#!/usr/bin/perl

use warnings;
use strict;
use Data::Dumper;
$Data::Dumper::Indent = 1;

use HTML::TreeBuilder;

my $t = HTML::TreeBuilder->new_from_file(q{html/monk.html})
  or die qq{cant build tree};

my $pre  = $t->look_down(
  _tag => q{pre}, 
  class => q{preElement}
);
my @divs = $pre->look_down(
  _tag => q{div}
);

my %table;
my ($type, $record);
for my $div (@divs){
  if ($div->attr(q{class}) eq q{secTitle}){
    $type = $div->as_text;
    next;
  }
  $record++;
  my @spans = $div->look_down(
    _tag => q{span}, 
    class => qr/^x|f/
  );
  for my $span (@spans){
    my $class = $span->attr(q{class});
    my $txt   = $span->as_text;
    $table{$type}{$record}{$class} = $txt;
  }
  
  my $trailing_txt = trailing_text($div);
  $table{$type}{$record}{family_data} = $trailing_txt;
}

print Dumper \%table;

sub trailing_text {
  my ($div) = @_;
  my @rights = $div->right;
  my @txt;
  for my $right (@rights){
    if (ref $right){
      last if $right->tag eq q{div};
      next if $right->tag eq q{br};
      my $t = $right->as_text;
      next unless $t =~ /\S/;
      push @txt, trim($t);
    }
    else{
      next unless $right =~ /\S/;
      push @txt, trim($right);
    }
  }
  return join(q{ }, @txt);
}

sub trim{
  for (@_){
    s/^\s+//;
    s/\s+$//;
    s/\s+/ /g;
  }
  return wantarray?@_:$_[0];
}

##</code><code>##

$VAR1 = {
  'WIFE' => {
    '2' => {
      'fn n' => 'Marjoram Washburn',
      'family_data' => 'Born: Died: Bef 21 Nov 1717 Father: Philip Washburn Mother: Elizabeth Irish'
    }
  },
  'CHILDREN' => {
    '6' => {
      'fn n' => 'Mary Leonard',
      'family_data' => 'Born: Bef 1710 Died: 1793 at Marlborough, MA Husband: Daniel Herrington'
    },
    '4' => {
      'fn n' => 'Elizabeth Leonard',
      'family_data' => 'Born: Abt 1702 Died: 14 Oct 1783 at Bridgewater, Plymouth, MA Husband: James Washburn'
    },
    '3' => {
      'fn n' => 'John Leonard',
      'family_data' => 'Born: Bet 1695 and 1723 Died: Bet 1748 and 1808 Wife: Anna Noble'
    },
    '7' => {
      'fn n' => 'Margene Leonard',
      'family_data' => 'Born: Abt 1710 Died: Husband: Nathaniel Pratt'
    },
    '5' => {
      'fn n' => 'Josiah Leonard',
      'family_data' => 'Born: Abt 1704 Died:'
    }
  },
  'HUSBAND' => {
    '1' => {
      'x-marriage-date' => '1699-11-2',
      'fn n' => 'Josiah Leonard',
      'family_data' => 'Other Spouses: Abigail Washburn Father: John Leonard Mother: Sarah Leonard',
      'x-gender' => 'Male',
      'x-death-date' => '1745-1-1',
      'x-death-location' => 'Bridgewater, Plymouth, MA',
      'x-marriage-location' => 'Bridgewater, Plymouth, MA'
    }
  }
};