1.導入jar包

2.實現源代碼

package com.zhishang.lucene;

import net.htmlparser.jericho.Element;
import net.htmlparser.jericho.HTMLElementName;
import net.htmlparser.jericho.Source;
import org.junit.Test;

import java.io.File;
import java.io.IOException;

/**
 * Created by Administrator on 2017/7/8.
 */
public class HtmlBeanUtil {

    @Test
    public void parseHtml(){
        String path = "G:\\data\\index.html";

        try {
            Source sc = new Source(new File(path));
            Element element = sc.getFirstElement(HTMLElementName.TITLE);
            System.out.println(element.getTextExtractor().toString());
            System.out.println(sc.getTextExtractor().toString());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

本文出自 “素顏” 博客，請務必保留此出處http://suyanzhu.blog.51cto.com/8050189/1945451

jericho解析html