# Robots.txt file maintained by the Monterey Bay Aquarium # For domains: # http://www.montereybayaquarium.com # http://www.seafoodwatch.org # Please note: There are a lot of pages on this site, and there are # some misbehaved spiders out there that go _way_ too fast. If you're # irresponsible, your access to the site may be blocked. # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Wikipedia work bots: User-agent: IsraBot Disallow: User-agent: Orthogaffe 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: / User-agent: MJ12bot 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: / # Limit crawl rate of Yandex bot due to DoS of our Websites due to HIGH volume crawling User-agent: Yandex Crawl-delay: 4.5 # 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: / # Crawl Delay to keep the traffic at a steady stream Crawl-delay: 10 # Disallow directories User-agent: * Disallow: /App_Browsers/ Disallow: /App_Config/ Disallow: /App_Data/ Disallow: /bin/ Disallow: /bin_x64/ Disallow: /sitecore/ Disallow: /sitecore modules/ Disallow: /sitecore_files/ Disallow: /temp/ Disallow: /upload/ Disallow: /xsl/ Disallow: /sitecore modules/Web/Utils/AllRecsList/ SITEMAP: http://www.montereybayaquarium.org/sitemap.xml Sitemap: sitemap.xml Sitemap: sitemap_sfw.xml