# robots.txt for http://www.graceharborministries.com/ Sitemap: http://www.graceharborministries.com/sitemap.xml # Google AdSense User-agent: Mediapartners-Google Allow: / # allow all files # Wayback-Machine User-agent: ia_archiver Disallow: /tmp*/ # temorary files # CRAWLER EXCLUSION LIST User-agent: duggmirror Disallow: / User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: wget Disallow: / User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: / # ALLOW ALL OTHER CRAWLERS User-agent: * Disallow: /images/ # image files Disallow: /scripts/ # script files Disallow: /styles/ # style sheet files Disallow: /cgi-bin/ # cgi files Disallow: /tmp*/ # temporary files Disallow: /*.js$ # all javascript files Disallow: /*.inc.php$ # all include script files Disallow: /*.css$ # all style sheet files Disallow: /*? # all urls with a string Allow: /images/*.png$ # png image files