# BioDataHub robots.txt
# Allow all search engines to crawl the site

User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /.git/
Disallow: /node_modules/
Disallow: /.next/

# Google specific
User-agent: Googlebot
Allow: /

# Bing specific
User-agent: Bingbot
Allow: /

# Crawl delay for all bots (in seconds)
Crawl-delay: 1

# Sitemap location
Sitemap: https://biobuntu.github.io/sitemap.xml
Sitemap: https://biobuntu.github.io/sitemap-index.xml
Sitemap: https://biobuntu.github.io/news-sitemap.xml

# Block bad bots
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /