in reply to Re^3: Parsing HTML/XML with Regular Expressions
in thread Parsing HTML/XML with Regular Expressions

Could it just be a version issue? The code you posted works fine for me:

use warnings;
use strict;
use XML::LibXML;

my $XML = <<'_END_XML_';
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html [ <!ENTITY atad "data"> ] >
<html xmlns="http://www.w3.org/1999/xhtml">
<div class="&atad;" id="Hello" />
<div class="&atad;" id="World" />
</html>
_END_XML_

print $XML::LibXML::VERSION, " ",
    XML::LibXML::LIBXML_DOTTED_VERSION, " ",
    XML::LibXML::LIBXML_VERSION, " ",
    XML::LibXML::LIBXML_RUNTIME_VERSION, "\n";
my $dom = XML::LibXML->load_xml(string=>$XML);
my $xpc = XML::LibXML::XPathContext->new;
$xpc->registerNs(xh => 'http://www.w3.org/1999/xhtml');
for my $div ($xpc->findnodes('//xh:div[@class="data"]', $dom)) {
    print "1:", $div->{id}, "\n"
}
for my $div ($xpc->findnodes('//xh:div', $dom)) {
    print "2:", $div->{id}, " ", $div->{class}, "\n"
}

__END__

2.0129 2.9.1 20901 20901
1:Hello
1:World
2:Hello data
2:World data

[download]

Replies are listed 'Best First'.
Re^5: Parsing HTML/XML with Regular Expressions
by choroba (Cardinal) on Oct 18, 2017 at 22:13 UTC
    I modified your original input: 
    <?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"[
<!ENTITY atad 'data'>
<!ATTLIST html
    xmlns:xsi CDATA #FIXED "http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation CDATA #IMPLIED  > ]>
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://www.w3.org/1999/xhtml
    http://www.w3.org/2002/08/xhtml/xhtml1-strict.xsd">
<head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"
+ />
    <title>Hello, World</title>
    <script type="text/javascript">
//<![CDATA[
console.log(' <div class="data" id="Hello">World</div> ');
//]]>
    </script>
</head>
<body>
<div class="data" id="Zero" />
<div class="data" id="One">Monday</div><div class="data" id="Two">Tues
+day</div>
<div id="Three" class='data'>Wednes<div id="day">day</div></div>
<div class="&atad;" id='Four'><b>Thursday</b></div>

    [download]
    etc. Four was missing from the output for both the libraries.

    ($q=q:Sq=~/;[c](.)(.)/;chr(-||-|5+lengthSq)`"S|oS2"`map{chr |+ord
}map{substrSq`S_+|`|}3E|-|`7**2-3:)=~y+S|`+$1,++print+eval$q,q,a,

    [download]
[reply]
[d/l]
[select]

      Although I'm definitely not an expert in the latter, there does seem to be a difference between XML::LibXML and XML::XSH2.

      <update> I think I found it, looks like it's the option load_ext_dtd=>0, from XML::LibXML::Parser: "Thus switching off external DTD loading, will disable entity expansion, validation, and complete attributes on internal subsets as well." </update>

      #!/usr/bin/env perl
use warnings;
use strict;

our $XML = <<'_END_XML_';
<!DOCTYPE html [ <!ENTITY atad "data"> ] >
<html xmlns="http://www.w3.org/1999/xhtml">
<div class="data"   id="One"   />
<div class="&atad;" id="Two"   />
<div class="&atad;" id="Three" />
</html>
_END_XML_

use XML::LibXML ();
print $XML::LibXML::VERSION, " ",
    XML::LibXML::LIBXML_DOTTED_VERSION, " ",
    XML::LibXML::LIBXML_VERSION, " ",
    XML::LibXML::LIBXML_RUNTIME_VERSION, "\n";

my $dom = XML::LibXML->load_xml(string=>$XML);
my $xpc = XML::LibXML::XPathContext->new($dom);
$xpc->registerNs(xh => 'http://www.w3.org/1999/xhtml');
for my $div ($xpc->findnodes('//xh:div[@class="data"]')) {
    print "1:", $div->{id}, "\n"
}
for my $div ($xpc->findnodes('//xh:div')) {
    print "2:", $div->{id}, " ", $div->{class}, "\n"
}

use XML::XSH2 'xsh';
print $XML::XSH2::VERSION, "\n";

xsh(<<'_END_XSH_');
open :s {$::XML} ;
register-namespace xh http://www.w3.org/1999/xhtml ;
for //xh:div[@class="data"] {
    echo "a:" @id ;
}
for //xh:div {
    echo "b:" @id @class ;
}
_END_XSH_

__END__

2.0130 2.9.1 20901 20901
1:One
1:Two
1:Three
2:One data
2:Two data
2:Three data
2.1.26
parsing string
done.
a: One
b: One data
b: Two data
b: Three data

      [download]
[reply]
[d/l]
[select]
        Yes, that's it. I turned it off because otherwise loading the XML took 2 minutes.

        You can get the same effect in XML::XSH2 with 

        load_ext_dtd 1 ;

        [download]
        ($q=q:Sq=~/;[c](.)(.)/;chr(-||-|5+lengthSq)`"S|oS2"`map{chr |+ord
}map{substrSq`S_+|`|}3E|-|`7**2-3:)=~y+S|`+$1,++print+eval$q,q,a,

        [download]
[reply]
[d/l]
[select]

In Section Meditations