--- /dev/null
+# (c) 2007 by Ralf Ertzinger <ralf@camperquake.de>
+# licensed under GNU GPL v2
+#
+# Grabber for Amazon
+
+package quotesite::AmazonGrabber;
+
+use quotesite::GrabberBase;
+@ISA = qw(quotesite::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'} = 'amazon';
+ $self->{'PATTERNS'} = ['(https?://(?:[-a-zA-Z0-9_.]+\.)*amazon\.(?:com|de|co\.uk|fr)/.*[dg]p(?:/product)?/([[:alnum:]]{10}))'];
+
+ bless($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;
+ my $t2;
+
+ $url =~ m|$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($url))) {
+ $self->error('Could not download quote');
+ return undef;
+ }
+
+ $self->debug($content);
+
+ $p = HTML::TokeParser->new(\$content);
+
+ OUTER: while ($t = $p->get_tag('h1')) {
+ if (exists($t->[1]->{'class'}) && ($t->[1]->{'class'} eq 'parseasinTitle')) {
+ $metadata->{'CONTENT'} = encode('utf8', decode('iso8859-1', $p->get_text('/h1')));
+ $metadata->{'CONTENT'} =~ s/^\s*//;
+ $metadata->{'CONTENT'} =~ s/\s*$//;
+ last OUTER;
+ }
+ }
+
+ unless(defined($metadata->{'CONTENT'})) {
+ $self->error('Could not extract quote content');
+ return undef;
+ }
+
+ return $metadata;
+}
+
+1;