external_file_import.php

<?php

function custom_import_import_files_batch_files(&$context) {
  db_set_active('import');

  // Build the total import count.
  // need to query D5 db 
  // mysql> select nr.body from node_revisions nr join node n on n.nid = nr.nid where n.type = 'homepage' and nr.body like '%flipperpage%';

  if (empty($context['sandbox'])) {
    $query = db_select('node_revisions', 'nr');
    $query->join('node', 'n', 'nr.vid = n.vid');
    $query->condition('n.type', 'homepage');
    $query->condition('nr.body', '%flipperpage%', 'LIKE');

    $query->addExpression('COUNT(*)', 'count');
    $max = $query->execute()->fetchField();

    $context['sandbox'] = array(
      'progress' => 0,
      'current_node' => 0,
      'max' => $max,
    );
  }

  $limit = 5; // Number of nodes to process at a time.
  $query = db_select('node_revisions', 'nr');
  $query->join('node', 'n', 'nr.vid = n.vid');
  $query->condition('n.type', 'homepage');
  $query->condition('nr.body', '%flipperpage%', 'LIKE');
  $query->orderBy('n.nid', 'asc');
  $query->fields('nr', array('body'));
  $query->fields('n');
  $query->condition('n.nid', $context['sandbox']['current_node'], '>');
  $query->range(0, $limit);
  $result = $query->execute();

  db_set_active('default'); // Switch back.
  foreach ($result as $row) {
    $urls = custom_import_import_files_grep_url($row->body);
    // Get rid of the regex match from the first element before iterating
    array_shift($urls);
    
    foreach ($urls[0] as $match) {
      $dl = drupal_http_request('http://flipperpage.com/pdf/' . $match);
      $pdf = file_save_data($dl->data, 'public://' . $match . '.pdf');
      drupal_chmod($pdf->uri, 0664);
      // Imagick can fall over sometimes when handled streams so we give
      // the full path
      $path = drupal_realpath($pdf->uri);

      // Convert pdf to image for the front page
      //      if (class_exists("Imagick")) {
      // TODO clean up the /tmp and make it drupal temp dir etc
      $image = new Imagick();
      // Set ratio and source for page 1
      $image->setResolution(100, 100); 
      $image->readImage($path . '[0]');
      $image->setImageFormat('png');
      $image->writeImage('/tmp/' . $pdf->filename . '.png');
      $image->clear();
      $image->destroy();

      $im = new stdClass();
      $im->uri = '/tmp/' . $pdf->filename . '.png';
      $im->status = 1;
      $im = file_move($im, 'public://');

      // Have to set display to TRUE or it'll fail
      // and have to ensure the file objects are arrays
      // so when it's processed by Drupal it doesn't fail
      $apdf = (array) $pdf;
      $apdf['display'] = 1;
      $aim = (array) $im;
      $aim['display'] = 1;
      $node = new stdClass();
      $node->type = 'edition';
      $node->title = $row->title;
      $node->language = LANGUAGE_NONE;
      $node->changed = $row->changed;
      $node->created = $row->created;
      $node->uid = 1;
      $node->status = 1;
      $node->field_file['und'][] = $apdf;
      $node->field_image['und'][] = $aim;

      $term = taxonomy_get_term_by_name($node->title, 'edition');
      foreach ($term as $term_tid) {
        // because we use the vocab id we are pretty safe to
        // assume there is only one term
        $tid = $term_tid->tid;
      }
      if ($tid) {
        $node->field_edition['und'][] = array(
          'tid' => $tid,
        );
      }
      node_save($node);
    } 

    $context['sandbox']['progress'] ++;
    $context['message'] = t('Importing node @title', array('@title' => $row->title));
    $context['sandbox']['current_node'] = $row->nid;
  }

  if ($context['sandbox']['progress'] != $context['sandbox']['max']) {
    $context['finished'] = $context['sandbox']['progress'] / $context['sandbox']['max'];
  }
}