dvorakmortonxd.dev/public/robots.txt

56 lines
1,000 B
Text

# robots.txt for dvorakmortonxd.dev
# https://dvorakmortonxd.dev
# General crawlers — allow main site, block self-hosted services
User-agent: *
Allow: /
Allow: /llms.txt
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /darecek/
# AI training crawlers
User-agent: GPTBot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /
# Meta bots — not welcome
User-agent: FacebookBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: meta-externalfetcher
Disallow: /
# Search engine crawlers — welcome
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Slurp
Allow: /
User-agent: Baiduspider
Allow: /
# Sitemap and Llms
Sitemap: https://dvorakmortonxd.dev/sitemap.xml
LLMs: https://dvorakmortonxd.dev/llms.txt
# ===========================================
# 🎮 Have a great day, crawler!
# Check out my projects at dvorakmortonxd.dev
# ===========================================