/*
*目的:想搞java网络爬虫,先做个简单的html
* 效果:把随意网站的html文件内容输出到本地*/
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
public class Reptile {
public static void main(String[] args) throws Exception {
//新建一个存放html的文件
File file=new File("F:\\new.txt");
if(!file.exists()){
file.createNewFile();
}
/*新建一个文件夹
File file1=new File("F:\\new\\");
if(!file1.exists()){
file1.mkdir();
}
*/
//从网站读取html内容
URL url=new URL("http://www.sivibrand.com/");
URLConnection conn=url.openConnection();
conn.setReadTimeout(10000);
BufferedReader reader=new BufferedReader(new InputStreamReader(
conn.getInputStream(),"utf-8"));
String line="";
//向文件中写入内容
FileWriter fw = null;
fw = new FileWriter(file);
BufferedWriter out = new BufferedWriter(fw);
while((line=reader.readLine())!=null){
System.out.println(line);
out.write(line, 0, line.length()-1);
}
out.close();
}
}