# $Id: robots.txt,v 1.9 2007/06/27 22:37:44 goba Exp $ # # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html User-agent: * Crawl-delay: 10 # Directories Disallow: /database/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /sites/ Disallow: /themes/ Disallow: /scripts/ Disallow: /updates/ Disallow: /profiles/ # Files Disallow: /xmlrpc.php Disallow: /cron.php Disallow: /update.php Disallow: /install.php Disallow: /INSTALL.txt Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /CHANGELOG.txt Disallow: /MAINTAINERS.txt Disallow: /LICENSE.txt Disallow: /UPGRADE.txt # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /logout/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=contact/ Disallow: /?q=logout/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ # $Id: robots.txt,v 1.9 2007/06/27 22:37:44 goba Exp $ # # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html # File identity - # So that the contents of this file are copied only once to DocumentRoot/robots.txt at # installation time the file must contain a unique string. # The copy_robots_text.pl program looks for a line with a string of the form "hhh ddd vvv ooo" # where hhh is '#' # ddd is 'Drupal' # vvv is 'version' # ooo is some other chars to make it unique. For instance, using the version and installation directory (see 3 lines down). # If copy_robots_text.pl finds that string in DocumentRoot/robots.txt it assumes that the data is already there and does not copy again. # DO NOT REMOVE THE NEXT LINE - it prevents copying to DocumentRoot more than once. # Drupal version 6.2 /the38bus/ User-agent: * Crawl-delay: 10 # Directories Disallow:/the38bus/database/ Disallow:/the38bus/includes/ Disallow:/the38bus/misc/ Disallow:/the38bus/modules/ Disallow:/the38bus/sites/ Disallow:/the38bus/themes/ Disallow:/the38bus/scripts/ Disallow:/the38bus/updates/ Disallow:/the38bus/profiles/ Disallow:/the38bus/_files/ # Files Disallow:/the38bus/xmlrpc.php Disallow:/the38bus/cron.php Disallow:/the38bus/update.php Disallow:/the38bus/install.php # Paths (clean URLs) Disallow:/the38bus/admin/ Disallow:/the38bus/comment/reply/ Disallow:/the38bus/contact/ Disallow:/the38bus/logout/ Disallow:/the38bus/node/add/ Disallow:/the38bus/search/ Disallow:/the38bus/user/register/ Disallow:/the38bus/user/password/ Disallow:/the38bus/user/login/ # Paths (no clean URLs) Disallow:/the38bus/?q=admin/ Disallow:/the38bus/?q=comment/reply/ Disallow:/the38bus/?q=contact/ Disallow:/the38bus/?q=logout/ Disallow:/the38bus/?q=node/add/ Disallow:/the38bus/?q=search/ Disallow:/the38bus/?q=user/password/ Disallow:/the38bus/?q=user/register/ Disallow:/the38bus/?q=user/login/