# Sampoq — https://www.sampoq.com
#
# Search crawlers and AI answer engines are welcome. Crawlers that collect
# training corpora are not: they take the work and return neither a link
# nor a reader. Our data is free — the open supply-chain dataset is
# CC BY 4.0 — and attribution is the whole of its price.
#
# Written in the repository (frontend/app/robots.txt/route.ts), not in a
# CDN dashboard, so that any change to it is a change someone can read.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /admin
Disallow: /admin/
Disallow: /verify
Disallow: /reset
Disallow: /embed/
Allow: /
Allow: /stock/
Allow: /stocks
Allow: /country/
Allow: /countries
Allow: /commodity/
Allow: /commodities
Allow: /funds
Allow: /entreprise/
Allow: /fonds-de-commerce
Allow: /supply-chain
Allow: /ai-capex
Allow: /learn
Allow: /community

# Answer engines: yes, on the same terms as any search crawler.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
Disallow: /admin
Disallow: /admin/
Disallow: /verify
Disallow: /reset
Disallow: /embed/
Allow: /
Allow: /stock/
Allow: /stocks
Allow: /country/
Allow: /countries
Allow: /commodity/
Allow: /commodities
Allow: /funds
Allow: /entreprise/
Allow: /fonds-de-commerce
Allow: /supply-chain
Allow: /ai-capex
Allow: /learn
Allow: /community

# Training corpora: no. `Disallow: /` and nothing else — a group that also
# listed Allow paths would be granting what the line above refuses.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Omgilibot
Disallow: /

Host: https://www.sampoq.com
Sitemap: https://www.sampoq.com/sitemap.xml
Sitemap: https://www.sampoq.com/news-sitemap.xml