User-agent: * Disallow: /cache/ Disallow: /converge_local/ Disallow: /hooks/ Disallow: /ips_kernel/ Disallow: /retail/ Disallow: /public/js/ Disallow: /public/style_captcha/ Disallow: /public/style_css/ Disallow: /index.php?app=core&module=task Disallow: /index.php?app=core&module=usercp&tab=forums&area=forumsubs Disallow: /index.php?app=core&module=usercp&tab=forums&area=watch&watch=topic Disallow: /index.php?app=forums&module=extras§ion=forward Disallow: /index.php?app=members&module=messaging Disallow: /index.php?app=members&module=chat Disallow: /index.php?app=members&module=search Disallow: /index.php?app=members&module=search&do=active Disallow: /index.php?&unlockUserAgent=1 Disallow: /*app=core&module=usercp Disallow: /*app=core&module=usercp Disallow: /*app=members&module=messaging Disallow: /*&p= Disallow: /*&pid= Disallow: /*&hl= Disallow: /*&start= Disallow: /*view__getnewpost$ Disallow: /*view__getlastpost$ Disallow: /*view__old$ Disallow: /*view__new$ Disallow: /*view__getfirst$ Disallow: /*view__getprevious$ Disallow: /*view__getnext$ Disallow: /*view__getlast$ Disallow: /*&view=getnewpost$ Disallow: /*&view=getlastpost$ Disallow: /*&view=old$ Disallow: /*&view=new$ Disallow: /*&view=getfirst$ Disallow: /*&view=getprevious$ Disallow: /*&view=getnext$ Disallow: /*&view=getlast$ # robots.txt for http://www.wikipedia.org/ and friends # # Modified by WikiGTA / GTAGames.nl # # 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. # 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: synthesio 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: / #Delay for bots (5 seconds or higher is in most cases good) Crawl-delay: 5