# GeoAxis robots.txt
# Default: allow crawling so the site appears in search + LLM answer engines
# (Google, Bing, ChatGPT, Claude, Perplexity, Gemini, Meta AI, etc).
# Block only dodgy scrapers: dataset hoarders and abusive bots.
# robots.txt is voluntary — real enforcement happens at the WAF / auth layer.

Sitemap: https://geoaxis.ai/sitemap.xml

# ---- Blocked: dataset hoarders / abusive scrapers ----
# Listed individually because most crawlers honor only their own UA block.
# SEO tools (Semrush, Ahrefs, DataForSEO, Serpstat) are intentionally NOT
# blocked: blocking them blinds us from rank-tracking our own site in
# those tools, and the data they expose is the data we need to compete.

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: SeekportBot
Disallow: /

# ---- Default: everyone else allowed ----
# Authenticated surfaces (dashboard, login, claim) and the JSON API are protected
# at the auth + WAF layer. We don't enumerate those paths here on purpose:
# robots.txt is voluntary and listing them just gives recon to scanners.
User-agent: *
Allow: /