linkparser.java

自己写的JAVA版提取指定网址所有超连接的实例

import java.util.regex.Pattern;
import java.util.regex.Matcher;
import java.util.ArrayList;

public class LinkParser {
public static ArrayList al = new ArrayList();

public static void parser(String string) {
String regex = "<\\s*a\\s*([^>]*)\\s*href\\s*=\\s*([^>]*)\\s*>";
Pattern p = Pattern.compile(regex);
Matcher m = p.matcher(string);

if(m.find()) {
al.add(m.group());
//System.out.println(m.group());
if(string.length()> m.end()) {
parser(string.substring(m.end()));
}
}
}

public static ArrayList getResultList() {
return al;
}

public static void cleanList() {
al.clear();
}

//public static void main(String[] args) {
//
//LinkGrabber lg = new LinkGrabber();
//LinkParser.parser(lg.linkGrabber("http://www.sohu.com"));
//ArrayList resultList = LinkParser.getResultList();
////LinkParser.cleanList();
////System.out.println("共找到了" + resultList.size() + "个?接！");
//for(int i = 0;i< resultList.size();i ++) {
//System.out.println(resultList.get(i).toString());
//}
//}
}