1、爬蟲工具類，用來獲取網頁內容

package com.dyw.crawler.util;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

/**
 * 爬蟲工具類
 * Created by dyw on 2017/9/1.
 */
public class CrawlerUtils {

    /**
     * 獲取html內容轉成string輸出。
     *
     * @param
 
 url url連結
     * @return 整個網頁轉成String字串
     */
    public static String getHtml(String url) throws Exception {
        URL url1 = new URL(url);//使用java.net.URL
        URLConnection connection = url1.openConnection();//開啟連結
        InputStream in = connection.getInputStream();//獲取輸入流
        InputStreamReader isr = new
 
 InputStreamReader(in);//流的包裝
        BufferedReader br = new BufferedReader(isr);

        String line;
        StringBuffer sb = new StringBuffer();
        while ((line = br.readLine()) != null) {//整行讀取
            sb.append(line, 0, line.length());//新增到StringBuffer中
            sb.append('\n');//新增換行符
        }
        //關閉各種流，先宣告的後關閉
 

        br.close();
        isr.close();
        in.close();
        return sb.toString();
    }

}

2、IO工具類，用來把獲取的html內容進行寫入到檔案中

package com.dyw.crawler.util;

import java.io.File;
import java.io.FileOutputStream;

/**
 * IO工具類
 * Created by dyw on 2017/9/1.
 */
public class IOUtils {

    /**
     * 建立檔案
     *
     * @param file File型別
     */
    public static void createFile(File file) throws Exception {
        try {
            if (!file.exists()) {
                file.createNewFile();
            }
        } catch (Exception e) {
            throw new Exception("建立檔案的時候錯誤！", e);
        }
    }

    /**
     * 寫入String到file中
     *
     * @param content  寫入內容
     * @param fileName 寫入位置
     */
    public static void writeFile(String content, File fileName) throws Exception {
        FileOutputStream o;
        try {
            o = new FileOutputStream(fileName);
            o.write(content.getBytes("Utf-8"));
            o.close();
        } catch (Exception e) {
            throw new Exception("寫入檔案的時候錯誤！", e);
        }
    }
}

3、main方法執行

package com.dyw.crawler.project;

import com.dyw.crawler.util.CrawlerUtils;
import com.dyw.crawler.util.IOUtils;

import java.io.File;

/**
 * 此包中的main方法
 * Created by dyw on 2017/9/1.
 */
public class Project {

    public static void main(String[] args) {
        //檔案放置的路徑
        String path = "C:\\Users\\dyw\\Desktop\\crawler";
        //爬取的網站地址
        String url = "http://blog.csdn.net/juewang_love";
        String fileRealName = path + "/index.html";
        File file = new File(fileRealName);
        //建立檔案
        try {
            IOUtils.createFile(file);
        } catch (Exception e) {
            throw new RuntimeException("建立檔案失敗!", e);
        }
        //獲取內容
        String htmlContent = null;
        try {
            htmlContent = CrawlerUtils.getHtml(url);
        } catch (Exception e) {
            throw new RuntimeException("獲取內容失敗!", e);
        }
        //寫入內容
        try {
            IOUtils.writeFile(htmlContent, file);
        } catch (Exception e) {
            throw new RuntimeException("內容寫入檔案失敗!", e);
        }
    }
}