count_text_and_code.pl

#!/usr/bin/env perl

use warnings;
use strict;

use HTML::TagParser;

my $url = 'http://blog.gustawdaniel.pl';
my @tags = ("h1 h2 h3 h4 li p","pre");
print "|     text |     code | title \n";

my @list = HTML::TagParser->new( $url )->getElementsByTagName( "h2" );
foreach my $elem ( @list ) {
    my $post = HTML::TagParser->new( $url.$elem->firstChild()->getAttribute( "href" ) );
    my @str = ("","");
    foreach my $i ( (0,1) ) {
        my @elements = map {$post->getElementsByTagName($_)} split / /, $tags[$i];
        $str[$i] = join("",map {$_->innerText} @elements);
    }
    printf("| %8d | %8d | %-60s \n", (map {$str[$_] =~ y===c} (0,1)), $elem->innerText);
}