User-agent: *
Allow: /

# The map is one app whose state lives in query strings (`?postalCode=` on every /alue and
# /kunta page, `?metric=` on every /sijoitukset page). Googlebot was following them, rendering
# ~3 000 copies of the SPA and fetching the API on each: JSON was 49% of crawl requests and
# 2.09 GB of downloads, because /api/v1/postal-codes is 18.4 MB every time. Google throttled
# the host, and 2 323 real pages stayed at "Discovered - currently not indexed" - never
# fetched. Nothing indexable carries a query string; every sitemap URL is path-based.
Disallow: /*?
Disallow: /api/

# AI crawlers and agents are explicitly welcome (data is CC BY 4.0, see /api/v1/license
# and /llms.txt) — named here so a future tightening of the wildcard rule can't silently
# block them.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

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