# # 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: Screaming Frog SEO Spider Disallow: / User-agent: AhrefsBot Disallow: / User-agent: * Crawl-delay: 30 Allow: / # Directories Disallow: /core/ Disallow: /profiles/ Disallow: /contact_page/ Disallow: /ipsos_site/ # Files Disallow: /README.txt Disallow: /web.config # Paths (clean URLs) Disallow: /*/admin* Disallow: /admin* Disallow: /*/comment/reply* Disallow: /comment/reply* Disallow: /*/filter/tips* Disallow: /filter/tips* Disallow: /*/node/add* Disallow: /node/add* Disallow: /*/search?* Disallow: /*/search$ Disallow: /search/* Disallow: /search$ Disallow: /*/user/register* Disallow: /user/register* Disallow: /*/user/password* Disallow: /user/password* Disallow: /*/user/login* Disallow: /user/login* Disallow: /*/user/logout* Disallow: /user/logout* Disallow: /*?ce= Disallow: /*&ce= # Paths (no clean URLs) Disallow: /index.php/admin/ Disallow: /index.php/comment/reply/ Disallow: /index.php/filter/tips/ Disallow: /index.php/node/add/ Disallow: /index.php/search/ Disallow: /index.php/user/password/ Disallow: /index.php/user/register/ Disallow: /index.php/user/login/ Disallow: /index.php/user/logout/ # Specific files Paths Disallow: /*/NEWBASE_EXPORTS* Disallow: /NEWBASE_EXPORTS*