#!/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__
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|