#!/usr/bin/perl
use warnings;
use strict;

my $start = 1;
my $end = 10;

for my $cnt ($start..$end) {
    print "<b>Current page count: $cnt</b><p>\n";
    my $uri = "http://www.allpoetry.com/chat/page=$cnt";

    my $html = get($uri);
    
    # retrieve the text and split into lines
    my @lines = split /[\r\n]+/, $html;
    
    # Now get into trouble for parsing HTML by hand
    # This skips through until the first chat message hopefully.
    while (@lines) {
        if ($lines[0] =~ m/^\<a href="javascript:t\('/)
        {
            last;
        }
        else
        {
            shift @lines;
        }
    }
    
    my @messages;
    while (@lines)
    {
        my $line = shift @lines;
        
        # get out after parsing all the messages from history
        # so we don't capture the current chatbox.
        last if $line =~ /^<\/font>/;
        
        #We use next because actions aren't grabbed properly
        # To handle them this needs to look for the line starting
        # with a <i> and no second <a href='...'>
        # There may be other messages this doesn't handle.
        next unless $line =~ s/^<a\shref="javascript:t\('
                                ([\d\w\s_]+)
                                '\)">\1<\/a>
                                <a\shref='\/poets\/\1'>:<\/a>//x;
        my $user = $1;
        next unless $line =~ s/^(.*?)
                                \((\d+\s+
                                (?:days|hours?|minutes|seconds)
                                \s+ago)\)
                                \s+(?:<br>|<p>)//x;
                                
        push @messages, {user => $user,
                        content => $1,
                        delay => $2};
            
    }
    
    foreach (@messages)
    {
        print sprintf("%15s:\%s (\%s)<br>\n",
             $_->{user},
             $_->{content},
             $_->{delay});
    }
}

exit(0);

sub get {
    my $uri = shift;
    $uri =~ /(\d+)$/;
    my $number = $1;
    open my $html, "<", $number or die "Couldn't open $number: $!";
    local $/;
    my $ret = <$html>;
    close $html or die "Couldn't close $number: $!";
    return $ret;
}
[download]