過濾html
1. java中如何過濾html的代碼
||把需要寫入資料庫的字元通過下面的方法過濾然後再寫入回 public static String converthtml(String input) { if (input == null || input.length() == 0) { return input; } StringBuffer buf = new StringBuffer(input.length() + 6); char ch = ' '; for (int i = 0; i < input.length(); i++) { ch = input.charAt(i); if (ch == '&') { buf.append("&"); } else if (ch == '<') { buf.append("<"); } else if (ch == '>') { buf.append(">"); } else if (ch == ' ') { buf.append(""); } else { buf.append(ch); } } return buf.toString(); }
希望采答納
2. 怎麼使用js過濾html標簽
你可以利用正則表達式來剔除這些標簽,也就是將所有的html類的標簽都替換為空即可:
//去除HTML標簽
str=str.replace(/</?[^>]*>/g,'');
3. 用正則表達式過濾HTML標簽
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* <p>
* Title: HTML相關的正則表達式工具類
* </p>
* <p>
* Description: 包括過濾HTML標記，轉換HTML標記，替換特定HTML標記
* </p>
* <p>
* Copyright: Copyright (c) 2006
* </p>
*
* @author hejian
* @version 1.0
* @createtime 2006-10-16
*/
public class HtmlRegexpUtil {
private final static String regxpForHtml = "<([^>]*)>"; // 過濾所有以<開頭以>結尾的標簽
private final static String regxpForImgTag = "<\\s*img\\s+([^>]*)\\s*>"; // 找出IMG標簽
private final static String regxpForImaTagSrcAttrib = "src=\"([^\"]+)\""; // 找出IMG標簽的SRC屬性
/**
*
*/
public HtmlRegexpUtil() {
// TODO Auto-generated constructor stub
}
/**
*
* 基本功能：替換標記以正常顯示
* <p>
*
* @param input
* @return String
*/
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());
}
/**
*
* 基本功能：判斷標記是否存在
* <p>
*
* @param input
* @return boolean
*/
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;
}
/**
*
* 基本功能：過濾所有以"<"開頭以">"結尾的標簽
* <p>
*
* @param str
* @return String
*/
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();
}
/**
*
* 基本功能：過濾指定標簽
* <p>
*
* @param str
* @param tag
* 指定標簽
* @return String
*/
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();
}
/**
*
* 基本功能：替換指定的標簽
* <p>
*
* @param str
* @param beforeTag
* 要替換的標簽
* @param tagAttrib
* 要替換的標簽屬性值
* @param startTag
* 新標簽開始標記
* @param endTag
* 新標簽結束標記
* @return String
* @如：替換img標簽的src屬性值為[img]屬性值[/img]
*/
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();
}
}
4. JS正則過濾指定的HTML標簽
1，得到網頁上的來鏈接地址源：
string
matchString =
@"<a[^>]+href=\s*(?:'(?<href>[^']+)'|""(?<href>[^""]+)""|(?<href>[^>\s]+))\s*[^>]*>";
2，得到網頁的標題：
string matchString = @"<title>(?<title>.*)</title>";
3，去掉網頁中的所有的html標記：
string temp = Regex.Replace(html, "<[^>]*>", ""); //html是一個要去除html標記的文檔
4, string matchString = @"<title>([\S\s\t]*?)</title>";
5,js去掉所有html標記的函數：
function delHtmlTag(str)
{
return str.replace(/<[^>]+>/g,"");//去掉所有的html標記
}
5. js如何過濾div內某特定HTML標簽
//這里為了方便使用jQuery
//移除使用tag類的div標記下的strong標記下a標記下沒有子元素版(鏈接為權空)的節點元素
jQuery('div.tagstronga:empty').parent().remove();
6. 怎樣用js方法過濾html等代碼
^<input type="text" id="theOne" value="">
<input type="button" onclick="NoHtml()" value="過濾html標簽">
<script>
function NoHtml(){
var t=document.getElementById("theOne").value;
t=t.replace(/({|})/g,''); //過濾{}
t=t.replace(/</g,'<'); //置換符號<
t=t.replace(/>/g,'>'); //置換符號>
// t=t.replace(/<\/?[^>]*>/g,''); //*<\/?[^>]*>可以匹配<script></style></body>等，版並置空權。而不是替換<和>兩個符號
document.getElementById("theOne").value=t;
}
</script>
7. 怎麼過濾html標簽
過濾html標簽代碼如下：
public string checkStr(string html)
{
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" on[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
html = regex1.Replace(html, ""); //過濾<script></script>標記
html = regex2.Replace(html, ""); //過濾href=javascript: (<A>) 屬性
html = regex3.Replace(html, " _disibledevent="); //過濾其它控制項的on...事件
html = regex4.Replace(html, ""); //過濾iframe
html = regex5.Replace(html, ""); //過濾frameset
html = regex6.Replace(html, ""); //過濾frameset
html = regex7.Replace(html, ""); //過濾frameset
html = regex8.Replace(html, ""); //過濾frameset
html = regex9.Replace(html, "");
html = html.Replace(" ", "");
html = html.Replace("</strong>", "");
html = html.Replace("<strong>", "");
return html;
}
8. 過濾所有html標簽的幾種方法
<!DOCTYPE html>
<html lang="en">
<head>
屬<meta charset="UTF-8">
<title>test</title>
<script type="text/javascript">
window.onload = function() {
var oTxt1 = document.getElementById('txt1');
var oTxt2 = document.getElementById('txt2');
var test = document.getElementById('test');
test.onclick = function() {
var reg = /<[^<>]+>/g;
oTxt2.value = oTxt1.value.replace(reg, '');
};
}
</script>
</head>
<body>
<div>
<input type="text" id="txt1">
<input type="text" id="txt2">
</div>
<div><button id="test">測試</button></div>
</body>
</html>
9. 急！！ 正則表達式過濾html
<%
Function stripHTML(strHTML)
'Strips the HTML tags from strHTML
Dim objRegExp, strOutput
Set objRegExp = New Regexp
objRegExp.IgnoreCase = True
objRegExp.Global = True
objRegExp.Pattern = "<.+?>"
'Replace all HTML tag matches with the empty string
strOutput = objRegExp.Replace(strHTML, "")
'Replace all < and > with < and >
strOutput = Replace(strOutput, "<", "<")
strOutput = Replace(strOutput, ">", ">")
stripHTML = strOutput 'Return the value of strOutput
Set objRegExp = Nothing
End Function
%>
10. js正則表達式過濾html標簽，這個正則式怎麼寫
|代碼雖短功能卻超強，運行效率也很高！
public static string ClearHtmlCode(string text)
{
text = text.Trim();
if (string.IsNullOrEmpty(text))
return string.Empty;
text = Regex.Replace(text, "[/s]{2,}", " "); //two or more spaces
text = Regex.Replace(text, "(<[b|B][r|R]/*>)+|(<[p|P](.|/n)*?>)", " "); //<br>
text = Regex.Replace(text, "(/s*&[n|N][b|B][s|S][p|P];/s*)+", " "); //
text = Regex.Replace(text, "<(.|/n)*?>", string.Empty); //any other tags
text = Regex.Replace(text, "/<//?[^>]*>/g", string.Empty); //any other tags
text = Regex.Replace(text, "/[ | ]* /g", string.Empty); //any other tags
text = text.Replace("'", "''");
text = Regex.Replace(text, "/ [/s| | ]* /g", string.Empty);
return text;
}