PHP와 phpSpider로 Sina Weibo 데이터를 캡처하는 방법에 대한 팁을 공유하세요!

curl -sS https://getcomposer.org/installer | php
mv composer.phar /usr/local/bin/composer

composer require dcb9/phpspider

require 'vendor/autoload.php';

use phpspidercorephpspider;
use phpspidercoreequests;
use phpspidercoreselector;
use phpspidercorelog;
use phpspidercoreutil;

$target_weibo_id = "1234567890"; // 新浪微博的id

// 设置日志目录
log::$log_file = dirname(__FILE__).'/log.log';

// 爬虫的基本配置
$configs = array(
    'name' => 'weiboSpider',
    'log_show' => false, // 是否显示日志
    'log_file' => dirname(__FILE__).'/data.log', // 日志文件保存的路径
    'tasknum' => 1, // 并发数
    'interval' => 1000, // 爬取间隔，单位毫秒
);

// 实例化爬虫对象
$spider = new phpspider($configs);

// 设置请求的header
$spider->on_start = function($spider) use ($target_weibo_id)
{
    $headers = array(
        'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36',
        'Cookie: your_cookie', // 替换成你的新浪微博Cookie
    );
    requests::set_header($headers);
    $url = "https://weibo.com/u/{$target_weibo_id}?profile_ftype=1&is_all=1#_0";
    $spider->add_url($url);
};

// 正则匹配微博数据
$spider->on_extract_page = function($page, $data) use ($target_weibo_id)
{
    $weibo_id = '';
    $content = '';
    $time = '';

    $selector = "//div[@class='WB_detail']/div[@class='WB_text']";
    $content = selector::select($content_html, $selector);
    $selector = "//div[@class='WB_detail']/div[@class='WB_from S_txt2']";
    $time = selector::select($content_html, $selector);

    $data['weibo_id'] = $weibo_id;
    $data['content'] = $content;
    $data['time'] = $time;

    return $data;
};

// 开始抓取
$spider->start();