使用java对Html操作-CSDN博客

本文链接：https://blog.csdn.net/weixin_42551921/article/details/109591040

本文介绍了一个实用的Java工具类，该工具可以将HTML格式的文本转换为纯文本TXT格式，并提供了XML操作的相关辅助方法。通过使用Jsoup和Apache Commons Lang库，这个工具能够有效地解析HTML并去除所有HTML标签，只保留文本内容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

html转txt
import org.apache.commons.lang3.StringEscapeUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Document.OutputSettings;
import org.jsoup.safety.Whitelist;


public class Html2Txt {
    
    public static String toPlainText(String html)  
    {  
        if (html == null)  
        {  
            return "";  
        }  

      
        final Document document =Jsoup.parse(html);  
        final OutputSettings outputSettings = new Document.OutputSettings().prettyPrint(false);  
        document.outputSettings(outputSettings);  
        document.select("br").append("\\n");  
        document.select("p").prepend("\\n");  
        document.select("p").append("\\n");  
        final String newHtml = document.html().replaceAll("\\\\n", "\n");  
        final String plainText = Jsoup.clean(newHtml, "", Whitelist.none(), outputSettings);  
        final String result = StringEscapeUtils.unescapeHtml4(plainText.trim());  
        return result;  
    }  
    
    public static void main(String[] args){
        
    }

}

-----------------

java操作xml

import org.dom4j.Attribute;
import org.dom4j.Element;


public class ElmUtils {
    public static Element addNode(Element elm, String nodeName, String txt) {
        Element node = elm.addElement(nodeName);
        txt = txt == null ? "" : txt;
        node.addText(txt);
        return node;
    }

    public static String getElmTxt(Element root, String elmNM) {
        Element tmpElm = (Element) root.selectSingleNode("//" + elmNM); 
        if (tmpElm == null) {
            return "";
        } else {
            return tmpElm.getText();
        }
    }
    
    public static String elementTxt(Element root, String elmNM) {
        Element tmpElm = (Element) root.element(elmNM); 
        if (tmpElm == null) {
            return "";
        } else {
            return tmpElm.getText();
        }
    }
    
    public static String getCurElmTxt(Element root, String elmNM) {
        Element tmpElm = (Element) root.selectSingleNode(elmNM);
        if (tmpElm == null) {
            return "";
        } else {
            return tmpElm.getText();
        }
    }
    
    public static String getElmAttrVal(Element root, String attrNM) {
        Attribute temAttr = root.attribute(attrNM);
        if (temAttr == null) {
            return "";
        } else {
            return temAttr.getValue();
        }
    }
    

    public static Element setElmTxt(Element elm, String elmName, String elmTxt) {
        Element tempElm = (Element) elm.selectSingleNode("//" + elmName);
        if(tempElm!=null){
            tempElm.setText(elmTxt);
        }
        return elm;
    }
    
    public static Element setElmAttr(Element elm, String attrName, String attrVal){
        Attribute attr = elm.attribute(attrName);
        attr.setValue(attrVal);
        return elm;
    }
}