File Coverage

blib/lib/WWW/Scraper/ISBN/ORA_Driver.pm

Criterion	Covered	Total	%
statement	62	64	96.8
branch	15	22	68.1
condition	5	15	33.3
subroutine	9	9	100.0
pod	1	1	100.0
total	92	111	82.8

package WWW::Scraper::ISBN::ORA_Driver;

use strict;
use warnings;

use vars qw($VERSION @ISA);
$VERSION = '0.22';

#--------------------------------------------------------------------------

=head1 NAME

WWW::Scraper::ISBN::ORA_Driver - Search driver for O'Reilly Media's online catalog.

=head1 SYNOPSIS

See parent class documentation (L)

=head1 DESCRIPTION

Searches for book information from the O'Reilly Media's online catalog.

=cut

#--------------------------------------------------------------------------

###########################################################################
# Inheritence

use base qw(WWW::Scraper::ISBN::Driver);

###########################################################################
# Modules

use WWW::Mechanize;

###########################################################################
# Constants

use constant	ORA		=> 'http://www.oreilly.com';
use constant	SEARCH	=> 'http://search.oreilly.com';
use constant	QUERY	=> '?submit.x=17&submit.y=8&q=%s';

#--------------------------------------------------------------------------

###########################################################################
# Public Interface

=head1 METHODS

=over 4

=item C

Creates a query string, then passes the appropriate form fields to the
O'Reilly Media server.

The returned page should be the correct catalog page for that ISBN. If not the
function returns zero and allows the next driver in the chain to have a go. If
a valid page is returned, the following fields are returned via the book hash:

  isbn          (now returns isbn13)
  isbn10
  isbn13
  ean13         (industry name)
  author
  title
  book_link
  image_link
  thumb_link
  description
  pubdate
  publisher
  binding       (if known)
  pages         (if known)
  weight        (if known) (in grammes)
  width         (if known) (in millimetres)
  height        (if known) (in millimetres)

The book_link and image_link refer back to the O'Reilly US website.

=back

=cut

sub search {
	my $self = shift;
	my $isbn = shift;
	$self->found(0);
	$self->book(undef);

	my $mech = WWW::Mechanize->new();
    $mech->agent_alias( 'Linux Mozilla' );

	my $url = SEARCH . sprintf(QUERY,$isbn);
	eval { $mech->get( $url ) };
    return $self->handler("O'Reilly Media website appears to be unavailable.")
	    if($@ || !$mech->success() || !$mech->content());

	# The Search Results page
    my $content = $mech->content();
    my ($book) = $content =~ m!\s*\s*

	unless(defined $book) {
        #print STDERR "\n#url=$url\n";
        #print STDERR "\n#content=".$mech->content();
	    return $self->handler("Could not extract data from the O'Reilly Media search page [".($mech->uri())."].");
    }

	eval { $mech->get( $book ) };
    return $self->handler("O'Reilly Media website appears to be unavailable.")
	    if($@ || !$mech->success() || !$mech->content());

    my $html = $mech->content();
    my $data = {};

    for my $name ('book.isbn','ean','target','reference','isbn','graphic','graphic_medium','graphic_large','book_title','author','keywords','description','date') {
        next    unless($html =~ m!!i);
        $data->{$name} = $1;
    }

    my (@isbns) = split(',',$data->{target});
    for my $isbn (@isbns) {
        $isbn =~ s/\D+//g;
        next unless($isbn);
        $data->{isbn10} = $isbn if(length($isbn) == 10);
        $data->{isbn13} = $isbn if(length($isbn) == 13);
    }

    #($data->{isbn13},$data->{isbn10}) = $html =~ m!(?:Print )?ISBN:]+>([\d-]+)\s* \| ISBN 10: ([\d-]+)!;
    ($data->{pages}) = $html =~ m!Pages: (\d+)!;

    $data->{graphic} ||= $data->{$_}    for('graphic_medium','graphic_large');  # alternative graphic fields

	unless(defined $data) {
        #print STDERR "\n#url=$book\n";
        #print STDERR "\n#content=".$mech->content();
	    return $self->handler("Could not extract data from the O'Reilly Media result page [".($mech->uri())."].");
    }

	# trim top and tail
	foreach (keys %$data) { next unless(defined $data->{$_});$data->{$_} =~ s/^\s+//;$data->{$_} =~ s/\s+$//; }

	my $bk = {
		'ean13'		    => $data->{ean},
		'isbn13'		=> $data->{ean},
		'isbn10'		=> $data->{isbn10},
		'isbn'			=> $data->{ean},
		'author'		=> $data->{author},
		'title'			=> $data->{book_title},
		'book_link'		=> $mech->uri(),
		'image_link'	=> ($data->{graphic} !~ /^http/ ? ORA : '') . $data->{graphic},
		'thumb_link'	=> ($data->{graphic} !~ /^http/ ? ORA : '') . $data->{graphic},
		'description'	=> $data->{description},
		'pubdate'		=> $data->{date},
		'publisher'		=> q!O'Reilly Media!,
		'binding'	    => $data->{binding},
		'pages'		    => $data->{pages},
		'weight'		=> $data->{weight},
		'width'		    => $data->{width},
		'height'		=> $data->{height}
	};
	$self->book($bk);
	$self->found(1);
	return $self->book;
}

1;

__END__