# robots.php # site: phl.databasesets.com # jamesqi # 2013-9-11\uff0c2018-1-5 # # 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 # modify start User-agent: GPTBot Disallow: / User-agent:Mediapartners-Google #Disallow: Disallow: /*user/log User-agent: * Allow: /sites/default/files/ Disallow: /cdn-cgi/ #Disallow: /*zicihao/* Disallow: /*comment/reply/* Disallow: /*image_captcha* Disallow: /node/26 Disallow: /node/52 Disallow: /node/51 Disallow: /node/27 Disallow: /node/32 Disallow: /node/28 Disallow: /node/34 Disallow: /node/29 Disallow: /node/30 # sitemap start Sitemap: https://phl.databasesets.com/sitemap.xml Sitemap: https://phl.databasesets.com/rss.xml Sitemap: https://phl.databasesets.com/sitemap_company-all_company.xml Sitemap: https://phl.databasesets.com/sitemap_company-all_province.xml Sitemap: https://phl.databasesets.com/sitemap_company-all_city.xml Sitemap: https://phl.databasesets.com/sitemap_company-all_date-incorporation.xml # sitemap end # modify end #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/*.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 # Directories Disallow: /*includes/ Disallow: /*misc/ Disallow: /*modules/ Disallow: /*profiles/ Disallow: /*scripts/ Disallow: /*themes/ # 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: /*admin/ Disallow: /*comment/reply/ Disallow: /*filter/tips/ Disallow: /*node/add/ Disallow: /*search/ Disallow: /*user/register/ Disallow: /*user/password/ Disallow: /*user/login/ Disallow: /*user/logout/ # 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: /*/user/login/