#!/usr/bin/perl

use strict;
use warnings;

# This program will print out all <a href=".."> links in a
# document together with the text that goes with it.
#
# See also HTML::LinkExtor
use Encode;
use HTML::Parser;

my $p = HTML::Parser->new(
    api_version => 3,
    start_h     => [\&a_start_handler, "self,tagname,attr"],
    report_tags => [qw(a img)],
);
$p->parse_file(shift || die) || die $!;

sub a_start_handler {
    my ($self, $tag, $attr) = @_;
    return unless $tag eq "a";
    return unless exists $attr->{href};
    print "A $attr->{href}\n";

    $self->handler(text  => [], '@{dtext}');
    $self->handler(start => \&img_handler);
    $self->handler(end   => \&a_end_handler, "self,tagname");
}

sub img_handler {
    my ($self, $tag, $attr) = @_;
    return unless $tag eq "img";
    push(@{$self->handler("text")}, $attr->{alt} || "[IMG]");
}

sub a_end_handler {
    my ($self, $tag) = @_;
    my $text = encode('utf8', join("", @{$self->handler("text")}));
    $text =~ s/^\s+//;
    $text =~ s/\s+$//;
    $text =~ s/\s+/ /g;
    print "T $text\n";

    $self->handler("text",  undef);
    $self->handler("start", \&a_start_handler);
    $self->handler("end",   undef);
}