################################### # MandalorianMercs.com Smart Robots v3.05 ################################### # This is a smart robots.txt which logs the ip and user agent of every visitor. # Due to the compatibility issues between different bots and whether they support # wildcards (*), multiple user-agents and end-anchors ($), I am providing different # blocks for some. # # Detected Spider/Bot: None # # Headers Sent: # Content-Type: text/plain # Expires: Wed, 27 Aug 2008 01:43:48 GMT (12 hour validity) # # # Google - Most Important bot # Unfortunately a robots.txt will only stop it crawling certain urls, and NOT adding any # urls which it comes across into its index. So we're relying on a meta noindex tag. User-agent: Googlebot # Don't index mobile versions Disallow: forum/index.php?*;wap Disallow: forum/index.php?*;wap2 Disallow: forum/index.php?*;imode # Yahoo - Too aggressive # So limit it as much as possible. User-agent: Slurp # Disallow Everything Disallow: forum/ # Now allow bits and then disallow bits Allow: forum/sitemap.xml$ Allow: forum/robots.txt$ Allow: forum/index.php$ Allow: forum/index.php?topic=*.0$ Allow: forum/index.php?topic=*.*0$ Allow: forum/index.php?topic=*.*5$ Allow: forum/index.php?board=*.0$ Allow: forum/index.php?board=*.*0$ Allow: forum/index.php?board=*.*5$ # But don't allow these Disallow: forum/index.php?*.msg Disallow: forum/index.php?topic=*.msg*0$ Disallow: forum/index.php?topic=*.msg*5$ Disallow: forum/index.php?*.new # Anything with a ; disallow Disallow: forum/index.php?*;* # Bad bot - Often ignores robots.txt - Waste of bandwidth # Despite claiming on their website to be a search engine in development # I'm suspicious as to whether they are a harvester pretending to be SE User-agent: Twiceler Disallow: forum/ User-Agent: W3C-checklink Disallow: forum/ # Stop following PHPSESSID's User-Agent: MJ12bot Disallow: forum/index.php?PHPSESSID # Catch all (remainder) # Will be followed by any bots other than ones identified above # Uses BASIC robots.txt directives without wildcards, end-anchors etc # So Spiders should understand these (including MSNBOT) User-agent: * # Default SMF Folders Disallow: forum/attachments/ Disallow: forum/Packages/ Disallow: forum/Smileys/ Disallow: forum/Sources/ Disallow: forum/Themes/ # Default SMF Actions Disallow: forum/index.php?action=activate Disallow: forum/index.php?action=admin Disallow: forum/index.php?action=calendar Disallow: forum/index.php?action=emailuser Disallow: forum/index.php?action=findmember Disallow: forum/index.php?action=help Disallow: forum/index.php?action=helpadmin Disallow: forum/index.php?action=login Disallow: forum/index.php?action=logout Disallow: forum/index.php?action=mlist Disallow: forum/index.php?action=modifykarma Disallow: forum/index.php?action=pm Disallow: forum/index.php?action=post Disallow: forum/index.php?action=printpage Disallow: forum/index.php?action=profile Disallow: forum/index.php?action=recent Disallow: forum/index.php?action=register Disallow: forum/index.php?action=reminder Disallow: forum/index.php?action=search Disallow: forum/index.php?action=theme Disallow: forum/index.php?action=unread Disallow: forum/index.php?action=unreadreplies Disallow: forum/index.php?action=verificationcode Disallow: forum/index.php?action=who Disallow: forum/index.php?theme # SMF Mod Related Disallow: forum/archive.php Disallow: forum/index.php?action=blog Disallow: forum/index.php?action=viewblog Disallow: forum/index.php?action=chess Disallow: forum/index.php?action=comment Disallow: forum/index.php?action=downloads Disallow: forum/index.php?action=links Disallow: forum/index.php?action=reporttm Disallow: forum/index.php?action=recenttopics Disallow: forum/index.php?action=mm Disallow: forum/index.php?action=sitemap Disallow: forum/index.php?action=staff Disallow: forum/index.php?action=tags Disallow: forum/index.php?action=thankyou Disallow: forum/index.php?action=viewkarma Disallow: forum/index.php?action=viewers Disallow: forum/index.php?f= Disallow: forum/index.php?filter Disallow: forum/index.php?referredby Disallow: forum/Downloads/ Disallow: forum/index.php?action=arcade;favorites Disallow: forum/index.php?action=arcade;sa=highscore Disallow: forum/index.php?action=arcade;sa=play;random Disallow: forum/index.php?action=arcade;category Disallow: forum/index.php?action=arcade;sort Disallow: forum/index.php?action=arcade;stats Disallow: forum/index.php?action=stats;expand Disallow: forum/index.php?action=stats;collapse