php結合curl實現多線程抓取

2024-05-04 23:37:31

字體：大中小

來源：轉載

供稿：網友

PHP利用 Curl可以完成各種傳送文件操作，比如模擬瀏覽器發送GET，POST請求等等，然而因為php語言本身不支持多線程，所以開發爬蟲程序效率并不高，因此經常需要借助Curl Multi Functions 這個功能實現并發多線程的訪問多個url地址以實現并發多線程抓取網頁或者下載文件

php結合curl實現多線程抓取

<?php

/*

curl 多線程抓取

*/

/**

* curl 多線程

*

* @param array $array 并行網址

* @param int $timeout 超時時間

* @return array

*/

function Curl_http($array,$timeout){

$res = array();

$mh = curl_multi_init();//創建多個curl語柄

$startime = getmicrotime();

foreach($array as $k=>$url){

$conn[$k]=curl_init($url);

curl_setopt($conn[$k], CURLOPT_TIMEOUT, $timeout);//設置超時時間

curl_setopt($conn[$k], CURLOPT_USERAGENT, 'Mozilla/5.0 (compatible; MSIE 5.01; Windows NT 5.0)');

curl_setopt($conn[$k], CURLOPT_MAXREDIRS, 7);//HTTp定向級別

curl_setopt($conn[$k], CURLOPT_HEADER, 0);//這里不要header，加塊效率

curl_setopt($conn[$k], CURLOPT_FOLLOWLOCATION, 1); // 302 redirect

curl_setopt($conn[$k],CURLOPT_RETURNTRANSFER,1);

curl_multi_add_handle ($mh,$conn[$k]);

}

//防止死循環耗死cpu 這段是根據網上的寫法

do {

$mrc = curl_multi_exec($mh,$active);//當無數據，active=true

} while ($mrc == CURLM_CALL_MULTI_PERFORM);//當正在接受數據時

while ($active and $mrc == CURLM_OK) {//當無數據時或請求暫停時，active=true

if (curl_multi_select($mh) != -1) {

do {

$mrc = curl_multi_exec($mh, $active);

} while ($mrc == CURLM_CALL_MULTI_PERFORM);

}

}

foreach ($array as $k => $url) {

curl_error($conn[$k]);

$res[$k]=curl_multi_getcontent($conn[$k]);//獲得返回信息

$header[$k]=curl_getinfo($conn[$k]);//返回頭信息

curl_close($conn[$k]);//關閉語柄

curl_multi_remove_handle($mh , $conn[$k]); //釋放資源

}

curl_multi_close($mh);

$endtime = getmicrotime();

$diff_time = $endtime - $startime;

return array('diff_time'=>$diff_time,

'return'=>$res,

'header'=>$header

);

}

//計算當前時間

function getmicrotime() {

list($usec, $sec) = explode(" ",microtime());

return ((float)$usec + (float)$sec);

}

//測試一下，curl 三個網址

$array = array(

"http://www.weibo.com/",

"http://www.renren.com/",

"http://www.qq.com/"

);

$data = Curl_http($array,'10');//調用

var_dump($data);//輸出

//如果POST的數據大于1024字節，curl并不會直接就發起POST請求

//發送請求時，header中包含一個空的Expect。curl_setopt($ch, CURLOPT_HTTPHEADER, array("Expect:"));

?>

我們再來看幾個例子

(1)下面這段代碼是實現抓取多個URL，然后將抓取的URL的頁面代碼寫入指定的文件

$urls = array(

'http://m.survivalescaperooms.com/',

'http://www.google.com/',

'http://www.example.com/'

); // 設置要抓取的頁面URL

$save_to='/test.txt'; // 把抓取的代碼寫入該文件

$st = fopen($save_to,"a");

$mh = curl_multi_init();

foreach ($urls as $i => $url) {

$conn[$i] = curl_init($url);

curl_setopt($conn[$i], CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)");

curl_setopt($conn[$i], CURLOPT_HEADER ,0);

curl_setopt($conn[$i], CURLOPT_CONNECTTIMEOUT,60);

curl_setopt($conn[$i], CURLOPT_FILE,$st); // 將爬取的代碼寫入文件

curl_multi_add_handle ($mh,$conn[$i]);

} // 初始化

do {

curl_multi_exec($mh,$active);

} while ($active); // 執行

foreach ($urls as $i => $url) {

curl_multi_remove_handle($mh,$conn[$i]);

curl_close($conn[$i]);

} // 結束清理

curl_multi_close($mh);

fclose($st);

(2)下面這段代碼和上面差不多意思，只不過這個地方是將獲得的代碼先放入變量，然后再將獲取到的內容寫入指定的文件

$urls = array(

'http://m.survivalescaperooms.com/',

'http://www.google.com/',

'http://www.example.com/'

);

$save_to='/test.txt'; // 把抓取的代碼寫入該文件

$st = fopen($save_to,"a");

$mh = curl_multi_init();

foreach ($urls as $i => $url) {

$conn[$i] = curl_init($url);

curl_setopt($conn[$i], CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)");

curl_setopt($conn[$i], CURLOPT_HEADER ,0);

curl_setopt($conn[$i], CURLOPT_CONNECTTIMEOUT,60);

curl_setopt($conn[$i],CURLOPT_RETURNTRANSFER,true); // 不將爬取代碼寫到瀏覽器，而是轉化為字符串

curl_multi_add_handle ($mh,$conn[$i]);

}

do {

curl_multi_exec($mh,$active);

} while ($active);

foreach ($urls as $i => $url) {

$data = curl_multi_getcontent($conn[$i]); // 獲得爬取的代碼字符串

fwrite($st,$data); // 將字符串寫入文件

} // 獲得數據變量，并寫入文件

foreach ($urls as $i => $url) {

curl_multi_remove_handle($mh,$conn[$i]);

curl_close($conn[$i]);

}

curl_multi_close($mh);

fclose($st);

(3)下面這段代碼實現的是利用 PHP 的 Curl Functions 實現并發多線程下載文件

$urls=array(

'http://m.survivalescaperooms.com/5w.zip',

'http://m.survivalescaperooms.com/5w.zip',

'http://m.survivalescaperooms.com/5w.zip'

);

$save_to='./home/';

$mh=curl_multi_init();

foreach($urls as $i=>$url){

$g=$save_to.basename($url);

if(!is_file($g)){

$conn[$i]=curl_init($url);

$fp[$i]=fopen($g,"w");

curl_setopt($conn[$i],CURLOPT_USERAGENT,"Mozilla/4.0(compatible; MSIE 7.0; Windows NT 6.0)");

curl_setopt($conn[$i],CURLOPT_FILE,$fp[$i]);

curl_setopt($conn[$i],CURLOPT_HEADER ,0);

curl_setopt($conn[$i],CURLOPT_CONNECTTIMEOUT,60);

curl_multi_add_handle($mh,$conn[$i]);

}

}

do{

$n=curl_multi_exec($mh,$active);

}while($active);

foreach($urls as $i=>$url){

curl_multi_remove_handle($mh,$conn[$i]);

curl_close($conn[$i]);

fclose($fp[$i]);

}

curl_multi_close($mh);$urls=array(

'http://m.survivalescaperooms.com/5w.zip',

'http://m.survivalescaperooms.com/5w.zip',

'http://m.survivalescaperooms.com/5w.zip'

);

$save_to='./home/';

$mh=curl_multi_init();

foreach($urls as $i=>$url){

$g=$save_to.basename($url);

if(!is_file($g)){

$conn[$i]=curl_init($url);

$fp[$i]=fopen($g,"w");

curl_setopt($conn[$i],CURLOPT_USERAGENT,"Mozilla/4.0(compatible; MSIE 7.0; Windows NT 6.0)");

curl_setopt($conn[$i],CURLOPT_FILE,$fp[$i]);

curl_setopt($conn[$i],CURLOPT_HEADER ,0);

curl_setopt($conn[$i],CURLOPT_CONNECTTIMEOUT,60);

curl_multi_add_handle($mh,$conn[$i]);

}

}

do{

$n=curl_multi_exec($mh,$active);

}while($active);

foreach($urls as $i=>$url){

curl_multi_remove_handle($mh,$conn[$i]);

curl_close($conn[$i]);

fclose($fp[$i]);

}

curl_multi_close($mh);