# robots.txt file User-agent: * # Applies to all robots # Author: Leg Resource wayne@legresource.com # REMINDERS: Wildcards * or ? are NOT allowed in robots.txt except as User-agent # Syntax assumes a trailing * wildcard in all cases # Leading wildcards are not possible # No blank lines allowed except before "User-agent" line(s) # DIRECTORY: Disallow: /id/ # To identify a maintenance visit -- view anytime during visit Disallow: /reports/ # # FILES: Disallow: /id # /id.htm: MIGHT be another, less versatile way to identify # a maintenance visit till we set up a protected directory. # (this way the page must be viewed first, to become the referer, # but I'm not sure the filter works when the referer is at the # same site.) # (Technically, "/id" is also probably enough to disallow the "/id/" # directory) Disallow: /standby.htm # This is the home page during major maintenance Disallow: /thanks.htm # Appears after form is submitted Disallow: /constr1.htm # Placeholder for page under construction Disallow: /tst # Test files # OLD UNACCEPTABLE WILDCARDS (just fyi): # Disallow: /*.old # Older version of current file # Disallow: /.* # These are various experimental duplicate pages that might or might not be present