java新闻抓取_【图片】【抓取】Java获取各大网站新闻【java吧】_百度贴吧

该楼层疑似违规已被系统折叠 隐藏此楼查看此楼

下面上源码，用一小时做的，还有些bug

package Getnews;

import java.io.*;

import java.net.*;

import com.itextpdf.text.List;

public class GetNews {

/*technology

*

*

*

* */

static URL url=null;

staticInputStreamReader isr=null;

staticBufferedReader br=null;

staticString get="";

static List link=new List();

static BufferedWriter bw=null;

public static void main(String[] args){

try {

url=new URL("http://tech.baidu.com/n?cmd=1&class=techfocus&pn=1");

HttpURLConnection uc=(HttpURLConnection) url.openConnection();

bw=new BufferedWriter(new FileWriter("C:\\Documents and Settings\\Administrator\\桌面\\result.htm"));

isr=new InputStreamReader(uc.getInputStream());

br=new BufferedReader(isr);

String temp;

while((temp=br.readLine())!=null){

get+=temp;

int index1=0;

int index2=0;

index1=get.indexOf("

index2=get.indexOf("mon=\"a=1");

if(index2>index1){

int tidex=get.indexOf(">", index2);

if(tidex!=-1){

String substr=get.substring(tidex+1, get.indexOf("

", tidex+1));//截取新闻标题

if(!substr.contains("

System.out.println(substr);

bw.write("

bw.write(get.substring(index1+2, get.indexOf("\" ", index1)));

bw.write("\">"+substr+"

");

bw.write("
");

}

}

get=get.substring(tidex, get.length());

}

//System.out.println(temp);

}

br.close();

bw.close();

uc.disconnect();

} catch (MalformedURLException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

}