Scrapes and returns a list of all genre IDs, aka 'geID' tag in iTunes Store media files.

itunes_genre_ids_scraper.php

#!/opt/local/bin/php71
<?php

// Usage:
// ./itunes_genre_ids_scraper.php > itunes_genre_ids.pl

// Ref: http://www.apple.com/itunes/affiliates/resources/documentation/genre-mapping.html
const GENRES_METADATA_URL =
  'http://itunes.apple.com/WebObjects/MZStoreServices.woa/ws/genres';

// Locale is U.S. English in UTF-8.
ini_set('default_charset', 'UTF-8');
setlocale(LC_ALL, 'en_US.UTF-8');

/**
  * @param array $hierarchy Higher level parent category or genres.
  */
function parse_genres ($json, &$hierarchy, &$genres) {
  array_push($hierarchy, $json->name);
  $genres[$json->id] = array(
    'id' => $json->id,
    'name' => implode('|', $hierarchy),
    'last_name' => $json->name,
    'last_name_html' => str_replace('&amp;', '&', htmlentities($json->name)),
  );
  if (isset($json->subgenres)) {
    foreach ($json->subgenres as $subgenre) {
      parse_genres($subgenre, $hierarchy, $genres);
    }
  }
  array_pop($hierarchy);
}

// Fetch iTunes genres metadata with cURL.
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, GENRES_METADATA_URL);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, TRUE);
# Enable all supported encoding types.
curl_setopt($curl, CURLOPT_ENCODING, '');
$json = curl_exec($curl);
curl_close($curl);

// Decode JSON string.
$json = json_decode($json);

// Loop through all genres, and store them in an array.
$hierarchy = array();
$genres = array();
foreach ($json as $category) {
  parse_genres($category, $hierarchy, $genres);
}

// Sort by numerical genre ID.
ksort($genres);

// Output all genres in your preferred format. Here as Perl source code for
// ExifTool. If genre name has accented letters, remove accents and add original
// name as comment in HTML.
function perl_escape_string ($str) {
  if (FALSE === strpos($str, "'")) {
    # No single quote in input.
    return sprintf("'%s'", $str);
  }
  if (FALSE === strpos($str, '"')) {
    # No double quote in input.
    return sprintf('"%s"', $str);
  }
  return sprintf("'%s'",
    str_replace(array("\\", "'"), array("\\\\", "\\'"), $str));
}
foreach ($genres as $genre) {
  if ($genre['last_name_html'] == $genre['last_name']) {
    $genre['last_name_html'] = '';
  } else {
    $genre['name'] =
      transliterator_transliterate('Any-Latin; Latin-ASCII', $genre['name']);
  }
  echo str_repeat(' ', 12) . sprintf("%d => %s,%s\n",
    $genre['id'],
    perl_escape_string($genre['name']),
    empty($genre['last_name_html']) ?
      '' :
      ' # (' . $genre['last_name_html'] . ')');
}