Douban の動画データを PHP と phpSpider でキャプチャするヒントを共有します!

composer require phpspider/phpspider

<?php
require 'vendor/autoload.php';
use phpspidercorephpspider;
use phpspidercoreequests;

// 设置要抓取的网页地址
$url = 'https://movie.douban.com/top250';

// 使用phpSpider进行数据抓取
$config = [
    'name' => 'douban_movie',
    'log_show' => false,
    'interval' => 1000,
    'user_agent' => 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0',
    'domains' => [
        'movie.douban.com'
    ],
    'scan_urls' => [
        $url
    ],
    'content_url_regexes' => [
        'https://movie.douban.com/subject/[0-9]+/'
    ],
    'fields' => [
        [
            'name' => 'title',
            'selector' => '#content h1 span:first',
            'required' => true
        ],
        [
            'name' => 'rating',
            'selector' => '.rating_num',
            'required' => true
        ],
        [
            'name' => 'summary',
            'selector' => '#link-report span[property="v:summary"]',
            'required' => true
        ],
    ]
];

// 在on_extract_page回调函数中处理抓取到的数据
function on_extract_page($page, $data){
    // 将抓取到的数据存储到数据库中或做其他处理
    $title = $data['title'];
    $rating = $data['rating'];
    $summary = $data['summary'];
    // 这里假设将数据存储到数据库中
    $db = new PDO('mysql:host=localhost;dbname=test', 'username', 'password');
    $stmt = $db->prepare('INSERT INTO movie(title, rating, summary) VALUES(?, ?, ?)');
    $stmt->execute([$title, $rating, $summary]);
}

// 启动phpSpider进行抓取
$request = new requests();
$request::$input_encoding = 'utf-8';
$spider = new phpspider($config);
$spider->on_extract_page = 'on_extract_page';
$spider->start();