将网页表格的内容提取出来

最新推荐文章于 2025-06-19 21:44:03 发布

BetterCoo1

最新推荐文章于 2025-06-19 21:44:03 发布

阅读量899

点赞数

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/qq_20278449/article/details/45105393

本文介绍了一种使用PHP进行网页数据抓取的方法，并详细展示了如何通过正则表达式和字符串操作函数来解析HTML表格数据，最终形成可进一步处理的数据数组。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

继昨天的网页抓取之后，后续的处理函数
<?php 
function get_td_array($table) {
$table = preg_replace("/<table[^>]*?>/is","",$table);
$table = preg_replace("/<tr[^>]*?>/si","",$table);
$table = preg_replace("/<td[^>]*?>/si","",$table);
$table = str_replace("</tr>","{tr}",$table);
$table = str_replace("</td>","{td}",$table);
$table = str_replace(" ","",$table);
$table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
$table = preg_replace("'([rn])[s]+'","",$table);
$table = str_replace(" ","",$table);
$table = str_replace(" ","",$table);

$table = explode('{tr}', $table);
array_pop($table);
foreach ($table as $key=>$tr) {
$td = explode('{td}', $tr);
$td = explode('{td}', $tr);//这个函数是将字符串转为数组，{td}为分隔符
array_pop($td);
$td_array[] = $td;
}
return $td_array;
}
?>

我们教务处的函数
<?php
$url = "http://202.119.81.118:7777/pls/wwwxk/xk.login";//output.php为接受文件，内容为print_r($_POST)
/*$post_data = array (
 "pwuser" => "jying1314",
 "pwpwd" => "fff12138"
);*/
$cookie_file=tempnam('./temp','cookie');
$post_fields='stuid=学号&pwd=密码';
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_URL, $url);//要访问的地址
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);//执行结果是否被返回，0是返回，1是不返回
curl_setopt($ch, CURLOPT_POST, 1);// 发送一个常规的POST请求
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);//POST提交的数据包
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
curl_setopt($ch, CURLOPT_TIMEOUT, 30);//设置超时
$output = curl_exec($ch);//执行并获取数据
curl_close($ch);
// var_dump($output);

$url='http://202.119.81.118:7777/pls/wwwxk/xk.CourseView';
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
$contents = curl_exec($ch);

$table = preg_replace("/<TABLE[^>]*?>/is","",$contents);
$table = preg_replace("/<TR[^>]*?>/is","",$table);
 $table = preg_replace("/<TD[^>]*?>/is","",$table);
 $table = str_replace("</TR>","{tr}",$table);
 $table = str_replace("</TH>","{tr}",$table);
 $table = str_replace("</TD>","{td}",$table);
 $table = str_replace(" ","",$table);
 $table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
 $table = preg_replace("'([rn])[s]+'","",$table);
 $table = str_replace(" ","",$table);

 $arr = explode('{tr}', $table);
 
 array_pop($arr);
// print_r($arr);
 foreach ($arr as $key=>$tr) {
 $td = explode('{td}', $tr);
 $td = explode('{td}', $tr);
 array_pop($td);
 $td_array[] = $td;
 }
 // print_r($td_array);
 // echo "<br>";
 // echo $td_array[12][0];
 //第二个参数表示列，第一个表示行，且两个一跳
 // if(empty($td_array[12][0])){
 // echo "这个为空值";
 // }else{echo "NO";}
 
for($b=0;$b<=6;$b++){
 $c=$b+1;
 echo "weekend".$c."<br>"; 
for($i=10; $i<=20; $i=$i+2)
{if(!empty($td_array[$i][$b]))
{ $d=($i-8)/2;
 echo $d.$td_array[$i][$b];
echo "<br>";}} 
}
/*echo $td_array[1][2];
echo $td_array[1][3];
echo $td_array[1][4];
echo $td_array[1][5];*/
/*$mode="/./";
$string="google";

if(preg_match($mode,$contents,$arr))
{echo "匹配成功".$arr[0];
print_r($arr);
}
else
{echo "匹配不成功";}
curl_close($ch);*/
?>