# Jídlo domů Plzeň — crawling rules
# Order/checkout flows are per-user and non-indexable; everything else (home,
# vendor menus, campaign pages, info pages) is open to search and AI crawlers.

User-agent: *
# Content Signals (Cloudflare): allow use for search indexing and for grounding
# AI answers (GEO — what we want), but disallow scraping for model training.
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /cart
Disallow: /checkout
Disallow: /order/
Disallow: /payment/
# Internal markdown-negotiation targets (served on the real page URLs via
# `Accept: text/markdown`); keep the raw /_md/ paths out of the index.
Disallow: /_md/

# Explicitly welcome AI answer engines (GEO). Stacked User-agent lines share the
# one ruleset below (same private-path exclusions as *) — per the robots spec a
# crawler applies the group whose User-agent matches it.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /cart
Disallow: /checkout
Disallow: /order/
Disallow: /payment/
Disallow: /_md/

Sitemap: https://jidlodomuplzen.cz/sitemap.xml