<META NAME="ROBOTS" CONTENT="NOINDEX, FOLLOW">
<META NAME="ROBOTS" CONTENT="INDEX, NOFOLLOW">
<META NAME="ROBOTS" CONTENT="NOINDEX, NOFOLLOW">
<META NAME="GOOGLEBOT" CONTENT="NOSNIPPET, NOARCHIVE">
# googlebot also understand http header
X-Robots-Tag: noindex
#http://www.google.com/support/webmasters/bin/topic.py?topic=8459
# http://help.yahoo.com/l/us/yahoo/search/webcrawler/index.html

#example /robots.txt
User-agent: *
Disallow: /guestbook #guestbook is the most attacked folder. even if you never have it and never links it, spambot will try to access it
Disallow: /cgi-bin/guestbook.cgi #your guestbook.cgi should be replaced with spambot trap
Disallow: /emailaccounts #use scripts to poison spambot with thousands/millions of fake email addresses
Disallow: /anothertrap
Disallow: /moretrap

RewriteEngine On 

# Forbid requests for exploits & annoyances 
# Bad requests 
RewriteCond %{REQUEST_METHOD}!^(GET¦HEAD¦POST) [NC,OR] 
# CodeRed 
RewriteCond %{REQUEST_URI} ^/default\.(ida¦idq) [NC,OR] 
RewriteCond %{REQUEST_URI} ^/.*\.printer$ [NC,OR] 
# Email 
RewriteCond %{REQUEST_URI} (mail.?form¦form¦form.?mail¦mail¦mailto)\.(cgi¦exe¦pl)$ [NC,OR] 
# MSOffice 
RewriteCond %{REQUEST_URI} ^/(MSOffice¦_vti) [NC,OR] 
# Nimda 
RewriteCond %{REQUEST_URI} /(admin¦cmd¦httpodbc¦nsiislog¦root¦shell)\.(dll¦exe) [NC,OR] 
# Various 
RewriteCond %{REQUEST_URI} ^/(bin/¦cgi/¦cgi\-local/¦sumthin) [NC,OR] 
RewriteCond %{THE_REQUEST} ^GET\ http [NC,OR] 
RewriteCond %{REQUEST_URI} /sensepost\.exe [NC] 
RewriteRule .* - [F] 

# Forbid if blank (or "-") Referer *and* UA 
RewriteCond %{HTTP_REFERER} ^-?$ 
RewriteCond %{HTTP_USER_AGENT} ^-?$ 
RewriteRule .* - [F] 

# Banning BOTS bellow 
# Address harvesters 
RewriteCond %{HTTP_USER_AGENT} ^InternetSeer.com [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(autoemailspider¦ExtractorPro) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^E?Mail.?(Collect¦Harvest¦Magnet¦Reaper¦Siphon¦Sweeper¦Wolf) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} (DTS.?Agent¦Email.?Extrac) [NC,OR] 
RewriteCond %{HTTP_REFERER} iaea\.org [NC,OR] 
# Download managers 
RewriteCond %{HTTP_USER_AGENT} ^(Alligator¦DA.?[0-9]¦DC\-Sakura¦Download.?(Demon¦Express¦Master¦Wonder)¦FileHound) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Flash¦Leech)Get [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Fresh¦Lightning¦Mass¦Real¦Smart¦Speed¦Star).?Download(er)? [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Gamespy¦Go!Zilla¦iGetter¦JetCar¦Net(Ants¦Pumper)¦SiteSnagger¦Teleport.?Pro¦WebReaper) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(My)?GetRight [NC,OR] 
# Image-grabbers 
RewriteCond %{HTTP_USER_AGENT} ^(AcoiRobot¦FlickBot¦webcollage) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Express¦Mister¦Web).?(Web¦Pix¦Image).?(Pictures¦Collector)? [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^Image.?(fetch¦Stripper¦Sucker) [NC,OR] 
# "Gray-hats" 
RewriteCond %{HTTP_USER_AGENT} ^(Atomz¦BlackWidow¦BlogBot¦EasyDL¦Marketwave¦Sqworm¦SurveyBot¦Webclipping\.com) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} (girafa\.com¦gossamer\-threads\.com¦grub\-client¦Netcraft¦Nutch) [NC,OR] 
# Site-grabbers 
RewriteCond %{HTTP_USER_AGENT} ^(eCatch¦(Get¦Super)Bot¦Kapere¦HTTrack¦JOC¦Offline¦UtilMind¦Xaldon) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^Web.?(Auto¦Cop¦dup¦Fetch¦Filter¦Gather¦Go¦Leach¦Mine¦Mirror¦Pix¦QL¦RACE¦Sauger) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^Web.?(site.?(eXtractor¦Quester)¦Snake¦ster¦Strip¦Suck¦vac¦walk¦Whacker¦ZIP) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} WebCapture [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^DISCo\ Pump [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^EirGrabber [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^Net\ Vampire [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^NetZIP [NC,OR] 
# Tools 
RewriteCond %{HTTP_USER_AGENT} ^(curl¦Dart.?Communications¦Enfish¦htdig¦Java¦larbin) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} (FrontPage¦Indy.?Library¦RPT\-HTTPClient) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(libwww¦lwp¦PHP¦Python¦www\.thatrobotsite\.com¦webbandit¦Wget¦Zeus) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Microsoft¦MFC).(Data¦Internet¦URL¦WebDAV¦Foundation).(Access¦Explorer¦Control¦MiniRedir¦Class) [NC,OR] 
# Unknown 
RewriteCond %{HTTP_USER_AGENT} ^(Crawl_Application¦Lachesis¦Nutscrape) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^[CDEFPRS](Browse¦Eval¦Surf) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Demo¦Full.?Web¦Lite¦Production¦Franklin¦Missauga¦Missigua).?(Bot¦Locat) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} (efp@gmx\.net¦hhjhj@yahoo\.com¦lerly\.net¦mapfeatures\.net¦metacarta\.com) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Industry¦Internet¦IUFW¦Lincoln¦Missouri¦Program).?(Program¦Explore¦Web¦State¦College¦Shareware) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Mac¦Ram¦Educate¦WEP).?(Finder¦Search) [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^(Moz+illa¦MSIE).?[0-9]?.?[0-9]?[0-9]?$ [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} ^Mozilla/[0-9]\.[0-9][0-9]?.\(compatible[\)\ ] [NC,OR] 
RewriteCond %{HTTP_USER_AGENT} NaverRobot [NC] 
RewriteRule .* - [F] 

#!/usr/bin/perl -w 

$remreq = $ENV{REQUEST_URI}; 
$remaddr = $ENV{REMOTE_ADDR}; 
$usragnt = $ENV{HTTP_USER_AGENT} ¦¦ "The UA is blank"; 
$referer = $ENV{'HTTP_REFERER'} ¦¦ "there is no referer"; 
$date = scalar localtime(time); 
$remmeth = $ENV{REQUEST_METHOD}; 
$remhost = $ENV{'HTTP_HOST'}; 

open(MAIL, "¦/usr/sbin/sendmail -t") ¦¦ die "Content-type: text/text\n\nCan't open /usr/sbin/sendmail!"; 
print MAIL "To: ****\@yyy\.zzz\n"; 
print MAIL "From: xxx\@yyy\.zzz\n"; 
print MAIL "Subject: You caught another one!\n\n"; 
print MAIL "The following 'intruder' was caught by the \"Bot Trap\" and has been added to the ban env in .htaccess:\n\n"; 
print MAIL "The ip address: $remaddr was listed on $date \n"; 
print MAIL "The file requested was: $remreq\n"; 
print MAIL "The method used was: $remmeth\n"; 
print MAIL "The intruder's user agent was: $usragnt\n"; 
print MAIL "The document was referred by: $referer\n"; 
print MAIL "The Host Server is was $remhost\n"; 
close(MAIL); 
exit;
#http://www.webmasterworld.com/forum92/413.htm

<form method="POST" action="" onsubmit="proccessbyjs();"> 
// so, users will need to activate js to be able to post form