# Matchble robots.txt
# Strategia: accessibile ai motori di ricerca tradizionali, blocco AI scrapers

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

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ─── Social preview crawler ────────────────────────────────────────────────
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Slackbot
Allow: /

# ─── AI / Answer engine (bloccati — scraping training data) ──────────
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: AnthropicAI
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# ─── Catch-all + zone riservate ────────────────────────────────────────────
User-agent: *
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/
Disallow: /studio/
Disallow: /auth/
Disallow: /onboarding/
Disallow: /staff/
Disallow: /club/*/join/
Disallow: /rivendica/
Disallow: /*?token=
Disallow: /*?reset=

# ─── Sitemap (matchble.app canonical, non Supabase edge function) ─────────
Sitemap: https://matchble.app/sitemap.xml
Sitemap: https://matchble.app/sitemap-index.xml