jsoup解析html

 方法输入标签名和属性即可返回内容，不填属性返回内容，   

<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.11.3</version>
</dependency>

package htmlBody;
 
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
 
public class HtmlParser {
    /* * 如果标签属性为null则返回标签里的文本
     * @param document
     * @param Tag  标签名
     * @param attr 标签属性
     * @return
     */
    public static List<String> getElementsContent(Document document,String tag,String attr){
        Elements e = document.getElementsByTag(tag);
        List<String> hrefDataList=new ArrayList<String>();
        for (Element element : e) {
            //实体对象构造方法，代码省略
        	if(attr==null) {
        		hrefDataList.add(element.text());
        	}else {
        		hrefDataList.add(element.attr(attr));
        	}
        }
        return hrefDataList;
    }


	public static void main(String[] args) throws IOException {
		Document doc = Jsoup.parse(new File("D:/index.jsp"), "utf-8");
		List<String> result = getElementsContent(doc,"input","value");
		System.out.println(result);
		List<String> result2 = getElementsContent(doc,"div",null);
		for (String string : result2) {
			System.out.println(string);
		}
		
	}
 
}

更多操作参照官网https://jsoup.org/apidocs/org/jsoup/nodes/Element.html