# TRT Index - public clinic directory
# Search engines are welcome. Wholesale scrapers and AI training crawlers are not.
# Reuse of this directory data without prior written permission is prohibited
# under our Terms of Service: https://trtindex.com/terms/

User-agent: *
Allow: /
Disallow: /api/
Disallow: /go/
Disallow: /sx/
Disallow: /search-index.json
Disallow: /zip-index.json
Disallow: /scraper-trap/

# AI training / LLM scrapers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

# Generic scraping toolkits / SEO harvesters
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SeekportBot
Disallow: /

Sitemap: https://trtindex.com/sitemap-index.xml