# Standard search engine crawlers
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

# AI training and data harvesting crawlers: content in, nothing back.
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: MetaBot
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: Sogou Pic Spider
Disallow: /

User-agent: GrokBot
Disallow: /

User-agent: xAI-Bot
Disallow: /

User-agent: Deepseekbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# AI answer engines: they fetch a page to answer a question and cite
# the source. Allowed on purpose -- being cited is the point of publishing.
User-agent: OAI-SearchBot
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

User-agent: ChatGPT-User
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

User-agent: PerplexityBot
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

User-agent: Perplexity-User
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

User-agent: Claude-User
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

User-agent: Claude-SearchBot
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

User-agent: DuckAssistBot
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /auth/

Sitemap: https://portaur.com/sitemap.xml