pb_csv.php

<?php
define('START', 0);
define('END', 948);

$output_handle = fopen('./projects.csv', 'w');
fputcsv($output_handle, [
  'category',
  'development status',
  'maintained',
  'body',
  'project type',
  'machine name',
  'has issue queue',
  'components',
  'has releases',
  'homepage url',
  'changelog url',
  'demo url',
  'documentation url',
  'screenshots url',
  'license',
  'number of images',
  'number supporting orgs',
  'issue version options',
  'security coverage',
  'ecosystem(s)',
  'next major version info',
  'has been replaced',
  'has issue summary template',
  'stars',
  'nid',
  'title',
  'url',
  'total usage',
]);
for ($number = START; $number <= END; $number++) {
  echo "Processing page $number\n";
  $resource = file_get_contents("https://www.drupal.org/api-d7/node.json?type=project_module&page=$number", 'r');
  $json = json_decode($resource);
  $all_modules = $json->list;

  // Iterate through all the modules.
  foreach($all_modules as $module) {
    $row = [];

    // Vocabulary 3.
    $v3 = [];
    foreach($module->taxonomy_vocabulary_3 as $term) {
      $v3[] = $term->id;
    }
    $row['vocab_3'] = '|' . implode('|', $v3) . '|';

    // Vocabulary 46.
    $row['vocab_46'] = ($module->taxonomy_vocabulary_46 ? $module->taxonomy_vocabulary_46->id : '');

    // Vocabulary 44.
    $row['vocab_44'] = ($module->taxonomy_vocabulary_44 ? $module->taxonomy_vocabulary_44->id : '');

    $row['body']= substr($module->body->value, 0, 100);
    $row['field_project_type'] = $module->field_project_type;
    $row['field_project_machine_name'] = $module->field_project_machine_name;
    $row['field_project_has_issue_queue'] = $module->field_project_has_issue_queue;
    $row['field_project_components'] = '|' . implode('|', $module->field_project_components) . '|';
    $row['field_project_has_releases'] = $module->field_project_has_releases;
    $row['field_project_homepage'] = $module->field_project_homepage->url;
    $row['field_project_changelog'] = $module->field_project_changelog->url;
    $row['field_project_demo'] = $module->field_project_demo->url;
    $row['field_project_documentation'] = $module->field_project_documentation->url;
    $row['field_project_screenshots'] = $module->field_project_screenshots->url;
    $row['field_project_license'] = $module->field_project_license->url;
    $row['num_project_images'] = count($module->field_project_images);
    $row['field_supporting_organizations'] = count($module->field_supporting_organizations);
    $row['num_project_docs'] = count($module->field_project_docs);
    $row['field_project_issue_version_opts'] = '|'. implode('|', $module->field_project_issue_version_opts) . '|';
    $row['field_security_advisory_coverage'] = $module->field_security_advisory_coverage;

    // Ecosystems.
    $ecosystems = [];
    foreach($module->field_project_ecosystem as $system) {
      $ecosystems[] = $system->id;
    }
    $row['field_project_ecosystem'] = '|' . implode('|', $ecosystems) . '|';

    $row['field_next_major_version_info'] = $module->field_next_major_version_info->value;
    $row['replaced'] = (bool)(count($module->field_replaced_by) > 0);
    $row['field_issue_summary_template'] = !empty($module->field_issue_summary_template->value);
    $row['stars'] = is_array($module->flag_project_star_user) ? count($module->flag_project_star_user) : 0;
    $row['nid'] = $module->nid;
    $row['title'] = $module->title;
    $row['url'] = $module->url;
    $row['total_usage'] = 0;
    if (property_exists($module, 'project_usage')) {
      foreach($module->project_usage as $branch => $usage) {
        $row['total_usage'] += (int)$usage;
      }
    }

    fputcsv($output_handle, $row);
  }
  sleep(2);
}