Php多线程的使用,首先需要PHP5.3以上版本,并安装pthreads PHP扩展,可以使PHP真正的支持多线程,扩展如何安装请自行百度
PHP扩展下载:https://github.com/krakjoe/pthreads
PHP手册文档:http://php.net/manual/zh/book.pthreads.php
在安装好扩展之后,就可以运用多线程了,下面贴个通过搜索结果抓取百度网盘内容的代码:
<?php include 'include/CurlLoad.class.php'; // 引入读取库 /** * 多线程抓取内容 * @param array $url 待抓取URL列表集合 * @return 成功返回指定内容,失败返回NULL */ function vget($url) { $ret = BaiduSRLinksGet ( $url, 1 ); // 获取结果列表地址 if ($ret != null) { if (array_key_exists ( "links", $ret )) { $infos = array (); $number = count ( $ret ['links'] ); for($i = 0; $i < $number; $i ++) {//循环创建线程对象 $thread_array [$i] = new baidu_thread_run ( $ret ['links'] [$i] ); $thread_array [$i]->start (); } foreach ( $thread_array as $thread_array_key => $thread_array_value ) {//检查线程是否执行结束 while ( $thread_array [$thread_array_key]->isRunning () ) { usleep ( 10 ); } if ($thread_array [$thread_array_key]->join ()) {//如果执行结束,取出结果 $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; } /** * 获取百度搜索结果列表URL * * @param string $url * 搜索结果页URL * @param int $format * 默认$format=0,获取默认地址;$format=1获取跳转后真实地址 * @return NULL multitype:array() */ function BaiduSRLinksGet($url, $format = 0) { $html = CurlLoad::HtmlGet ( $url ); // 获取页面 if ($html == null) return null; try { preg_match_all ( "/"url":"(?<links>.*)"}/", $html, $rets ); // 搜索结果链接筛选 if (! array_key_exists ( 'links', $rets )) // 如果数组中不包含Links键名,表示获取失败 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 ); // 通过headr获取真实地址 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; } } /** * 百度网盘资源信息获取 * * @param string $url * 网盘资源页URL * @return NULL array */ function PanInfoGet($url) { $html = CurlLoad::HtmlGet ( $url ); // 获取页面 if ($html == null) return null; try { if (preg_match_all ( "/文件名:(?<name>.*) 文件大小:(?<size>.*) 分享者:(?<user>.*) 分享时间:(?<date>.*) 下载次数:(?<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 ); } /** * 多线程抓取对象 * @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 );//线程执行方法 } } } ?>