搜索引擎蜘蛛爬行记录—WordPress

网站收录有问题时，就会可能需求连续的搜索引擎蜘蛛的抓取环境。网站文章不收录时，第一时间就是要看看网站蜘蛛抓取的日志，但通过访问服务器的方式查看蜘蛛日志有点麻烦，我们可以用代码来实现给WordPress网站添加记录蜘蛛抓取日志的功能！

将下放代码放入主题的functions.php文件中：

function get_naps_bot()
{
    $useragent = strtolower($_SERVER['HTTP_USER_AGENT']);

    if (strpos($useragent, 'googlebot') !== false) {
        return 'Googlebot';
    }

    if (strpos($useragent, 'msnbot') !== false) {
        return 'MSNbot';
    }

    if (strpos($useragent, 'slurp') !== false) {
        return 'Yahoobot';
    }

    if (strpos($useragent, 'baiduspider') !== false) {
        return 'Baiduspider';
    }

    if (strpos($useragent, 'sohu-search') !== false) {
        return 'Sohubot';
    }

    if (strpos($useragent, 'lycos') !== false) {
        return 'Lycos';
    }

    if (strpos($useragent, 'robozilla') !== false) {
        return 'Robozilla';
    }

    return false;
}

function nowtime()
{
    date_default_timezone_set('Asia/Shanghai');
    $date = date("Y-m-d.G:i:s");
    return $date;
}

$searchbot = get_naps_bot();

if ($searchbot) {
    $tlc_thispage = addslashes($_SERVER['HTTP_USER_AGENT']);
    $url = $_SERVER['HTTP_REFERER'];
    $file = "robotslogs.txt";
    $time = nowtime();
    $data = fopen($file, "a");
    $PR = "$_SERVER[REQUEST_URI]";
    fwrite($data, "Time:$time robot:$searchbot URL:$tlc_thispage\n page:$PR\r\n");
    fclose($data);
}