提取富文本的纯文字内容

红太狼 2024-02-05 20:10 61阅读 0赞

package com.unicom.park.service.web.utils;
    
    import java.io.ByteArrayInputStream;
    import java.io.IOException;
    import java.io.InputStream;
    import java.io.InputStreamReader;
    import java.io.Reader;
    
    import javax.swing.text.html.HTMLEditorKit;
    import javax.swing.text.html.parser.ParserDelegator;
    
    public class Html2Text extends HTMLEditorKit.ParserCallback {
    
        private static Html2Text html2Text = new Html2Text();
    
        StringBuffer s;
    
        public Html2Text() {
        }
    
        public void parse(String str) throws IOException {
    
            InputStream iin = new ByteArrayInputStream(str.getBytes());
            Reader in = new InputStreamReader(iin);
            s = new StringBuffer();
            ParserDelegator delegator = new ParserDelegator();
            // the third parameter is TRUE to ignore charset directive
            delegator.parse(in, this, Boolean.TRUE);
            iin.close();
            in.close();
        }
    
        public void handleText(char[] text, int pos) {
            s.append(text);
        }
    
        public String getText() {
            return s.toString();
        }
    
        public static String getContent(String str) {
            try {
                html2Text.parse(str);
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
            return html2Text.getText();
        }
    
    
    
    }

//String s = HtmlUtil.cleanHtmlTag(activity.getContent());
                String s = HtmlUtil.cleanHtmlTag(activity.getContent());
                screenInformationVO.setContent(s);
    
                if(StringUtils.isNotBlank(s)) {
                    String content = Html2Text.getContent(s).replace(" ","");
                    if(StringUtils.isNotBlank(content)) {
                        int length = content.length() >= 18 ? 18 : content.length();
                        screenInformationVO.setIntroduction(content.substring(0, length));
                    }
                }