User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-login.php

User-agent: AhrefsBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: AwarioBot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
Disallow: /

User-agent: Baiduspider
User-agent: Baiduspider-image
User-agent: Baiduspider-video
User-agent: Baiduspider-news
User-agent: Baiduspider-favo
User-agent: Baiduspider-ads
User-agent: Baiduspider-cpro
Disallow: /

User-agent: barkrowler
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: Buck
Disallow: /

# Bytedance
#
# Fairly certain Bytedance does not respect robots.txt, but I'm monitoring.
User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: coccocbot
User-agent: coccocbot-web
User-agent: coccocbot-image
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: FacebookBot
Disallow: /

# Google
#
# The standard GoogleBot, used to crawl the web for their
# search results is allowed. I don't see the value in having
# my content consumed by the others.
User-agent: Google-Extended
User-agent: Googlebot-Image
User-agent: Mediapartners-Google
User-agent: Adsbot-Google
Disallow: /

User-agent: grapeshot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Ioncrawl
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: proximic
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SentiBot
Disallow: /

User-agent: serpstatbot
Disallow: /

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

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: Zoominfobot
Disallow: /