java使用正则表达式过滤html标签

前段时间开发的时候要读取一篇文章的简介内容（也就是前200个字符），使用了隐藏字段，可能有人就要问了，那后台也是可以截取字符的啊，那是因为编辑器里面包含了html标签，所以后台就需要处理html标签的正则表达式，前些天上网搜了下，发现有人写好的一个类，给大家共享下，不要闲小弟落伍了...

import java.util.regex.Matcher; 
import java.util.regex.Pattern; 
 
 
 
public class HtmlRegexpUtil { 
 private final static String regxpForHtml = "<([^>]*)>"; // 过滤所有以<开头以>结尾的标签 
 
 private final static String regxpForImgTag = "<\s*img\s+([^>]*)\s*>"; // 找出IMG标签 
 
 private final static String regxpForImaTagSrcAttrib = "src="([^"]+)""; // 找出IMG标签的SRC属性 
 
  
 public HtmlRegexpUtil() { 
  // TODO Auto-generated constructor stub 
 } 
 
  
 public String replaceTag(String input) { 
  if (!hasSpecialChars(input)) { 
   return input; 
  } 
  StringBuffer filtered = new StringBuffer(input.length()); 
  char c; 
  for (int i = 0; i <= input.length() - 1; i++) { 
   c = input.charAt(i); 
   switch (c) { 
   case '<': 
    filtered.append("<"); 
    break; 
   case '>': 
    filtered.append(">"); 
    break; 
   case '"': 
    filtered.append("""); 
    break; 
   case '&': 
    filtered.append("&"); 
    break; 
   default: 
    filtered.append(c); 
   } 
 
  } 
  return (filtered.toString()); 
 } 
 
  
 public boolean hasSpecialChars(String input) { 
  boolean flag = false; 
  if ((input != null) && (input.length() > 0)) { 
   char c; 
   for (int i = 0; i <= input.length() - 1; i++) { 
    c = input.charAt(i); 
    switch (c) { 
    case '>': 
     flag = true; 
     break; 
    case '<': 
     flag = true; 
     break; 
    case '"': 
     flag = true; 
     break; 
    case '&': 
     flag = true; 
     break; 
    } 
   } 
  } 
  return flag; 
 } 
 
  
 public static String filterHtml(String str) { 
  Pattern pattern = Pattern.compile(regxpForHtml); 
  Matcher matcher = pattern.matcher(str); 
  StringBuffer sb = new StringBuffer(); 
  boolean result1 = matcher.find(); 
  while (result1) { 
   matcher.appendReplacement(sb, ""); 
   result1 = matcher.find(); 
  } 
  matcher.appendTail(sb); 
  return sb.toString(); 
 } 
 
  
 public static String fiterHtmlTag(String str, String tag) { 
  String regxp = "<\s*" + tag + "\s+([^>]*)\s*>"; 
  Pattern pattern = Pattern.compile(regxp); 
  Matcher matcher = pattern.matcher(str); 
  StringBuffer sb = new StringBuffer(); 
  boolean result1 = matcher.find(); 
  while (result1) { 
   matcher.appendReplacement(sb, ""); 
   result1 = matcher.find(); 
  } 
  matcher.appendTail(sb); 
  return sb.toString(); 
 } 
 
  
 public static String replaceHtmlTag(String str, String beforeTag, 
   String tagAttrib, String startTag, String endTag) { 
  String regxpForTag = "<\s*" + beforeTag + "\s+([^>]*)\s*>"; 
  String regxpForTagAttrib = tagAttrib + "="([^"]+)""; 
  Pattern patternForTag = Pattern.compile(regxpForTag); 
  Pattern patternForAttrib = Pattern.compile(regxpForTagAttrib); 
  Matcher matcherForTag = patternForTag.matcher(str); 
  StringBuffer sb = new StringBuffer(); 
  boolean result = matcherForTag.find(); 
  while (result) { 
   StringBuffer sbreplace = new StringBuffer(); 
   Matcher matcherForAttrib = patternForAttrib.matcher(matcherForTag 
     .group(1)); 
   if (matcherForAttrib.find()) { 
    matcherForAttrib.appendReplacement(sbreplace, startTag 
      + matcherForAttrib.group(1) + endTag); 
   } 
   matcherForTag.appendReplacement(sb, sbreplace.toString()); 
   result = matcherForTag.find(); 
  } 
  matcherForTag.appendTail(sb); 
  return sb.toString(); 
 } 
} 

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持考高分网。