# robots.txt for https://cynefin.io Sitemap: https://cynefin.io/sitemap/sitemap.xml # 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. # # Observed spamming large amounts of https://en.wikipedia.org/?curid=NNNNNN # and ignoring 429 ratelimit responses, claims to respect robots: # http://mj12bot.com/ User-agent: MJ12bot Disallow: / # 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: / # 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: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: wget Disallow: / 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: / # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # Inktomi's "Slurp" can read a minimum delay between hits; if your # bot supports such a thing using the 'Crawl-delay' or another # instruction, please let us know. # # There is a special exception for API mobileview to allow dynamic # mobile web & app views to load section content. # These views aren't HTTP-cached but use parser cache aggressively # and don't expose special: pages etc. # # Another exception is for REST API documentation, located at # /api/rest_v1/?doc. # User-agent: * Allow: /w/api.php?action=mobileview& Allow: /w/load.php? Allow: /api/rest_v1/?doc Disallow: /w/ Disallow: /api/ Disallow: /trap/ Disallow: /wiki/Special: Disallow: /wiki/Spezial: Disallow: /wiki/Spesial: Disallow: /wiki/Special%3A Disallow: /wiki/Spezial%3A Disallow: /wiki/Spesial%3A Disallow: /wiki/Special: Disallow: /wiki/MediaWiki:Spam-blacklist Disallow: /wiki/MediaWiki%3ASpam-blacklist Disallow: /wiki/MediaWiki_talk:Spam-blacklist Disallow: /wiki/MediaWiki_talk%3ASpam-blacklist Disallow: /extensions Disallow: /skins Disallow: /index.php? Disallow: /wiki/Widget: # Talk Disallow: /wiki/Talk: Disallow: /wiki/Talk%3A # # User talk Disallow: /wiki/User_talk: Disallow: /wiki/User_talk%3A # # # File talk Disallow: /wiki/File_talk: Disallow: /wiki/File_talk%3A # # MediaWiki and MediaWiki talk Disallow: /wiki/MediaWiki: Disallow: /wiki/MediaWiki%3A Disallow: /wiki/MediaWiki_talk: Disallow: /wiki/MediaWiki_talk%3A # # Template and Template talk Disallow: /wiki/Template: Disallow: /wiki/Template%3A Disallow: /wiki/Template_talk: Disallow: /wiki/Template_talk%3A # # Meta and Meta talk Disallow: /wiki/Meta: Disallow: /wiki/Meta%3A Disallow: /wiki/Meta_talk: Disallow: /wiki/Meta_talk%3A # # Widget talk Disallow: /wiki/Widget_talk: Disallow: /wiki/Widget_talk%3A # # GeoJson talk Disallow: /wiki/GeoJson_talk: Disallow: /wiki/GeoJson_talk%3A # # Module talk Disallow: /wiki/Module_talk: Disallow: /wiki/Module_talk%3A # # Gadget talk Disallow: /wiki/Gadget_talk: Disallow: /wiki/Gadget_talk%3A # # Gadget defintion and Gadget defintion talk Disallow: /wiki/Gadget_defintion: Disallow: /wiki/Gadget_defintion%3A Disallow: /wiki/Gadget_defintion_talk: Disallow: /wiki/Gadget_defintion_talk%3A