java源码 网络爬虫_java源代码网络爬虫

import java.io.BufferedReader;

import java.io.BufferedWriter;

import java.io.File;

import java.io.FileOutputStream;

import java.io.InputStreamReader;

import java.io.OutputStreamWriter;

import http://www.doczj.com/doc/1b957d068e9951e79a892753.html.HttpURLConnection;

import http://www.doczj.com/doc/1b957d068e9951e79a892753.html.URL;

public class WebPageSource {

public static void main(String args[]){

URL url;

int responsecode;

HttpURLConnection urlConnection;

BufferedReader reader;

BufferedWriter writer;

String line;

try{

//生成一个URL对象，要获取源代码的网页地址为：

http://www.doczj.com/doc/1b957d068e9951e79a892753.html

url=new URL("http://www.doczj.com/doc/1b957d068e9951e79a892753.html");

//打开URL

urlConnection = (HttpURLConnection)url.openConnection(); //获取服务器响应代码

responsecode=urlConnection.getResponseCode();

if(responsecode==200){

//得到输入流，即获得了网页的内容

reader=new BufferedReader(new InputStreamReader(urlCo nnection.getInputStream(),"GBK"));

writer = new BufferedWriter(new OutputStreamWriter(ne w FileOutputStream(new File("d://test.txt"))));

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

writer.write(line);

writer.newLine();

}

}

else{

System.out.println("获取不到网页的源码，服务器响应代码为："+responsecode);

}

}

catch(Exception e){

System.out.println("获取不到网页的源码,出现异常："+e); }