java网络爬虫

第一种方式是爬本地的网页，把网页保存再本地，然后爬取。

核心代码：

BufferedReader buf=new BufferedReader(new File());

String st=buf.readLine();

Pattern p=Pattern.compile(Regex);

Matcher ma=p.matcher(st);

while(ma.find())

{print(ma.group());}

package com.wanhao;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class RegexDemo {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		try {
			regex_test();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}

	public static void regex_test() throws IOException {
	
		BufferedReader bufIn=new BufferedReader(new FileReader("f:\\mail.html"));
		String regex="\\w+@\\w+(\\.\\w+)+";
		List<String>lis=new ArrayList<String>();
		
		Pattern p=Pattern.compile(regex);
		String mail=null;
		while((mail=bufIn.readLine())!=null)
		{
		   Matcher ma=	 p.matcher(mail);
		   while(ma.find())
		   {
			   lis.add(ma.group());
		   }
		}
		for(String s:lis)
		{
			System.out.println(s);
		}
	}
}

第二种直接爬取网站上的邮箱信息：

基本思路是相同的，不同处在于BufferedReader的获取方式不同了。

URL url=new URL("要爬的网址");

BufferedReader buf=new BufferedReader(new InputStreamReader(url.openStream()));

package com.wanhao;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class RegexDemo {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		try {
			regex_test();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}

	public static void regex_test() throws IOException {
	
		URL url=new URL("http://tieba.baidu.com/p/4221284005?fr=ala0&pstaala=2&tpl=5");
		BufferedReader bufIn=new BufferedReader(new InputStreamReader(url.openStream()));
		String regex="\\w+@\\w+(\\.\\w+)+";
		List<String>lis=new ArrayList<String>();
		
		Pattern p=Pattern.compile(regex);
		String mail=null;
		while((mail=bufIn.readLine())!=null)
		{
		   Matcher ma=	 p.matcher(mail);
		   while(ma.find())
		   {
			   lis.add(ma.group());
		   }
		}
		for(String s:lis)
		{
			System.out.println(s);
		}
	}
}