Java获取网页源代码
public class HtmlParser {

	public static String getHtmlContent(URL url, String encode) {
			StringBuffer contentBuffer = new StringBuffer();

			int responseCode = -1;
			HttpURLConnection con = null;
			try {
				con = (HttpURLConnection) url.openConnection();
				con.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");// IE代理进行下载
				con.setConnectTimeout(60000);
				con.setReadTimeout(60000);
				// 获得网页返回信息码
				responseCode = con.getResponseCode();
				if (responseCode == -1) {
					System.out.println(url.toString() + " : connection is failure...");
					con.disconnect();
					return null;
				}
				if (responseCode >= 400) // 请求失败
				{
					System.out.println("请求失败:get response code: " + responseCode);
					con.disconnect();
					return null;
				}

				InputStream inStr = con.getInputStream();
				InputStreamReader istreamReader = new InputStreamReader(inStr, encode);
				BufferedReader buffStr = new BufferedReader(istreamReader);

				String str = null;
				while ((str = buffStr.readLine()) != null)
					contentBuffer.append(str);
				inStr.close();
			} catch (IOException e) {
				e.printStackTrace();
				contentBuffer = null;
				System.out.println("error: " + url.toString());
			} finally {
				con.disconnect();
			}
			return contentBuffer.toString();
		}

		public static String getHtmlContent(String url, String encode) {
			if (!url.toLowerCase().startsWith("http://")) {
				url = "http://" + url;
			}
			try {
				URL rUrl = new URL(url);
				return getHtmlContent(rUrl, encode);
			} catch (Exception e) {
				e.printStackTrace();
				return null;
			}
		}
		
		public static void main(String argsp[]){
			System.out.println(getHtmlContent("blog.csdn.net/powmxypow","utf-8")) ;
		}
}
(转载请注明出处:http://blog.csdn.net/powmxypow/article/details/12349099 
毛兴宇)

java代码实现网页源码爬取
java代码基于Eclipse简单实现网页源码爬取
哈哈,大家好！我是yanxiaolxy,前天四级英语考试考完了,作业也不多了,感觉整个人都变得轻松了许多。
今天给大家分享我的最新java学习进程--java网页源码爬虫，废话不多说盘代码。

仅需一页代码:
package 网站爬虫2;
/**
 * 爬取目标网页源代码示例
 * @作者 YanXiaolxy
 * @版本 2020.03
 * @时间 2020年12月14日 下午1:14:14
 */
import java.io.BufferedWriter;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileWriter;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
public class webHtmlCrawer {
	public static void main(String[] args) {
		newFile();
	}
	public static String getConnection() {
		String path = "https://www.taobao.com/";
		try {
			HttpURLConnection conn = (HttpURLConnection) new URL(path).openConnection();
			conn.setRequestMethod("GET");
            conn.setConnectTimeout(5000);
            if (conn.getResponseCode() == 200) {
                InputStream xml = conn.getInputStream();
                byte[] data = read(xml);
                //System.out.println(xml);
                return new String(data);
            }else {
                System.out.println("连接失败！");
            }
		} catch (Exception e) {
			e.printStackTrace();
		}
		return null;
	}
	//读取数据流,转换为字符串
    public static byte[] read(InputStream xml) throws Exception {
        ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
        byte[] buffer = new byte[1024];
        int len = 0;
        while ((len = xml.read(buffer)) != -1) {
            outputStream.write(buffer, 0, len);

        }
        xml.close();
        return outputStream.toByteArray();
    }
    public static void newFile() {
        String html = getConnection();
        String dir = "D:/javafile/";//定义创建目录位置
        File contents = new File(dir);
        contents.mkdirs();//创建文件目录
        try {
            byte bytes[] = {1, 2, 3, 4};
            File file = new File("D:/javafile/test.txt");
            //判断文件是否存在，如果不存在就创建
            if (!file.exists()) {
                file.createNewFile();
            }
            FileWriter fw = new FileWriter(file.getAbsoluteFile());
            BufferedWriter bw = new BufferedWriter(fw);
            System.out.println("正在写入.....");
            bw.write(html);
            bw.close();
            System.out.println("录入完毕");
        } catch (Exception e) {
        	e.getStackTrace();
        }    
    }    
}

使用注意:
1.图中红色标记为设置目标网站路径.

图片: 12.设置网页源代码存放目录和文件创建

欢迎各位发表评论和问题。

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



//数据抓取核心类
public class Copy {

    // 获取网页数据
    /*
     * @param url:目标网址
     * 
     * @param encoding：编码
     */
    public static String getHtmlResourceByUrl(String url, String encoding) {


        StringBuffer buffer=new StringBuffer();
        InputStreamReader isr=null;

        try {
            // 建立网络连接
            URL urlObj = new URL(url);
            // 打开网络连接
            URLConnection uc = urlObj.openConnection();
            /*
             * io 流
             * 从服务器下载源码到本地
             * */
            isr =new InputStreamReader(uc.getInputStream(),encoding);//建立文件的输入流
            BufferedReader reader =new BufferedReader(isr);//缓冲

            String line=null;
            while ((line=reader.readLine())!=null) {

                buffer.append(line+"\n");

            }


        } catch (Exception e) {
            e.printStackTrace();
        }
        finally{

                try{
                if(null!=isr)isr.close();}
                catch(IOException e){
                    e.printStackTrace();
                }
        }
        return buffer.toString();

    }

    // 主函数
    public static void main(String[] args) {

        String htmlString=getHtmlResourceByUrl("http://www.qq.com", "gbk");
        System.out.println(htmlString);

    }

}

    

全栈工程师开发手册 （作者：栾鹏）
 java教程全解

java获取网页网页源代码
测试代码
public static void main(String[] args) {
		System.out.println(getwebcode("http://blog.csdn.net/luanpeng825485697?viewmode=contents","UTF-8"));
	}

发送申请，获取响应网页源代码函数实现，输入参数为网址和解码器类型
//获取网页源代码
	public static String  getwebcode(String urlpath,String encoder) {
		StringBuilder sb=new StringBuilder();
		InputStream in = null;   
        try {
            // 建立输入输出流
            URL url = new URL(urlpath); 
            in = url.openStream();        
            // 从 URL 拷贝到输出流
            byte[] buffer = new byte[4096];
            int bytes_read;
            while((bytes_read = in.read(buffer)) != -1)
            {
                sb.append(new String(buffer,encoder));
            }
        }
        // 捕获异常，输出报错信息
        catch (Exception e) {
            System.err.println(e);
            System.err.println("Usage: java GetURL <URL> [<filename>]");
        }
        finally {  // 保证关闭输入流和输出流
            try { in.close();  } catch (Exception e) {}
        }
        return sb.toString();
	}