这两天有一客户定制了一个免登录发布模块,因为在模块中需要涉及到很多图片下载的问题,考虑到性能问题,所以特别写了一个CURL_MULTI远程采集网页的函数,以方便以后使用,估计以后都不会使用原来的单线程curl函数去foreach了,其性能对比很明显的。同样获取我的博客的十个不同网页,curl_multi:4.5246081352234,file_get_contents:33.001797914505,将近8倍的效率,可想而知,如果在附件更多的情况下,性能差异就越明显了,希望对您有所帮助!
PHP $text = remote(array('//www.jb51.cc/','http://www.baidu.com/')); print_r($text);
function remote($urls) { if (!is_array($urls) or count($urls) == 0) { return false; }
$curl = $text = array(); $handle = curl_multi_init(); foreach($urls as $k => $v) { $nurl[$k]= preg_replace('~([^:\/\.]+)~ei',"rawurlencode('\\1')",$v); $curl[$k] = curl_init($nurl[$k]); curl_setopt($curl[$k],CURLOPT_RETURNTRANSFER,1); curl_setopt($curl[$k],CURLOPT_HEADER,0); curl_multi_add_handle ($handle,$curl[$k]); }
$active = null; do { $mrc = curl_multi_exec($handle,$active); } while ($mrc == CURLM_CALL_MULTI_PERFORM);
while ($active && $mrc == CURLM_OK) { if (curl_multi_select($handle) != -1) { do { $mrc = curl_multi_exec($handle,$active); } while ($mrc == CURLM_CALL_MULTI_PERFORM); } }
foreach ($curl as $k => $v) { if (curl_error($curl[$k]) == "") { $text[$k] = (string) curl_multi_getcontent($curl[$k]); } curl_multi_remove_handle($handle,$curl[$k]); curl_close($curl[$k]); } curl_multi_close($handle); return $text; }