# # robots.txt for http://www.greenbyte.ch/ and friends # # 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: / # 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: / User-agent: Meltwater Disallow: / User-agent: NewsNow Disallow: / User-agent: Bloodhound Disallow: / User-agent: cydralspider Disallow: / User-agent: downloadexpress Disallow: / User-agent: gammaSpider Disallow: / User-agent: ObjectsSearch Disallow: / User-agent: Pimptrain Disallow: / User-agent: Raven Disallow: / User-agent: wapspider Disallow: / User-agent: WebZinger Disallow: / User-agent: Fasterfox 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: / # Don't allow the alexa & wayback-maschine to index user-pages User-agent: ia_archiver Disallow: / # Don't allow the archive.org to index user-pages User-agent: ia_archiver-web.archive.org Disallow: / #User-agent: Googlebot-News* #Disallow: Crawl-delay: 60 Sitemap: /sitemap.xml.gz User-agent: * Disallow: /wp-content/uploads/2012/06/axxiv-server-skyscraper.jpg User-agent: * Disallow: /nofollow-analytics-black-hole/ User-agent: * Disallow: /greenbyte-ch-social-app/ #----------------------------------------------------------#