#!/usr/bin/perl -w

use strict;
use HTML::Parser;

my $parser = HTML::Parser->new(
    start_h => [ \&_starttag, 'self, tagname, attr' ],
    end_h   => [ \&_endtag,   'self, tagname' ],
    text_h  => [ \&_text,     'self, dtext' ]
);

my @chunks;
$parser->parse_file(\*DATA);

print "----------\n$_\n----------\n\n" for @chunks;

sub _starttag {
    my ($self, $tag, $attr) = @_;
    $self->{'_pre'} = 1 if ($tag eq 'pre');
}

sub _endtag {
    my ($self, $tag) = @_;
    $self->{'_pre'} = undef if ($tag eq 'pre');
}

sub _text {
    my ($self, $dtext) = @_;

    $dtext =~ s/\A\s+//;
    $dtext =~ s/\s+\z//;
    return() unless ( length($dtext) > 0 and $dtext =~ /[^\s]/ );

    if ( defined($self->{'_pre'}) ) {
        push(@chunks, "PRE: $dtext");
    }
    else {
        push(@chunks, "TEXT: $dtext");
    }
}

__END__
<p>This is a bad try to display text then code
<pre>#! usr/bin/perl
use strict;
use warnings;

print "Hello World!";</pre>
and then plain text again</p>

[download]

In reply to Re: split html via HTML::Parser by saskaqueer
in thread split html via HTML::Parser by reneeb

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.