Bóc tách dữ liệu zing

index.php

<?php

/* 
 * Cài đặt và chạy như nào?
 * 
 * $ composer require fapbot/goutte
 * $ php index.php 
 *
 * Tham khảo thêm :
 *  - https://github.com/FriendsOfPHP/Goutte
 *  - http://symfony.com/doc/current/components/dom_crawler.html
 */

require_once __DIR__ . '/vendor/autoload.php';

use Goutte\Client;
use Symfony\Component\DomCrawler\Crawler;

$client = new Client();
$crawler = $client->request('GET', "http://news.zing.vn/iphone-xach-tay-van-ban-tot-sau-hang-loat-thong-tin-bat-loi-post738556.html");

print_r(
    (new ParseContent($crawler))->parse()
);

class ParseContent 
{
    private $_crawler;
    private $_result; 

    public function __construct($crawler) 
    {
        $this->_crawler = $crawler;

        return $this->parse();
    }

    public function parse() 
    {
        $this->result['title']      = $this->parseTitle();
        $this->result['summary']    = $this->parseSummary();
        $this->result['body']       = $this->parseBody();
        $this->result['author']     = $this->parseAuthor();
        $this->result['tags']       = $this->parseTags();

        return $this->result;
    }

    public function parseTitle() 
    {
        $str = $this->_crawler->filter('#page-article h1')->text();
        $str = trim($str);

        return $str;
    }

    public function parseSummary() 
    {
        $str = $this->_crawler->filter('#page-article .the-article-summary')->text();
        $str = trim($str);

        return $str;
    }

    public function parseBody() 
    {
        $body = null;

        $html = $this->_crawler->filter('#page-article .the-article-body')->html();

        $body = trim($html);

        return $html;
    }

    public function parseAuthor() 
    {
        $str = $this->_crawler->filter('#page-article .author')->text();
        $str = trim($str);

        return $str;
    }

    public function parseTags() 
    {
        $tags = [];

        $tags = $this->_crawler
            ->filter('#page-article .the-article-tags > *')
            ->each(function (Crawler $node) {
                return trim($node->text());
            });

        return $tags;
    }
}