How can I protect my site from HTTrack or other software's ripping?

Posted: 11-04-2020 | Views: 2922
How can I protect my site from HTTrack or other software's ripping?

1. In .htaccess file (If not exists create one in public_html folder)
<IfModule mod_rewrite.c>

    <IfModule mod_negotiation.c>
        Options -MultiViews
    </IfModule>

    RewriteEngine On

    ##
    ## You may need to uncomment the following line for some hosting environments,
    ## if you have installed to a subdirectory, enter the name here also.
    ##
    RewriteBase /

    ##
    ## Protect from tracker apps
    ##
    RewriteCond %{HTTP_USER_AGENT} almaden [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Anarchie [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ASPSeek [OR]
    RewriteCond %{HTTP_USER_AGENT} ^attach [OR]
    RewriteCond %{HTTP_USER_AGENT} ^autoemailspider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^BackWeb [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Bandit [OR]
    RewriteCond %{HTTP_USER_AGENT} ^BatchFTP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^BlackWidow [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Bot\ mailto:craftbot@yahoo.com [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Buddy [OR]
    RewriteCond %{HTTP_USER_AGENT} ^bumblebee [OR]
    RewriteCond %{HTTP_USER_AGENT} ^CherryPicker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ChinaClaw [OR]
    RewriteCond %{HTTP_USER_AGENT} ^CICC [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Collector [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Copier [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Crescent [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Custo [OR]
    RewriteCond %{HTTP_USER_AGENT} ^DA [OR]
    RewriteCond %{HTTP_USER_AGENT} ^DIIbot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^DISCo [OR]
    RewriteCond %{HTTP_USER_AGENT} ^DISCo\ Pump [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} ^eCatch [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EasyDL/2.99 [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EirGrabber [OR]
    RewriteCond %{HTTP_USER_AGENT} email [NC,OR]
    RewriteCond %{HTTP_USER_AGENT} ^EmailCollector [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EmailSiphon [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EmailWolf [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Express\ WebPictures [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ExtractorPro [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EyeNetIE [OR]
    RewriteCond %{HTTP_USER_AGENT} ^FileHound [OR]
    RewriteCond %{HTTP_USER_AGENT} ^FlashGet [OR]
    RewriteCond %{HTTP_USER_AGENT} FrontPage [NC,OR]
    RewriteCond %{HTTP_USER_AGENT} ^GetRight [OR]
    RewriteCond %{HTTP_USER_AGENT} ^GetSmart [OR]
    RewriteCond %{HTTP_USER_AGENT} ^GetWeb! [OR]
    RewriteCond %{HTTP_USER_AGENT} ^gigabaz [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Go\!Zilla [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Go!Zilla [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Go-Ahead-Got-It [OR]
    RewriteCond %{HTTP_USER_AGENT} ^gotit [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Grabber [OR]
    RewriteCond %{HTTP_USER_AGENT} ^GrabNet [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Grafula [OR]
    RewriteCond %{HTTP_USER_AGENT} ^grub-client [OR]
    RewriteCond %{HTTP_USER_AGENT} ^HMView [OR]
    RewriteCond %{HTTP_USER_AGENT} ^HTTrack [OR]
    RewriteCond %{HTTP_USER_AGENT} ^httpdown [OR]
    RewriteCond %{HTTP_USER_AGENT} .*httrack.* [NC,OR]
    RewriteCond %{HTTP_USER_AGENT} ^ia_archiver [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Image\ Stripper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Image\ Sucker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Indy*Library [OR]
    RewriteCond %{HTTP_USER_AGENT} Indy\ Library [NC,OR]
    RewriteCond %{HTTP_USER_AGENT} ^InterGET [OR]
    RewriteCond %{HTTP_USER_AGENT} ^InternetLinkagent [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Internet\ Ninja [OR]
    RewriteCond %{HTTP_USER_AGENT} ^InternetSeer.com [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Iria [OR]
    RewriteCond %{HTTP_USER_AGENT} ^JBH*agent [OR]
    RewriteCond %{HTTP_USER_AGENT} ^JetCar [OR]
    RewriteCond %{HTTP_USER_AGENT} ^JOC\ Web\ Spider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^JustView [OR]
    RewriteCond %{HTTP_USER_AGENT} ^larbin [OR]
    RewriteCond %{HTTP_USER_AGENT} ^LeechFTP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^LexiBot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^lftp [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Link*Sleuth [OR]
    RewriteCond %{HTTP_USER_AGENT} ^likse [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Link [OR]
    RewriteCond %{HTTP_USER_AGENT} ^LinkWalker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mag-Net [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Magnet [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mass\ Downloader [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Memo [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Microsoft.URL [OR]
    RewriteCond %{HTTP_USER_AGENT} ^MIDown\ tool [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mirror [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mister\ PiX [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mozilla.*Indy [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mozilla.*NEWT [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mozilla*MSIECrawler [OR]
    RewriteCond %{HTTP_USER_AGENT} ^MS\ FrontPage* [OR]
    RewriteCond %{HTTP_USER_AGENT} ^MSFrontPage [OR]
    RewriteCond %{HTTP_USER_AGENT} ^MSIECrawler [OR]
    RewriteCond %{HTTP_USER_AGENT} ^MSProxy [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Navroad [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NearSite [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetAnts [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetMechanic [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetSpider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Net\ Vampire [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetZIP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NICErsPRO [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Ninja [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Octopus [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Offline\ Explorer [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Offline\ Navigator [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Openfind [OR]
    RewriteCond %{HTTP_USER_AGENT} ^PageGrabber [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Papa\ Foto [OR]
    RewriteCond %{HTTP_USER_AGENT} ^pavuk [OR]
    RewriteCond %{HTTP_USER_AGENT} ^pcBrowser [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Ping [OR]
    RewriteCond %{HTTP_USER_AGENT} ^PingALink [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Pockey [OR]
    RewriteCond %{HTTP_USER_AGENT} ^psbot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Pump [OR]
    RewriteCond %{HTTP_USER_AGENT} ^QRVA [OR]
    RewriteCond %{HTTP_USER_AGENT} ^RealDownload [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Reaper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Recorder [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ReGet [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Scooter [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Seeker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Siphon [OR]
    RewriteCond %{HTTP_USER_AGENT} ^sitecheck.internetseer.com [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SiteSnagger [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SlySearch [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SmartDownload [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Snake [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SpaceBison [OR]
    RewriteCond %{HTTP_USER_AGENT} ^sproose [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Stripper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Sucker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SuperBot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SuperHTTP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Surfbot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Szukacz [OR]
    RewriteCond %{HTTP_USER_AGENT} ^tAkeOut [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Teleport\ Pro [OR]
    RewriteCond %{HTTP_USER_AGENT} ^URLSpiderPro [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Vacuum [OR]
    RewriteCond %{HTTP_USER_AGENT} ^VoidEYE [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} ^[Ww]eb[Bb]andit [OR]
    RewriteCond %{HTTP_USER_AGENT} ^webcollage [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebCopier [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Web\ Downloader [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebEMailExtrac.* [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebFetch [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebGo\ IS [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebHook [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebLeacher [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebMiner [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebMirror [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebReaper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebSauger [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Website [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Website\ eXtractor [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Website\ Quester [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Webster [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebStripper [OR]
    RewriteCond %{HTTP_USER_AGENT} WebWhacker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebZIP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Wget [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Whacker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Widow [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WWWOFFLE [OR]
    RewriteCond %{HTTP_USER_AGENT} ^x-Tractor [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Xaldon\ WebSpider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Xenu [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Zeus.*Webster [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Zeus
    RewriteRule ^.* – [F,L]

</IfModule>
2. In robots.txt file (If not exists create one in public_html folder)

Note: Block all but AdsBot crawlers

More details about robots.txt => About robots.txt

robots.txt generated for www.example.com

User-agent: *
Disallow: /

Sitemap: https://example.com/sitemap.xml

Add comment