#User-agent: * #Disallow: / #disallow indexing of all pages # # Revised robots.text file for whole of blackandwhite.org nov23/98 # This tells scanning robots where they are and are not welcome # User-agent: can also specify by name; "*" is for all robots # Disallow: if this matches first part of the requested path, forget # it. # tardis.ed.ac.uk/home/sxw/robots/check/ # this site checks syntax errors on this file # Unlock this exclusion before launch, exclude files by directory # name before rollout #zdnet.com/devhead/resources/tools/htmlcheck/ #this checks links,html etc. #If you want to exclude all robots from the entire #server, use the following syntax: # #User-agent: * #Disallow: / # User-agent: * Disallow: /Shellx/ Disallow: /incoming/ Disallow: /listat/ Disallow: /inbox/ Disallow: /pico.save/ Disallow: /tmp # directories below pertain to Savvy unused Disallow: /allopad Disallow: /doctors Disallow: /holopad Disallow: /members Disallow: /newstand Disallow: /patipad Disallow: /pred Disallow: /outlaw # # first robots.text file for whole of blackandwhite.org 10/31/98 # This tells scanning robots where they are and are not welcome # User-agent: can also specify by name; "*" is for all robots # Disallow: if this matches first part of the requested path, forget # it. # tardis.ed.ac.uk/home/sxw/robots/check/ # this site checks syntax errors on this file # Unlock this excluison before launch, exclude files by directory # name before rollout # #User-agent: * #applies to all robots #Disallow: / #disallow indexing of all pages # Tell the Internet Archive not to keep a copy User-agent: ia_archiver Disallow: / # User-agent: ia_archiver/1.6 Disallow: / # User-agent: EmailSiphon Disallow: / # User-agent: Gulliver/1.2 Disallow: / # # Keep out Tovek Tools User-agent: TovekTools Web Indexer/1.0beta [Win32] Disallow: / # User-agent: InfoNaviRobot Disallow: / # # robots.txt --- index my site for search but don't archive it #User-agent: * #Disallow: # User-agent: HURIDOCS Disallow: / # User-agent: Openfind Disallow: / # User-agent: EmailWolf Disallow: / # User-agent: ExtractorPro Disallow: / # User-agent: Harvest/1.5 Disallow: / # # # #If you want to exclude all robots from specific #areas or folders on the server, you'll need to #specify the excluded folders: # #User-agent: * #Disallow: /cgi-bin/ #Disallow: /dev/ # #The "*" in the User-agent directive has the #special value of "any or all robots". #To allow a single robot complete access and #exclude all others, use a syntax like the #following: # #User-agent: Lycos #Disallow: #User-agent: * #Disallow: / # #User-agent: * #Disallow: /cgi-bin/ #Disallow: /dev/ #Disallow: /membersonly.shtml/ # #server are excluded: cgi-bin, a live development folder #called "dev" and the html page, "membersonly.shtml". #You'll need to establish a separate "Disallow" directive #for each path you want to exclude. Be careful not to #include any empty lines in the text file, as the bots will #intepret this as though you were referring to multiple #sites. And, you can't use the asterix anywhere else #within this text file besides within the user-agent field. # #You'll need to know the exact name of the robot agents #in order to exclude certain bots by name.