DON'T EDIT/REMOVE - referred to in http://perlmonks.org/?node_id=1024748

orsr.pl

#!/usr/bin/perl
# Which companies are the names associated with?
use strict;
use warnings;
use HTML::LinkExtor;
use LWP::Simple;
use URI::Encode qw(uri_encode);

my $names_file = shift;

open my $fh, "<", $names_file;
my @names = <$fh>;
close $fh;

for my $name (@names) {
    chomp $name;
    print "Working on '$name'\n";
    my $base_url = 'http://www.orsr.sk';

    my @names = split ' ', $name;
    if ( scalar @names ne 2 ) {    # strange name
        print "Skipping: >$name<\n";
        next;
    }

    my $gname   = uri_encode( lc $names[0] );
    my $surname = uri_encode( lc $names[1] );

    #my $gname   = lc $names[0];
    #my $surname = lc $names[1];

    my $url =
"${base_url}/hladaj_osoba.asp?PR=${surname}&MENO=${gname}&SID=0&T=f0&R=on";
    print ">$url<\n";    # Debug

    sleep int rand(3);    # lets be decent and wait for some random time
    my @ids = get_ids($url);
    if ( @ids == 0 ) {

        # The name is not associated with any company
    } else {
        print "$name associated with ", scalar @ids, " companies\n";
        for my $id (@ids) {
            print "\t$base_url/vypis.asp?ID=${id}&SID=5&P=0\n";
        }
    }
}

####################
sub get_ids {
####################
    my $url = shift;

    my @ids;    # internal ORSR IDs
    my $parser = HTML::LinkExtor->new();
    $parser->parse( get $url)->eof;
    for my $linkarray ( $parser->links ) {
        my @element = @$linkarray;
        my ( $elt_type, $attr_name, $link ) = @element;
        if ( $elt_type eq 'a' and $attr_name eq 'href' ) {

            # vypis.asp?ID=101797&SID=5&P=0
            push @ids, $1 if $link =~ /^vypis\.asp\?ID=(\d+).*P=0$/;
        }
    }

    return @ids;
}