PHP와 Selenium: 안정적이고 효율적인 웹 크롤러 구축을 위한 가이드

composer require facebook/webdriver

<?php

require_once('vendor/autoload.php');
use FacebookWebDriverRemoteRemoteWebDriver;

$host = 'http://localhost:9515'; // 默认Chrome浏览器启动地址
$driver = RemoteWebDriver::create($host, DesiredCapabilities::chrome());

$driver->get('http://github.com');
echo "网页标题：" . $driver->getTitle() . PHP_EOL;
$driver->quit();

<?php

require_once('vendor/autoload.php');
use FacebookWebDriverRemoteRemoteWebDriver;
use FacebookWebDriverRemoteDesiredCapabilities;

// 替换以下参数为自己的github账户和密码
$username = 'yourusername';
$password = 'yourpassword';

// 启动浏览器并登录
$host = 'http://localhost:9515'; // 默认Chrome浏览器启动地址
$driver = RemoteWebDriver::create($host, DesiredCapabilities::chrome());
$driver->get('http://github.com/login');
$driver->findElement(FacebookWebDriverWebDriverBy::cssSelector('input[name="login"]'))->sendKeys($username);
$driver->findElement(FacebookWebDriverWebDriverBy::cssSelector('input[name="password"]'))->sendKeys($password);
$driver->findElement(FacebookWebDriverWebDriverBy::cssSelector('input[type="submit"]'))->click();

// 检查是否登录成功
$cookies = $driver->manage()->getCookies();
if (count($cookies) == 0) {
    echo "登录失败" . PHP_EOL;
    exit;
}

echo "登录成功" . PHP_EOL;

<?php

// 获取某仓库star数目
$driver->get('https://github.com/twbs/bootstrap');
$starText = $driver->findElement(FacebookWebDriverWebDriverBy::cssSelector('.js-social-count'))->getText();
$starCount = (int)str_replace(',', '', $starText);
echo "star数目：" . $starCount . PHP_EOL;

<?php

// 获取某用户的star数目
$driver->get('https://github.com/yourusername?tab=stars');
$stars = $driver->findElements(FacebookWebDriverWebDriverBy::cssSelector('.col-12.d-inline-block>a'));
echo "star数目：" . count($stars) . PHP_EOL;

<?php

// Github starred仓库分页
$driver->get('https://github.com/yourusername?tab=stars');
$pageNum = 1;
while (true) {
    echo "第{$pageNum}页：" . PHP_EOL;
    $pageStars = $driver->findElements(FacebookWebDriverWebDriverBy::cssSelector('.col-12.d-inline-block>a'));
    foreach ($pageStars as $star) {
        echo $star->getText() . PHP_EOL;
    }
    
    $nextPageBtn = $driver->findElement(FacebookWebDriverWebDriverBy::cssSelector('.pagination>button:last-child'));
    if ($nextPageBtn->getAttribute('disabled') == 'true') {
        break;
    }
    $nextPageBtn->click();
    $pageNum++;
}