File Coverage

blib/lib/WWW/Gazetteer/Getty.pm

Criterion	Covered	Total	%
statement	65	69	94.2
branch	7	10	70.0
condition			n/a
subroutine	9	9	100.0
pod	2	2	100.0
total	83	90	92.2

package WWW::Gazetteer::Getty;
use strict;
use warnings;
use Carp qw(croak);
use HTTP::Cookies;
use LWP::UserAgent;
use URI::QueryParam;

use vars qw($VERSION);
$VERSION = '0.11';

my $countries = {
    af => 'Afghanistan',
    al => 'Albania',
    dz => 'Algeria',
    as => 'American Samoa',
    ad => 'Andorra',
    ao => 'Angola',
    ai => 'Anguilla',
    aq => 'Antarctica',
    ag => 'Antigua and Barbuda',
    ar => 'Argentina',
    am => 'Armenia',
    aw => 'Aruba',
    au => 'Australia',
    at => 'Austria',
    az => 'Azerbaijan',
    bs => 'Bahamas',
    bh => 'Bahrain',
    bd => 'Bangladesh',
    bb => 'Barbados',
    by => 'Belarus',
    be => 'Belgium',
    bz => 'Belize',
    bj => 'Benin',
    bm => 'Bermuda',
    bt => 'Bhutan',
    bo => 'Bolivia',
    ba => 'Bosnia and Herzegovina',
    bw => 'Botswana',
    bv => 'Bouvet Island',
    br => 'Brazil',
    io => 'British Indian Ocean Territory',
    bn => 'Brunei Darussalam',
    bg => 'Bulgaria',
    bf => 'Burkina Faso',
    bi => 'Burundi',
    kh => 'Cambodia',
    cm => 'Cameroon',
    ca => 'Canada',
    cv => 'Cape Verde',
    ky => 'Cayman Islands',
    cf => 'Central African Republic',
    td => 'Chad',
    cl => 'Chile',
    cn => 'China',
    cx => 'Christmas Island',
    cc => 'Cocos (Keeling) Islands',
    co => 'Colombia',
    km => 'Comoros',
    cg => 'Congo',
    ck => 'Cook Islands',
    cr => 'Costa Rica',
    ci => "Cote D'Ivoire",
    hr => 'Croatia',
    cu => 'Cuba',
    cy => 'Cyprus',
    cz => 'Czech Republic',
    dk => 'Denmark',
    dj => 'Djibouti',
    dm => 'Dominica',
    do => 'Dominican Republic',
    tl => 'East Timor',
    ec => 'Ecuador',
    eg => 'Egypt',
    sv => 'El Salvador',
    gq => 'Equatorial Guinea',
    er => 'Eritrea',
    ee => 'Estonia',
    et => 'Ethiopia',
    fk => 'Falkland Islands (Malvinas)',
    fo => 'Faroe Islands',
    fj => 'Fiji',
    fi => 'Finland',
    fr => 'France',
    fx => 'France, Metropolitan',
    gf => 'French Guiana',
    pf => 'French Polynesia',
    tf => 'French Southern Territories',
    ga => 'Gabon',
    gm => 'Gambia',
    ge => 'Georgia',
    de => 'Germany',
    gh => 'Ghana',
    gi => 'Gibraltar',
    gr => 'Greece',
    gl => 'Greenland',
    gd => 'Grenada',
    gp => 'Guadeloupe',
    gu => 'Guam',
    gt => 'Guatemala',
    gn => 'Guinea',
    gw => 'Guinea-Bissau',
    gy => 'Guyana',
    ht => 'Haiti',
    hm => 'Heard Island and McDonald Islands',
    va => 'Holy See (Vatican City State)',
    hn => 'Honduras',
    hk => 'Hong Kong',
    hu => 'Hungary',
    is => 'Iceland',
    in => 'India',
    id => 'Indonesia',
    ir => 'Iran, Islamic Republic of',
    iq => 'Iraq',
    ie => 'Ireland',
    il => 'Israel',
    it => 'Italy',
    jm => 'Jamaica',
    jp => 'Japan',
    jo => 'Jordan',
    kz => 'Kazakhstan',
    ke => 'Kenya',
    ki => 'Kiribati',
    kp => "Korea, Democratic People's Republic of",
    kr => 'Korea, Republic of',
    kw => 'Kuwait',
    kg => 'Kyrgyzstan',
    la => "Lao People's Democratic Republic",
    lv => 'Latvia',
    lb => 'Lebanon',
    ls => 'Lesotho',
    lr => 'Liberia',
    ly => 'Libyan Arab Jamahiriya',
    li => 'Liechtenstein',
    lt => 'Lithuania',
    lu => 'Luxembourg',
    mo => 'Macao',
    mk => 'Macedonia, the Former Yugoslav Republic of',
    mg => 'Madagascar',
    mw => 'Malawi',
    my => 'Malaysia',
    mv => 'Maldives',
    ml => 'Mali',
    mt => 'Malta',
    mh => 'Marshall Islands',
    mq => 'Martinique',
    mr => 'Mauritania',
    mu => 'Mauritius',
    yt => 'Mayotte',
    mx => 'Mexico',
    fm => 'Micronesia, Federated States of',
    md => 'Moldova, Republic of',
    mc => 'Monaco',
    mn => 'Mongolia',
    ms => 'Montserrat',
    ma => 'Morocco',
    mz => 'Mozambique',
    mm => 'Myanmar',
    na => 'Namibia',
    nr => 'Nauru',
    np => 'Nepal',
    nl => 'Netherlands',
    an => 'Netherlands Antilles',
    nc => 'New Caledonia',
    nz => 'New Zealand',
    ni => 'Nicaragua',
    ne => 'Niger',
    ng => 'Nigeria',
    nu => 'Niue',
    nf => 'Norfolk Island',
    mp => 'Northern Mariana Islands',
    no => 'Norway',
    om => 'Oman',
    pk => 'Pakistan',
    pw => 'Palau',
    ps => 'Palestinian Territory, Occupied',
    pa => 'Panama',
    pg => 'Papua New Guinea',
    py => 'Paraguay',
    pe => 'Peru',
    ph => 'Philippines',
    pn => 'Pitcairn',
    pl => 'Poland',
    pt => 'Portugal',
    pr => 'Puerto Rico',
    qa => 'Qatar',
    re => 'Reunion',
    ro => 'Romania',
    ru => 'Russian Federation',
    rw => 'Rwanda',
    sh => 'Saint Helena',
    kn => 'Saint Kitts and Nevis',
    lc => 'Saint Lucia',
    pm => 'Saint Pierre and Miquelon',
    vc => 'Saint Vincent and the Grenadines',
    ws => 'Samoa',
    sm => 'San Marino',
    st => 'Sao Tome and Principe',
    sa => 'Saudi Arabia',
    sn => 'Senegal',
    sc => 'Seychelles',
    sl => 'Sierra Leone',
    sg => 'Singapore',
    sk => 'Slovakia',
    si => 'Slovenia',
    sb => 'Solomon Islands',
    so => 'Somalia',
    za => 'South Africa',
    gs => 'South Georgia and the South Sandwich Islands',
    es => 'Spain',
    lk => 'Sri Lanka',
    sd => 'Sudan',
    sr => 'Suriname',
    sj => 'Svalbard and Jan Mayen',
    sz => 'Swaziland',
    se => 'Sweden',
    ch => 'Switzerland',
    sy => 'Syrian Arab Republic',
    tw => 'Taiwan, Province of China',
    tj => 'Tajikistan',
    tz => 'Tanzania, United Republic of',
    th => 'Thailand',
    tg => 'Togo',
    tk => 'Tokelau',
    to => 'Tonga',
    tt => 'Trinidad and Tobago',
    tn => 'Tunisia',
    tr => 'Turkey',
    tm => 'Turkmenistan',
    tc => 'Turks and Caicos Islands',
    tv => 'Tuvalu',
    ug => 'Uganda',
    ua => 'Ukraine',
    ae => 'United Arab Emirates',
    gb => 'United Kingdom',
    uk => 'United Kingdom',
    us => 'United States',
    um => 'United States Minor Outlying Islands',
    uy => 'Uruguay',
    uz => 'Uzbekistan',
    vu => 'Vanuatu',
    ve => 'Venezuela',
    vn => 'Vietnam',
    vg => 'Virgin Islands, British',
    vi => 'Virgin Islands, U.S.',
    wf => 'Wallis and Futuna',
    eh => 'Western Sahara',
    ye => 'Yemen',
    yu => 'Yugoslavia',
    zr => 'Zaire',
    zm => 'Zambia',
    zw => 'Zimbabwe',
};

sub new {
    my ($class) = @_;

    my $self = {};
    my $ua   = LWP::UserAgent->new(
        env_proxy  => 1,
        keep_alive => 1,
        timeout    => 30,
    );
    $ua->agent( "WWW::Gazetteer::Getty/$VERSION " . $ua->agent );

    $self->{ua} = $ua;

    bless $self, $class;
    return $self;
}

sub find {
    my ( $self, $city, $country ) = @_;

    if ( $countries->{ lc $country } ) {
        $country = $countries->{ lc $country };
    }

    my $ua = $self->{ua};

# http://www.getty.edu/vow/TGNServlet?english=Y&find=London&place=&page=1&nation=United+Kingdom
    my $search_url = URI->new("http://www.getty.edu/vow/TGNServlet");
    $search_url->query_param( 'english' => 'Y' );
    $search_url->query_param( 'find'    => $city );
    $search_url->query_param( 'place'   => undef );
    $search_url->query_param( 'page'    => 1 );
    $search_url->query_param( 'nation'  => $country );

    my $request = HTTP::Request->new( 'GET', $search_url );
    my $response = $ua->request($request);

    if ( not $response->is_success ) {
        croak("WWW::Gazetteer::Getty: City $city in $country not found");
        return;
    }

    my @cities;
    my $content = $response->content;

    my @bits = split /checkbox/, $content;

    my @ids;
    foreach my $bit (@bits) {
        my ($id) = $bit =~ m{subjectid=(\d+)};
        next unless $id;
        push @ids, $id;
    }

    foreach my $id (@ids) {

# http://www.getty.edu/vow/TGNFullDisplay?find=London&place=&nation=United+Kingdom&prev_page=1&english=Y&subjectid=7018906
        my $detail_url = URI->new("http://www.getty.edu/vow/TGNFullDisplay");
        $detail_url->query_param( 'english'   => 'Y' );
        $detail_url->query_param( 'find'      => $city );
        $detail_url->query_param( 'place'     => undef );
        $detail_url->query_param( 'page'      => 1 );
        $detail_url->query_param( 'nation'    => $country );
        $detail_url->query_param( 'subjectid' => $id );

        $request = HTTP::Request->new( 'GET', $detail_url );
        $response = $ua->request($request);

        if ( not $response->is_success ) {
            croak("WWW::Gazetteer::Getty: City $city in $country not found");
            return;
        }

        $content = $response->content;

#
#
        my ($latitude)
            = $content
            =~ m{Lat:\s+([0-9.-]+)  decimal degrees};
        my ($longitude)
            = $content
            =~ m{Long:\s+([0-9.-]+)  decimal degrees};

        push @cities,
            {
            city      => $city,
            country   => $country,
            latitude  => $latitude,
            longitude => $longitude,
            };
    }
    return wantarray ? @cities : \@cities;
}

__END__