use warnings; use strict; use XML::LibXML; my $parser = XML::LibXML->new(); $parser->keep_blanks(0); # $parser->recover_silently(1); # <-- for bad HTML my $doc = $parser->parse_fh(\*DATA); # If you have well balanced snippet like below # my $doc = $parser->parse_html_fh(\*DATA); # If you have HTML. my $xml = XML::LibXML::Document->new(); $xml->setDocumentElement( $xml->createElement("engines") ); for my $spec_row ( $doc->findnodes('//div[@class="spec_row"]') ) { my $engine = $xml->createElement("engine"); $xml->getDocumentElement->appendChild($engine); my $type = $xml->createElement("type"); ( my $text = $spec_row->firstChild->textContent ) =~ s/\A\s+|\s+\z//g; $type->appendChild( $xml->createTextNode($text) ); $engine->appendChild( $type ); my $builder = $xml->createElement("builder"); ( $text = $spec_row->lastChild->textContent ) =~ s/\A\s+|\s+\z//g; $builder->appendChild( $xml->createTextNode($text) ); $engine->appendChild( $builder ); } print $xml->serialize(1); __DATA__
Engine
Type
Diesel
Builder
MTU
Model
2x 16V396TB94
Power
2561kw / 3480hp
Total Power
5121kw / 6960hp
Engine Propulsion
Twin Screws