#!/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");
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|