- 相干保举
PHP若何利用curl完成数据抓取
导语:PHP若何利用curl完成数据抓取呢?上面是小编给大师供给的完成代码,大师能够参考浏览,更多概况请存眷应届毕业生测验网。
<?php
define ( 'IS_PROXY', true ); //是不是启用代办署理
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(); // 开启多线程
$i = 0;
foreach($url_array as $url) {
$ch = curl_init();
if (IS_PROXY) {
//以下代码设置代办署理办事器
//代办署理办事器地点//www.cnproxy.com/proxy1.html !!Hong Kong, China的速率比拟好
curl_setopt ($ch, CURLOPT_PROXY,'110.4.12.170:80' );
}
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); // return don't print
curl_setopt($ch, CURLOPT_TIMEOUT, 30); //设置超不时候
curl_setopt($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); //HTTp定向级别
curl_multi_add_handle($mh, $ch); // 把 curl resource 放进 multi curl handler 里
$handle[$i++] = $ch;
}
/* 履行 */
do {
$mrc = curl_multi_exec($mh, $running);
if ($wait_usec > 0) /* 每一个 connect 要距离多久 */
usleep($wait_usec); // 250000 = 0.25 sec
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
while ($running && $mrc == CURLM_OK) {
if (curl_multi_select($mh) != -1) {
do {
$mrc = curl_multi_exec($mh, $running);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
}
}
/* 读取材料 */
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;
}
$urls = array('//map.baidu.com');
$re = async_get_url($urls);
echo $re[0];
?>
【PHP若何利用curl完成数据抓取】相干文章:
PHP中利用cURL完成Get和Post要求的方式12-03
若何完成PHP获得表单数据与HTML嵌入PHP剧本03-25
php的curl进修总结03-31
PHP中多态若何完成03-07
php若何完成考证码11-26
教你若何利用php的session11-16