一个用java正则表达式实现的爬取网页上的email地址的小程序
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.regex.*;
public class Test {
public static void main(String[] args) throws Exception{
BufferedReader bufferedReader=new BufferedReader(new FileReader("email.htm"));
String line="";
while((line=bufferedReader.readLine())!=null){
parase(line);
}
}
private static void parase(String line){
Pattern p=Pattern.compile("[\\w[.-]]+@[\\w[.-]]+\\.[\\w]+");
Matcher m=p.matcher(line);
while(m.find()){
System.out.println(m.group());
}
}
}