# # robots.txt for http://www.normanteeling.com # reply-to: webmaster@normanteeling.com # last modified: 09/03/08 # For the efficient robot, an index of available sitemaps # Sitemap: http://www.normanteeling.com/sitemap.xml.gz Sitemap: http://www.normanteeling.com/sitemap_cm_index.php # Do not crawl these directories/files # User-agent: * Disallow: /cgi-bin/ Disallow: /images/ Disallow: /_*/ Disallow: /cm/ # These directories/files should be crawled # Allow: /cm/displayimage* Allow: /cm/gallery_sitemap_xml.php* Allow: /cm/index* Allow: /cm/register* Allow: /cm/search* Allow: /cm/thumbnails* Allow: /cm/*cat=* # Catch stragglers Disallow: *_vti* # Trouble bots: Please follow The Robots Exclusion Protocol - www.robotstxt.org # 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: NPBot Disallow: / User-agent: WebReaper Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: /