← back to Restaurant Directory

public/robots.txt

83 lines

# LA County Eats — robots policy
# Search engines (Google, Bing, DuckDuckGo) WELCOME on the public detail pages.
# AI training crawlers BLOCKED. Bulk scrape endpoints BLOCKED for everyone.
# Cloudflare WAF + nginx UA rules enforce this beyond the polite-bot honor system.

User-agent: *
Disallow: /api/
Disallow: /healthz

# ─── AI training crawlers — full block ──────────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# ─── SEO / link-graph scrapers — full block ─────────────────────────────
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /