User-agent: * Disallow: Sitemap: https://www.bellaitaliatour.com/sitemap.xml User-agent: sistrix Disallow: / # Copied from wikipedia robots.txt # 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: 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: / # # 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: / User-agent: Mail.RU_Bot Disallow: / # blocks access to the entire site User-agent: WeSEE Disallow: / # https://www.grapeshot.com/crawler/ User-agent: grapeshot Disallow: / # Local advertising crawler User-agent: MaxPointCrawler Disallow: / # SEO - http://www.analyticsseo.com/the-analytics-seo-crawler-curious-george/ User-agent: Curious George Disallow: / # https://www.brandwatch.com/magpie-crawler/ User-agent: magpie-crawler Disallow: / # http://www.trovit.com/bot.html User-agent: trovitBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: Vegi bot Disallow: /