#----------------------------------------------------------------------------- # robots.txt #----------------------------------------------------------------------------- # This file is under RCS control; use 'co -l robots.txt' (unix command) to # reserve it for modification, and 'ci -u robots.txt' to replace it when you # are finished. Use 'rcsdiff robots.txt' to see differences between the # working version and the checked-in version, and 'rlog robots.txt' to get a # summary of changes that have been made. # # $Id: robots.txt,v 1.7 2009/05/06 06:11:09 kos025 Exp $ #----------------------------------------------------------------------------- User-Agent: ATNFCrawler Allow: /_Mail_Archives/ # Mail_Archives Disallow: /_Server/ # wwwstat server statistics files Allow: /aips++/ # huge AIPS++ document tree Disallow: /cgi-bin/ # for internal use Disallow: /common/ # all common files Allow: /computing/news/nexus Allow: /computing/nexus Allow: /computing/policy.html # big documentation tree Allow: /computing/software/Midas/ # big documentation tree Allow: /computing/software/aips++/ # big documentation tree Allow: /computing/software/miriad/ # big documentation tree Disallow: /database/ # database files, no html Disallow: /feedback/ Disallow: /images/library/ Disallow: /ims/ Disallow: /includes/ #Disallow: /internal/ # should we allow any scans here? Disallow: /internal/computing/web/statistics/ # Contains links to pages we may not want searched Disallow: /internal/computing/web/test/ Disallow: /internal/computing/pmwiki/ Disallow: /internal/test/ Disallow: /java/ # test progs only Disallow: /linkscan/ Allow: /local/ # restricted local pages Allow: /management/ Allow: /meetings/ Allow: /mnrf/restricted/ Allow: /news/webnew/ # What's New pages **WHY DISALLOW? Allow: /overview/computing/ Allow: /overview/management/ Disallow: /people/Neil.Killeen/test/ Disallow: /people/Neil.Killeen/test/ELARA_3/mitk/ Disallow: /people/allrite/ Disallow: /people/dbarnes/.private/ Allow: /people/mcalabre/data/ Allow: /people/rnorris/COLA/data/ Allow: /projects/mnrf/restricted/ Allow: /research/pulsar/psrlunch/ User-Agent: * Disallow: /_Mail_Archives/ # Mail_Archives Disallow: /_Server/ # wwwstat server statistics files Disallow: /aips++/ # huge AIPS++ document tree Disallow: /cgi-bin/ # for internal use Disallow: /common/ # all common files Disallow: /computing/news/nexus Disallow: /computing/nexus Disallow: /computing/policy.html # big documentation tree Disallow: /computing/software/Midas/ # big documentation tree Disallow: /computing/software/aips++/ # big documentation tree Disallow: /computing/software/miriad/ # big documentation tree Disallow: /database/ # database files, no html Disallow: /feedback/ Disallow: /images/library/ Disallow: /ims/ Disallow: /includes/ #Disallow: /internal/ # should we allow any scans here? Disallow: /internal/computing/web/statistics/ # Contains links to pages we may not want searched Disallow: /internal/computing/web/test/ Disallow: /internal/computing/pmwiki/ Disallow: /internal/test/ Disallow: /java/ # test progs only Disallow: /linkscan/ Disallow: /local/ # restricted local pages Disallow: /management/ Disallow: /meetings/ Disallow: /mnrf/restricted/ Disallow: /news/webnew/ # What's New pages **WHY DISALLOW? Disallow: /overview/computing/ Disallow: /overview/management/ Disallow: /people/Neil.Killeen/test/ Disallow: /people/Neil.Killeen/test/ELARA_3/mitk/ Disallow: /people/allrite/ Disallow: /people/dbarnes/.private/ Disallow: /people/mcalabre/data/ Disallow: /people/rnorris/COLA/data/ Disallow: /projects/mnrf/restricted/ Disallow: /research/pulsar/psrlunch/