# # 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: * 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 #Disallow Sogou spider crawling - 17-01-2017 by huy User-agent: Sogou web spider Disallow: / User-agent: sogou spider Disallow: / User-agent: * Disallow: # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ Disallow: /zaobao/ Disallow: /info/ Disallow: /mobile/ Disallow: /mobilecn/ Disallow: /ssi/ Disallow: /tmp/ Disallow: /webapp/ Disallow: /elfinder/ Disallow: /irc/ Disallow: /microsite/ Disallow: /p/ # Disallow: /sites/all Disallow: /webapp_qa/ Disallow: /zbmail/ Disallow: /scheduler/ Disallow: /zbmail/ Disallow: /PHPMailer_v5.1/ Disallow: /baidu-dataapi/ Disallow: /yx/ Disallow: /yl/ Disallow: /cj/ Disallow: /zg/ Disallow: /ajax-block/ # 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) Disallow: /node/ Disallow: /users/ Disallow: /admin/ Disallow: /taxonomy/ Disallow: /tags/ Disallow: /comment/reply/ Disallow: /filter/tips/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ Disallow: /user/logout/ Disallow: /print-news/ Disallow: /ajax-call/ Disallow: /5908/ZB_SG/ Disallow: /5908/ZB_CN/ Disallow: /zproperty/singapore-property/features/story20160117-571901 # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=filter/tips/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Disallow: /?q=user/logout/ # disallow all files ending in specific extension Disallow: /*.php$ Disallow: /*.pl$ Disallow: /rate/vote/ Disallow: /api/ Disallow: /story/next_prev/ Disallow: /buyeng/translate/ # block freemium paywall Images Disallow: /sites/default/files/freemium/ Sitemap: http://www.zaobao.com/sitemap-baidu.xml Sitemap: http://www.zaobao.com.sg/sitemap.xml Sitemap: http://www.zaobao.com.sg/google-news-sitemap.xml Sitemap: http://www.zaobao.com.sg/sitemap-zpolitics.xml Sitemap: https://www.zaobao.com/sitemap-baidu.xml Sitemap: https://www.zaobao.com.sg/sitemap.xml Sitemap: https://www.zaobao.com.sg/google-news-sitemap.xml Sitemap: https://www.zaobao.com.sg/sitemap-zpolitics.xml