function aggregator_parse_feed

Parse a feed and store its items.

Parameters

$data: The feed data.

$feed: An associative array describing the feed to be parsed.

Return value

0 on error, 1 otherwise.

File

modules/aggregator/aggregator.module, line 699

Used to aggregate syndicated content (RSS, RDF, and Atom).

Code

function aggregator_parse_feed(&$data, $feed) {
  global $items, $image, $channel;

  // Unset the global variables before we use them:
  unset($GLOBALS['element'], $GLOBALS['item'], $GLOBALS['tag']);
  $items = array();
  $image = array();
  $channel = array();

  // parse the data:
  $xml_parser = drupal_xml_parser_create($data);
  xml_set_element_handler($xml_parser, 'aggregator_element_start', 'aggregator_element_end');
  xml_set_character_data_handler($xml_parser, 'aggregator_element_data');
  if (!xml_parse($xml_parser, $data, 1)) {
    watchdog('aggregator', 'The feed from %site seems to be broken, due to an error "%error" on line %line.', array(
      '%site' => $feed['title'],
      '%error' => xml_error_string(xml_get_error_code($xml_parser)),
      '%line' => xml_get_current_line_number($xml_parser),
    ), WATCHDOG_WARNING);
    drupal_set_message(t('The feed from %site seems to be broken, because of error "%error" on line %line.', array(
      '%site' => $feed['title'],
      '%error' => xml_error_string(xml_get_error_code($xml_parser)),
      '%line' => xml_get_current_line_number($xml_parser),
    )), 'error');
    return 0;
  }
  xml_parser_free($xml_parser);

  // We reverse the array such that we store the first item last, and the last
  // item first. In the database, the newest item should be at the top.
  $items = array_reverse($items);

  // Initialize variables.
  $title = $link = $author = $description = $guid = NULL;
  foreach ($items as $item) {
    unset($title, $link, $author, $description, $guid);

    // Prepare the item:
    foreach ($item as $key => $value) {
      $item[$key] = trim($value);
    }

    // Resolve the item's title. If no title is found, we use up to 40
    // characters of the description ending at a word boundary but not
    // splitting potential entities.
    if (!empty($item['TITLE'])) {
      $title = $item['TITLE'];
    }
    elseif (!empty($item['DESCRIPTION'])) {
      $title = preg_replace('/^(.*)[^\\w;&].*?$/', "\\1", truncate_utf8($item['DESCRIPTION'], 40));
    }
    else {
      $title = '';
    }

    // Resolve the items link.
    if (!empty($item['LINK'])) {
      $link = $item['LINK'];
    }
    else {
      $link = $feed['link'];
    }

    // Atom feeds use ID rather than GUID.
    if (isset($item['GUID'])) {
      $guid = $item['GUID'];
    }
    elseif (isset($item['ID'])) {
      $guid = $item['ID'];
    }
    else {
      $guid = '';
    }

    // Atom feeds have a CONTENT and/or SUMMARY tag instead of a DESCRIPTION tag.
    if (!empty($item['CONTENT:ENCODED'])) {
      $item['DESCRIPTION'] = $item['CONTENT:ENCODED'];
    }
    else {
      if (!empty($item['SUMMARY'])) {
        $item['DESCRIPTION'] = $item['SUMMARY'];
      }
      else {
        if (!empty($item['CONTENT'])) {
          $item['DESCRIPTION'] = $item['CONTENT'];
        }
      }
    }

    // Try to resolve and parse the item's publication date. If no date is
    // found, we use the current date instead.
    $date = 'now';
    foreach (array(
      'PUBDATE',
      'DC:DATE',
      'DCTERMS:ISSUED',
      'DCTERMS:CREATED',
      'DCTERMS:MODIFIED',
      'ISSUED',
      'CREATED',
      'MODIFIED',
      'PUBLISHED',
      'UPDATED',
    ) as $key) {
      if (!empty($item[$key])) {
        $date = $item[$key];
        break;
      }
    }
    $timestamp = strtotime($date);

    // As of PHP 5.1.0, strtotime returns FALSE on failure instead of -1.
    if ($timestamp <= 0) {
      $timestamp = aggregator_parse_w3cdtf($date);

      // Returns FALSE on failure
      if (!$timestamp) {
        $timestamp = time();

        // better than nothing
      }
    }

    // Resolve dc:creator tag as the item author if author tag is not set.
    if (empty($item['AUTHOR']) && !empty($item['DC:CREATOR'])) {
      $item['AUTHOR'] = $item['DC:CREATOR'];
    }

    // Save this item. Try to avoid duplicate entries as much as possible. If
    // we find a duplicate entry, we resolve it and pass along its ID is such
    // that we can update it if needed.
    if (!empty($guid)) {
      $entry = db_fetch_object(db_query("SELECT iid FROM {aggregator_item} WHERE fid = %d AND guid = '%s'", $feed['fid'], $guid));
    }
    else {
      if ($link && $link != $feed['link'] && $link != $feed['url']) {
        $entry = db_fetch_object(db_query("SELECT iid FROM {aggregator_item} WHERE fid = %d AND link = '%s'", $feed['fid'], $link));
      }
      else {
        $entry = db_fetch_object(db_query("SELECT iid FROM {aggregator_item} WHERE fid = %d AND title = '%s'", $feed['fid'], $title));
      }
    }
    $item += array(
      'AUTHOR' => '',
      'DESCRIPTION' => '',
    );
    aggregator_save_item(array(
      'iid' => isset($entry->iid) ? $entry->iid : '',
      'fid' => $feed['fid'],
      'timestamp' => $timestamp,
      'title' => $title,
      'link' => $link,
      'author' => $item['AUTHOR'],
      'description' => $item['DESCRIPTION'],
      'guid' => $guid,
    ));
  }

  // Remove all items that are older than flush item timer.
  $age = time() - variable_get('aggregator_clear', 9676800);
  $result = db_query('SELECT iid FROM {aggregator_item} WHERE fid = %d AND timestamp < %d', $feed['fid'], $age);
  $items = array();
  $num_rows = FALSE;
  while ($item = db_fetch_object($result)) {
    $items[] = $item->iid;
    $num_rows = TRUE;
  }
  if ($num_rows) {
    db_query('DELETE FROM {aggregator_category_item} WHERE iid IN (' . implode(', ', $items) . ')');
    db_query('DELETE FROM {aggregator_item} WHERE fid = %d AND timestamp < %d', $feed['fid'], $age);
  }
  return 1;
}