perl htmltreexpather.pl fudge.html
Hmm, so I would use the stack approach, ie *find*
q{
//div[@id='bodyContent']/*
}
everything before first h2 tag is key/value pairs
after that , each h2 tag is the key , and the non-h2 tags that follow are the value
#!/usr/bin/perl --
use strict; use warnings;
use HTML::TreeBuilder::XPath;
my $page = q{<html>
<head></head>
<body>
<div id="bodyContent">
<!-- start content -->
<p>Key words: Some words.
</p>
<p>Date: 2012-01-16
</p>
<p>Actualised: 2008-01-08
</p>
<p>Commented: 05.06.2007
</p>
<p>Encoded: Some code.
</p>
<h2> <span class="mw-headline" id="Problem"> Problem </span></h2
+>
<p>Problem description.
</p>
<p>Another description.
</p>
<h2> <span class="mw-headline" id="Solution1"> Solution 1 </span
+></h2>
<p>Solution description.
</p>
<h2> <span class="mw-headline" id="Solution2"> Solution 2 </span
+></h2>
<p>Solution description.
</p>
<h2> <span class="mw-headline" id="Comment"> Comment. </span></h
+2>
<p>Text of the comment.
</p>
<p>
<br/>
</p>
</div>
<hr/>
</body>
</html>};
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.",
}