php爬虫

内容导读

互联网集市收集整理的这篇技术教程文章主要介绍了php爬虫，小编现在分享给大家，供广大互联网技能从业者学习和参考。文章包含2310字，纯文字阅读大概需要4分钟。

内容图文

<?php 

header("Content-Type:text/html; charset=gb2312"); 
$url1 = "http://i8i8.cc/"; 
$ch1 = curl_init(); 
curl_setopt($ch1, CURLOPT_URL, $url1 ); 
curl_setopt($ch1, CURLOPT_RETURNTRANSFER, true); 
$output1 = curl_exec($ch1); 
curl_close($ch1); 
$regx1='/(<a href=")(\/cclass\/((9|10|11|12|13|14|15)_1\.html))(">)(.*)(<\/a>)/'; 
preg_match_all ($regx1,$output1,$result, PREG_SET_ORDER); 

//print_r($result); 
$conn=mysql_connect(localhost,test,111111); 
mysql_select_db("test",$conn); 
mysql_query('SET NAMES gb2312;'); 
foreach($result as $key =>$value) 
{ 

$url2 = "http://i8i8.cc".$result[$key][2]; 
//print_r($url2); 
$ch2 = curl_init(); 
curl_setopt($ch2, CURLOPT_URL, $url2 ); 
curl_setopt($ch2, CURLOPT_RETURNTRANSFER, true); 
$output2 = curl_exec($ch2); 
//print_r($output2); 
curl_close($ch2); 
$regx2='/(<li>)(<a href=")(.*\.html)(.*)(<img src=")(.*)(" alt=)(.*)(<span>)(.*)(<\/span>)/'; 
preg_match_all ($regx2,$output2,$movie, PREG_SET_ORDER); 

//print_r($movie); 

foreach($movie as$k =>$v ) 
{ 
$movie[$k][3]=substr($movie[$k][3],2); 
$movie[$k][3]="http://i8i8.cc".$movie[$k][3]; 
//print_r($movie[$k][3]); 

$url3 = $movie[$k][3]; 
$ch3 = curl_init(); 
curl_setopt($ch3, CURLOPT_URL, $url3 ); 
curl_setopt($ch3, CURLOPT_RETURNTRANSFER, true); 
$output3 = curl_exec($ch3); 
//var_dump($output3); 
curl_close($ch3); 

$regx_name='/(<div class=")(row_right)("><strong>)(.*)<\/strong>/'; 
preg_match_all ($regx_name,$output3,$movie_name, PREG_SET_ORDER); 

$regx_actor='/(<div class="img">)(.*)(artlist&keyword=)(.*)(>)(.*)(<\/a>)/'; 
preg_match_all ($regx_actor,$output3,$movie_actor, PREG_SET_ORDER); 

$regx_catalog='/(<div class="row_right"><A href="\/cclass\/(.*).html">)(.*)(<\/A> )/'; 
preg_match_all ($regx_catalog,$output3,$movie_catalog, PREG_SET_ORDER); 

$regx_year='/<a href="\/year\/(.*).html">(.*)<\/a>/'; 
preg_match_all ($regx_year,$output3,$movie_year, PREG_SET_ORDER); 
//print_r($movie_year);//[2] 

$regx_update='/(更新时间：<\/div><div class="row_right">)(.*)<\/div>/'; 
preg_match_all ($regx_update,$output3,$movie_update, PREG_SET_ORDER); 
//print_r($movie_update);//[2] 

$regx_desc='/(主演。)(.*)<\/div>/'; 
preg_match_all ($regx_desc,$output3,$movie_desc, PREG_SET_ORDER); 
//var_dump($movie_desc);//[2] 
} 



//mysql_query("insert into t_catalog values('{$key}','{$result[$key][6]}');"); 
} 
mysql_close($conn); 
?>

内容总结

以上是互联网集市为您收集整理的php爬虫全部内容，希望文章能够帮你解决php爬虫所遇到的程序开发问题。 如果觉得互联网集市技术教程内容还不错，欢迎将互联网集市网站推荐给程序员好友。

内容备注

版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 gblab@vip.qq.com 举报，一经查实，本站将立刻删除。

内容手机端

---