# WSN: World Sports Network # http://www.wsn.com/robots.txt # Please use Sitemap Sitemap: http://www.wsn.com/sitemap_index.xml # Explicitly allow AdSense Bot: User-agent: Mediapartners-Google* Disallow: # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / # 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: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: DotSpotsBot Disallow: / User-agent: LinksManager.com_bot Disallow: / User-agent: Gaisbot Disallow: / User-agent: CollapsarWEB Disallow: / User-agent: WebCensusProjectBot Disallow: / User-agent: Mp3Bot Disallow: / User-agent: yacybot Disallow: / # Sorry, wget in its recursive mode is a frequent problem. 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: / # # All the rest are welcome to crawl responsibly # User-agent: * # Advertising Disallow: /content/ Disallow: /bet-now/ # Security: Disallow: /adodb/ Disallow: /cache/ Disallow: /cgi-bin/ Disallow: /email/ Disallow: /wsn_cms/ # SVN Disallow: /branches/ Disallow: /tags/ Disallow: /trunk/ # Duplication / Optimization: Disallow: /search/ # Wordpress Disallow: /blog/private Disallow: /blog/wp-admin Disallow: /blog/wp-includes Disallow: /blog/wp-content Disallow: /blog/wt-js