in reply to Re: More efficient use of HTML::TokeParser::Simple
in thread More efficient use of HTML::TokeParser::Simple

Just by way of closing this post, and giving back a bit so that others in my position can search for it (and find the answer without bothering the murmuring monks): 
#!/usr/bin/perl

use strict;
use warnings;
no warnings 'uninitialized';
use HTML::TokeParser::Simple;

my $p = HTML::TokeParser::Simple->new($ARGV[0]);
my $tag = '';

while (my $tkn = $p->get_token)
{
    if ($tkn->is_start_tag('title')) { $tag = "TITLE"; }

    elsif ($tkn->is_start_tag('h1')) { $tag = "H1"; }

    elsif ($tkn->is_start_tag('h2')) { $tag = "H2"; }

    elsif ($tkn->is_start_tag('h3')) { $tag = "H3"; }

    elsif ($tkn->is_start_tag('h4')) { $tag = "H4"; }

    elsif ($tkn->is_start_tag('h5')) { $tag = "H5"; }

    elsif ($tkn->is_start_tag('h6')) { $tag = "H6"; }

    elsif ($tkn->is_start_tag('b')) { $tag = "B"; }

    elsif ($tkn->is_start_tag('i')) { $tag = "I"; }

    elsif ($tkn->is_start_tag('u')) { $tag = "U"; }

    elsif ($tkn->is_start_tag('a')) { $tag = "A"; }

    elsif ($tkn->is_start_tag('img')) { $tag = "IMG"; }

    elsif ($tkn->is_start_tag('meta')) { $tag = "META"; }

    elsif (
        $tkn->is_end_tag('title') ||
        $tkn->is_end_tag('h1') ||
        $tkn->is_end_tag('h2') ||
        $tkn->is_end_tag('h3') ||
        $tkn->is_end_tag('h4') ||
        $tkn->is_end_tag('h5') ||
        $tkn->is_end_tag('h6') ||
        $tkn->is_end_tag('b')  ||
        $tkn->is_end_tag('i')  ||
        $tkn->is_end_tag('u')  ||
        $tkn->is_end_tag('a')  ||
        $tkn->is_end_tag('img') ||
        $tkn->is_end_tag('meta')
        ) { $tag = ''; }

    elsif ($tkn->is_text() && $tag && $tag ne 'META')
    {
        print "TAG: $tag, VALUE: ".$tkn->as_is . "\n";
    }

    if ($tag eq 'IMG' && $tkn->get_attr('alt'))
    {
        print "TAG: $tag, ALT VALUE: ". $tkn->get_attr('alt') . "\n";
    }

    if ($tag eq 'META' &&
        $tkn->get_attr('name') eq 'keywords' &&
        $tkn->get_attr('content'))
    {
        print "META-TAG: $tag, KEYWORDS VALUE: ". $tkn->get_attr('cont
+ent') . "\n";
    }

    if ($tag eq 'META' &&
        $tkn->get_attr('name') eq 'description' &&
        $tkn->get_attr('content'))
    {
        print "META-TAG: $tag, DESCRIPTION VALUE: ". $tkn->get_attr('c
+ontent') . "\n";
    }
}

[download]

Replies are listed 'Best First'.
Re^3: More efficient use of HTML::TokeParser::Simple
by wfsp (Abbot) on Jul 11, 2006 at 12:52 UTC
    The $t->is_start_tag can take a regex which could be useful in this case.

    Also, the title and meta tags appear in the head section of the html and all the others appear later in the body section. In these cases I use two loops.

    #!/usr/bin/perl

use strict;
use warnings;
use HTML::TokeParser::Simple;

my $html = join '', <DATA>;

my $p = HTML::TokeParser::Simple->new(\$html);

my ($title, $content, $keywords);

while (my $t = $p->get_token){
  
  last if $t->is_start_tag('body');
  
  $title = $p->get_trimmed_text('/title') 
    if $t->is_start_tag('title');

  $content = $t->get_attr('content') if 
    $t->is_start_tag('meta') and
    $t->get_attr('name') and
    $t->get_attr('name') eq 'Description';
    
  $keywords = $t->get_attr('content') if 
    $t->is_start_tag('meta') and
    $t->get_attr('name') and
    $t->get_attr('name') eq 'Keywords';
    
}

print "title: $title\n";
print "content: $content\n";

my $tag;

while (my $t = $p->get_token) {

  $tag = $t->get_tag
    if $t->is_start_tag(qr/^h[123456]|[biua]$/);

  if ($t->is_start_tag('img') and $t->get_attr('alt')){ 
    my $attr = $t->get_attr('alt');
    print "img attr: $attr\n";
    $tag = '';
  }
  elsif ($tag and $t->is_text){
    my $txt = $t->as_is;      
    print "$tag: $txt\n";
    $tag = '';
  }
  
}

__DATA__
<html>
<head>
<title>henka's test page</title>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1
+" />
<meta name="Description" content="the glories of HTML::TokeParser::Sim
+ple" />
<meta name="keywords" content="one two three four five six seven eight
+ nine ten" />
<meta name="robots" content="noindex" />
<link rel="stylesheet" type="text/css" href="cwi.css" />
</head>

<body>
<h1>header one</h1>
<h2>header two</h2>
<h3>header three</h3>
<h4>header four</h4>
<h5>header five</h5>
<h6>header siz</h6>

<p>p tag paragraph</p>
<p>p tag containing <u>underline</u> and <b>bold</b> and a <a href="li
+nk.html">link</a></p>
<img alt="image alt text" src="my.gif">

</body>
</html>

    [download]
    output: 
    ---------- Capture Output ----------
> "c:\perl\bin\perl.exe" monk06.pl
title: henka's test page
content: the glories of HTML::TokeParser::Simple
h1: header one
h2: header two
h3: header three
h4: header four
h5: header five
h6: header siz
u: underline
b: bold
a: link
img attr: image alt text
> Terminated with exit code 0.

    [download]
[reply]
[d/l]
[select]

In Section Seekers of Perl Wisdom