User-agent: *
Allow: /
Disallow: /admin

# Answer engines are allowed, on purpose. Parkadoo exists to be found, and
# these crawlers are how a page gets cited and linked in an AI answer — they
# are not the ones that take content for model training. Their own docs say
# so: PerplexityBot "is designed to surface and link websites in search
# results" (perplexity.ai/hub/technical-faq), and ChatGPT-User fetches a page
# because a person asked about it (platform.openai.com/docs/bots). Blocking
# them removed Parkadoo from those answers while protecting nothing.
User-agent: PerplexityBot
Disallow: /admin
Crawl-delay: 5

User-agent: ChatGPT-User
Disallow: /admin

# AI training / data-collection crawlers — blocked entirely. Does not affect
# search visibility: Googlebot/Bingbot (used for search indexing) and
# Mediapartners-Google/AdsBot-Google (used to serve ads) are separate user
# agents from the ones below and are still covered by the "Allow: /" default.
# A crawler matching its own group ignores the "*" group, so the two allowed
# above repeat the /admin rule.
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Amazonbot
Disallow: /

# Ahrefs is allowed: it's the tool we use to audit this site and see our own
# backlinks, so blocking it only blinds us. Both its crawlers obey Crawl-Delay
# (ahrefs.com/robot). 5 seconds keeps them to about 12 URLs a minute, under the
# 25-a-minute limit the on-demand car pages enforce per IP (src/lib/bot-guard.mjs)
# — Site Audit's own default is 30 a minute, which would trip it. A crawler that
# matches its own group ignores the "*" group, so /admin is repeated here.
User-agent: AhrefsBot
Disallow: /admin
Crawl-delay: 5

User-agent: AhrefsSiteAudit
Disallow: /admin
Crawl-delay: 5

# Aggressive SEO/aggregator crawlers — no benefit to Parkadoo, just load.
User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SerpstatBot
Disallow: /

User-agent: MegaIndex
Disallow: /

Sitemap: https://parkadoo.com/sitemap-index.xml