# # 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/robotstxt.html User-agent: PetalBot Disallow: / User-agent: * Crawl-delay: 10 # CSS, JS, Images Allow: /misc/*.css$ Allow: /misc/*.css? Allow: /misc/*.js$ Allow: /misc/*.js? Allow: /misc/*.gif Allow: /misc/*.jpg Allow: /misc/*.jpeg Allow: /misc/*.png Allow: /modules/*.css$ Allow: /modules/*.css? Allow: /modules/*.js$ Allow: /modules/*.js? Allow: /modules/*.gif Allow: /modules/*.jpg Allow: /modules/*.jpeg Allow: /modules/*.png Allow: /profiles/*.css$ Allow: /profiles/*.css? Allow: /profiles/*.js$ Allow: /profiles/*.js? Allow: /profiles/*.gif Allow: /profiles/*.jpg Allow: /profiles/*.jpeg Allow: /profiles/*.png Allow: /themes/*.css$ Allow: /themes/*.css? Allow: /themes/*.js$ Allow: /themes/*.js? Allow: /themes/*.gif Allow: /themes/*.jpg Allow: /themes/*.jpeg Allow: /themes/*.png # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ # Files Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /INSTALL.sqlite.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /MAINTAINERS.txt Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /xmlrpc.php # Paths (clean URLs) # /admin/ Disallow: /admin/ Disallow: /en/admin/ Disallow: /nl/admin/ Disallow: /fr/admin/ Disallow: /de/admin/ # /comment/reply/ Disallow: /comment/reply/ Disallow: /en/comment/reply/ Disallow: /nl/comment/reply/ Disallow: /fr/comment/reply/ Disallow: /de/comment/reply/ # /filter/tips/ Disallow: /filter/tips/ Disallow: /en/filter/tips/ Disallow: /nl/filter/tips/ Disallow: /fr/filter/tips/ Disallow: /de/filter/tips/ # /node/add/ Disallow: /node/add/ Disallow: /en/node/add/ Disallow: /nl/node/add/ Disallow: /fr/node/add/ Disallow: /de/node/add/ # /search/ Disallow: /search/ Disallow: /en/search/ Disallow: /nl/search/ Disallow: /fr/search/ Disallow: /de/search/ # /user/register/ Disallow: /user/register/ Disallow: /en/user/register/ Disallow: /nl/user/register/ Disallow: /fr/user/register/ Disallow: /de/user/register/ # /user/password/ Disallow: /user/password/ Disallow: /en/user/password/ Disallow: /nl/user/password/ Disallow: /fr/user/password/ Disallow: /de/user/password/ # /user/login/ Disallow: /user/login/ Disallow: /en/user/login/ Disallow: /nl/user/login/ Disallow: /fr/user/login/ Disallow: /de/user/login/ # /user/logout/ Disallow: /user/logout/ Disallow: /en/user/logout/ Disallow: /nl/user/logout/ Disallow: /fr/user/logout/ Disallow: /de/user/logout/ # Paths (no clean URLs) # /?q=admin/ Disallow: /?q=admin/ Disallow: /?q=en/admin/ Disallow: /?q=nl/admin/ Disallow: /?q=fr/admin/ Disallow: /?q=de/admin/ # /?q=comment/reply/ Disallow: /?q=comment/reply/ Disallow: /?q=en/comment/reply/ Disallow: /?q=nl/comment/reply/ Disallow: /?q=fr/comment/reply/ Disallow: /?q=de/comment/reply/ # /?q=filter/tips/ Disallow: /?q=filter/tips/ Disallow: /?q=en/filter/tips/ Disallow: /?q=nl/filter/tips/ Disallow: /?q=fr/filter/tips/ Disallow: /?q=de/filter/tips/ # /?q=node/add/ Disallow: /?q=node/add/ Disallow: /?q=en/node/add/ Disallow: /?q=nl/node/add/ Disallow: /?q=fr/node/add/ Disallow: /?q=de/node/add/ # /?q=search/ Disallow: /?q=search/ Disallow: /?q=en/search/ Disallow: /?q=nl/search/ Disallow: /?q=fr/search/ Disallow: /?q=de/search/ # /?q=user/password/ Disallow: /?q=user/password/ Disallow: /?q=en/user/password/ Disallow: /?q=nl/user/password/ Disallow: /?q=fr/user/password/ Disallow: /?q=de/user/password/ # /?q=user/register/ Disallow: /?q=user/register/ Disallow: /?q=en/user/register/ Disallow: /?q=nl/user/register/ Disallow: /?q=fr/user/register/ Disallow: /?q=de/user/register/ # /?q=user/login/ Disallow: /?q=user/login/ Disallow: /?q=en/user/login/ Disallow: /?q=nl/user/login/ Disallow: /?q=fr/user/login/ Disallow: /?q=de/user/login/ # /?q=user/logout/ Disallow: /?q=user/logout/ Disallow: /?q=en/user/logout/ Disallow: /?q=nl/user/logout/ Disallow: /?q=fr/user/logout/ Disallow: /?q=de/user/logout/ # a-z page. The bots are going through all urls # Not needed as all links there are indexed from elsewhere Disallow: /a-z Disallow: /fr/a-z Disallow: /nl/a-z Disallow: /de/a-z Disallow: /en/a-z Disallow: /?q=a-z Disallow: /?q=fr/a-z Disallow: /?q=nl/a-z Disallow: /?q=de/a-z Disallow: /?q=en/a-z