# National Albanian Registry — robots.txt
# Posture: open to all reputable search and AI crawlers. We want to be cited.

User-agent: *
Allow: /
Disallow: /api/
# PostHog reverse-proxy base — only /ph/* is proxied; not a content path
Disallow: /ph
Disallow: /admin
Disallow: /register/step-
Disallow: /thank-you
Disallow: /unsubscribe
Disallow: /regional-leads/kit/
Disallow: /pitch
# Magic-link short redirects — single-use tokens, not for indexing
Disallow: /v/
Disallow: /vo/
# Member portal — auth-gated; bare /account 302s to /account/login
Disallow: /account
Disallow: /sq/account
# Org portal — auth-gated; bare /org 302s to /org/login.
# MUST stay end-anchored ($) + subtree (/org/) — a bare "Disallow: /org" is a
# prefix match under Google/RFC 9309 longest-match semantics and blocks the
# entire public Organizations Hub (/organizations, /sq/organizations and every
# org detail page) from crawling.
Disallow: /org$
Disallow: /org/
Disallow: /sq/org$
Disallow: /sq/org/
# Legacy redirect aliases (301 to canonical paths) — block to keep them out of GSC
Disallow: /home
Disallow: /index
Disallow: /handbook
Disallow: /press-kit
Disallow: /sq/press-kit
# Non-HTML resources — GSC was crawling these (correctly never indexing them);
# block to save crawl budget. Browsers/clients ignore robots.txt, so the
# blog client-search fetch and <track> subtitles keep working.
Disallow: /blog/search-index.json
Disallow: /docs/
Disallow: /press/videos/

# AI crawlers — explicitly allowed for citation visibility (GEO/AIO strategy)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Amazonbot
Allow: /

# Sitemaps
Sitemap: https://albanianregistry.org/sitemap-index.xml