use strict;
use Data::Random::WordList;
use CGI qw/:standard/;
my $cgi         = CGI->new();

my ($punct,             # punctuation, . ! ? or :
    @punct,
    $punc,
    $tld);              # top-level domain

my $log         = "/webroot/logs/raid";
my $wordlist    = "/usr/share/dict/american-english";

#########################################################
# To activate this in Apache, add these two lines to your
# httpd.conf in the appropriate section:
#
# AddHandler cgi-script .cgi .pl
# AliasMatch ^/raid/.* /path/to/this/cgi/raid.pl
#             ^^^^^
my $ap_alias    = "/raid/";

#########################################################
# list of domains hosted on this machine that will always
# point to this script:
my @domains     = qw/www.foo.bar foo.bar foo.com/;

# Throttle
# sleep(10);

# wrapped for Perl Monks, this is not a multi-line regex
exit if ($ENV{HTTP_USER_AGENT} =~ /google|Googlebot|
                                   inktomi|search|
                                   altavista|wget|htdig/i);

if (-e $log ) { 
        open LOG, ">>$log";
} else {
        open LOG, ">$log";
}

my $time                = localtime;
print LOG "$time $ENV{'REMOTE_ADDR'}
      $ENV{'HTTP_HOST'}$ENV{'REQUEST_URI'}" .
    " $ENV{'HTTP_REFERER'} \"$ENV{'HTTP_USER_AGENT'}\"\n";
close LOG;

$punct[1]       = ".";
$punct[2]       = "!";
$punct[3]       = "\?";
$punct[4]       = ":"; 

my $numurl = my @url = map { "${_}${ap_alias}" } @domains;

#########################################################
# Select 'n' words at random from the list, sorted
my $wl = new Data::Random::WordList(
         wordlist => '/usr/share/dict/american-english');
my @word = $wl->get_words(2000);
$wl->close();

my $wordnum     = @word;

# Create a random title from those random words in the list
my $title       = $word[int(rand $wordnum)] . " " 
                . $word[int(rand $wordnum)] . " " 
                . $word[int(rand $wordnum)] . " " 
                . $word[int(rand $wordnum)];

print $cgi->header(), start_html(-title    => "$title",
                                 -bgcolor  => '#ffffff');

my $para        = int(rand 10)+3;
my $pagenum     = 0;

while($pagenum < $para) {
        $pagenum++;
        my $words_in_page = int(rand 80)+10;
        my $total_words = 0;
        while($total_words < $words_in_page) {
                $total_words++;
                my $prword = $word[int(rand $wordnum)];
                print "$prword";
                if((rand 10)<1) {
                        $punc = $punct[int(rand 4)+1];
                        print $punc . br() . "\n";
                }
                print " ";
        }
        print br(), "\n";
        my $num_addr = int(rand 10)+10;
        my $pres_addr = 0;
        while ($pres_addr < $num_addr) {
                my $urlpos;
                $pres_addr++;
                my $name = $word[int(rand $wordnum)];
                my $d1   = $word[int(rand $wordnum)];
                my $d2   = $word[int(rand $wordnum)];
                if((rand 4)>1) {
                        if((rand 3)>1) {
                                $tld = "com";
                        } else {
                                $tld = "net";
                        }
                } else {
                        $tld = "org";
                }
                my $mailaddr = $name . '@' . 
                               $d1 . $d2 . "." . $tld;

                if((rand 4)>3) {
                        my $urlh = "http://";
                        my $urlb = $url[int(rand $numurl)];
                        my $urlt = 
                                 $word[int(rand $wordnum)];

                        if ((rand 5)>1) {
                                $urlt .= ".html";
                        } else {
                                $urlt .= "/";
                        }
                        $urlpos = $urlh . $urlb . $urlt;

                } else {
                        $urlpos = "mailto:" . $mailaddr;
                }
                print a({-href => "$urlpos"}, 
                      "$mailaddr"), br(), "\n";
        }
}
print end_html(), "\n";
exit;
[download]

---

---

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! —

• How do I compose an effective node title?
• How do I post a question effectively?
• Markup in the Monastery

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:
	&		&
	<		&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.