提取HTML中的链接和锚文本

说是原创，其实也参考了老师的PDF文档和java书籍，刚开始学，权且写写，献丑啦，O(∩_∩)O哈哈~

/*ReadLink.java*/

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;

import org.htmlparser.util.ParserException;


public class ReadLink {
	public static void main(String[] args) throws IOException, ParserException{
		try {
			FileReader fr=new FileReader("E:/MyeElipseProject/新浪首页.htm");//FileReader可以将文件中的内容以字符的形式读出来
			BufferedReader br=new BufferedReader(fr);//字符按行读出
			String line="";
			StringBuffer sb=new StringBuffer();//StringBuffer和String类似，不过其实可以改变的
			while((line=br.readLine())!=null){
				sb.append(line);
			}
			String result=new String(sb);
			readLink1.getLink(result);
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		
	}

}

/*readLink1.java*/

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;


public class readLink1 {
	public static void getLink(String result) throws ParserException{
		Parser parser;
		NodeList nodeList;
		parser=Parser.createParser(result, "utf-8");
		NodeFilter linkFilter=new NodeClassFilter(LinkTag.class);
		OrFilter lastFilter=new OrFilter();
		lastFilter.setPredicates(new NodeFilter[]{linkFilter});
		nodeList=parser.parse(lastFilter);
		Node[] nodes=nodeList.toNodeArray();
		String link="";
		String linkText="";
		for(int i=0;i<nodes.length;i++){
			Node node=nodes[i];
			if(node instanceof LinkTag)
			{
				LinkTag linkNode=(LinkTag)(node);
				link=linkNode.getLink();
				linkText=linkNode.getLinkText();
				
			}
			System.out.print(link);
			System.out.print(linkText);
		}
	}
	

}