# robots.txt for http://arXiv.org/ and mirror sites http://*.arXiv.org/ User-agent: * Disallow: /cgi-bin/ Disallow: /ad/ User-agent: Googlebot Allow: /archive Allow: /year Allow: /list Allow: /abs Allow: /pdf Allow: /html Allow: /catchup Disallow: /cgi-bin/ User-agent: Yahoo! Slurp Crawl-delay: 20 Allow: /archive Allow: /year Allow: /list Allow: /abs Disallow: /cgi-bin/