# robots.txt — SMC Salud
# Full crawl access for all search engines AND AI answer engines.
# AI crawlers are explicitly allowed so content appears in Google AI
# Overviews, ChatGPT, Claude, Perplexity, and other generative engines.

# ─── General search engines ───────────────────────────────────────────
User-agent: *
Allow: /

# ─── AI / LLM crawlers — explicitly allowed for AEO / GEO ─────────────
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: cohere-ai
Allow: /

# ─── Additional AI / LLM crawlers — explicitly allowed ────────────────
User-agent: ChatGPT-User
Allow: /

User-agent: Google-CloudVertex
Allow: /

User-agent: YouBot
Allow: /

User-agent: Omgili
Allow: /

User-agent: Omgilibot
Allow: /

User-agent: ImagesiftBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: AI2Bot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Timpibot
Allow: /

User-agent: VelenPublicWebCrawler
Allow: /

User-agent: NewsNow
Allow: /

User-agent: Kangaroo Bot
Allow: /

# ─── Admin / dashboard / utility pages — blocked from indexing ──────────
# These pages are either behind auth, marked noindex, or are operational
# tools that add no SEO value. Language-prefixed wildcard rules cover all
# 10 language variants (en, es, fr, de, it, pt, tr, ar, zh, ru).

Disallow: /*/settings
Disallow: /*/patient-intake
Disallow: /*/payment
Disallow: /*/search
Disallow: /*/site-index
Disallow: /*/language-config
Disallow: /*/translation-dashboard
Disallow: /*/content-coverage
Disallow: /*/performance-dashboard
Disallow: /*/search-engine-registration
Disallow: /*/visa-dashboard
Disallow: /*/translation-audit
Disallow: /*/seo-audit
Disallow: /*/missing-translations
Disallow: /*/cost-estimator

# ─── Sitemap & AI content declarations ─────────────────────────────────
Sitemap: https://smcsalud.org/sitemap.xml
Sitemap: https://smcsalud.org/sitemap-ai.xml