filtertest.java

来自「一个搜索引擎,希望对大家有用」· Java 代码 · 共 34 行

package ch9.htmlparser;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.AndFilter;
import org.htmlparser.filters.HasChildFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.http.ConnectionManager;
import org.htmlparser.lexer.Page;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;

public class FilterTest {
	public static void main(String[] args) {
		ConnectionManager manager;
		try {
			manager = Page.getConnectionManager();
			Parser parser = new Parser(manager.openConnection("http://www.sina.com.cn"));
			parser.setEncoding("GB2312");
			NodeFilter filter = new AndFilter(new TagNameFilter("a"),
					new HasChildFilter(new TagNameFilter("img")));
			NodeList nodelist=parser.parse(filter);
			NodeIterator it=nodelist.elements();
			while(it.hasMoreNodes()){
				Node node=(Node)it.nextNode();
				System.out.println(node.toHtml());
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}