#!/usr/bin/perl --
use strict; use warnings;
use HTML::TreeBuilder::XPath;
my $page = q{
Key words: Some words.
Date: 2012-01-16
Actualised: 2008-01-08
Commented: 05.06.2007
Encoded: Some code.
Problem
Problem description.
Another description.
Solution 1
Solution description.
Solution 2
Solution description.
Text of the comment.
};
my $p = HTML::TreeBuilder::XPath->new_from_content( $page );
{
my @nodes = $p->findnodes( q{//div[@id='bodyContent']/*});
use List::AllUtils qw( before );
my @before_h2 = before { $_->tag eq 'h2' } @nodes;
splice @nodes, 0, scalar( @before_h2 );
my %body = map { split ':', $_->as_trimmed_text, 2 } @before_h2;
while( @nodes ){
my $key = shift(@nodes)->as_trimmed_text;
while( @nodes and $nodes[0]->tag ne 'h2' ){
my $val = shift(@nodes)->as_trimmed_text;
$body{ $key } .= $val;
}
}
use Data::Dump; dd\%body;
}
__END__
{
"Actualised" => " 2008-01-08",
"Comment." => "Text of the comment.",
"Commented" => " 05.06.2007",
"Date" => " 2012-01-16",
"Encoded" => " Some code.",
"Key words" => " Some words.",
"Problem" => "Problem description.Another description.",
"Solution 1" => "Solution description.",
"Solution 2" => "Solution description.",
}