File Coverage

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

Criterion	Covered	Total	%
statement	21	78	26.9
branch	0	38	0.0
condition	0	21	0.0
subroutine	7	8	87.5
pod	1	1	100.0
total	29	146	19.8

package WWW::Scraper::ISBN::BookDepository_Driver;

use strict;
use warnings;

use vars qw($VERSION @ISA);
$VERSION = '0.13';

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

=head1 NAME

WWW::Scraper::ISBN::BookDepository_Driver - Search driver for The Book Depository online book catalog.

=head1 SYNOPSIS

See parent class documentation (L)

=head1 DESCRIPTION

Searches for book information from The Book Depository online book catalog

=cut

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

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

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

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

use WWW::Mechanize;

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

use constant    REFERER    => 'http://www.bookdepository.co.uk/';
use constant    SEARCH    => 'http://www.bookdepository.co.uk/search?search=search&searchTerm=';
my ($URL1,$URL2) = ('http://www.bookdepository.co.uk/book/','/[^?]+\?b=\-3\&t=\-26\#Bibliographicdata\-26');

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

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

=head1 METHODS

=over 4

=item C

Creates a query string, then passes the appropriate form fields to the
Book Depository 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
  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 The Book Depository website.

=back

=cut

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

    # validate and convert into EAN13 format
    my $ean = $self->convert_to_ean13($isbn);
    return $self->handler("Invalid ISBN specified")
        if(!$ean || (length $isbn == 13 && $isbn ne $ean)
                 || (length $isbn == 10 && $isbn ne $self->convert_to_isbn10($ean)));

    my $mech = WWW::Mechanize->new();
    $mech->agent_alias( 'Windows IE 6' );
    $mech->add_header( 'Accept-Encoding' => undef );
    $mech->add_header( 'Referer' => REFERER );

#print STDERR "\n# search=[".SEARCH."$ean]\n";
    eval { $mech->get( SEARCH . $ean ) };
    return $self->handler("The Book Depository website appears to be unavailable.")
        if($@ || !$mech->success() || !$mech->content());

    # The Book page
    my $html = $mech->content();

    return $self->handler("Failed to find that book on The Book Depository website. [$isbn]")
        if($html =~ m!Sorry, there are no results for!si);

    $html =~ s/&/&/g;
#print STDERR "\n# content2=[\n$html\n]\n";

    my $data;

    # first pass wih metadata
    #($data->{isbn13})       = $html =~ m!
    ($data->{publisher})    = $html =~ m!
    ($data->{pubdate})      = $html =~ m!
    ($data->{title})        = $html =~ m!
    ($data->{author})       = $html =~ m!
    ($data->{description})  = $html =~ m!
    ($data->{image})        = $html =~ m!
    ($data->{url})          = $html =~ m!
    ($data->{pages})        = $html =~ m!

    # second pass with page data
    ($data->{isbn13})       = $html =~ m!ISBN13\s*(\d+)!si                          unless($data->{isbn13});
    ($data->{publisher})    = $html =~ m!Publisher\s*]+>\s*]+>\s*]+>([^<]+)!si       unless($data->{publisher});
    ($data->{pubdate})      = $html =~ m!Publication date\s*([^<]+)!si     unless($data->{pubdate});
    ($data->{title})        = $html =~ m!]*>([^<]+)!si                                               unless($data->{title});
    ($data->{author})       = $html =~ m!]*>([^<]+)!si                                           unless($data->{author});
    ($data->{pages})        = $html =~ m!(\d+) pages\s*!si                                unless($data->{pages});
    ($data->{image})        = $html =~ m!"(https://\w+.cloudfront.net/assets/images/book/lrg/\d+/\d+/\d+.jpg)"!si               unless($data->{image});
    ($data->{title},$data->{author})
                            = $html =~ m!(.*):\s+([^:]+)\s+:\s+\d+\s*!                                           unless($data->{title} && $data->{author});
    ($data->{description})  = $html =~ m!\s*(.*?)\s*!si
                                                                                                                                unless($data->{description});

    # other page data
    ($data->{isbn10})       = $html =~ m!ISBN10\s*(\d+)!si;
    ($data->{binding})      = $html =~ m!Format\s*\s*([^\|]+)\|!si;
    ($data->{thumb})        = $html =~ m!"(https://\w+.cloudfare.net/assets/images/book/medium/\d+/\d+/\d+.jpg)"!si;
    ($data->{width},$data->{height},$data->{depth},$data->{weight})
                            = $html =~ m!Dimensions\s*\s*([\d.]+)\s*x\s*([\d.]+)\s*x\s*([\d.]+)mm\s*\|\s*([\d.]+)g!;

    # clean up
    $data->{publisher} =~ s/�?39;/'/g     if($data->{publisher});
    $data->{width}  = int($data->{width})   if($data->{width});
    $data->{height} = int($data->{height})  if($data->{height});
    $data->{weight} = int($data->{weight})  if($data->{weight});
    unless($data->{thumb}) {
        $data->{thumb} = $data->{image};
        $data->{thumb} =~ s!/large/!/medium/!;
    }

#use Data::Dumper;
#print STDERR "\n# " . Dumper($data);

    return $self->handler("Could not extract data from The Book Depository result page.")
        unless(defined $data);

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

    my $url = $mech->uri();
    $url =~ s/\?.*//;

    my $bk = {
        'ean13'       => $data->{isbn13},
        'isbn13'      => $data->{isbn13},
        'isbn10'      => $data->{isbn10},
        'isbn'        => $data->{isbn13},
        'author'      => $data->{author},
        'title'       => $data->{title},
        'book_link'   => "$url",
        'image_link'  => $data->{image},
        'thumb_link'  => $data->{thumb},
        'description' => $data->{description},
        'pubdate'     => $data->{pubdate},
        'publisher'   => $data->{publisher},
        'binding'     => $data->{binding},
        'pages'       => $data->{pages},
        'weight'      => $data->{weight},
        'width'       => $data->{width},
        'height'      => $data->{height},
#        'html'        => $html
    };

#use Data::Dumper;
#print STDERR "\n# book=".Dumper($bk);

    $self->book($bk);
    $self->found(1);
    return $self->book;
}

1;

__END__