# https://www.robotstxt.org/robotstxt.html

User-agent: Amazonbot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: omgili
Disallow: /
 
User-agent: omgilibot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: ClaudeBot
Disallow: /
 
User-agent: Claude-Web
Disallow: /
 
User-agent: anthropic-ai
Disallow: /
 
User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: YandexAdditional
Disallow: /

User-agent: YandexAdditionalBot
Disallow: /

User-agent: TurnitinBot
Disallow: /

# General rules for all other bots
User-agent: *

# Place allows first to avoid bots skipping after Disallow: /
# Allow exactly the homepage
Allow: /$
# Allow the homepage with any query parameters
Allow: /?*

Allow: /posts/*
Allow: /resources/*
Allow: /a/*
Allow: /alerts/*
Allow: /assets/*
Allow: /landing/*
Allow: /agencies/*/groups/*

# Now block everything else
Disallow: /