# advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Wikipedia work bots: User-agent: IsraBot Disallow: User-agent: Orthogaffe Disallow: # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. 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: / # # Sorry, wget in its recursive mode is a frequent problem. # Please read the man page and use it properly; there is a # --wait option you can use to set the delay between hits, # for instance. # User-agent: wget Disallow: / # # The 'grub' distributed client has been *very* poorly behaved. # User-agent: grub-client Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: / # # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / User-agent: * Disallow: /chalmers-sv Disallow: /chalmers-en Disallow: /insidan Disallow: /ait/Internt Disallow: /am/Internt Disallow: /ap/Internt Disallow: /arch/Internt Disallow: /biocenter/Internt Disallow: /chem/Internt Disallow: /cec/Internt Disallow: /cee/Internt Disallow: /clc/Internt Disallow: /cse/Internt Disallow: /ee/Internt Disallow: /fc/Internt Disallow: /fp/Internt Disallow: /ghz/Internt Disallow: /industrihogskolan/Internt Disallow: /its/Internt Disallow: /gmv/Internt Disallow: /materials/Internt Disallow: /math/Internt Disallow: /mmt/Internt Disallow: /mc2/Internt Disallow: /ppd/Internt Disallow: /rss/Internt Disallow: /s2/Internt Disallow: /safer/Internt Disallow: /smt/Internt Disallow: /soft/Internt Disallow: /tme/Internt User-agent: SiteSeekerCrawler/1.0 Allow: /insidan Allow: /ait/Internt Allow: /am/Internt Allow: /ap/Internt Allow: /arch/Internt Allow: /biocenter/Internt Allow: /chem/Internt Allow: /cec/Internt Allow: /cee/Internt Allow: /clc/Internt Allow: /cse/Internt Allow: /ee/Internt Allow: /fc/Internt Allow: /fp/Internt Allow: /ghz/Internt Allow: /industrihogskolan/Internt Allow: /its/Internt Allow: /gmv/Internt Allow: /materials/Internt Allow: /math/Internt Allow: /mmt/Internt Allow: /mc2/Internt Allow: /ppd/Internt Allow: /rss/Internt Allow: /s2/Internt Allow: /safer/Internt Allow: /smt/Internt Allow: /soft/Internt Allow: /tme/Internt