Sitemap: http://www.citeulike.org/sitemap.xml # Useless/Evil bots # User-agent: LinkWalker User-agent: NPBot User-agent: sna-0 User-agent: ConveraCrawler User-agent: MJ12bot User-agent: Yahoo Pipes 1.0 User-agent: Yahoo Pipes 2.0 Disallow: / # Google supports wildcards # Without this restriction we just end up with too many pages User-agent: Googlebot Disallow: /copy Disallow: /delete Disallow: /deletenote Disallow: /bibtex/ Disallow: /endnote/ Disallow: /delicious/ Disallow: /bibtex_options/ Disallow: /pdf_options/ Disallow: /login Disallow: /login? Disallow: /login?from Disallow: /logout Disallow: /posturl Disallow: /add Disallow: /post_url.adp Disallow: /posturl2 Disallow: /rss/ Disallow: /search/ Disallow: /search/all Disallow: /nocrawl/ Disallow: /login.do Disallow: /post_known.do Disallow: /post_unknown.do Disallow: /register.do User-agent: MJ12bot Disallow: /copy Disallow: /delete Disallow: /deletenote Disallow: /bibtex/ Disallow: /endnote/ Disallow: /delicious/ Disallow: /bibtex_options/ Disallow: /pdf_options/ Disallow: /login Disallow: /login? Disallow: /login?from Disallow: /logout Disallow: /posturl Disallow: /add Disallow: /post_url.adp Disallow: /posturl2 Disallow: /rss/ Disallow: /search/ Disallow: /search/all Disallow: /nocrawl/ Disallow: /login.do Disallow: /post_known.do Disallow: /post_unknown.do Disallow: /register.do Crawl-delay: 1 User-agent: * Disallow: /copy Disallow: /delete Disallow: /deletenote Disallow: /bibtex/ Disallow: /endnote/ Disallow: /delicious/ Disallow: /bibtex_options/ Disallow: /pdf_options/ Disallow: /login Disallow: /login? Disallow: /login?from Disallow: /logout Disallow: /posturl Disallow: /add Disallow: /post_url.adp Disallow: /posturl2 Disallow: /rss/ Disallow: /search/ Disallow: /search/all Disallow: /nocrawl/ Disallow: /login.do Disallow: /post_known.do Disallow: /post_unknown.do Disallow: /register.do Crawl-delay: 2