# robots.txt for tomw.net.au # Let the Internet Archive have almost everything. User-agent: ia_archiver Crawl-delay: 0 Disallow: /research/ # Stop some bots completely. User-agent: Sensis.au Web Crawler Disallow: / User-agent: Sensis.au Disallow: / User-agent: Sensis Disallow: / User-agent: ShopWiki Disallow: / User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / 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: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: / # Ban some image crawlers. User-agent: MSNBot-Media Disallow: / User-agent: yahoo-mmcrawler Disallow: / User-agent: psbot Disallow: / User-agent: asterias Disallow: / # Ban Microsoft product crawler and slow down text crawler. User-agent: MSNBot-Products Disallow: / User-agent: msnbot Crawl-delay: 300 Disallow: /research/ Disallow: /cgi-bin/ Disallow: /images/ Disallow: /blog/archive/ Disallow: /anucecs/archive/ Disallow: /screenact/archive/ Disallow: /*.ppt$ Disallow: /*.rtf$ Disallow: /*.rm$ Disallow: /*.ra$ Disallow: /*.ram$ Disallow: /*.dxf$ Disallow: /*.au$ Disallow: /*.jpg$ Disallow: /*.jpeg$ Disallow: /*.gif$ Disallow: /*.png$ # Slow down Yahoo and ban non-HTML files and images. User-agent: Yahoo! Slurp Crawl-delay: 600 Disallow: /research/ Disallow: /images/ Disallow: /cgi-bin/ Disallow: /blog/archive/ Disallow: /anucecs/archive/ Disallow: /screenact/archive/ Disallow: /*.ppt$ Disallow: /*.rtf$ Disallow: /*.rm$ Disallow: /*.ra$ Disallow: /*.ram$ Disallow: /*.dxf$ Disallow: /*.au$ Disallow: /*.jpg$ Disallow: /*.jpeg$ Disallow: /*.gif$ Disallow: /*.png$ # Allow Google to crawl images but not non-HTML files. User-agent: Googlebot-Image Crawl-delay: 0 Disallow: /research/ User-agent: Googlebot Crawl-delay: 0 Disallow: /research/ Disallow: /cgi-bin/ Disallow: /blog/archive/ Disallow: /anucecs/archive/ Disallow: /screenact/archive/ Disallow: /*.ppt$ Disallow: /*.rtf$ Disallow: /*.rm$ Disallow: /*.ra$ Disallow: /*.ram$ Disallow: /*.dxf$ Disallow: /*.au$ Disallow: /*.pdf$ # Other crawlers ban non-HTML files and images. Slow down a little. User-agent: * Crawl-delay: 10 Disallow: /research/ Disallow: /cgi-bin/ Disallow: /images/ Disallow: /blog/archive/ Disallow: /anucecs/archive/ Disallow: /screenact/archive/ Disallow: /2000/bat.ppt Disallow: /2000/icarba.ppt Disallow: /2000/iim2000.ppt Disallow: /2000/iim2000.rtf Disallow: /2000/ipub.ppt Disallow: /2000/isup.ppt Disallow: /2000/pt.ppt Disallow: /2000/pt/pt.rm Disallow: /2000/scsp.ppt Disallow: /2000/yxml.ppt Disallow: /2000/yxml2.ppt Disallow: /2001/bat2001.ppt Disallow: /2001/eal/keynote.ppt Disallow: /2001/eal/notb2b.ppt Disallow: /2001/esb/invoice.rtf Disallow: /2001/itv.ppt Disallow: /2001/wf.ppt Disallow: /2001/wwgw/wireless.ppt Disallow: /2002/acra.ppt Disallow: /2002/atoxml.ppt Disallow: /2002/ebcwxml.ppt Disallow: /2002/edm.ppt Disallow: /2002/fit.ppt Disallow: /2002/maa.ppt Disallow: /2002/mka.ppt Disallow: /2002/nbt.ppt Disallow: /2003/bws.ppt Disallow: /2003/xmlstd.ppt Disallow: /2003/xmltech.ppt Disallow: /as/apan.ppt Disallow: /gsr/gsrit.ppt Disallow: /intrnt.rtf Disallow: /irc/irc1intr.au Disallow: /irc/irc1rm.au Disallow: /irc/irc5.au Disallow: /nt/nt.pdf Disallow: /nt/ntad.rtf Disallow: /nt/ntflyr.rtf Disallow: /nt/ntposter.doc Disallow: /nt/nts.ppt Disallow: /papers/ccit99.rtf Disallow: /papers/outint.rtf Disallow: /tomwlcme.au Disallow: /travel/ausalps1.au Disallow: /travel/balloon1.au Disallow: /uso/uso.pdf Disallow: /uso/usocvr.rtf Disallow: /uso/usoflyr.rtf Disallow: /uso/w3d.ppt Disallow: /uso/w3d.rtf