contrib/htaccess

   1 RewriteEngine on
   2
   3 # Allow only GET and POST verbs
   4 RewriteCond %{REQUEST_METHOD} !^(GET|POST)$ [NC,OR]
   5
   6 # Ban Typical Vulnerability Scanners and others
   7 # Kick out Script Kiddies
   8 RewriteCond %{HTTP_USER_AGENT} ^(java|curl|wget).* [NC,OR]
   9 RewriteCond %{HTTP_USER_AGENT} ^.*(libwww-perl|curl|wget|python|nikto|wkito|pikto|scan|acunetix).* [NC,OR]
  10 RewriteCond %{HTTP_USER_AGENT} ^.*(winhttp|HTTrack|clshttp|archiver|loader|email|harvest|extract|grab|miner).* [NC,OR]
  11
  12 # Ban Search Engines, Crawlers to your administrative panel
  13 # No reasons to access from bots
  14 # Ultimately Better than the useless robots.txt
  15 # Did google respect robots.txt?
  16 # Try google: intitle:phpMyAdmin intext:"Welcome to phpMyAdmin *.*.*" intext:"Log in" -wiki -forum -forums -questions intext:"Cookies must be enabled"
  17 RewriteCond %{HTTP_USER_AGENT} ^.*(AdsBot-Google|ia_archiver|Scooter|Ask.Jeeves|Baiduspider|Exabot|FAST.Enterprise.Crawler|FAST-WebCrawler|www\.neomo\.de|Gigabot|Mediapartners-Google|Google.Desktop|Feedfetcher-Google|Googlebot|heise-IT-Markt-Crawler|heritrix|ibm.com\cs/crawler|ICCrawler|ichiro|MJ12bot|MetagerBot|msnbot-NewsBlogs|msnbot|msnbot-media|NG-Search|lucene.apache.org|NutchCVS|OmniExplorer_Bot|online.link.validator|psbot0|Seekbot|Sensis.Web.Crawler|SEO.search.Crawler|Seoma.\[SEO.Crawler\]|SEOsearch|Snappy|www.urltrends.com|www.tkl.iis.u-tokyo.ac.jp/~crawler|SynooBot|crawleradmin.t-info@telekom.de|TurnitinBot|voyager|W3.SiteSearch.Crawler|W3C-checklink|W3C_Validator|www.WISEnutbot.com|yacybot|Yahoo-MMCrawler|Yahoo\!.DE.Slurp|Yahoo\!.Slurp|YahooSeeker).* [NC]
  18 RewriteRule .* - [F]
  19