htmlparser提取网页 显示网页的树形结构

package com.core;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.nodes.TagNode;
import org.htmlparser.util.NodeList;

public class Test3 {
public static void main(String[] args) {
try {
Parser parser = new Parser("http://iask.sina.com.cn/b/8459115.html");// 要解析的网页
parser.setEncoding("gb2312");// 设置编码

NodeFilter filter_html = new TagNameFilter("html");// title节点过滤
NodeList nodelist1 = parser.extractAllNodesThatMatch(filter_html);// 过滤得符合过滤要求的节点的LIST

Node fatherNode = nodelist1.elementAt(0);
getTree(fatherNode, 0);

} catch (Exception e) {
e.printStackTrace();
}
}

public static void getTree(Node fatherNode, int i) {
print(i);
System.out.println("子节点为:" + fatherNode.getText());
NodeList childNodes = fatherNode.getChildren();
if (childNodes != null) {
for (int j = 0; j < childNodes.size(); j++) {
Node childNode = childNodes.elementAt(j);
if (childNode instanceof TagNode) {
getTree(childNode, i + 1);
}
}
}
}

public static void print(int i) {
for (int j = 0; j < i; j++)
System.out.print("      ");
}
}