# XML Sitemap & Google News Feeds version 4.6.3 - http://status301.net/wordpress-plugins/xml-sitemap-feed/ Sitemap: https://int-ent.de/sitemap-news.xml Sitemap: https://int-ent.de/sitemap.xml Sitemap: https://int-ent.de/news-sitemap.xml User-agent: * Allow: /wp-admin/admin-ajax.php Disallow: /wp-admin Disallow: /cgi-bin Disallow: /wp-includes Disallow: /wp-content/plugins Disallow: /wp-content/cache Disallow: /wp-content/themes Disallow: /trackback Disallow: /feed Disallow: /comments Disallow: /category/*/* Disallow: */trackback/ Disallow: */feed/ Disallow: */comments/ # Allow styles and js for rendering Allow: /wp-content/cache/*.css Allow: /wp-content/cache/*.js Allow: /wp-content/plugins/simple-share-buttons-adder/css/*.css Allow: /wp-content/plugins/simple-share-buttons-adder/buttons/simple/*.png Allow: /wp-includes/js/jquery/*.js Allow: /wp-content/uploads/wordpress-popular-posts/*.jpg # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. 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: / # Misbehaving: requests much too fast: User-agent: fast Disallow: / # # Sorry, wget in its recursive mode is a frequent problem. # Please read the man page and use it properly; there is a # --wait option you can use to set the delay between hits, # for instance. # User-agent: wget Disallow: / # # The 'grub' distributed client has been *very* poorly behaved. # User-agent: grub-client Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: / # # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: /