# # robots.txt for http://www.slstudents.org # User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: wget Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: / # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # if your bot supports such a thing using the 'Crawl-delay' or another # instruction, please let us know. # User-agent: * Disallow: /sri_lankan_other_institutions.htm Disallow: /canada_resources.htm Disallow: /usa_resources.htm Disallow: /sri_lankan_schools.htm Disallow: /sri_lankan_students_associations.htm Disallow: /student_resources.php Disallow: /cache/ Disallow: /student_list.php Disallow: /student_list_info.php Disallow: /student_resources.php Disallow: /student_record.php Disallow: /jump.php Disallow: /login/lostpw Disallow: /register Disallow: /act.htm Disallow: /lsat.htm Disallow: /toefl.htm Disallow: /toefl2.htm Disallow: /ielts.htm Disallow: /gre.htm Disallow: /gmat.htm Disallow: /sat.htm Disallow: /mcat.htm Disallow: /psat.htm Disallow: /forums/memberlist.php Disallow: /forums/profile.php Disallow: /forums/posting.php # *at least* 2 second please. preferably more :D Crawl-delay: 2