PHP批量获取百度搜索结果网址

发表于 2013年07月12日
周边

类似的实现方法很多，这里是使用PHP获取的，关于用途你懂，源码如下:

<?php 
error_reporting(E_ERROR); 
set_time_limit(0); 
$keyword = '爱情' ; // 批量关键字
$filedir= "test.txt"; 
$timeout = 20;  
$startpage = 1;  
$lastpage = 4; // 抓取量
$list = ReadBaiduList($keyword,$timeout,$startpage,$lastpage); 
$num = count($list); 
$fp = fopen("$filedir",w); 
if($fp) { 
for($i=0;$i<=$num;$i++) { 
fwrite($fp,$list[$i]."\n"); 
} 
}else { 
echo '<font color=red>can not open file'; 
} 
fclose($fp); 
 
 
//http://www.baidu.com/s?wd=爱情&pn=40&ie=utf-8&usm=1
function ReadBaiduList($keyword,$timeout,$startpage,$lastpage) { 
for($i=$startpage; $i<$lastpage; $i++) { 
$nowpage = ($i-1)*10; 
$fp = @fsockopen('www.baidu.com',80,$errno,$errstr,$timeout); 
@fputs($fp,"GET /s?wd=".urlencode($keyword)."&pn=".$nowpage." HTTP/1.1\r\nHost:www.baidu.com\r\nConnection: Close\r\n\r\n"); 
while ($fp && !feof($fp)) 
$data .= fread($fp, 1024); 
@fclose($fp); 
preg_match_all("/<span class=\"g\">(.*)<\/span>/iU",$data,$tmp); 
} 
foreach($tmp[1] as $value) { 
$list = explode('/',$value); 
$lastlist[] = $list[0]; 
} 
$lastlist = array_unique($lastlist); 
return $lastlist; 
}
?>