PHP擴充下載：https://github.com/krakjoe/pthreads
PHP手冊文檔：http://php.net/manual/zh/book.pthreads.php
在安裝好擴充之後，就可以運用多線程了，下面貼個通過搜尋結果抓取百度網盤內容的代碼：
| 代碼如下 |
複製代碼 |
<?php
include 'include/CurlLoad.class.php'; // 引入讀取庫
/**
* 多線程抓取內容
* @param array $url 待抓取URL列表集合
* @return 成功返回指定內容，失敗返回NULL
*/
function vget($url) {
$ret = BaiduSRLinksGet ( $url, 1 ); // 擷取結果清單地址
if ($ret != null) {
if (array_key_exists ( "links", $ret )) {
$infos = array ();
$number = count ( $ret ['links'] );
for($i = 0; $i < $number; $i ++) {//迴圈建立線程對象
$thread_array [$i] = new baidu_thread_run ( $ret ['links'] [$i] );
$thread_array [$i]->start ();
}
foreach ( $thread_array as $thread_array_key => $thread_array_value ) {//檢查線程是否執行結束
while ( $thread_array [$thread_array_key]->isRunning () ) {
usleep ( 10 );
}
if ($thread_array [$thread_array_key]->join ()) {//如果執行結束，取出結果
$temp = $thread_array [$thread_array_key]->data;
if ($temp != null)
$infos ['res'] [] = $temp;
}
}
$infos ['pages'] = $ret ['pages'];
$infos ['status'] = "1";
} else
$infos = null;
} else
$infos = null;
return $infos;
}
/**
* 擷取百度搜尋結果列表URL
*
* @param string $url
* 搜尋結果頁URL
* @param int $format
* 預設$format=0，擷取預設地址；$format=1擷取跳轉後真真實位址
* @return NULL multitype:array()
*/
function BaiduSRLinksGet($url, $format = 0) {
$html = CurlLoad::HtmlGet ( $url ); // 擷取頁面
if ($html == null)
return null;
try {
preg_match_all ( "/"url":"(?<links>.*)"}/", $html, $rets ); // 搜尋結果連結篩選
if (! array_key_exists ( 'links', $rets )) // 如果數組中不包含Links鍵名，表示擷取失敗
return null;
$ret = array ();
if ($format == 1) {
$number = count ( $rets ['links'] );
for($i = 0; $i < $number; $i ++) {
$headr_temp = CurlLoad::Get_Headers ( $rets ['links'] [$i], 1 ); // 通過headr擷取真真實位址
if (array_key_exists ( "Location", $headr_temp ))
$ret ['links'] [$i] = $headr_temp ['Location'];
else
$ret ['links'] = $rets ['links'];
}
} else
$ret ['links'] = $rets ['links'];
preg_match_all ( '/href="?/s?wd=site%3Apan.baidu.com%20(?<url>.+?)&ie=utf-8">/', $html, $out );
unset ( $out ['url'] [0] );
$number = count ( $out ['url'] );
for($i = 1; $i < $number; $i ++) {
preg_match_all ( '/&pn=(.*)/', $out ['url'] [$i], $temp );
$ret ['pages'] [$temp [1] [0] / 10] = base64_encode ( $out ['url'] [$i] );
}
return $ret;
} catch ( Exception $e ) {
WriteLog ( $e );
return null;
}
}
/**
* 百度網盤資源資訊擷取
*
* @param string $url
* 網盤資源頁URL
* @return NULL array
*/
function PanInfoGet($url) {
$html = CurlLoad::HtmlGet ( $url ); // 擷取頁面
if ($html == null)
return null;
try {
if (preg_match_all ( "/檔案名稱:(?<name>.*) 檔案大小:(?<size>.*) 分享者:(?<user>.*) 分享時間:(?<date>.*) 下載次數:(?<number>[0-9]+)/", $html, $ret ) == 0)
return null;
$rets ['name'] = $ret ['name'] [0];
$rets ['size'] = $ret ['size'] [0];
$rets ['user'] = $ret ['user'] [0];
$rets ['date'] = $ret ['date'] [0];
$rets ['number'] = $ret ['number'] [0];
$rets ['link'] = $url;
return $rets;
} catch ( Exception $e ) {
WriteLog ( $e );
return null;
}
}
function WriteLog($str) {
$file = fopen ( "../error.log", "a+" );
fwrite ( $file, "Warning:" . date ( "Y/m/d H:i:s" ) . ":" . $str . "rn" );
fclose ( $file );
}
/**
* 多線程抓取對象
* @author MuXi
*
*/
class baidu_thread_run extends Thread {
public $url;
public $data;
public function __construct($url) {
$this->url = $url;
}
public function run() {
if (($url = $this->url)) {
$this->data = PanInfoGet ( $url );//線程執行方法
}
}
}
?> |
