php爬虫库QueryList的简单运用

素颜马尾好姑娘i 2022-05-25 07:38 168阅读 0赞

<?php
        require 'QueryList/phpQuery.php';
        require 'QueryList/QueryList.php';
        use QL\QueryList;   
    
    
        $url = 'http://www.netbian.com/baidu';
        $rules = array(
            'sensus_img'=> array('.list ul li>a>img','src'),
            'sensus_img_text'=> array('.list ul li>b>a','text'),
            'update_time'=> array('.list ul li p','text')
        );
        $data = QueryList::Query($url,$rules)->data;
    
    
        $time = date('Y-m-d');
        if(!is_dir($time)){
            mkdir($time);
        }
    
    
        foreach ($data as $key => $value) {
            if(isset($value['sensus_img']) && $value['sensus_img']){
                $img_ext = substr($value['sensus_img'], strrpos($value['sensus_img'], '.'));//图片后缀
                if(isset($value['sensus_img_text']) && $value['sensus_img_text']){
                    //phpquery在抓取目标页面代码时，未能获取到meta中的编码信息时一律转换为ISO-8859-1编码，于是先将抓来的中文由utf-8转换为ISO-8859-1 如下mb_convert_encoding($value['sensus_img_text'],'ISO-8859-1','utf-8') ，然后输出中文时就发现他们变成了比较熟悉的gbk乱码形式，然后再从gbk转换成utf-8即可，mb_convert_encoding($value['sensus_img_text'],'utf-8','GBK')，前后转了两次解决了中文乱码问题
                    $value['sensus_img_text'] = mb_convert_encoding($value['sensus_img_text'],'ISO-8859-1','utf-8');
                    $value['sensus_img_text'] = mb_convert_encoding($value['sensus_img_text'],'utf-8','GBK');
                    $value['update_time'] = mb_convert_encoding($value['update_time'],'ISO-8859-1','utf-8');
                    $value['update_time'] = mb_convert_encoding($value['update_time'],'utf-8','GBK');
                    //解决file_get_contents和file_put_contents的乱码问题，其根源在操作系统上，系统编码的问题,于是对文件名进行转码.文件用的是utf-8编码,但是系统默认为gbk转换成gbk即可解决
                    $value['sensus_img_text'] = mb_convert_encoding($value['sensus_img_text'],'gbk','utf-8');
                    file_put_contents('./'.$time.'/'.$value['sensus_img_text'].$img_ext, file_get_contents($value['sensus_img']));
                }
            }
        }

截图:

![2018051014120980][]

![2018051014024927][]

[2018051014120980]: /images/20220525/9ce4c36eb8da4032998fd4b055dada1a.png
[2018051014024927]: /images/20220525/a88bca30bbb545ec92b45e45727a9270.png