htmlcleaner使用方法及xpath语法初探

html-clean-demo.html



	 
	 
	



	

		
bar 
		
foo 
		
gzz 
	


	

		
text-1 
		
text-2 
		
text-3 
		
text-4 
	

package com.chenlb;
import java.io.File;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.TagNode;
/**
 * htmlcleaner 使用示例.
 *
 */
public class HtmlCleanerDemo {
	public static void main(String[] args) throws Exception {
		HtmlCleaner cleaner = new HtmlCleaner();
		TagNode node = cleaner.clean(new File("html/html-clean-demo.html"), "GBK");
		//按tag取.
		Object[] ns = node.getElementsByName("title", true);	//标题
		if(ns.length > 0) {
			System.out.println("title="+((TagNode)ns[0]).getText());
		}
		System.out.println("ul/li:");
		//按xpath取
		ns = node.evaluateXPath("//div[@class='d_1']//li");
		for(Object on : ns) {
			TagNode n = (TagNode) on;
			System.out.println("\ttext="+n.getText());
		}
		System.out.println("a:");
		//按属性值取
		ns = node.getElementsByAttValue("name", "my_href", true, true);
		for(Object on : ns) {
			TagNode n = (TagNode) on;
			System.out.println("\thref="+n.getAttributeByName("href")+", text="+n.getText());
		}
	}
}

import java.io.UnsupportedEncodingException;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.TagNode;
import org.htmlcleaner.XPatherException;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
//import com.moore.index.BabyStory;
import com.moore.util.HttpClientUtil;
/**
 * 用途：TODO
 * 
 * @author bbdtek
 */
public class ParserAirport {
	private static Logger log = LoggerFactory.getLogger(ParserAirport.class);
	/**
	 * @param args
	 * @throws UnsupportedEncodingException
	 * @throws XPatherException
	 */
	public static void main(String[] args) throws UnsupportedEncodingException,
			XPatherException {
		String url = "http://zh.wikipedia.org/wiki/%E4%B8%AD%E5%8D%8E%E4%BA%BA%E6%B0%91%E5%85%B1%E5%92%8C%E5%9B%BD%E6%9C%BA%E5%9C%BA%E5%88%97%E8%A1%A8";
		String contents = HttpClientUtil.getUtil().getCon(url);
		HtmlCleaner hc = new HtmlCleaner();
		TagNode tn = hc.clean(contents);
		String xpath = "//div[@class='mw-content-ltr']//table[@class='wikitable + sortable']//tbody//tr[@align='right']";
		Object[] objarr = null;
		objarr = tn.evaluateXPath(xpath);
		if (objarr != null && objarr.length > 0) {
			for (Object obj : objarr) {
				TagNode tntr = (TagNode) obj;
				String xptr = "//td[@align='left']//a";
				Object[] objarrtr = null;
				objarrtr = tntr.evaluateXPath(xptr);
				if (objarrtr != null && objarrtr.length > 0) {
					for (Object obja : objarrtr) {
						TagNode tna = (TagNode) obja;
						String str = tna.getText().toString();
						log.info(str);
					}
				}
			}
		}
	}
}