perl htmltreexpather.pl fudge.html
------------------------------------------------------------------
HTML::Element=HASH(0xb338e4) 0.1.0.0
Key words: Some words.
/html/body/div/p
//div[@id='bodyContent']/p
//div[@id='bodyContent']/p
------------------------------------------------------------------
HTML::Element=HASH(0xb33944) 0.1.0.1
Date: 2012-01-16
/html/body/div/p[2]
//div[@id='bodyContent']/p[2]
//div[@id='bodyContent']/p[2]
------------------------------------------------------------------
HTML::Element=HASH(0xb339b4) 0.1.0.2
Actualised: 2008-01-08
/html/body/div/p[3]
//div[@id='bodyContent']/p[3]
//div[@id='bodyContent']/p[3]
------------------------------------------------------------------
HTML::Element=HASH(0xb33a24) 0.1.0.3
Commented: 05.06.2007
/html/body/div/p[4]
//div[@id='bodyContent']/p[4]
//div[@id='bodyContent']/p[4]
------------------------------------------------------------------
HTML::Element=HASH(0xb33a94) 0.1.0.4
Encoded: Some code.
/html/body/div/p[5]
//div[@id='bodyContent']/p[5]
//div[@id='bodyContent']/p[5]
------------------------------------------------------------------
HTML::Element=HASH(0xb33b14) 0.1.0.5
Problem
/html/body/div/h2
//div[@id='bodyContent']/h2
//div[@id='bodyContent']/h2
------------------------------------------------------------------
HTML::Element=HASH(0xb33bd4) 0.1.0.5.0
Problem
/html/body/div/h2/span
//span[@id='Problem']
//span[@id='Problem']
------------------------------------------------------------------
HTML::Element=HASH(0xb33bc4) 0.1.0.6
Problem description.
/html/body/div/p[6]
//div[@id='bodyContent']/p[6]
//div[@id='bodyContent']/p[6]
------------------------------------------------------------------
HTML::Element=HASH(0xb33c64) 0.1.0.7
Another description.
/html/body/div/p[7]
//div[@id='bodyContent']/p[7]
//div[@id='bodyContent']/p[7]
------------------------------------------------------------------
HTML::Element=HASH(0xb33ce4) 0.1.0.8
Solution 1
/html/body/div/h2[2]
//div[@id='bodyContent']/h2[2]
//div[@id='bodyContent']/h2[2]
------------------------------------------------------------------
HTML::Element=HASH(0xb33da4) 0.1.0.8.0
Solution 1
/html/body/div/h2[2]/span
//span[@id='Solution1']
//span[@id='Solution1']
------------------------------------------------------------------
HTML::Element=HASH(0xb33d94) 0.1.0.9
Solution description.
/html/body/div/p[8]
//div[@id='bodyContent']/p[8]
//div[@id='bodyContent']/p[8]
------------------------------------------------------------------
HTML::Element=HASH(0xb33e44) 0.1.0.10
Solution 2
/html/body/div/h2[3]
//div[@id='bodyContent']/h2[3]
//div[@id='bodyContent']/h2[3]
------------------------------------------------------------------
HTML::Element=HASH(0xb33f04) 0.1.0.10.0
Solution 2
/html/body/div/h2[3]/span
//span[@id='Solution2']
//span[@id='Solution2']
------------------------------------------------------------------
HTML::Element=HASH(0xb33f44) 0.1.0.11
Solution description.
/html/body/div/p[9]
//div[@id='bodyContent']/p[9]
//div[@id='bodyContent']/p[9]
------------------------------------------------------------------
HTML::Element=HASH(0xb33fb4) 0.1.0.12
Comment.
/html/body/div/h2[4]
//div[@id='bodyContent']/h2[4]
//div[@id='bodyContent']/h2[4]
------------------------------------------------------------------
HTML::Element=HASH(0xb34074) 0.1.0.12.0
Comment.
/html/body/div/h2[4]/span
//span[@id='Comment']
//span[@id='Comment']
------------------------------------------------------------------
HTML::Element=HASH(0xb34064) 0.1.0.13
Text of the comment.
/html/body/div/p[10]
//div[@id='bodyContent']/p[10]
//div[@id='bodyContent']/p[10]
------------------------------------------------------------------
##################################################################
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.",
}