User-Agent: * Allow: / Disallow: /cgi-bin # 01March05 Scott P. Hunter Allowed all robots and commented out Searchengineworld entries. # User-agent: * # Disallow: / # Robots.txt file from http://www.searchengineworld.com # # Built from text file http://info.webcrawler.com/mak/projects/robots/active/all.txt # # This restricts access to only known and registered robots. # # User-agent: Mozilla/3.0 (compatible;miner;mailto:miner@miner.com.br) # Disallow: # User-agent: WebFerret # Disallow: # User-agent: Due to a deficiency in Java it's not currently possible # to set the User-agent. # Disallow: # User-agent: no # Disallow: # User-agent: 'Ahoy! The Homepage Finder' # Disallow: # User-agent: Arachnophilia # Disallow: # User-agent: ArchitextSpider # Disallow: # User-agent: ASpider/0.09 # Disallow: # User-agent: AURESYS/1.0 # Disallow: # User-agent: BackRub/*.* # Disallow: # User-agent: Big Brother # Disallow: # User-agent: BlackWidow # Disallow: # User-agent: BSpider/1.0 libwww-perl/0.40 # Disallow: # User-agent: CACTVS Chemistry Spider # Disallow: # User-agent: Digimarc CGIReader/1.0 # Disallow: # User-agent: Checkbot/x.xx LWP/5.x # Disallow: # User-agent: CMC/0.01 # Disallow: # User-agent: combine/0.0 # Disallow: # User-agent: conceptbot/0.3 # Disallow: # User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0 # Disallow: # User-agent: root/0.1 # Disallow: # User-agent: CS-HKUST-IndexServer/1.0 # Disallow: # User-agent: CyberSpyder/2.1 # Disallow: # User-agent: Deweb/1.01 # Disallow: # User-agent: DragonBot/1.0 libwww/5.0 # Disallow: # User-agent: EIT-Link-Verifier-Robot/0.2 # Disallow: # User-agent: Emacs-w3/v[0-9\.]+ # Disallow: # User-agent: EmailSiphon # Disallow: # User-agent: EMC Spider # Disallow: # User-agent: explorersearch # Disallow: # User-agent: Explorer # Disallow: # User-agent: ExtractorPro # Disallow: # User-agent: FelixIDE/1.0 # Disallow: # User-agent: Hazel's Ferret Web hopper, # Disallow: # User-agent: ESIRover v1.0 # Disallow: # User-agent: fido/0.9 Harvest/1.4.pl2 # Disallow: # User-agent: H„m„h„kki/0.2 # Disallow: # User-agent: KIT-Fireball/2.0 libwww/5.0a # Disallow: # User-agent: Fish-Search-Robot # Disallow: # User-agent: Mozilla/2.0 (compatible fouineur v2.0; # fouineur.9bit.qc.ca) # Disallow: # User-agent: Robot du CRIM 1.0a # Disallow: # User-agent: Freecrawl # Disallow: # User-agent: FunnelWeb-1.0 # Disallow: # User-agent: gcreep/1.0 # Disallow: # User-agent: ??? # Disallow: # User-agent: GetURL.rexx v1.05 # Disallow: # User-agent: Golem/1.1 # Disallow: # User-agent: Gromit/1.0 # Disallow: # User-agent: Gulliver/1.1 # Disallow: # User-agent: yes # Disallow: # User-agent: AITCSRobot/1.1 # Disallow: # User-agent: wired-digital-newsbot/1.5 # Disallow: # User-agent: htdig/3.0b3 # Disallow: # User-agent: HTMLgobble v2.2 # Disallow: # User-agent: no # Disallow: # User-agent: IBM_Planetwide, # Disallow: # User-agent: gestaltIconoclast/1.0 libwww-FM/2.17 # Disallow: # User-agent: INGRID/0.1 # Disallow: # User-agent: IncyWincy/1.0b1 # Disallow: # User-agent: Informant # Disallow: # User-agent: InfoSeek Robot 1.0 # Disallow: # User-agent: Infoseek Sidewinder # Disallow: # User-agent: InfoSpiders/0.1 # Disallow: # User-agent: inspectorwww/1.0 # http://www.greenpac.com/inspectorwww.html # Disallow: # User-agent: 'IAGENT/1.0' # Disallow: # User-agent: IsraeliSearch/1.0 # Disallow: # User-agent: JCrawler/0.2 # Disallow: # User-agent: Jeeves v0.05alpha (PERL, LWP, lglb@doc.ic.ac.uk) # Disallow: # User-agent: Jobot/0.1alpha libwww-perl/4.0 # Disallow: # User-agent: JoeBot, # Disallow: # User-agent: JubiiRobot # Disallow: # User-agent: jumpstation # Disallow: # User-agent: Katipo/1.0 # Disallow: # User-agent: KDD-Explorer/0.1 # Disallow: # User-agent: KO_Yappo_Robot/1.0.4(http://yappo.com/info/robot.html) # Disallow: # User-agent: LabelGrab/1.1 # Disallow: # User-agent: LinkWalker # Disallow: # User-agent: logo.gif crawler # Disallow: # User-agent: Lycos/x.x # Disallow: # User-agent: Lycos_Spider_(T-Rex) # Disallow: # User-agent: Magpie/1.0 # Disallow: # User-agent: MediaFox/x.y # Disallow: # User-agent: MerzScope # Disallow: # User-agent: NEC-MeshExplorer # Disallow: # User-agent: MOMspider/1.00 libwww-perl/0.40 # Disallow: # User-agent: Monster/vX.X.X -$TYPE ($OSTYPE) # Disallow: # User-agent: Motor/0.2 # Disallow: # User-agent: MuscatFerret # Disallow: # User-agent: MwdSearch/0.1 # Disallow: # User-agent: NetCarta CyberPilot Pro # Disallow: # User-agent: NetMechanic # Disallow: # User-agent: NetScoop/1.0 libwww/5.0a # Disallow: # User-agent: NHSEWalker/3.0 # Disallow: # User-agent: Nomad-V2.x # Disallow: # User-agent: NorthStar # Disallow: # User-agent: Occam/1.0 # Disallow: # User-agent: HKU WWW Robot, # Disallow: # User-agent: Orbsearch/1.0 # Disallow: # User-agent: PackRat/1.0 # Disallow: # User-agent: Patric/0.01a # Disallow: # User-agent: Peregrinator-Mathematics/0.7 # Disallow: # User-agent: Duppies # Disallow: # User-agent: Pioneer # Disallow: # User-agent: PGP-KA/1.2 # Disallow: # User-agent: Resume Robot # Disallow: # User-agent: Road Runner: ImageScape Robot (lim@cs.leidenuniv.nl) # Disallow: # User-agent: Robbie/0.1 # Disallow: # User-agent: ComputingSite Robi/1.0 (robi@computingsite.com) # Disallow: # User-agent: Roverbot # Disallow: # User-agent: SafetyNet Robot 0.1, # Disallow: # User-agent: Scooter/1.0 # Disallow: # User-agent: not available # Disallow: # User-agent: Senrigan/xxxxxx # Disallow: # User-agent: SG-Scout # Disallow: # User-agent: Shai'Hulud # Disallow: # User-agent: SimBot/1.0 # Disallow: # User-agent: Open Text Site Crawler V1.0 # Disallow: # User-agent: SiteTech-Rover # Disallow: # User-agent: Slurp/2.0 # Disallow: # User-agent: ESISmartSpider/2.0 # Disallow: # User-agent: Snooper/b97_01 # Disallow: # User-agent: Solbot/1.0 LWP/5.07 # Disallow: # User-agent: Spanner/1.0 (Linux 2.0.27 i586) # Disallow: # User-agent: no # Disallow: # User-agent: Mozilla/3.0 (Black Widow v1.1.0; Linux 2.0.27; Dec 31 1997 12:25:00 # Disallow: # User-agent: Tarantula/1.0 # Disallow: # User-agent: tarspider # Disallow: # User-agent: dlw3robot/x.y (in TclX by http://hplyot.obspm.fr/~dl/) # Disallow: # User-agent: Templeton/ # Disallow: # User-agent: TitIn/0.2 # Disallow: # User-agent: TITAN/0.1 # Disallow: # User-agent: UCSD-Crawler # Disallow: # User-agent: urlck/1.2.3 # Disallow: # User-agent: Valkyrie/1.0 libwww-perl/0.40 # Disallow: # User-agent: Victoria/1.0 # Disallow: # User-agent: vision-search/3.0' # Disallow: # User-agent: VWbot_K/4.2 # Disallow: # User-agent: w3index # Disallow: # User-agent: W3M2/x.xxx # Disallow: # User-agent: WWWWanderer v3.0 # Disallow: # User-agent: WebCopy/ # Disallow: # User-agent: WebCrawler/3.0 Robot libwww/5.0a # Disallow: # User-agent: WebFetcher/0.8, # Disallow: # User-agent: weblayers/0.0 # Disallow: # User-agent: WebLinker/0.0 libwww-perl/0.1 # Disallow: # User-agent: no # Disallow: # User-agent: WebMoose/0.0.0000 # Disallow: # User-agent: Digimarc WebReader/1.2 # Disallow: # User-agent: webs@recruit.co.jp # Disallow: # User-agent: webvac/1.0 # Disallow: # User-agent: webwalk # Disallow: # User-agent: WebWalker/1.10 # Disallow: # User-agent: WebWatch # Disallow: # User-agent: Wget/1.4.0 # Disallow: # User-agent: w3mir # Disallow: # User-agent: no # Disallow: # User-agent: WWWC/0.25 (Win95) # Disallow: # User-agent: none # Disallow: # User-agent: XGET/0.7 # Disallow: # User-agent: Nederland.zoek # Disallow: # User-agent: BizBot04 kirk.overleaf.com # Disallow: # User-agent: HappyBot (gserver.kw.net) # Disallow: # User-agent: CaliforniaBrownSpider # Disallow: # User-agent: EI*Net/0.1 libwww/0.1 # Disallow: # User-agent: Ibot/1.0 libwww-perl/0.40 # Disallow: # User-agent: Merritt/1.0 # Disallow: # User-agent: StatFetcher/1.0 # Disallow: # User-agent: TeacherSoft/1.0 libwww/2.17 # Disallow: # User-agent: WWW Collector # Disallow: # User-agent: processor/0.0ALPHA libwww-perl/0.20 # Disallow: # User-agent: wobot/1.0 from 206.214.202.45 # Disallow: # User-agent: Libertech-Rover www.libertech.com? # Disallow: # User-agent: WhoWhere Robot # Disallow: # User-agent: ITI Spider # Disallow: # User-agent: w3index # Disallow: # User-agent: MyCNNSpider # Disallow: # User-agent: SummyCrawler # Disallow: # User-agent: OGspider # Disallow: # User-agent: linklooker # Disallow: # User-agent: CyberSpyder (amant@www.cyberspyder.com) # Disallow: # User-agent: SlowBot # Disallow: # User-agent: heraSpider # Disallow: # User-agent: Surfbot # Disallow: # User-agent: Bizbot003 # Disallow: # User-agent: WebWalker # Disallow: # User-agent: SandBot # Disallow: # User-agent: EnigmaBot # Disallow: # User-agent: spyder3.microsys.com # Disallow: # User-agent: www.freeloader.com. # Disallow: # User-agent: Googlebot # Disallow: # User-agent: METAGOPHER # Disallow: # User-agent: * # Disallow: /