#!/usr/bin/perl
use strict;
use warnings;
use LWP::Simple;
#####################################################################
### Set how many times to run, how long (in seconds) to wait between
### page hits, and how often to print an interim status report.
my ($iterations, $nice, $status_print_interval) = (100, 5, 5);
#####################################################################
my %quips;
$SIG{INT} = sub{ print_results(\%quips); exit(0) };
my $loopcount = 0;
print "Beginning PerlMonks Quip Gatherer...\n";
while($iterations > 0){
my $content = get('http://www.perlmonks.org');
die "Failed to load content!\n" unless defined($content);
extract_quip(\%quips, \$content);
$iterations--;
$loopcount++;
print "Found ", scalar keys %quips,
" quip(s) so far, $iterations iteration(s) left...\n"
if ($loopcount % $status_print_interval == 0);
sleep($nice) if ($iterations);
}
print_results(\%quips);
#####################################################################
### SUBS ###
#####################################################################
sub extract_quip{
my ($quips, $content) = @_;
if ($$content =~ m!<td class="monkquip"[^>]+>(.*?)</td>!s){
my $data = $1;
$data =~ s!\<[^>]*>!!sg;
$data =~ s!\s{2,}!!sg;
$quips->{$data}++;
}
}
sub print_results{
my $quips = shift;
print "\n********** RESULTS **********\n";
while (my ($key, $val) = each(%$quips)){
print "$val time(s): $key\n";
}
}
-
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.
|