Java爬虫性能优化：多线程抓取JSP动态数据实践

<dependencies>
    <!-- Jsoup HTML解析 -->
    <dependency>
        <groupId>org.jsoup</groupId>
        <artifactId>jsoup</artifactId>
        <version>1.15.4</version>
    </dependency>
    
    <!-- Apache HttpClient -->
    <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpclient</artifactId>
        <version>4.5.13</version>
    </dependency>
    
    <!-- Selenium WebDriver (用于动态渲染) -->
    <dependency>
        <groupId>org.seleniumhq.selenium</groupId>
        <artifactId>selenium-java</artifactId>
        <version>4.8.0</version>
    </dependency>
</dependencies>

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.apache.http.HttpHost;
import org.apache.http.auth.AuthScope;
import org.apache.http.auth.UsernamePasswordCredentials;
import org.apache.http.client.CredentialsProvider;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.BasicCredentialsProvider;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

import java.util.concurrent.*;

public class JSPDynamicCrawler {
    private static final int THREAD_POOL_SIZE = 10; // 线程池大小
    private static final BlockingQueue<String> taskQueue = new LinkedBlockingQueue<>(); // 任务队列

    // 代理配置
    private static final String PROXY_HOST = "www.16yun.cn";
    private static final int PROXY_PORT = 5445;
    private static final String PROXY_USER = "16QMSOML";
    private static final String PROXY_PASS = "280651";

    public static void main(String[] args) {
        // 初始化线程池
        ExecutorService executor = Executors.newFixedThreadPool(THREAD_POOL_SIZE);

        // 添加初始URL（示例）
        taskQueue.add("https://example.com/dynamic.jsp");

        // 启动消费者线程
        for (int i = 0; i < THREAD_POOL_SIZE; i++) {
            executor.submit(new CrawlerTask());
        }

        executor.shutdown();
    }

    static class CrawlerTask implements Runnable {
        @Override
        public void run() {
            // 1. 配置代理
            HttpHost proxy = new HttpHost(PROXY_HOST, PROXY_PORT);

            // 2. 设置代理认证
            CredentialsProvider credentialsProvider = new BasicCredentialsProvider();
            credentialsProvider.setCredentials(
                    new AuthScope(PROXY_HOST, PROXY_PORT),
                    new UsernamePasswordCredentials(PROXY_USER, PROXY_PASS)
            );

            // 3. 创建带代理的HttpClient
            try (CloseableHttpClient httpClient = HttpClients.custom()
                    .setDefaultCredentialsProvider(credentialsProvider)
                    .setProxy(proxy)
                    .build()) {

                while (true) {
                    String url = taskQueue.poll(1, TimeUnit.SECONDS); // 非阻塞获取任务
                    if (url == null) break; // 队列为空则退出

                    // 发起HTTP请求（带代理）
                    HttpGet request = new HttpGet(url);
                    String html = httpClient.execute(request, response ->
                            EntityUtils.toString(response.getEntity()));

                    // 解析HTML（Jsoup）
                    Document doc = Jsoup.parse(html);
                    Elements links = doc.select("a[href]");

                    // 提取新链接并加入队列
                    for (Element link : links) {
                        String newUrl = link.absUrl("href");
                        if (newUrl.contains("dynamic.jsp")) { // 仅抓取目标页面
                            taskQueue.offer(newUrl);
                        }
                    }

                    // 提取数据（示例：抓取标题）
                    String title = doc.title();
                    System.out.println("抓取成功: " + title);
                }
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }
}

import org.openqa.selenium.WebDriver;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.chrome.ChromeOptions;

public class SeleniumCrawler {
    public static void main(String[] args) {
        // 设置ChromeDriver路径
        System.setProperty("webdriver.chrome.driver", "path/to/chromedriver");
        
        // 无头模式（Headless）
        ChromeOptions options = new ChromeOptions();
        options.addArguments("--headless");
        
        WebDriver driver = new ChromeDriver(options);
        driver.get("https://example.com/dynamic.jsp");
        
        // 获取渲染后的HTML
        String renderedHtml = driver.getPageSource();
        System.out.println(renderedHtml);
        
        driver.quit();
    }
}

RequestConfig config = RequestConfig.custom()
    .setConnectTimeout(5000)
    .setSocketTimeout(5000)
    .build();
HttpClientBuilder.create().setDefaultRequestConfig(config);