一些处理的小方法，Java代码

一些处理的小方法，Java代码

1、去html文本的标签，换行等特殊字符，转为纯文本格式

	String claimspath_result = claimspath.replaceAll("\\&[a-zA-Z]{1,10};", "") //去除类似< >  的字串
				.replaceAll("<[a-zA-Z]+[1-9]?[^><]*>", "") //去除开始标签及没有结束标签的标签
				.replaceAll("</[a-zA-Z]+[1-9]?>", ""); //去除结束标签

2、计算某一日期与当前日期的差额

   		LocalDateTime now = LocalDateTime.now();
         int year = now.getYear();
         int month = now.getMonthValue();
         int day = now.getDayOfMonth();
         String appDate = resultKey.getString("appDate");
         String[] dateList = appDate.split("\\.");
         int year1 = Integer.parseInt(dateList[0]);
         int month1 = Integer.parseInt(dateList[1]);
         int day1 = Integer.parseInt(dateList[2]);
         LocalDate startDate = LocalDate.of(year1, month1, day1);
         LocalDate endDate = LocalDate.of(year, month, day);
         double days = startDate.until(endDate, ChronoUnit.DAYS);

3、计算文章相似度（海明距离）

借鉴博客 海明距离https://blog.youkuaiyun.com/sinat_37239798/article/details/122893346

4、Java获取li标签内容（正则表达式+Jsoup）

（1）正则表达式可处理–简单–的标签主要用到Pattern 和Matcher 方法，获取li标签内数据，但不推荐，建议都改成Jsoup

	String text = "获取的样式"; 
 	String regex = "<li>(.*?)</li>";   //正则表达式
 	List<String> liListNews = getContentByRegex(text , regex, 1);	// 获取到的内容

  public static List<String> getContentByRegex(String html, String regex, int index) {
        List<String> list = new ArrayList<>();	// 创建一个空列表
        Pattern pattern = Pattern.compile(regex, Pattern.DOTALL);
        Matcher match = pattern.matcher(html);
        while (match.find()) {
            list.add(match.group(index));
        }
        return list;
    }

（2）–复杂–样式的用Jsoup，获取a标签及span标签

	  String title = "";
      String href = "";
      String date = "";
	  String domNodeObj = "获取的样式";
 	  Document doc = Jsoup.parse(domNodeObj);
      Elements links_href = doc.select("a[href]");
      Elements links_a = doc.select("a"); // 选择所有的<a>标签
      Elements links_span = doc.select("span"); // 选择所有的<span>标签
      for (Element link_href : links_href) {
          href = link_href.attr("abs:href");
      }
      for (Element link_a : links_a) {
          // 获取<a>标签内的文本内容
          title = link_a.text();
      }
      for (Element link_span : links_span) {
          // 获取<span>标签内的文本内容
          date = link_span.text();
      }
      //获取完后断点查看title内容，可能用到下面代码
      //title = title.substring(0,title.length()-date.length()-1);

5、打包下载

	downLoadZip(){
		window.location.href=httpurl+'expertsdatabase2/downLoadZipFile?PID='+this.EXPERTSDATABASE_ID;
	},

	@RequestMapping(value="/downLoadZipFile")
	public void downLoadZipFile(HttpServletResponse response) throws Exception {
		PageData pd = this.getPageData();
		//获取相关文件信息
		pd.put("DEL","0");
		pd.put("F_TYPE","2");
		List<PageData> files = is_filesService.listAll(pd);
		if (files != null && files.size() > 0) {
			response.setContentType("application/zip");
			response.setHeader("Content-Disposition", "attachment; filename=" + this.get32UUID() + ".zip");
			InputStream inputStream = null;
			OutputStream outputStream = response.getOutputStream();
			ZipOutputStream zos = new ZipOutputStream(outputStream);
			List<String> filenams = new ArrayList<>();
			for (int i = 0; i < files.size(); i++) {
				//将相关文件打成压缩包下载
				String f_path = files.get(i).getString("FILE_PATH");
				int i1 = f_path.indexOf("/");
//				String objectName = files.get(i).getString("URL");
				String objectName = f_path.substring(i1+1);
				inputStream = MinioUtil.getObject(minioDefaultBucket, objectName);
				String pre_name = files.get(i).getString("PRE_NAME");
				String suf_name = files.get(i).getString("SUF_NAME");
				String or_name = pre_name + "." +suf_name;
				//压缩包中不能有重名的文件
				for (int k = 0; k < filenams.size(); k++) {
					if (or_name.equals(filenams.get(k))) {
						or_name = or_name.replaceAll(pre_name, pre_name + "_d");
					}
				}
				zos.putNextEntry(new ZipEntry(or_name));
				filenams.add(or_name);
				byte b[] = new byte[1024];
				int j = 0;
				while ((j = inputStream.read(b)) != -1) {
					zos.write(b, 0, j);
				}
				inputStream.close();
			}
			zos.flush();
			zos.close();
			outputStream.flush();
			outputStream.close();
		}
	}

6、打印功能

		goPrint(){
				//打印前将不想打印的部分隐藏
				$('#files_div').hide();
				$('#print_btn').hide();
				window.print();
				//再显示
				$('#files_div').show();
				$('#print_btn').show();
			},

7、下载（视频）

 			downLoadFile(path,name){
                    let fielurl = minioUrlTcm+path;
                    // window.location.href = fielurl;
                    fetch(fielurl)
                        .then(res => res.blob())
                        .then(blob => {
                            const a = document.createElement("a");
                            const objectUrl = window.URL.createObjectURL(blob);
                            a.download = name;
                            a.href = objectUrl;
                            a.click();
                            window.URL.revokeObjectURL(objectUrl);
                            a.remove();
                        })
                },

8、处理长篇详情文章中的各项数据，保证规范演示

		formatRichText(html){
				  let newContent= html.replace(/<img[^>]*>/gi,function(match,capture){
					  match = match.replace(/style\s*?=\s*?([‘"])[\s\S]*?\1/ig, '').replace(/style\s*?=\s*?([‘"])[\s\S]*?\1/ig, '');
					  return match;
				  });
				  newContent = newContent.replace(/style="[^"]+"/gi,function(match,capture){
					  match = match.replace(/width:[^;]+;/gi, 'max-width:100%;').replace(/width:[^;]+;/gi, 'max-width:100%;');
					  return match;
				  });
				  newContent = newContent.replace(/\<strong/gi, '<strong style="padding-bottom:12px;display:block"');
				  newContent = newContent.replace(/\<p/gi, '<p style="padding-bottom:12px;"');
				  newContent = newContent.replace(/<br[^>]*\/>/gi, '');
				  newContent = newContent.replace(/\<img/gi, '<img style="max-width:100%;height:auto;display:block;margin:10px 0;"');
				  return newContent;
			},