# My Sitemap Sitemap: http://www.merapahad.com/forum/sitemap/?xml # Google - Most Important bot User-agent: Googlebot Allow: /forum/index.php?action=sitemap;xml Disallow: /Sources/* Disallow: /Smileys/* Disallow: /Packages/* Disallow: /header/* Disallow: /avatars/* Disallow: /attachments/* Disallow: /Themes/* Disallow: /index.php?action=printpage* Disallow: /index.php?action=post* Disallow: /index.php?action=permissions* Disallow: /index.php?action=pm* Disallow: /index.php?action=help* Disallow: /index.php?action=register* Disallow: /index.php?action=login* Disallow: /index.php?action=mlist* Disallow: /index.php?action=search* Disallow: /index.php?action=who* Disallow: /index.php?*rss* Disallow: /index.php?action=stats Disallow: /index.php?PHPSESSID= Disallow: /index.php?*wap* Disallow: /index.php?*imode* Disallow: /index.php?action=post* Disallow: /index.php?action=activate* Disallow: /index.php?action=reminder* Disallow: /index.php?wap2* Disallow: /*sort Disallow: /*sort, Disallow: /*action= Disallow: /*.new.html Disallow: /*.msg Disallow: /*.prev_next # Don't index mobile versions Disallow: /forum/index.php?*;wap Disallow: /forum/index.php?*;wap2 Disallow: /forum/index.php?*;imode # Default SMF Actions Disallow: /forum/index.php?theme # 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/index.php?action=sitemap;xml Allow: /sitemap.xml$ Allow: /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$ Disallow: /*?action* Disallow: /*sort=* Disallow: /*msg* Disallow: /forum/*wap* # 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 Disallow: /forum/attachments/ Disallow: /forum/Packages/ Disallow: /forum/Smileys/ Disallow: /forum/Sources/ Disallow: /forum/Themes/ # Default SMF Actions Disallow: /forum/index.php?theme # 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: / User-Agent: W3C-checklink Disallow: / User-agent: TurnitinBot Disallow: / # 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?theme Disallow: /forum/*?action* Disallow: /forum/*sort=* Disallow: /forum/*msg* Disallow: /forum/*wap*