#!/opt/bin/perl
use CGI;
use LWP::Simple;
use HTML::TokeParser;

$cgiobject=new CGI;
$cgiobject->use_named_parameters;
print $cgiobject->header;

print $cgiobject->start_html
                  (-title=>'Page Parser',
                   -bgcolor=>'white');
                          

print $cgiobject->startform
                  (-method=>'get',
                   -action=>'parsepage.cgi');
print "URL to Analyze:".$cgiobject->textfield
                                    (-name=>'url',
                                     -size=>'40');
print "<br>".$cgiobject->submit(-value=>'Analyze');
print $cgiobject->endform;
print "<hr>";                                     


#retrieve web page
$fetchURL=$cgiobject->param("url");
unless ($fetchURL) 
 {$fetchURL="http://www.wdvl.com"}

$webPage=get($fetchURL);

print <<ENDHTML;
<center><h2>$fetchURL<br>
has been sliced and diced,
 thus revealing:</h2></center>
ENDHTML
                                      
&parse_title;
&parse_meta_description;
&parse_meta_keywords;
&parse_images;
&parse_hyperlinks;
print $cgiobject->end_html;


sub parse_title{
#parse and output page title
$parser=HTML::TokeParser->new(\$webPage);
$parser->get_tag("title");
print "<p><h2>Page title</h2> ".
      $parser->get_trimmed_text."</p>";
}

sub parse_meta_keywords{
#parse and output meta data
$parser=HTML::TokeParser->new(\$webPage);
while (my $token=$parser->get_tag("meta"))
 { if ($token->[1]{name}=~/keywords/i)
    { print "<p><h2>Meta Keywords</h2> ".
            $token->[1]{content}."</p>" }
 }
}

sub parse_meta_description{
#parse and output meta data
$parser=HTML::TokeParser->new(\$webPage);
while (my $token=$parser->get_tag("meta"))
 { if ($token->[1]{name}=~/description/i)
    { print "<p><h2>Meta Description</h2> ".
            $token->[1]{content}."</p>" }
 }
}


sub parse_images{
#parse and count images
$parser=HTML::TokeParser->new(\$webPage);
my $imageTotal=0;
while ($parser->get_tag("img"))
 { $imageTotal++ }
print "<p><h2>Image Count</h2> ".
      "Total = $imageTotal</p>";
} 

sub parse_hyperlinks{
#parse and output hyperlinks
$parser=HTML::TokeParser->new(\$webPage);
print "<p><h2>Hyperlink Summary</h2>";
while (my $token = $parser->get_tag("a")) 
 { my $linkURL = $token->[1]{href} || "-";
   my $linkText = $parser->get_trimmed_text("/a");
   if ($linkText=~/<image/i) {$linkText="image"}
   print "<small>$linkText</small> ".
         "<b>links to</b> $linkURL<br>"
  }
}