi
User-agent: MojeekBot			# Mojeek
User-agent: NaverBot			# Naver
User-agent: PetalBot			# Petal
User-agent: Qwantbot			# Qwant
User-agent: SeznamBot			# Seznam
User-agent: Slack-ImgProxy		# Slack
User-agent: Slackbot			# Slack
User-agent: Slackbot-LinkExpanding	# Slack
User-agent: Slurp			# Yahoo!
User-agent: Sogou web spider		# Sogou
User-agent: YandexBot			# Yandex
Allow: /

# Disallow AI crawlers, scrapers, and other bad actors
# No use closing the barn door after the horse is gone
User-agent: Bytespider			# ByteDance
User-agent: CCBot			# Common Crawl
User-agent: ChatGPT-User		# OpenAI
User-agent: CMS-Checker
User-agent: ev-crawler			# Headline
User-agent: fasthttp
User-agent: Go-http-client
User-agent: GPTBot			# OpenAI
User-agent: IAB-Tech-Lab		# IAB
User-agent: meta-externalads		# Meta
User-agent: meta-externalagent		# Meta
User-agent: meta-externalfetcher	# Meta
User-agent: meta-webindexer		# Meta
User-agent: NetcraftSurveyAgent		# Netcraft
User-agent: OAI-SearchBot		# OpenAI
User-agent: python-httpx
User-agent: python-requests
User-agent: Python-urllib
User-agent: SaluteBot			# Sberbank
Disallow: /

Sitemap: https://massimiliano.farinetti.eu/sitemap.xml