#!/usr/bin/perl

use strict;
use warnings;

my $poet = $ARGV[0];
my $name = $ARGV[1];

if (!$poet || !$name) {
    print "No poet specified.";
    exit();
}

my $flag = 1;
my $count = 1;
my %hash;

print "Going to retrieve poet number $poet, who you say is $name.\n";

while ($flag) {

    $flag = 0;

    if ($count > 1) {
        print "On page $count.\n";
        $poet = $ARGV[0] . "\/$count";
    }

    unlink($name . "_poet.html");
    system("wget -q -O\'" . $name . "_poet.html\' \'http:\/\/plagiaris
+t.com\/poetry\/poets\/" . $poet . "\/\'");
    open(FILE, $name . "_poet.html");

    my $line;
    $flag = 0;
    foreach $line (<FILE>) {
        if ($line =~ m/<li><a href=\"http\:\/\/plagiarist\.com\/poetry
+\/(\d+)\/\">/) {
            $flag = 1;
            print "           Getting poem number $1.\n";
            unlink("temp.html");
            system("wget -q -O\'" . $name . "_temp.html\' \'http://pla
+giarist.com/poetry/" . $1 . "/\'");
            open(POEM, $name . "_temp.html");

            {
                local $/ = undef;
                my $poem = <POEM>;
                my ($match) = $poem =~ m/<div id=\"poem\">(.*?)<\/div>
+/ms;
                my ($title) = $match =~ m/<title>(.*?)<\/title>/ms;
                $match =~ s/(?:<.*?>|\<!--|-->|\n\n\n)//mg;
                $match =~ s/^(?:Submitted by.*|    poem|    )$//mg;

                $hash{$title} .= $match;

            }

            close(POEM);

        }
    }

    close(FILE);
    
    $count ++;
}

print "Writing it down...\n";

unlink($name . ".txt");
open(OUTPUT, ">$name" . ".txt");

my $title;

foreach $title (sort(keys(%hash))) {
    print "       $title\n";
    print OUTPUT "_PAGEBREAK_\n\n$hash{$title}\n";
}

close(OUTPUT);

unlink($name . "_temp.html");
unlink($name . "_poet.html");
[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.