Google

WEB CRAWLER AND HTML EXTRACTOR Please input the URL of the site to be searched Please use a full URL (eg. http://www.dcs.shef.ac. http://www.google.com/ Google .gif" width=276 height=110 alt="Google">

Terminating on signal SIGINT(2) ##

##

use WWW::Mechanize;
 use URI;
  
 print "WEB CRAWLER AND HTML EXTRACTOR \n";
 print "Please input the URL of the site to be searched \n";
 print "Please use a full URL (eg. http://www.dcs.shef.ac.uk/) \n";
 
 #Create an instance of the webcrawler
 my $webcrawler = WWW::Mechanize->new();

 my $url_name = ; # The user inputs the URL to be searched
 
 my $uri = URI->new($url_name); # Process the URL and make it a URI
 
 #Grab the contents of the URL given by the user
 $webcrawler->get($uri);
  
 # Put the links that exist in the HTML of the URL given by the user in an array
 my @website_links = $webcrawler->links($uri);  
 
 # The HTML is stripped off the contents and the text is stored in an array of  strings
 my $x = 0;
 my @stripped_html;
 $stripped_html[$x] = $webcrawler->content( format => "text" );
 print $stripped_html[$x];