# $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 6.6 /cata/cms/ User-agent: * Crawl-delay: 10 # Directories Disallow: /cata/cms/database/ Disallow: /cata/cms/includes/ Disallow: /cata/cms/misc/ Disallow: /cata/cms/modules/ Disallow: /cata/cms/sites/ Disallow: /cata/cms/themes/ Disallow: /cata/cms/scripts/ Disallow: /cata/cms/updates/ Disallow: /cata/cms/profiles/ Disallow: /cata/cms/_files/ # Files Disallow: /cata/cms/xmlrpc.php Disallow: /cata/cms/cron.php Disallow: /cata/cms/update.php Disallow: /cata/cms/install.php Disallow: /cata/cms/_files/INSTALL.txt Disallow: /cata/cms/_files/INSTALL.mysql.txt Disallow: /cata/cms/_files/INSTALL.pgsql.txt Disallow: /cata/cms/_files/CHANGELOG.txt Disallow: /cata/cms/_files/MAINTAINERS.txt Disallow: /cata/cms/_files/LICENSE.txt Disallow: /cata/cms/_files/UPGRADE.txt # Paths (clean URLs) Disallow: /cata/cms/admin/ Disallow: /cata/cms/comment/reply/ Disallow: /cata/cms/contact/ Disallow: /cata/cms/logout/ Disallow: /cata/cms/node/add/ Disallow: /cata/cms/search/ Disallow: /cata/cms/user/register/ Disallow: /cata/cms/user/password/ Disallow: /cata/cms/user/login/ # Paths (no clean URLs) Disallow: /cata/cms/?q=admin/ Disallow: /cata/cms/?q=comment/reply/ Disallow: /cata/cms/?q=contact/ Disallow: /cata/cms/?q=logout/ Disallow: /cata/cms/?q=node/add/ Disallow: /cata/cms/?q=search/ Disallow: /cata/cms/?q=user/password/ Disallow: /cata/cms/?q=user/register/ Disallow: /cata/cms/?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 6.12 /cms1/ User-agent: * Crawl-delay: 10 # Directories Disallow: /cms1/database/ Disallow: /cms1/includes/ Disallow: /cms1/misc/ Disallow: /cms1/modules/ Disallow: /cms1/sites/ Disallow: /cms1/themes/ Disallow: /cms1/scripts/ Disallow: /cms1/updates/ Disallow: /cms1/profiles/ Disallow: /cms1/_files/ # Files Disallow: /cms1/xmlrpc.php Disallow: /cms1/cron.php Disallow: /cms1/update.php Disallow: /cms1/install.php Disallow: /cms1/_files/INSTALL.txt Disallow: /cms1/_files/INSTALL.mysql.txt Disallow: /cms1/_files/INSTALL.pgsql.txt Disallow: /cms1/_files/CHANGELOG.txt Disallow: /cms1/_files/MAINTAINERS.txt Disallow: /cms1/_files/LICENSE.txt Disallow: /cms1/_files/UPGRADE.txt # Paths (clean URLs) Disallow: /cms1/admin/ Disallow: /cms1/comment/reply/ Disallow: /cms1/contact/ Disallow: /cms1/logout/ Disallow: /cms1/node/add/ Disallow: /cms1/search/ Disallow: /cms1/user/register/ Disallow: /cms1/user/password/ Disallow: /cms1/user/login/ # Paths (no clean URLs) Disallow: /cms1/?q=admin/ Disallow: /cms1/?q=comment/reply/ Disallow: /cms1/?q=contact/ Disallow: /cms1/?q=logout/ Disallow: /cms1/?q=node/add/ Disallow: /cms1/?q=search/ Disallow: /cms1/?q=user/password/ Disallow: /cms1/?q=user/register/ Disallow: /cms1/?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 6.13 /feeds/ User-agent: * Crawl-delay: 10 # Directories Disallow: /feeds/database/ Disallow: /feeds/includes/ Disallow: /feeds/misc/ Disallow: /feeds/modules/ Disallow: /feeds/sites/ Disallow: /feeds/themes/ Disallow: /feeds/scripts/ Disallow: /feeds/updates/ Disallow: /feeds/profiles/ Disallow: /feeds/_files/ # Files Disallow: /feeds/xmlrpc.php Disallow: /feeds/cron.php Disallow: /feeds/update.php Disallow: /feeds/install.php Disallow: /feeds/_files/INSTALL.txt Disallow: /feeds/_files/INSTALL.mysql.txt Disallow: /feeds/_files/INSTALL.pgsql.txt Disallow: /feeds/_files/CHANGELOG.txt Disallow: /feeds/_files/MAINTAINERS.txt Disallow: /feeds/_files/LICENSE.txt Disallow: /feeds/_files/UPGRADE.txt # Paths (clean URLs) Disallow: /feeds/admin/ Disallow: /feeds/comment/reply/ Disallow: /feeds/contact/ Disallow: /feeds/logout/ Disallow: /feeds/node/add/ Disallow: /feeds/search/ Disallow: /feeds/user/register/ Disallow: /feeds/user/password/ Disallow: /feeds/user/login/ # Paths (no clean URLs) Disallow: /feeds/?q=admin/ Disallow: /feeds/?q=comment/reply/ Disallow: /feeds/?q=contact/ Disallow: /feeds/?q=logout/ Disallow: /feeds/?q=node/add/ Disallow: /feeds/?q=search/ Disallow: /feeds/?q=user/password/ Disallow: /feeds/?q=user/register/ Disallow: /feeds/?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 6.14 /home/ User-agent: * Crawl-delay: 10 # Directories Disallow: /home/database/ Disallow: /home/includes/ Disallow: /home/misc/ Disallow: /home/modules/ Disallow: /home/sites/ Disallow: /home/themes/ Disallow: /home/scripts/ Disallow: /home/updates/ Disallow: /home/profiles/ Disallow: /home/_files/ # Files Disallow: /home/xmlrpc.php Disallow: /home/cron.php Disallow: /home/update.php Disallow: /home/install.php Disallow: /home/_files/INSTALL.txt Disallow: /home/_files/INSTALL.mysql.txt Disallow: /home/_files/INSTALL.pgsql.txt Disallow: /home/_files/CHANGELOG.txt Disallow: /home/_files/MAINTAINERS.txt Disallow: /home/_files/LICENSE.txt Disallow: /home/_files/UPGRADE.txt # Paths (clean URLs) Disallow: /home/admin/ Disallow: /home/comment/reply/ Disallow: /home/contact/ Disallow: /home/logout/ Disallow: /home/node/add/ Disallow: /home/search/ Disallow: /home/user/register/ Disallow: /home/user/password/ Disallow: /home/user/login/ # Paths (no clean URLs) Disallow: /home/?q=admin/ Disallow: /home/?q=comment/reply/ Disallow: /home/?q=contact/ Disallow: /home/?q=logout/ Disallow: /home/?q=node/add/ Disallow: /home/?q=search/ Disallow: /home/?q=user/password/ Disallow: /home/?q=user/register/ Disallow: /home/?q=user/login/