# 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.
# 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
Allow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
# END Cloudflare Managed Content
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
User-agent: AhrefsBot
User-agent: aiohttp
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: APIs-Google
User-agent: Applebot-Extended
User-agent: archive.org_bot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: barkrowler
User-agent: bl.uk_lddc_bot
User-agent: BLEXBot
User-agent: Buck
User-agent: bytespider
User-agent: CCBot
User-agent: ChatGPT
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: DomainAppender
User-agent: dotbot
User-agent: FacebookBot
User-agent: Feed a Fever
User-agent: GenAI
User-agent: Go-NEB
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GPTBot
User-agent: heritrix
User-agent: HTTrack
User-agent: ia_archiver
User-agent: JamesBOT
User-agent: LCC
User-agent: linkdexbot
User-agent: LinkedInBot
User-agent: ltx71
User-agent: magpie-crawler
User-agent: Mediapartners-Google
User-agent: meta-externalagent
User-agent: MJ12bot
User-agent: oBot
User-agent: omgili
User-agent: omgilibot
User-agent: panscient
User-agent: PerplexityBot
User-agent: RankActiveLinkBot
User-agent: rogerbot
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SemrushBot-BM
User-agent: SemrushBot-CT
User-agent: SemrushBot-SA
User-agent: SemrushBot-SEOAB
User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA
User-agent: serpstatbot
User-agent: spbot
User-agent: special_archiver
User-agent: XoviBot
User-agent: YouBot
User-agent: Zoominfobot
Disallow: /
User-agent: *
Crawl-delay: 1
Disallow: /cgi-bin/
Disallow: /cms/
Disallow: /ehasbrouck.asc
Sitemap: https://hasbrouck.org/sitemap.xml