一文教你使用 Java 代码访问博客

声明：刷访问量 (:-& 是不对的！OK？明确这一点我们来从技术层面来探讨，如何实现刷 ****博客 访问量。
****博客 是具有防爬虫功能的，如果只是简单的刷新、抓取并不会增加访客数量，那么…😛

Don’t say much, just go to the code.

package org.bood.tasks;

import org.springframework.context.annotation.Configuration;
import org.springframework.scheduling.annotation.EnableScheduling;
import org.springframework.scheduling.annotation.Scheduled;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * 定时访问CSDN博客内容，增加浏览量
 *
 * @author bood
 * @since 2024/01/05
 */
@Configuration
@EnableScheduling
public class IncreaseBlogViews {

    /**
     * 用户ID
     */
    private static final String USER_ID = "BUG_call110";
    /**
     * CSDN博客文章列表前缀URL
     */
    private static final String HOME_URL = "https://blog.csdn.net/" + USER_ID + "/article/list/";

    @Scheduled(fixedRate = 180000)
    public void run() {
        try {
            Set<String> urls = fetchArticleUrls();
            visitUrls(urls);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    /**
     * 获取所有文章的URL
     *
     * @return {@link Set }<{@link String }>
     * @author bood
     * @since 2024/01/05
     */
    private Set<String> fetchArticleUrls() throws IOException {
        Set<String> urls = new HashSet<>();
        for (int i = 1; i <= 10; i++) {
            System.out.println("正在查找第 " + i + " 页");
            String pageUrl = HOME_URL + i;
            System.out.println(pageUrl);

            String pageContent = doGet(pageUrl);

            // 检查页面是否还有博文链接，如果没有则终止循环
            if (pageContent.contains("空空如也")) {
                System.out.println("没有更多页面！");
                break;
            }

            // 使用正则表达式提取所有博文链接
            List<String> links = getMatherSubstrs(pageContent, "https://blog.csdn.net/" + USER_ID + "/article/details/[0-9]+");
            urls.addAll(links);

            System.out.println("第 " + i + " 页查找成功");
        }
        System.out.println("总文章数为: " + urls.size());
        return urls;
    }

    /**
     * 访问提取出的URL以增加访问量
     *
     * @param urls URL列表
     * @author bood
     * @since 2024/01/05
     */
    private void visitUrls(Set<String> urls) throws IOException {
        System.out.println("开始访问每个链接!");
        int count = 0;
        for (String url : urls) {
            doGet(url);
            count++;
            System.out.println("成功访问第 " + count + " 个链接,共 " + urls.size() + " 个: " + url);
        }
        System.out.println("运行完毕，成功增加访问数：" + count);
    }

    private static String doGet(String urlStr) throws IOException {
        URL url = new URL(urlStr);
        HttpURLConnection conn = (HttpURLConnection) url.openConnection();
        conn.setRequestProperty("User-Agent",
                "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36");

        try (BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream(), "UTF-8"))) {
            StringBuilder sb = new StringBuilder();
            String line;
            while ((line = reader.readLine()) != null) {
                sb.append(line);
            }
            return sb.toString();
        } finally {
            conn.disconnect(); // 断开连接
        }
    }


    /**
     * 使用正则表达式匹配字符串
     *
     * @param str   字符串
     * @param regex 正则表达式
     * @return {@link List }<{@link String }>
     * @author bood
     * @since 2024/01/05
     */
    private static List<String> getMatherSubstrs(String str, String regex) {
        List<String> list = new ArrayList<>();
        Pattern pattern = Pattern.compile(regex);
        Matcher matcher = pattern.matcher(str);
        while (matcher.find()) {
            list.add(matcher.group());
        }
        return list;
    }
    
}