use WWW::Newsgrabber; 
use LWP::Simple;
use HTML::ContentExtractor;
use LWP::UserAgent;

$kot_tekst='HASH|albania.htmlcomments|lajmet|free_web_stats|index.html$|ne.html$|arkivi.html$|IMG|html#c';

my $extractor = HTML::ContentExtractor->new();
my $agent=LWP::UserAgent->new;
$dirname = "C:\\Users\\Administrator\\Desktop\\corpus";
my $j=1;

$obj[0]= WWW::Newsgrabber->new( url => 'http://www.shekulli.com.al/biznes/', regex => '\.html' );
$obj[1] = WWW::Newsgrabber->new( url => 'http://www.gazeta-shqip.com/#/ekonomi', regex => '\.html' );

foreach $item (@obj){
my $ResultHashRef = $item->getNews();

while ( my ($url,$name)=each(%{$ResultHashRef})){
        if ($url !~ /$kot_tekst/){
        $counter++;
        my $res=$agent->get($url);
    my $HTML = $res->decoded_content();
    $extractor->extract($url,$HTML);
    $c= $extractor->as_text();
    $c =~ m/ KOMENTE/g;
    $c=substr($c,1,pos($c)-7);    
    $hash_biznes{$url}=$c;
}}};