function linkchecker_cron in Link checker 5.2

Same name and namespace in other branches

1. 8 linkchecker.module \linkchecker_cron()
2. 5 linkchecker.module \linkchecker_cron()
3. 6.2 linkchecker.module \linkchecker_cron()
4. 7 linkchecker.module \linkchecker_cron()

Implementation of hook_cron().

File

./linkchecker.module, line 677

This module periodically check links in given node types, blocks, cck fields, etc.

Code

function linkchecker_cron() {

  // Get max_execution_time from configuration, override 0 with 240 seconds.
  $max_execution_time = ini_get('max_execution_time') == 0 ? 240 : ini_get('max_execution_time');

  // Remove outdated links no longer in use once per day.
  if (time() - variable_get('linkchecker_cleanup_links_last', 0) >= 86400) {
    _linkchecker_cleanup_links();
    variable_set('linkchecker_cleanup_links_last', time());
  }

  // TODO: Implement cURL support.

  //$has_curl = function_exists('curl_init');

  // TODO: Remove some confusion about the max links that can be checked per
  // cron run and guess that 2 link can be checked per second what is
  // nevertheless uncommon. But we can use the max_execution_time to calculate
  // a value that is higher, but not totally out of scope to keep the query
  // resultset small. For cURL we need to add this setting back or a thread
  // limit per remote server for not overloading them.
  $check_links_max_per_cron_run = $max_execution_time;

  //$check_links_max_per_cron_run = variable_get('linkchecker_check_links_max', 10);
  $check_links_interval = variable_get('linkchecker_check_links_interval', 2419200);
  $useragent = variable_get('linkchecker_check_useragent', 'Drupal (+http://drupal.org/)');

  // Get URLs for checking.
  $result = db_query_range("SELECT * FROM {linkchecker_links} WHERE last_checked < %d AND status = %d ORDER BY last_checked, lid ASC", time() - $check_links_interval, 1, 0, $check_links_max_per_cron_run);
  while ($link = db_fetch_object($result)) {

    // Fetch URL.
    $response = drupal_http_request($link->url, array(
      'User-Agent' => 'User-Agent: ' . $useragent,
    ), $link->method, NULL, 1);
    _linkchecker_status_handling($link, $response);
    if (timer_read('page') / 1000 > $max_execution_time / 2) {
      break;

      // Stop once we have used over half of the maximum execution time.
    }
  }
}