• 通过curl模拟多线程抓取网页(curl_multi_*)


      curl请求多个url,以前都是使用循环来处理。最近发现可以通过curl_multi_*系列函数来模拟多线程。比对一下,发现如果请求的url只有几个,2种方案耗时差不多,但是url比较多,差距就非常明显了。

      先来看下使用for循环的方案: 

     1 <?php
     2 //for循环 基础方案
     3 $start = microtime(true);
     4 
     5 header('Content-type:text/html;charset=utf-8');
     6 
     7 $arrs = [
     8     'https://www.yahoo.com/',
     9     'http://www.jtthink.com/',
    10     'https://www.hao123.com/',
    11     'http://www.cnblogs.com/loveyouyou616/',
    12     'http://www.qq.com/',
    13     'http://www.sina.com.cn/',
    14     'http://www.163.com/',
    15     'https://www.yahoo.com/',
    16     'http://www.jtthink.com/',
    17     'https://www.hao123.com/',
    18     'http://www.cnblogs.com/loveyouyou616/',
    19     'http://www.qq.com/',
    20     'http://www.sina.com.cn/',
    21     'http://www.163.com/',
    22     'https://www.yahoo.com/',
    23     'http://www.jtthink.com/',
    24     'https://www.hao123.com/',
    25     'http://www.cnblogs.com/loveyouyou616/',
    26     'http://www.qq.com/',
    27     'http://www.sina.com.cn/',
    28     'http://www.163.com/'
    29 ];
    30 
    31 $headers = array(
    32     'User-Agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.107 Safari/537.36',
    33 );
    34 
    35 $mh = curl_multi_init();
    36 
    37 foreach ($arrs as $i=>$url){
    38     $ch = curl_init($url);
    39     curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
    40     curl_setopt($ch, CURLOPT_HTTPHEADER,$headers);
    41     curl_setopt($ch, CURLOPT_HEADER, 0);
    42     curl_setopt($ch, CURLOPT_TIMEOUT, 20);
    43 
    44 
    45     if (strpos($url,'https')){
    46         curl_setopt ( $ch, CURLOPT_SSL_VERIFYPEER, false );
    47         curl_setopt ( $ch, CURLOPT_SSL_VERIFYHOST, 2 );
    48     }
    49 
    50     $con = curl_exec($ch);
    51     curl_close($ch);
    52     var_dump($con);
    53 }
    54 
    55 
    56 $end = microtime(true) - $start;
    57 
    58 echo '<br/>';
    59 echo $end;  //平均19.002983093262s

      接下来使用curl_multi_* 一次发送多个url请求

      

     1 <?php
     2 //此模型虽然是一次多个url请求,但缺陷是 要等所有数据请求结束一起返回,才能逐个处理数据。
     3 $start = microtime(true);
     4 
     5 header('Content-type:text/html;charset=utf-8');
     6 
     7 $arrs = [
     8     'https://www.yahoo.com/',
     9     'http://www.jtthink.com/',
    10     'https://www.hao123.com/',
    11     'http://www.cnblogs.com/loveyouyou616/',
    12     'http://www.qq.com/',
    13     'http://www.sina.com.cn/',
    14     'http://www.163.com/',
    15     'https://www.yahoo.com/',
    16     'http://www.jtthink.com/',
    17     'https://www.hao123.com/',
    18     'http://www.cnblogs.com/loveyouyou616/',
    19     'http://www.qq.com/',
    20     'http://www.sina.com.cn/',
    21     'http://www.163.com/',
    22     'https://www.yahoo.com/',
    23     'http://www.jtthink.com/',
    24     'https://www.hao123.com/',
    25     'http://www.cnblogs.com/loveyouyou616/',
    26     'http://www.qq.com/',
    27     'http://www.sina.com.cn/',
    28     'http://www.163.com/'
    29 ];
    30 
    31 $headers = array(
    32     'User-Agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.107 Safari/537.36',
    33 );
    34 
    35 $mh = curl_multi_init();
    36 
    37 foreach ($arrs as $i=>$url){
    38     $conn[$i] = curl_init($url);
    39     curl_setopt($conn[$i],CURLOPT_RETURNTRANSFER,1);
    40     curl_setopt($conn[$i], CURLOPT_HTTPHEADER,$headers);
    41     curl_setopt($conn[$i], CURLOPT_HEADER, 0);
    42     curl_setopt($conn[$i], CURLOPT_TIMEOUT, 20);
    43 
    44 
    45     if (strpos($url,'https')){
    46         curl_setopt ( $conn[$i], CURLOPT_SSL_VERIFYPEER, false );
    47         curl_setopt ( $conn[$i], CURLOPT_SSL_VERIFYHOST, 2 );
    48     }
    49     curl_multi_add_handle($mh,$conn[$i]);
    50 }
    51 
    52 $active = null;
    53 /*
    54  * 这样写会轻易导致CPU占用100%
    55 
    56 do {
    57     $n=curl_multi_exec($mh,$active);
    58 } while ($active);
    59  *
    60  */
    61 
    62 //改写
    63 /*
    64 do {
    65     $mrc = curl_multi_exec($mh,$active);
    66 }while($mrc == CURLM_CALL_MULTI_PERFORM);
    67 
    68 while ($active and $mrc == CURLM_OK){
    69     if (curl_multi_select($mh) != -1) {
    70         do {
    71             $mrc = curl_multi_exec($mh, $active);
    72         } while ($mrc == CURLM_CALL_MULTI_PERFORM);
    73     }
    74 }
    75 */
    76 
    77 //最简单方案
    78 do {
    79     curl_multi_exec($mh, $running);
    80     curl_multi_select($mh);
    81 } while ($running > 0);
    82 
    83 
    84 //获取内容
    85 foreach ($arrs as $i => $url) {
    86     $res[$i]=curl_multi_getcontent($conn[$i]);
    87     var_dump($res[$i]);
    88     curl_close($conn[$i]);
    89     //等待所有http请求结束返回数据依次生成文件。
    90     file_put_contents('curl_multi.log',$res[$i]."
    
    
    
    ",FILE_APPEND);
    91 }
    92 
    93 $end = microtime(true) - $start;
    94 
    95 echo '<br/>';
    96 echo $end; // 平均 10.091157913208s

      执行上面2段代码,可以发现使用curl_multi_*系列函数来处理,效率明显高不少。

      但是上面的模型也存在一个问题,返回的时间依赖最长的请求,通俗的说就是结果数据要等所有http请求结束后一起返回,然后逐个处理数据。

  • 相关阅读:
    [NOI2008] 糖果雨
    [NOI2006] 神奇口袋
    [NOI2014] 购票
    Prince and Princess HDU
    Network POJ
    CodeForces
    Codeforces Global Round 12
    Codeforces Round #688 (Div. 2)
    [USACO05DEC]Layout G
    # Technocup 2021
  • 原文地址:https://www.cnblogs.com/loveyouyou616/p/5624139.html
Copyright © 2020-2023  润新知