#!/usr/bin/perl -w use strict; use warnings; use XML::LibXML qw( ); use LWP::UserAgent qw( ); sub text_to_xml { my ($text) = @_; $text =~ s/&/&/g; $text =~ s/new(); my $response = $ua->get($url); $response->is_success() or die "Request failed: ". $response->status_line() ."\n"; my $xhtml = $response->decoded_content(charset => "none"); $xhtml =~ s{(]*>)(.*?)()}{"$1".text_to_xml("$2")."$3"}sieg; $xhtml =~ s/&(?!#|[a-zA-Z0-9]{1,8};)/&/g; my $parser = XML::LibXML->new; my $doc = $parser->parse_string($xhtml);