# robots.txt for www.marathoncoach.com
# Updated 2026-10-16. Crawler access is managed here; Cloudflare block toggles are off.

# Default: every crawler not named below may crawl everything except the 404 page.

User-agent: *
Disallow: /404

# Search, AI search, and AI assistant crawlers (explicitly allowed)
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Google-Extended
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: Meta-WebIndexer
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Amazonbot
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: MistralAI-Index
User-agent: MistralAI-User
User-agent: CCBot
User-agent: archive.org_bot
Allow: /
Disallow: /404

# Crawlers with no value for Marathon's search or AI visibility (blocked)
User-agent: Bytespider
User-agent: PetalBot
User-agent: Baiduspider
User-agent: FacebookBot
User-agent: Google-CloudVertexBot
User-agent: Timpibot
User-agent: Novellum
User-agent: Arquivo-web-crawler
Disallow: /


Sitemap: https://www.marathoncoach.com/sitemap.xml