php多线程抓取信息测试例子

作者：袖梨 2022-06-24

PHP 5.3 以上版本，使用pthreads PHP扩展，可以使PHP真正地支持多线程。多线程在处理重复性的循环任务，能够大大缩短程序执行时间。

PHP扩展下载：https://github.com/krakjoe/pthreads
PHP手册文档：http://php.net/manual/zh/book.pthreads.php

1、扩展的编译安装(Linux），编辑参数 --enable-maintainer-zts 是必选项：

cd /Data/tgz/php-5.3.8
./configure --prefix=/Data/apps/php --with-config-file-path=/Data/apps/php/etc --with-mysql=/Data/apps/mysql --with-mysqli=/Data/apps/mysql/bin/mysql_config --with-iconv-dir --with-freetype-dir=/Data/apps/libs --with-jpeg-dir=/Data/apps/libs --with-png-dir=/Data/apps/libs --with-zlib --with-libxml-dir=/usr --enable-xml --disable-rpath --enable-bcmath --enable-shmop --enable-sysvsem --enable-inline-optimization --with-curl --enable-mbregex --enable-fpm --enable-mbstring --with-mcrypt=/Data/apps/libs --with-gd --enable-gd-native-ttf --with-openssl --with-mhash --enable-pcntl --enable-sockets --with-xmlrpc --enable-zip --enable-soap --enable-opcache --with-pdo-mysql --enable-maintainer-zts
make clean
make
make install       
 
unzip pthreads-master.zip
cd pthreads-master
/Data/apps/php/bin/phpize
./configure --with-php-config=/Data/apps/php/bin/php-config
make
make install

添加扩展：


 vi /Data/apps/php/etc/php.ini

 extension = "pthreads.so"

一段PHP多线程、与For循环，抓取百度搜索页面的PHP代码示例：

 代码如下 复制代码
  class test_thread_run extends Thread  
  { 
      public $url; 
      public $data; 
 
      public function __construct($url) 
      { 
          $this->url = $url; 
      } 
 
      public function run() 
      { 
          if(($url = $this->url)) 
          { 
              $this->data = model_http_curl_get($url); 
          } 
      } 
  } 
 
  function model_thread_result_get($urls_array)  
  { 
      foreach ($urls_array as $key => $value)  
      { 
          $thread_array[$key] = new test_thread_run($value["url"]); 
          $thread_array[$key]->start(); 
      } 
 
      foreach ($thread_array as $thread_array_key => $thread_array_value)  
      { 
          while($thread_array[$thread_array_key]->isRunning()) 
          { 
              usleep(10); 
          } 
          if($thread_array[$thread_array_key]->join()) 
          { 
              $variable_data[$thread_array_key] = $thread_array[$thread_array_key]->data; 
          } 
      } 
      return $variable_data; 
  } 
 
  function model_http_curl_get($url,$userAgent="")  
  { 
      $userAgent = $userAgent ? $userAgent : 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)';  
      $curl = curl_init(); 
      curl_setopt($curl, CURLOPT_URL, $url); 
      curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); 
      curl_setopt($curl, CURLOPT_TIMEOUT, 5); 
      curl_setopt($curl, CURLOPT_USERAGENT, $userAgent); 
      $result = curl_exec($curl); 
      curl_close($curl); 
      return $result; 
  } 
 
  for ($i=0; $i < 100; $i++)  
  {  
      $urls_array[] = array("name" => "baidu", "url" => "http://www.baidu.com/s?wd=".mt_rand(10000,20000)); 
  } 
 
  $t = microtime(true); 
  $result = model_thread_result_get($urls_array); 
  $e = microtime(true); 
  echo "多线程：".($e-$t)."n"; 
 
  $t = microtime(true); 
  foreach ($urls_array as $key => $value)  
  { 
      $result_new[$key] = model_http_curl_get($value["url"]); 
  } 
  $e = microtime(true); 
  echo "For循环：".($e-$t)."n"; 
?>

例子，采集数据

 

 代码如下 复制代码

$urls = array(
'http://www.111com.net/',
'http://www.sohu.com/',
'http://www.163.com/'
);

$save_to='/test.txt'; // 把抓取的代码写入该文件
$st = fopen($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[$i],CURLOPT_RETURNTRANSFER,true); // 设置不将爬取代码写到浏览器，而是转化为字符串
curl_multi_add_handle ($mh,$conn[$i]);
}

do {
curl_multi_exec($mh,$active);
} while ($active);

foreach ($urls as $i => $url) {
$data = curl_multi_getcontent($conn[$i]); // 获得爬取的代码字符串
fwrite($st,$data); // 将字符串写入文件。当然，也可以不写入文件，比如存入数据库
} // 获得数据变量，并写入文件

foreach ($urls as $i => $url) {
curl_multi_remove_handle($mh,$conn[$i]);
curl_close($conn[$i]);
}

curl_multi_close($mh);
fclose($st);
?>

相关文章

精彩推荐