将query存进数组 php,thinkphp下通过QueryList获取网站指定数据并封装成数组，存入数据库...

1.安装QueryList插件到自己的项目中，一般在vendor文件夹中

[geandeiMac:Html gean$ cd /Volumes/程序开发/www/Html/myapp/

[geandeiMac:Html myapp gean$ composer require jaeger/querylist

执行上面的代码会自动安装插件

2.获取指定网站某div下的数据(以fx168为例获取新闻列表以及每篇文章的content)

namespace app\controller;

use app\BaseController;

use QL\QueryList;

class Demo extends BaseController

{

public function index()

{

$result = [

'status' => 1,

'message' => 'ok',

'code' => 200

];

return json($result);

}

//通过QueryList插件采集新闻内容

public function GetHtmlCode()

{

$url = 'https://news.fx168.com/top/';

$rules = [

// 采集文章链接

'href' => ['.yy_div1>a', 'href'],

// 采集文章标题

'title' => ['.yy_pp2>a', 'text'],

// 采集图片

'img' => ['.yy_div1>a>img', 'slt'],

//采集摘要

'tags' => ['.yy_div2 .yy_pp3>a', 'text'],

//采集时间

'date' => ['.yy_span2', 'text']

];

$range = '#yy_sticker ul li';

$rt = QueryList::get($url)->rules($rules)->range($range)->query()->getData();

$data = $rt->all();

dump($rt);

foreach($data as $k=>$v){

$data[$k] = array_filter($v);

}

$data = array_filter($data);

foreach ($data as $key => $k){

$content_url = $data[$key]['href'];

$c_rules = [

//采集文章内容

'content' => ['.TRS_Editor', 'html'],

];

$c_range = '.text';

$c_rt = QueryList::get($content_url)->rules($c_rules)->range($c_range)->query()->getData();

$content = $c_rt->all();

$data[$key]['content_url'] = $content_url;

$data[$key]['content'] = $content;

}

dump($data);

}

}