#!/usr/bin/perl

use strict;
use warnings;

use LWP::Simple qw(get);
my $url = "http://www.oceanoutlook.com.au/table/perth.html";
my $source = get($url);

use HTML::Tree;
my $tree = HTML::Tree->new();

$tree->parse($source);

my (@tds) = $tree->look_down( '_tag', 'td' );

my @headers;
my @data;
my $month;

my $i = 0;
foreach (@tds) {
  $i++;
  next if ($i < 5); # The first 4 headers we dont need
  next if ($i == 16); # Bad HTML... skip it
  next if ($i == scalar(@tds)); # The last one we dont need
  if (($i >= 5) && ($i <= 15)) { # These are the headers we want
    my $header = $_->as_text;
    if ($i == 5) {
      $month = $_->as_text;
      $header = "Date";
    } # end-if
    $header = "Swell Direction" if ($header eq "Dir");
    push(@headers, $header);
  } # end-if
  if ($i > 16) { # This is the data
    push(@data, $_->as_text);
  } # end-if
} # end-foreach

# Output to xml
use XML::Writer;
my $writer = new XML::Writer();

$writer->startTag("doc", class => "simple");
$writer->dataElement( 'title', "Swell Forecast");
$writer->dataElement( 'month', $month);

my $count = -1;
for ($i=0;$i<scalar(@data);$i++) {
  $count++;
  if ($count == 0) {
    $writer->startTag( "prediction", date => $data[$i]);
    $writer->dataElement( 'title', $data[$i]);
    $i++;
    $count++;
  } # end-if
  if ($count == 2) {
    $writer->startTag( "swell_height" );
    $writer->dataElement( 'unit', 'meters');
  } # end-if
  if ($count == 5) {
    $writer->startTag( "peak_period" );
    $writer->dataElement( 'unit', 'seconds');
  } # end-if
  if ($count == 8) {
    $writer->startTag( "wind" );
    $writer->dataElement( 'unit', 'knots');
  } # end-if

  $writer->dataElement( 'item', $data[$i], name => $headers[$count]);

  if ($count == 4) {
    $writer->endTag( "swell_height" );
  } # end-if
  if ($count == 7) {
    $writer->endTag( "peak_period" );
  } # end-if
  if ($count == 10) {
    $writer->endTag( "wind" );
  } # end-if

  if ($count == scalar(@headers)-1) {
    $writer->endTag();
    $count = -1;
  } # end-if
} # end-for

$writer->endTag();
$writer->end();

exit;
[download]