# robots.txt — info.belgia
# Updated: 2026-06-16 (guide + editorial production cutover)
# Policy: allow search + citation bots; deny model-training + bulk-dataset bots.
# This file is a public policy signal, not an access-control mechanism.
# For rights reservation details see /.well-known/tdmrep.json and /mentiuni-legale.html.
# For compact crawler/LLM project context see /.well-known/ai-context.json.
# For editorial update methodology see /cum-se-actualizeaza.html.

# ── Search engines ────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# ── AI search / citation (user-triggered or search-surface crawlers) ──────────
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ── Training / bulk-dataset crawlers — DISALLOWED ─────────────────────────────
# Rights reserved under EU TDM rules. See /.well-known/tdmrep.json.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# ── Default: allow all other crawlers ─────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /admin.html
Disallow: /dashboard-demo.html
Disallow: /parteneri.html
Disallow: /promoveaza.html
Disallow: /cont-firma.html
Disallow: /cont-firma-invitatie.html
Disallow: /cont-firma-stare.html

# ── Content-Signal (Cloudflare / rights declaration) ──────────────────────────
# search=yes  → classic search indexing allowed
# ai-input=yes → AI search / citation / user-grounded answers allowed
# ai-train=no  → model training and bulk TDM reserved (EU copyright/TDM rules)
Content-Signal: search=yes, ai-input=yes, ai-train=no

# ── Sitemap ───────────────────────────────────────────────────────────────────
Sitemap: https://ghid.popmedia.digital/sitemap.xml