# # 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 Sitemap: https://underwaterasia.info/sitemap.xml User-agent: * # My command to stop dupe urls in crawl Disallow: /live/* # CSS, JS, Images Allow: /live/core/*.css$ Allow: /live/core/*.css? Allow: /live/core/*.js$ Allow: /live/core/*.js? Allow: /live/core/*.gif Allow: /live/core/*.jpg Allow: /live/core/*.jpeg Allow: /live/core/*.png Allow: /live/core/*.svg Allow: /live/profiles/*.css$ Allow: /live/profiles/*.css? Allow: /live/profiles/*.js$ Allow: /live/profiles/*.js? Allow: /live/profiles/*.gif Allow: /live/profiles/*.jpg Allow: /live/profiles/*.jpeg Allow: /live/profiles/*.png Allow: /live/profiles/*.svg Allow: /live/*.js* Allow: /live/*.css* Allow: /live/*.gif Allow: /live/*.jpg Allow: /live/*.jpeg Allow: /live/*.png Allow: /live/*.svg Allow: /live/sites/default/files/js/*.js Allow: /live/sites/default/files/css/*.css Allow: /live/sites/default/files/css/*.css Allow: /live/sites/default/files/css/*.gif Allow: /live/sites/default/files/css/*.jpg Allow: /live/sites/default/files/css/*.jpeg Allow: /live/sites/default/files/css/*.png # Directories Disallow: /live/core/ Disallow: /live/profiles/ Disallow: /taranoblesingh/ # Files Disallow: /live/README.txt Disallow: /live/web.config # Paths (clean URLs) Disallow: /live/admin/ Disallow: /live/comment/reply/ Disallow: /live/filter/tips Disallow: /live/node/add/ Disallow: /live/search/ Disallow: /live/user/register/ Disallow: /live/user/password/ Disallow: /live/user/login/ Disallow: /live/user/logout/ # Paths (no clean URLs) Disallow: /live/index.php/admin/ Disallow: /live/index.php/comment/reply/ Disallow: /live/index.php/filter/tips Disallow: /live/index.php/node/add/ Disallow: /live/index.php/search/ Disallow: /live/index.php/user/password/ Disallow: /live/index.php/user/register/ Disallow: /live/index.php/user/login/ Disallow: /live/index.php/user/logout/ # User-agent: Googlebot # Allow: /live/*.js* # Allow: /live/*.css* # the most specific rule based on the length of the [path] entry will trump the less specific (shorter) rule. # The order of precedence for rules with wildcards is undefined # https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt # Thanks to Marcel Jong and sunishabraham # Allow: /misc/*.js # Allow: /live/sites/default/files/js/*.js # Allow: /live/sites/default/files/css/*.css # Allow: /modules/*.js # Allow: /modules/*.css