User-agent: *
Disallow: /cgi-bin/
Disallow: /tmp/
Allow:  /opten/cegism/
Allow: /opten/cegtarlight/cegker.php
Allow: /opten/ttlight/optentt.php
Disallow: /opten/
Disallow: /opten-data/

RewriteCond %{ENV:IS_ROBOT} true
#RewriteCond %{REMOTE_HOST} !\.googlebot\.com$    [NC]
RewriteRule .* /cgi-bin/bad.pl [L,T=application/x-httpd-cgi]



#Robots known or highly suspected of collecting email addresses for spam
RewriteCond %{HTTP_USER_AGENT} ^(autoemailspider|Bullseye|CherryPicker|Crescent|ecollector|EmailCollector|Email.Extractor|EmailSiphon|EmailWolf|ExtractorPro|fastlwspider|.*LWP|Digger|.*hhjhj@yahoo|Microsoft.URL|Mozilla/3.Mozilla/2.01|Mozilla.*NEWT|NICErsPRO|SurfWalker|Telesoft|WebBandit|WebEMailExtrac|Zeus.*Webster) [NC,OR]
 
 # Robots (sometimes called spiders) which regularly violate robots.txt
RewriteCond %{HTTP_USER_AGENT} ^(ADSARobot|.*almaden\.ibm|ASSORT|big.brother|bumblebee|Digimarc|FavOrg|FAST|.*fluffy|.*Girafabot|HomePageSearch|IncyWincy|Ingelin|NPBot|Openfind|OpenTextSiteCrawler|OrangeBot|Robozilla|ScoutAbout|.*searchhippo|searchterms\.it|sitecheck|UIowaCrawler|.*webcraft@bea\.com|WEBMASTERS|WhosTalking|WISEbot|Yandex) [NC,OR]
 
 # Agents used for both good and bad purposes, such as sucking up bandwidth
 # by downloading entire sites, or probing servers for security exploits.
RewriteCond %{HTTP_USER_AGENT} ^(ASPSeek|Deweb|Fetch|FlashGet|Getleft|GetURL|GetWebPage|.*HTTrack|KWebGet|libwww-perl|Mirror|NetAnts|NetCarta|netprospector|Net.Vampire|pavuk|PSurf|PushSite|reget|Rsync|Shai|SpiderBot|SuperBot|tarspider|Templeton|w3mir|web.by.mail|WebCopier|WebCopy|WebMiner|WebReaper|WebSnake|WebStripper|webvac|webwalk|WebZIP|Wget|XGET) [NC,OR]
 
 # Miscellaneous (suspicious -- more information would be appreciated)
RewriteCond %{HTTP_USER_AGENT} ^(ah-ha|aktuelles|amzn_assoc|ATHENS|attache|bew|disco|.*DTS.Agent|Favorites.Sweeper|FEZhead|Generic|GetRight|go-ahead-got-it|.*Harvest|IBM_Planetwide|leech|MCspider|NetResearchServer|nost\.info|OpaL|PackRat|RepoMonkey|.*Rover|Spegla|SqWorm|.*TrueRobot|UtilMind|vspider|.*WUMPUS) [NC,OR]
 
 # Blank or 10-letter user agent
RewriteCond %{HTTP_USER_AGENT} ^(-?|[A-Z]{10})$                    [OR]
 
 # A host which tries to hide itself in reverse DNS lookup
RewriteCond %{REMOTE_HOST} ^private$                               [NC,OR]
 
# Web surveying sites (may require using ipchains)
RewriteCond %{HTTP_REFERER} (traffixer|netfactual|netcraft)\.com   [NC,OR]
RewriteCond %{REMOTE_HOST} \.netcraft\.com$                        [NC,OR]
 
 # A fake referrer that's often used -- use this unless your pages are related
 # in some way to atomic energy and could really be linked to from www.iaea.org
RewriteCond %{HTTP_REFERER} ^[^?]*iaea\.org                        [NC,OR]
 
 # "addresses.com" is a referer used by an email address extractor
RewriteCond %{HTTP_REFERER} ^[^?]*addresses\.com                   [NC,OR]
 
 # A fake referrer that's used in conjuncting with formmail exploits
RewriteCond %{HTTP_REFERER} ^[^?]*\.ideography\.co\.uk             [NC]
 
 # The rule which blocks out further access from the host
RewriteRule .* /cgi-bin/bad.pl [L,T=application/x-httpd-cgi]