# (c) 2010 by Ralf Ertzinger # licensed under GNU GPL v2 # # Grabber for totalbash.org package TotalBashGrabber; use GrabberBase; @ISA = qw(GrabberBase); use LWP::Simple qw(!get); use HTML::TokeParser; use Data::Dumper; use Encode; use strict; sub new { my $class = shift; my $self = $class->SUPER::new(); $self->{'NAME'} = 'TotalBash'; $self->{'PATTERNS'} = ['(http://(?:[-a-zA-Z0-9_.]+\.)*totalbash\.org/(\d+))']; bless($self, $class); $self->_prepare_parameters(); return $self; } sub _parse { my $self = shift; my $url = shift; my $pattern = shift; my $content; my $metadata = {}; my $p; my $t; $url =~ m|$pattern|; $url = $1; $metadata->{'URL'} = $url; $metadata->{'ID'} = $2; $metadata->{'TYPE'} = 'quote'; $metadata->{'SOURCE'} = $self->{'NAME'}; $metadata->{'CONTENT'} = undef; # Get the HTML file containing the quote unless(defined($content = LWP::Simple::get(sprintf('http://www.totalbash.org/%s', $2)))) { $self->error('Could not download quote'); return undef; } $p = HTML::TokeParser->new(\$content); while ($t = $p->get_tag('div')) { if (exists($t->[1]->{'class'}) && ($t->[1]->{'class'} eq 'beitrag_p')) { $metadata->{'CONTENT'} = $p->get_text('/div'); $metadata->{'CONTENT'} =~ s/^\s*//mg; } } unless(defined($metadata->{'CONTENT'})) { $self->error('Could not extract quote content'); return undef; } return $metadata; } 1;