TP5框架使用QueryList采集框架爬小说操作示例

namespace QL;
require ‘phpQuery.php';

use phpQuery,Exception,ReflectionClass;
use Monolog\Logger;
use Monolog\Handler\StreamHandler;
use Iterator,Countable,ArrayAess;//使用phpQuuery接口

<?php
namespace app\index\Controller;
use think\Controller;
use QL\QueryList;
 
class Xiaoshuo extends Controller
{
  public function index()
  {
    //采集目标
    //$url = 'https://.17k./list/3032846.html?offset=';
     $url = 'https://.17k./list/3041226.html?offset=';
    //采集规则
    $rules = array(
          'title'=>array('.ellipsis','text'),//获取书每个章节名
          'link'=>array('.Volume a','href','-.folding -copy -a'),//获取每个章节链接
        );
    //开始采集
    $data = QueryList::Query($url,$rules)->data;
    //var_dump($data);
    //求数组长度
     $j = count($data);
    if($data)
    {
      for($i=0;$i<=$j-1;$i++)
      {
       $values = ['title'=>$data[$i]['title'],'link'=>$data[$i+1]['link']];
       $_POST['url']=$data[$i+1]['link'];
       if (!preg_match("/^(http|ftp):/", $_POST['url']))//给链接加上域名头
        {
         $url1 = 'https://.17k.'.$_POST['url'];
        }
       $rules1 = array(
          'novel'=>array('.p','text','-li -a'),
          );
       $data1 = QueryList::Query($url1,$rules1)->data;
       //var_dump($data1);
       $values1 = ['title'=>$data[$i]['title'],'novel'=>$data1[0]['novel']];//将章节名、内容插入数据库
       $data2 = \think\Db::name('novel6')->insert($values1); 
      }
    }
    
  }
}