java socket抓取资源_Java 通过 Socket 的形式抓取网页内容

package com.hmw.net;

import java.io.BufferedReader;

import java.io.BufferedWriter;

import java.io.IOException;

import java.io.InputStreamReader;

import java.io.OutputStreamWriter;

import java.net.InetAddress;

import java.net.Socket;

/**

* Java 通过 Socket 的形式抓取网页内容

* 创建日期:2011-1-20

* @author 何明旺

*/

public class FetchHtmlBySocket {

public static void main(String[] args) {

String html = new FetchHtmlBySocket().htmlContent(new HtmlPage("blog.csdn.net", "/hemingwang0902"));

System.out.println(html);

}

/**

* 抓取网页原代码

* 创建日期:2011-1-20

* @param hp

* @return指定网页的源代码,如果抓取失败,则返回一个长度为 0 的空字符串

* @author 何明旺

*/

public String htmlContent(HtmlPage hp){

StringBuffer html = new StringBuffer();

Socket socket = null;

BufferedWriter writer = null;

BufferedReader reader = null;

try {

// 建立一个Socket

socket = new Socket(InetAddress.getByName(hp.getServer()), hp.getPort());

StringBuffer command = new StringBuffer()

.append("GET " + hp.getPath() + " HTTP/1.0/r/n")

.append("HOST:" + hp.getServer() + "/r/n")

.append("/r/n");

// 发送命令

writer = new BufferedWriter(new OutputStreamWriter(socket.getOutputStream(), hp.getCharset()));

writer.write(command.toString());

writer.flush();

// 接收返回的结果

reader = new BufferedReader(new InputStreamReader(socket.getInputStream(), hp.getCharset()));

String line;

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

html.append(line).append("/r/n");

}

} catch (Exception e) {

e.printStackTrace();

} finally {

try {

if (reader != null)

reader.close();

if (writer != null)

writer.close();

if (socket != null)

socket.close();

} catch (IOException e) {

e.printStackTrace();

}

}

return html.toString();

}

static class HtmlPage {

private String server;

private int port = 80;

private String path;

private String charset = "UTF-8";

public HtmlPage() {

super();

}

public HtmlPage(String server, String path) {

super();

this.server = server;

this.path = path;

}

public HtmlPage(String server, String path, String charset) {

super();

this.server = server;

this.path = path;

this.charset = charset;

}

public HtmlPage(String server, int port, String path, String charset) {

super();

this.server = server;

this.port = port;

this.path = path;

this.charset = charset;

}

public String getServer() {

return server;

}

public void setServer(String server) {

this.server = server;

}

public int getPort() {

return port;

}

public void setPort(int port) {

this.port = port;

}

public String getPath() {

return path;

}

public void setPath(String path) {

this.path = path;

}

public String getCharset() {

return charset;

}

public void setCharset(String charset) {

this.charset = charset;

}

}

}

  • 1
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值