# 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: IRLbot 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: / # # 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: / # # YAHOO-related # Slurp: http://help.yahoo.com/help/us/ysearch/slurp/index.html # HOST: .inktomisearch.com; .mail.mud.yahoo.com # Slurp CHINA: http://misc.yahoo.com.cn/help.html # Slurp DE: http://help.yahoo.com/help/us/ysearch/slurp) # Blogs: http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html # MM: mms dash mmcrawler dash support at yahoo dash inc dot com # Y!J-BSC/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html) # Yahoo! Mindset (http://mindset.research.yahoo.com/) # # User-agent: Slurp # User-agent: Yahoo-Blogs # User-agent: Yahoo-Blogs/v3.9 # User-agent: Yahoo-MMCrawler # User-agent: Yahoo-MMCrawler/3.x # User-agent: YahooYSMcm # User-agent: YahooYSMcm/2.0.0 # User-agent: Yahoo! Mindset # User-agent: Y!J-BSC # User-agent: Y!J-BSC/1.0 # User-agent: Y!J-BSC/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html) # User-agent: y!j-bsc # User-agent: y!j-bsc/1.0 # User-agent: y!j-bsc/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html) # User-agent: Y!J # User-agent: Y!J/1.0 # User-agent: Y!J/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html) # User-agent: y!j # User-agent: y!j/1.0 # User-agent: y!j/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html) # User-agent: Mozilla/4.0 (compatible; Y!J; for robot study; keyoshid) # User-agent: Mozilla/4.0 (compatible; y!j; for robot study; keyoshid) # User-agent: Mozilla/5.0 (compatible; Yahoo! Slurp China; http://misc.yahoo.com.cn/help.html) # User-agent: Mozilla/5.0 (compatible; Yahoo! DE Slurp; http://help.yahoo.com/help/us/ysearch/slurp) # Disallow: / # # Friendly, low-speed bots are welcome viewing article pages, but not # the following dynamically-generated pages please. # User-agent: * Disallow: /maintenance/ Disallow: /skins/ Disallow: /tests/ Disallow: /config/ Disallow: /docs/ Disallow: /math/ Disallow: /languages/ Disallow: /index.php?title=Speci%C3%A1lis:Random Disallow: /index.php?title=Special:Random Disallow: /index.php?title=Speci%C3%A1lis%3ARandom Disallow: /index.php?title=Special%3ARandom Disallow: /index.php?title=Speci%C3%A1lis:Randompage Disallow: /index.php?title=Special:Randompage Disallow: /index.php?title=Speci%C3%A1lis%3ARandompage Disallow: /index.php?title=Special%3ARandompage Disallow: /index.php?title=Speci%C3%A1lis:Lap_tal%C3%A1lomra Disallow: /index.php?title=Speci%C3%A1lis%3ALap_tal%C3%A1lomra Disallow: /index.php?title=Speci%C3%A1lis:Search Disallow: /index.php?title=Speci%C3%A1lis%3ASearch Disallow: /index.php?title=Special:Search Disallow: /index.php?title=Special%3ASearch Crawl-delay: 60.0