Interdire l’aspiration de votre site Plusieurs webmasters ont marre lorsqu’ils trouvent le contenu de leur site à été aspiré à l’aide des outils comme httrack, flashget…
Une des méthodes pour stopper cette action c’est de créer un fichier .htaccess à la racine de votre site et y mettre:
RewriteEngine on
RewriteCond %{HTTP_USER_AGENT} ADSARobot [OR]
RewriteCond %{HTTP_USER_AGENT} ah-ha [NC,OR]
RewriteCond %{HTTP_USER_AGENT} aktuelles [NC,OR]
RewriteCond %{HTTP_USER_AGENT} amzn_assoc [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Anarchie [OR]
RewriteCond %{HTTP_USER_AGENT} ASPSeek [OR]
RewriteCond %{HTTP_USER_AGENT} ASSORT [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ATHENS [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Atomz [OR]
RewriteCond %{HTTP_USER_AGENT} attach [NC,OR]
RewriteCond %{HTTP_USER_AGENT} attache [NC,OR]
RewriteCond %{HTTP_USER_AGENT} autoemailspider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} BackWeb [OR]
RewriteCond %{HTTP_USER_AGENT} Bandit [OR]
RewriteCond %{HTTP_USER_AGENT} BatchFTP [OR]
RewriteCond %{HTTP_USER_AGENT} bdfetch [NC,OR]
RewriteCond %{HTTP_USER_AGENT} big.brother [NC,OR]
RewriteCond %{HTTP_USER_AGENT} BlackWidow [OR]
RewriteCond %{HTTP_USER_AGENT} bmclient [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Boston\ Project [OR]
RewriteCond %{HTTP_USER_AGENT} BravoBrian\ SpiderEngine\ MarcoPolo [OR]
RewriteCond %{HTTP_USER_AGENT} Buddy [OR]
RewriteCond %{HTTP_USER_AGENT} Bullseye [NC,OR]
RewriteCond %{HTTP_USER_AGENT} bumblebee [NC,OR]
RewriteCond %{HTTP_USER_AGENT} capture [OR]
RewriteCond %{HTTP_USER_AGENT} ChinaClaw [OR]
RewriteCond %{HTTP_USER_AGENT} CICC [OR]
RewriteCond %{HTTP_USER_AGENT} clipping [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Crescent [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Crescent\ Internet\ ToolPak [OR]
RewriteCond %{HTTP_USER_AGENT} Custo [OR]
RewriteCond %{HTTP_USER_AGENT} cyberalert [OR]
RewriteCond %{HTTP_USER_AGENT} Deweb [NC,OR]
RewriteCond %{HTTP_USER_AGENT} diagem [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Digger [OR]
RewriteCond %{HTTP_USER_AGENT} Digimarc [OR]
RewriteCond %{HTTP_USER_AGENT} DIIbot [OR]
RewriteCond %{HTTP_USER_AGENT} disco [NC,OR]
RewriteCond %{HTTP_USER_AGENT} DISCoFinder [OR]
RewriteCond %{HTTP_USER_AGENT} Download\ Demon [OR]
RewriteCond %{HTTP_USER_AGENT} Download\ Wonder [OR]
RewriteCond %{HTTP_USER_AGENT} Downloader [OR]
RewriteCond %{HTTP_USER_AGENT} Drip [OR]
RewriteCond %{HTTP_USER_AGENT} DSurf15a [OR]
RewriteCond %{HTTP_USER_AGENT} DTS.Agent [NC,OR]
RewriteCond %{HTTP_USER_AGENT} EasyDL [OR]
RewriteCond %{HTTP_USER_AGENT} ecollector [NC,OR]
RewriteCond %{HTTP_USER_AGENT} efp_AT_gmx\.net [OR]
RewriteCond %{HTTP_USER_AGENT} Email\ Extractor [OR]
RewriteCond %{HTTP_USER_AGENT} EirGrabber [OR]
RewriteCond %{HTTP_USER_AGENT} EmailSiphon [OR]
RewriteCond %{HTTP_USER_AGENT} Express\ WebPictures [OR]
RewriteCond %{HTTP_USER_AGENT} EyeNetIE [OR]
RewriteCond %{HTTP_USER_AGENT} fastlwspider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} FavOrg [OR]
RewriteCond %{HTTP_USER_AGENT} Favorites\ Sweeper [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Fetch [NC,OR]
RewriteCond %{HTTP_USER_AGENT} FEZhead [NC,OR]
RewriteCond %{HTTP_USER_AGENT} FileHound [OR]
RewriteCond %{HTTP_USER_AGENT} FlashGet\ WebWasher [OR]
RewriteCond %{HTTP_USER_AGENT} FlickBot [OR]
RewriteCond %{HTTP_USER_AGENT} fluffy [NC,OR]
RewriteCond %{HTTP_USER_AGENT} GalaxyBot [OR]
RewriteCond %{HTTP_USER_AGENT} Generic [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Getleft [NC,OR]
RewriteCond %{HTTP_USER_AGENT} GetRight [OR]
RewriteCond %{HTTP_USER_AGENT} GetSmart [OR]
RewriteCond %{HTTP_USER_AGENT} GetWeb! [OR]
RewriteCond %{HTTP_USER_AGENT} GetWebPage [NC,OR]
RewriteCond %{HTTP_USER_AGENT} gigabaz [OR]
RewriteCond %{HTTP_USER_AGENT} Girafabot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} go-ahead-got-it [NC,OR]
RewriteCond %{HTTP_USER_AGENT} GornKer [OR]
RewriteCond %{HTTP_USER_AGENT} Grabber [NC,OR]
RewriteCond %{HTTP_USER_AGENT} GrabNet [OR]
RewriteCond %{HTTP_USER_AGENT} Grafula [OR]
RewriteCond %{HTTP_USER_AGENT} Green\ Research [OR]
RewriteCond %{HTTP_USER_AGENT} Harvest [NC,OR]
RewriteCond %{HTTP_USER_AGENT} hhjhj_AT_yahoo [NC,OR]
RewriteCond %{HTTP_USER_AGENT} hloader [OR]
RewriteCond %{HTTP_USER_AGENT} HMView [OR]
RewriteCond %{HTTP_USER_AGENT} HomePageSearch [OR]
RewriteCond %{HTTP_USER_AGENT} httpdown [OR]
RewriteCond %{HTTP_USER_AGENT} http\ generic [OR]
RewriteCond %{HTTP_USER_AGENT} IBM_Planetwide [OR]
RewriteCond %{HTTP_USER_AGENT} Image\ Stripper [OR]
RewriteCond %{HTTP_USER_AGENT} Image\ Sucker [OR]
RewriteCond %{HTTP_USER_AGENT} imagefetch [OR]
RewriteCond %{HTTP_USER_AGENT} IncyWincy [NC,OR]
RewriteCond %{HTTP_USER_AGENT} informant [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Ingelin [NC,OR]
RewriteCond %{HTTP_USER_AGENT} InterGET [OR]
RewriteCond %{HTTP_USER_AGENT} Internet\ Ninja [OR]
RewriteCond %{HTTP_USER_AGENT} InternetLinkAgent [OR]
RewriteCond %{HTTP_USER_AGENT} InternetSeer\.com [OR]
RewriteCond %{HTTP_USER_AGENT} Iria [OR]
RewriteCond %{HTTP_USER_AGENT} Irvine [OR]
RewriteCond %{HTTP_USER_AGENT} JBH*Agent [OR]
RewriteCond %{HTTP_USER_AGENT} JetCar [OR]
RewriteCond %{HTTP_USER_AGENT} JOC [OR]
RewriteCond %{HTTP_USER_AGENT} JOC\ Web\ Spider [OR]
RewriteCond %{HTTP_USER_AGENT} JustView [OR]
RewriteCond %{HTTP_USER_AGENT} KWebGet [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Lachesis [OR]
RewriteCond %{HTTP_USER_AGENT} larbin [NC,OR]
RewriteCond %{HTTP_USER_AGENT} LeechFTP [OR]
RewriteCond %{HTTP_USER_AGENT} LexiBot [OR]
RewriteCond %{HTTP_USER_AGENT} lftp [OR]
RewriteCond %{HTTP_USER_AGENT} libwww [OR]
RewriteCond %{HTTP_USER_AGENT} likse [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Link*Sleuth [OR]
RewriteCond %{HTTP_USER_AGENT} LINKS\ ARoMATIZED [OR]
RewriteCond %{HTTP_USER_AGENT} Web\ Data\ Extractor [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Web\ Downloader [OR]
RewriteCond %{HTTP_USER_AGENT} Web\ Image\ Collector [OR]
RewriteCond %{HTTP_USER_AGENT} Web\ Sucker [OR]
RewriteCond %{HTTP_USER_AGENT} WebAuto [OR]
RewriteCond %{HTTP_USER_AGENT} Webclipping [OR]
RewriteCond %{HTTP_USER_AGENT} webcollector [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebCopier [OR]
RewriteCond %{HTTP_USER_AGENT} webcraft_AT_bea [NC,OR]
RewriteCond %{HTTP_USER_AGENT} webdevil [NC,OR]
RewriteCond %{HTTP_USER_AGENT} webdownloader [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Webdup [OR]
RewriteCond %{HTTP_USER_AGENT} WebFetch [OR]
RewriteCond %{HTTP_USER_AGENT} WebGo\ IS [OR]
RewriteCond %{HTTP_USER_AGENT} WebHook [OR]
RewriteCond %{HTTP_USER_AGENT} Webinator [OR]
RewriteCond %{HTTP_USER_AGENT} WebLeacher [OR]
RewriteCond %{HTTP_USER_AGENT} WEBMASTERS [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebMiner [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebMirror [OR]
RewriteCond %{HTTP_USER_AGENT} webmole [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebReaper [OR]
RewriteCond %{HTTP_USER_AGENT} WebSauger [OR]
RewriteCond %{HTTP_USER_AGENT} Website\ eXtractor [OR]
RewriteCond %{HTTP_USER_AGENT} Website\ Quester [OR]
RewriteCond %{HTTP_USER_AGENT} WebSnake [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Webster [OR]
RewriteCond %{HTTP_USER_AGENT} WebStripper [OR]
RewriteCond %{HTTP_USER_AGENT} websucker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} webvac [NC,OR]
RewriteCond %{HTTP_USER_AGENT} webwalk [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebWhacker [OR]
RewriteCond %{HTTP_USER_AGENT} webweasel [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebZIP [OR]
RewriteCond %{HTTP_USER_AGENT} Wget [OR]
RewriteCond %{HTTP_USER_AGENT} whizbang [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WhosTalking [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Widow [OR]
RewriteCond %{HTTP_USER_AGENT} WISEbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WUMPUS [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Wweb [OR]
RewriteCond %{HTTP_USER_AGENT} WWWOFFLE [OR]
RewriteCond %{HTTP_USER_AGENT} Xaldon\ WebSpider [OR]
RewriteCond %{HTTP_USER_AGENT} XGET [NC,OR]
RewriteCond %{HTTP_USER_AGENT} x-Tractor [OR]
RewriteCond %{HTTP_USER_AGENT} Yandex [OR]
RewriteCond %{REMOTE_HOST} ^private$ [NC,OR]
RewriteCond %{HTTP_USER_AGENT} traffixer [NC,OR]
RewriteCond %{HTTP_USER_AGENT} netfactual [NC,OR]
RewriteCond %{HTTP_USER_AGENT} netcraft [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^[^?]*iaea\.org [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^[^?]*addresses\.com [NC,OR]
RewriteCond %{HTTP_USER_AGENT} [0-9A-Za-z]{15,} [OR]
RewriteCond %{HTTP_USER_AGENT} ^[0-9A-Za-z]+$ [OR]
RewriteCond %{HTTP_USER_AGENT} ^[^?]*\.ideography\.co\.uk [NC] |