#!/usr/bin/perl --
use strict;
use warnings;
use HTML::Encoding 'encoding_from_http_message';
use WWW::Mechanize;
use Encode;
use HTML::Tree;
my $file = shift or die "
Usage: xmlfixup.pl file:in.xml > out.xml
xmlfixup.pl http://example.com/foo.xml > out.utf8.xml
";
my $resp = WWW::Mechanize->new( autocheck => 1 )->get( $file );
my $enco = encoding_from_http_message( $resp );
my $utf8;

if( $enco ) {
    $utf8 = decode( $enco => $resp->content );
} else {
    $utf8 = $resp->content;
}
my $t = HTML::TreeBuilder->new(
    qw(
      ignore_unknown 0
      no_space_compacting 1
      ignore_ignorable_whitespace 0
      implicit_tags 0
      no_expand_entities 1
      store_comments 1
      store_pis 1
      )
);
#~ $t->xml_mode( 1 );
$t->parse_content( $utf8 );
binmode STDOUT, ':utf8';
print $_->as_XML for $t->content_list;
__END__

[download]

In reply to Re: XMLin question (xmlfixup.pl) by Anonymous Monk
in thread XMLin question by stryda42

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.