java网页爬虫

java实现网页源码中获取邮箱的步骤：

　　(1)新建URL对象，表示要访问的网址。如：url=new URL("http://www.zhihu.com/topic/19563612/top-answers");

　　(2)建立HTTP连接，返回连接对象urlConnection对象。如：urlConnection = (HttpURLConnection)url.openConnection();

　　(3)获取相应HTTP 状态码。如responsecode=urlConnection.getResponseCode();

　　(4)如果HTTP 状态码为200，表示成功。从urlConnection对象获取输入流对象来获取请求的网页源代码。

代码示例：

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class WebPageSource {
    public static void main(String args[]){    
        URL url;
        int responsecode;
        HttpURLConnection urlConnection;
        BufferedReader bufr;
        String line = null;
        try{
            //生成一个URL对象，要获取源代码的网页地址为：http://www.zhihu.com/topic/19563612/top-answers
            url = new URL("http://www.zhihu.com/topic/19563612/top-answers");
            
            //邮箱正则规则
            String mailRegex = "\\w+@\\w+(\\.\\w)+";
            
            //将规则封装成对象
            Pattern pattern = Pattern.compile(mailRegex);
            
            //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 
                bufr = new BufferedReader(new InputStreamReader(urlConnection.getInputStream(),"utf-8"));
              
                while((line=bufr.readLine())!=null){  
                	//让正则对象和要作用的字符串相关联。获取匹配器对象
                	Matcher matcher = pattern.matcher(line);
                	//将规则作用在字符串上，并进行符合规则的字串查找
                	while(matcher.find()){
                		//用于获取匹配后的结果
                		System.out.println(matcher.group());
                	}
                }
            }
            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);
        }
    }
}