一般 CURL 抓網頁的方法, 是一頁一頁抓, 假設要抓 4頁, 所費時間各別是 5,10,7,5 秒, 那全部總合所花的時間就是 5 + 10 + 7 + 5 = 27 秒.
若能同時間去抓取多個網頁, 所花費的時間 5,10,7,5 秒, 全部總合所花的時間是 10 秒.(花費最多時間的秒數)
於 JavaScript 可使用 AJAX 的 async(YAHOO.util.Connect.asyncRequest) 來達成, 於 PHP 可以用 CURL 來達成此 Multi-Threading 的效果.
程式(async.php)
function async_get_url($url_array, $wait_usec = 0)
{
if (!is_array($url_array))
return false;
$wait_usec = intval($wait_usec);
$data = array();
$handle = array();
$running = 0;
$mh = curl_multi_init(); // multi curl handler
$i = 0;
foreach($url_array as $url) {
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); // return don't print
curl_setopt($ch, CURLOPT_TIMEOUT, 30);
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)');
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); // 302 redirect
curl_setopt($ch, CURLOPT_MAXREDIRS, 7);
curl_multi_add_handle($mh, $ch); // 把 curl resource 放進 multi curl handler 裡
$handle[$i++] = $ch;
}
/* 執行 */
/* 此種做法會造成 CPU loading 過重 (CPU 100%)
do {
curl_multi_exec($mh, $running);
if ($wait_usec > 0) // 每個 connect 要間隔多久
usleep($wait_usec); // 250000 = 0.25 sec
} while ($running > 0);
*/
/* 此做法就可以避免掉 CPU loading 100% 的問題 */
// 參考自: http://www.hengss.com/xueyuan/sort0362/php/info-36963.html
do {
$mrc = curl_multi_exec($mh, $active);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
while ($active and $mrc == CURLM_OK) {
if (curl_multi_select($mh) != -1) {
do {
$mrc = curl_multi_exec($mh, $active);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
}
}
/* 讀取資料 */
foreach($handle as $i => $ch) {
$content = curl_multi_getcontent($ch);
$data[$i] = (curl_errno($ch) == 0) ? $content : false;
}
/* 移除 handle*/
foreach($handle as $ch) {
curl_multi_remove_handle($mh, $ch);
}
curl_multi_close($mh);
return $data;
}
?>
使用
$urls = array('http://example1.com', 'http://example2.com');
print_r(async_get_url($urls)); // [0] => example1, [1] => example2
?>
測試
sleep.php # 看時間延長取得的效果
sleep(intval($_GET['time']));
echo intval($_GET['time']);
?>
$url_array = array(
'http://example.com/sleep.php?time=5',
'http://example.com/sleep.php?time=10',
'http://example.com/sleep.php?time=7',
'http://example.com/sleep.php?time=5',
);
print_r(async_get_url($url_array));
// 總花費時間會是 10 秒, 並印出 [0] => 5, [1] => 10, [2] => 7, [3] => 5
?>
|
