# CJP: robots.txt,v 1.0 2010/06/02 # jenkins-powell.com # 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 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: * # Directories # You can specify Direcotries not to crawl here with the command Allow: /directoryname/ Disallow: /tmp/ Disallow: /uploads/ Disallow: /modules/ Disallow: /plugins/ Disallow: /styles/ Disallow: /lib/ Disallow: /js/ Disallow: /admin/ Disallow: /doc/ Disallow: /_install/ Disallow: /logs/ Disallow: /cgi-bin/ # Files # You can specify files not to crawl here with the command Disallow: /filename.extension # Paths (clean URLs) # You can specify URLS not to crawl here with the command Disallow: /path without domain/ # Paths (no clean URLs) # I like to keep clean and complex URL separate # You can specify URLS not to crawl here with the command Disallow: /?q=path without domain/