# ThanksDoc robots.txt

# All search engines
User-agent: *
Allow: /

# Block sensitive areas
Disallow: /api/
Disallow: /admin/
Disallow: /account/
Disallow: /booking/payment/
Disallow: /*?token=
Disallow: /*?utm_

# Block known bad bots that scrape but don't index
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

# Sitemap
Sitemap: https://thanksdoc.co.uk/sitemap.xml

# Crawl-delay courtesy for less critical bots
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10