TP5框架使用QueryList采集框架爬小說(shuō)操作示例

namespace QL;
require ‘phpQuery.php';

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

?php
namespace app\index\Controller;
use think\Controller;
use QL\QueryList;
 
class Xiaoshuo extends Controller
{
  public function index()
  {
    //采集目標(biāo)
    //$url = 'https://www.17k.com/list/3032846.html?offset=';
     $url = 'https://www.17k.com/list/3041226.html?offset=';
    //采集規(guī)則
    $rules = array(
          'title'=>array('.ellipsis','text'),//獲取書每個(gè)章節(jié)名
          'link'=>array('.Volume a','href','-.folding -copy -a'),//獲取每個(gè)章節(jié)鏈接
        );
    //開(kāi)始采集
    $data = QueryList::Query($url,$rules)->data;
    //var_dump($data);
    //求數(shù)組長(zhǎng)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']))//給鏈接加上域名頭
        {
         $url1 = 'https://www.17k.com'.$_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']];//將章節(jié)名、內(nèi)容插入數(shù)據(jù)庫(kù)
       $data2 = \think\Db::name('novel6')->insert($values1); 
      }
    }
    
  }
}