#!/usr/bin/perl -w
use strict;
use LWP::Simple qw(get);
use HTML::TokeParser;
use URI;

my $new_link = "http://www.baz.com/cgi-bin/doubleclick.cgi?url=";

my $url = $ARGV[0] or die "usage: ". __FILE__ ." http://www.foo.com/bar.html\n";

my $file = get($url) or die "Cannot get the page '$url'\n";

my $P = HTML::TokeParser->new(\$file);

while (my $T = $P->get_token() )
{                     #   0     1     2       3        4
    if($$T[0] eq "S") # ["S", $tag, $attr, $attrseq, $text]
    {
        if($$T[1] eq 'img')
        {
            &handle_link($T, 'src');
        }
        elsif($$T[1] eq 'a')
        {
            &handle_link($T, 'href');
        }
        elsif($$T[1] eq 'script')
        {
            &handle_link($T, 'src');
        }
        else # nothing we wanna change
        {
            print $$T[4];
        }
    }
    elsif($$T[0] =~ /^(?:E|PI)$/ ) # end tag | process instruction
    {
        print $$T[2];
    }
    elsif($$T[0] =~ /^(?:T|C|D)$/ ) # text | comment | declaration
    {
        print $$T[1];
    }
} # endof while (my $T = $P->get_token)


sub handle_link
{
    my ( $T, $A) = @_;
    my $URI = new URI( $$T[2]->{$A} );

#   0     1     2       3        4
# ["S", $tag, $attr, $attrseq, $text]
    my $scheme = $URI->scheme();

    if( $scheme and $scheme =~ /^(http|ftp)$/i ) # only if its not relative url (yes scheme)
    {
        $$T[2]->{$A} = $new_link . $URI->path(); # path is escaped
    }

    print "<$$T[1]",
          ( map { qq| $_="$$T[2]->{$_}"| }
                @{$$T[3]}
          )
          , '>';
}