This piece of code download the two images you need, at least i hope ;)

#!/usr/bin/perl 
use strict;
use warnings;
use WWW::Mechanize;
$|++;


my $site = 'http://www.ebi.ac.uk';
my $start =
'/thornton-srv/databases/cgi-bin/pdbsum/GetPage.pl?pdbcode=2j6p&templa
+te=ligands.html&l=1.1';
my $img_string = 'ligplot\d{2}_\d{2}';

my $m = WWW::Mechanize->new( autocheck => 1 );
$m->get( $site . $start );

my @links = 
@{ $m->find_all_links( tag => 'a', text_regex => qr/^EPE\s/ ) };

for my $link (@links) {

    print $link->text, "\n", $link->url, "\n";

    $m->follow_link( tag => 'a', text_regex => qr/^EPE\s/ )
      or die "can't follow link";

    my $img = $m->find_link( url_regex => qr/$img_string/ );
    
    $img->url =~ /($img_string)/;
    next unless defined $1; 
    
    print " Fetching $1...",
    $m->mirror( $img->url_abs, $1 )->message, "\n";
}
[download]

hth,
PooLpi