# robots.txt for University of Southern Indiana (usi.edu) # https://www.usi.edu/robots.txt # ----------------------------------------------- # Default: allow crawling but protect admin/search areas # ----------------------------------------------- User-agent: * Disallow: /search Disallow: /search/ Disallow: /search?q= Disallow: /search/?q= Disallow: /umbraco/ Disallow: /umbraco-preview/ Disallow: /install/ Disallow: /mini-profiler-resources/ Disallow: /admin/ # ----------------------------------------------- # Block known bad/aggressive bots # ----------------------------------------------- # Vulnerability scanners & attack tools User-agent: Nikto Disallow: / User-agent: sqlmap Disallow: / User-agent: Havij Disallow: / User-agent: masscan Disallow: / User-agent: zgrab Disallow: / # Email harvesters User-agent: EmailCollector Disallow: / User-agent: EmailSiphon Disallow: / User-agent: WebBandit Disallow: / User-agent: EmailWolf Disallow: / # Aggressive/disreputable scrapers User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: SeznamBot Disallow: / User-agent: PetalBot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: serpstatbot Disallow: / User-agent: SEOkicks Disallow: / User-agent: 008 Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: Buck Disallow: / User-agent: magpie-crawler Disallow: / User-agent: SiteExplorer Disallow: / User-agent: YouBot Disallow: / User-agent: Omgilibot Disallow: / # ----------------------------------------------- # Sitemap # ----------------------------------------------- Sitemap: https://www.usi.edu/sitemap.xml