# $Id: robots.txt,v 1.7.2.3 2008/12/10 20:24:38 drumm 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: * Allow: / #Disallow: / ####################################### ############### SITEMAP ############### ####################################### Sitemap: http://www.aselcom.nl/sitemap/sitemap.xml ####################################### ################ PAGES ################ ####################################### Disallow: /privacy-policy-cookie-restriction-mode/ Disallow: /terms/ ####################################### ##### DIRECTORIES & FILES ##### ####################################### ##### Directories ##### Disallow: /404/ Disallow: /app/ Disallow: /cgi-bin/ Disallow: /downloader/ Disallow: /includes/ Disallow: /js/ Disallow: /lib/ Disallow: /magento/ Disallow: /pkginfo/ Disallow: /report/ #Disallow: /skin/ Disallow: /stats/ Disallow: /var/ ##### Paths (clean URLs) ##### Disallow: /index.php/ Disallow: /catalog/product_compare/ Disallow: /catalog/category/view/ Disallow: /catalog/product/view/ Disallow: /catalog/product/gallery/ Disallow: /catalogsearch/ Disallow: /checkout/ Disallow: /control/ Disallow: /contacts/ Disallow: /customer/ Disallow: /customize/ Disallow: /newsletter/ Disallow: /poll/ Disallow: /review/ Disallow: /sendfriend/ Disallow: /tag/ Disallow: /wishlist/ Disallow: /home/ ##### Files ##### Disallow: /cron.php Disallow: /cron.sh Disallow: /error_log Disallow: /install.php Disallow: /LICENSE.html Disallow: /LICENSE.txt Disallow: /LICENSE_AFL.txt Disallow: /STATUS.txt ####################################### ######## QUERY STRING BLOCKER ######### ####################################### #Uncomment if your site is a brand new un-cached site. #Disallow: /*?* ####################################### #### WORDPRESS DIRECTORIES & FILES #### ####################################### ##### Uncomment if using Wordpress in subdirectory ##### #Disallow: /blog/wp-content/plugins/ #Disallow: /blog/wp-content/themes/ #Disallow: /blog/wp-content/upgrade/ #Disallow: /blog/wp-admin/ #Disallow: /blog/wp-includes/ Disallow: /blog/cat/ ####################################### ########### SCREAMING FROG ############ ####################################### User-agent: Screaming Frog SEO Spider Allow: / Disallow: /*.gif$ Disallow: /*.jpg$ Disallow: /*.png$ Disallow: /*.bmp$ Disallow: /*.xml$ Disallow: /*.css$ Disallow: /*.js$ User-agent: * # Directories Disallow: /database/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /sites/ Disallow: /themes/ Disallow: /updates/ Disallow: /software/ # Files Disallow: /files # Paths (clean URLs) Disallow: /checkout/ Disallow: /admin/ Disallow: /aggregator Disallow: /comment/reply/ Disallow: /contacts Disallow: /logout Disallow: /search/ Disallow: /user/register Disallow: /user/password Disallow: /user/login # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=aggregator/ 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/ # Additional Rules 2011 Disallow: /node$