如何使用JavaScript或JQuery对HTML实体进行编码和解码？
var varTitle = "Chris' corner";
我希望它是：
var varTitle = "Chris' corner";
答案 0 :(得分：240)
我建议不要使用被接受为答案的jQuery代码。虽然它不会将字符串插入到页面中进行解码，但它确实会导致创建脚本和HTML元素等内容。这比我们需要的代码更多。相反，我建议使用更安全，更优化的功能。
var decodeEntities = (function() {
// this prevents any overhead from creating the object each time
var element = document.createElement('div');
function decodeHTMLEntities (str) {
if(str && typeof str === 'string') {
// strip script/html tags
str = str.replace(/<script[^>]*>([\S\s]*?)<\/script>/gmi, '');
str = str.replace(/<\/?\w(?:[^"'>]|"[^"]*"|'[^']*')*>/gmi, '');
element.innerHTML = str;
str = element.textContent;
element.textContent = '';
}
return str;
}
return decodeHTMLEntities;
})();
要使用此函数，只需调用decodeEntities("&")，它将使用与jQuery版本相同的基础技术 - 但没有jQuery的开销，并且在清理输入中的HTML标记之后。有关如何过滤HTML标记，请参阅已接受答案的Mike Samuel's comment。
通过在项目中添加以下行，可以将此函数轻松用作jQuery插件。
jQuery.decodeEntities = decodeEntities;
答案 1 :(得分：199)
您可以尝试以下方式：
var Title = $('<textarea />').html("Chris' corner").text();
console.log(Title);<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
更具互动性的版本：
$('form').submit(function() {
var theString = $('#string').val();
var varTitle = $('<textarea />').html(theString).text();
$('#output').text(varTitle);
return false;
});<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<form action="#" method="post">
<fieldset>
<label for="string">Enter a html-encoded string to decode</label>
<input type="text" name="string" id="string" />
</fieldset>
<fieldset>
<input type="submit" value="decode" />
</fieldset>
</form>
<div id="output"></div>
答案 2 :(得分：95)
就像Robert K所说，不要使用jQuery.html（）。text（）解码html实体，因为它不安全，因为用户输入永远不能访问DOM。请阅读XSS，了解这是不安全的原因。
请尝试使用Underscore.js和escape方法附带的unescape实用程序带库：
转义字符串以插入HTML，替换&，<，>，"，`和'个字符。
_.escape('Curly, Larry & Moe');
=> "Curly, Larry & Moe"
与逃避相反，用未转义的对手替换&，<，>，"，`和'。< / p>
_.unescape('Curly, Larry & Moe');
=> "Curly, Larry & Moe"
要支持解码更多字符，只需复制下划线unescape方法并向地图添加更多字符。
答案 3 :(得分：35)
这是一个快速方法，不需要创建div，并解码“最常见的”HTML转义字符：
function decodeHTMLEntities(text) {
var entities = [
['amp', '&'],
['apos', '\''],
['#x27', '\''],
['#x2F', '/'],
['#39', '\''],
['#47', '/'],
['lt', '<'],
['gt', '>'],
['nbsp', ' '],
['quot', '"']
];
for (var i = 0, max = entities.length; i < max; ++i)
text = text.replace(new RegExp('&'+entities[i][0]+';', 'g'), entities[i][1]);
return text;
}
答案 4 :(得分：17)
受Robert K的解决方案的启发，此版本不会删除HTML标记，并且同样安全。
var decode_entities = (function() {
// Remove HTML Entities
var element = document.createElement('div');
function decode_HTML_entities (str) {
if(str && typeof str === 'string') {
// Escape HTML before decoding for HTML Entities
str = escape(str).replace(/%26/g,'&').replace(/%23/g,'#').replace(/%3B/g,';');
element.innerHTML = str;
if(element.innerText){
str = element.innerText;
element.innerText = '';
}else{
// Firefox support
str = element.textContent;
element.textContent = '';
}
}
return unescape(str);
}
return decode_HTML_entities;
})();
答案 5 :(得分：14)
这是我最喜欢解码HTML字符的方法。使用此代码的优点是标签也会被保留。
function decodeHtml(html) {
var txt = document.createElement("textarea");
txt.innerHTML = html;
return txt.value;
}
输入：
Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>
输出：
Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>
答案 6 :(得分：11)
jQuery提供了一种编码和解码html实体的方法。
如果您使用“＆lt; div /＆gt;”标签，它将删除所有的HTML。
function htmlDecode(value) {
return $("<div/>").html(value).text();
}
function htmlEncode(value) {
return $('<div/>').text(value).html();
}
如果您使用“＆lt; textarea /＆gt;”标记，它将保留html标记。
function htmlDecode(value) {
return $("<textarea/>").html(value).text();
}
function htmlEncode(value) {
return $('<textarea/>').text(value).html();
}
答案 7 :(得分：10)
这是另一个版本：
function convertHTMLEntity(text){
const span = document.createElement('span');
return text
.replace(/&[#A-Za-z0-9]+;/gi, (entity,position,text)=> {
span.innerHTML = entity;
return span.innerText;
});
}
console.log(convertHTMLEntity('Large < £ 500'));
答案 8 :(得分：9)
将不受信任的HTML注入页面是危险的，如How to decode HTML entities using jQuery?中所述。
另一种方法是使用PHP的html_entity_decode（来自http://phpjs.org/functions/html_entity_decode:424）的仅JavaScript实现。这个例子就像是：
var varTitle = html_entity_decode("Chris' corner");
答案 9 :(得分：9)
受Robert K的解决方案启发，剥离html标签，阻止执行脚本和事件处理程序，如：<img src=fake onerror="prompt(1)">
测试了最新的Chrome，FF，IE（应该从IE9开始，但尚未测试）。
var decodeEntities = (function () {
//create a new html document (doesn't execute script tags in child elements)
var doc = document.implementation.createHTMLDocument("");
var element = doc.createElement('div');
function getText(str) {
element.innerHTML = str;
str = element.textContent;
element.textContent = '';
return str;
}
function decodeHTMLEntities(str) {
if (str && typeof str === 'string') {
var x = getText(str);
while (str !== x) {
str = x;
x = getText(x);
}
return x;
}
}
return decodeHTMLEntities;
})();
只需致电：
decodeEntities('<img src=fake onerror="prompt(1)">');
decodeEntities("<script>alert('aaa!')</script>");
答案 10 :(得分：9)
添加另一个＆＃34;灵感来自Robert K＆＃34;在列表中，这是另一个安全版本，其中不会删除HTML标记。它不是通过HTML解析器运行整个字符串，而是仅提取实体并转换它们。
var decodeEntities = (function() {
// this prevents any overhead from creating the object each time
var element = document.createElement('div');
// regular expression matching HTML entities
var entity = /&(?:#x[a-f0-9]+|#[0-9]+|[a-z0-9]+);?/ig;
return function decodeHTMLEntities(str) {
// find and replace all the html entities
str = str.replace(entity, function(m) {
element.innerHTML = m;
return element.textContent;
});
// reset the value
element.textContent = '';
return str;
}
})();
答案 11 :(得分：9)
这是完整版
function htmldecode(s){
window.HTML_ESC_MAP = {
"nbsp":" ","iexcl":"¡","cent":"¢","pound":"£","curren":"¤","yen":"¥","brvbar":"¦","sect":"§","uml":"¨","copy":"©","ordf":"ª","laquo":"«","not":"¬","reg":"®","macr":"¯","deg":"°","plusmn":"±","sup2":"²","sup3":"³","acute":"´","micro":"µ","para":"¶","middot":"·","cedil":"¸","sup1":"¹","ordm":"º","raquo":"»","frac14":"¼","frac12":"½","frac34":"¾","iquest":"¿","Agrave":"À","Aacute":"Á","Acirc":"Â","Atilde":"Ã","Auml":"Ä","Aring":"Å","AElig":"Æ","Ccedil":"Ç","Egrave":"È","Eacute":"É","Ecirc":"Ê","Euml":"Ë","Igrave":"Ì","Iacute":"Í","Icirc":"Î","Iuml":"Ï","ETH":"Ð","Ntilde":"Ñ","Ograve":"Ò","Oacute":"Ó","Ocirc":"Ô","Otilde":"Õ","Ouml":"Ö","times":"×","Oslash":"Ø","Ugrave":"Ù","Uacute":"Ú","Ucirc":"Û","Uuml":"Ü","Yacute":"Ý","THORN":"Þ","szlig":"ß","agrave":"à","aacute":"á","acirc":"â","atilde":"ã","auml":"ä","aring":"å","aelig":"æ","ccedil":"ç","egrave":"è","eacute":"é","ecirc":"ê","euml":"ë","igrave":"ì","iacute":"í","icirc":"î","iuml":"ï","eth":"ð","ntilde":"ñ","ograve":"ò","oacute":"ó","ocirc":"ô","otilde":"õ","ouml":"ö","divide":"÷","oslash":"ø","ugrave":"ù","uacute":"ú","ucirc":"û","uuml":"ü","yacute":"ý","thorn":"þ","yuml":"ÿ","fnof":"ƒ","Alpha":"Α","Beta":"Β","Gamma":"Γ","Delta":"Δ","Epsilon":"Ε","Zeta":"Ζ","Eta":"Η","Theta":"Θ","Iota":"Ι","Kappa":"Κ","Lambda":"Λ","Mu":"Μ","Nu":"Ν","Xi":"Ξ","Omicron":"Ο","Pi":"Π","Rho":"Ρ","Sigma":"Σ","Tau":"Τ","Upsilon":"Υ","Phi":"Φ","Chi":"Χ","Psi":"Ψ","Omega":"Ω","alpha":"α","beta":"β","gamma":"γ","delta":"δ","epsilon":"ε","zeta":"ζ","eta":"η","theta":"θ","iota":"ι","kappa":"κ","lambda":"λ","mu":"μ","nu":"ν","xi":"ξ","omicron":"ο","pi":"π","rho":"ρ","sigmaf":"ς","sigma":"σ","tau":"τ","upsilon":"υ","phi":"φ","chi":"χ","psi":"ψ","omega":"ω","thetasym":"ϑ","upsih":"ϒ","piv":"ϖ","bull":"•","hellip":"…","prime":"′","Prime":"″","oline":"‾","frasl":"⁄","weierp":"℘","image":"ℑ","real":"ℜ","trade":"™","alefsym":"ℵ","larr":"←","uarr":"↑","rarr":"→","darr":"↓","harr":"↔","crarr":"↵","lArr":"⇐","uArr":"⇑","rArr":"⇒","dArr":"⇓","hArr":"⇔","forall":"∀","part":"∂","exist":"∃","empty":"∅","nabla":"∇","isin":"∈","notin":"∉","ni":"∋","prod":"∏","sum":"∑","minus":"−","lowast":"∗","radic":"√","prop":"∝","infin":"∞","ang":"∠","and":"∧","or":"∨","cap":"∩","cup":"∪","int":"∫","there4":"∴","sim":"∼","cong":"≅","asymp":"≈","ne":"≠","equiv":"≡","le":"≤","ge":"≥","sub":"⊂","sup":"⊃","nsub":"⊄","sube":"⊆","supe":"⊇","oplus":"⊕","otimes":"⊗","perp":"⊥","sdot":"⋅","lceil":"⌈","rceil":"⌉","lfloor":"⌊","rfloor":"⌋","lang":"〈","rang":"〉","loz":"◊","spades":"♠","clubs":"♣","hearts":"♥","diams":"♦","\"":"quot","amp":"&","lt":"<","gt":">","OElig":"Œ","oelig":"œ","Scaron":"Š","scaron":"š","Yuml":"Ÿ","circ":"ˆ","tilde":"˜","ndash":"–","mdash":"—","lsquo":"‘","rsquo":"’","sbquo":"‚","ldquo":"“","rdquo":"”","bdquo":"„","dagger":"†","Dagger":"‡","permil":"‰","lsaquo":"‹","rsaquo":"›","euro":"€"};
if(!window.HTML_ESC_MAP_EXP)
window.HTML_ESC_MAP_EXP = new RegExp("&("+Object.keys(HTML_ESC_MAP).join("|")+");","g");
return s?s.replace(window.HTML_ESC_MAP_EXP,function(x){
return HTML_ESC_MAP[x.substring(1,x.length-1)]||x;
}):s;
}
用法
htmldecode("∑ >€");
答案 12 :(得分：2)
@William Lahti回答的更具功能性的方法：
var entities = {
'amp': '&',
'apos': '\'',
'#x27': '\'',
'#x2F': '/',
'#39': '\'',
'#47': '/',
'lt': '<',
'gt': '>',
'nbsp': ' ',
'quot': '"'
}
function decodeHTMLEntities (text) {
return text.replace(/&([^;]+);/gm, function (match, entity) {
return entities[entity] || match
})
}
答案 13 :(得分：1)
我知道我的游戏有点晚了，但我想我可能会提供以下代码段作为我如何使用jQuery解码HTML实体的示例：
var varTitleE = "Chris' corner";
var varTitleD = $("<div/>").html(varTitleE).text();
console.log(varTitleE + " vs. " + varTitleD);
不要忘记启动检查器/ firebug以查看控制台结果 - 或者只是替换console.log（...）w / alert（...）
也就是说，这是我通过Google Chrome检查员阅读的控制台：
Chris' corner vs. Chris' corner
答案 14 :(得分：1)
因为@Robert K和@mattcasey都有很好的代码，我想我会在这里为CoffeeScript版本做出贡献，以防将来有人使用它：
String::unescape = (strict = false) ->
###
# Take escaped text, and return the unescaped version
#
# @param string str | String to be used
# @param bool strict | Stict mode will remove all HTML
#
# Test it here:
# https://jsfiddle.net/tigerhawkvok/t9pn1dn5/
#
# Code: https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d
###
# Create a dummy element
element = document.createElement("div")
decodeHTMLEntities = (str) ->
if str? and typeof str is "string"
unless strict is true
# escape HTML tags
str = escape(str).replace(/%26/g,'&').replace(/%23/g,'#').replace(/%3B/g,';')
else
str = str.replace(/<script[^>]*>([\S\s]*?)<\/script>/gmi, '')
str = str.replace(/<\/?\w(?:[^"'>]|"[^"]*"|'[^']*')*>/gmi, '')
element.innerHTML = str
if element.innerText
# Do we support innerText?
str = element.innerText
element.innerText = ""
else
# Firefox
str = element.textContent
element.textContent = ""
unescape(str)
# Remove encoded or double-encoded tags
fixHtmlEncodings = (string) ->
string = string.replace(/\&#/mg, '&#') # The rest, for double-encodings
string = string.replace(/\"/mg, '"')
string = string.replace(/\"e;/mg, '"')
string = string.replace(/\_/mg, '_')
string = string.replace(/\'/mg, "'")
string = string.replace(/\"/mg, '"')
string = string.replace(/\>/mg, '>')
string = string.replace(/\</mg, '<')
string
# Run it
tmp = fixHtmlEncodings(this)
decodeHTMLEntities(tmp)
请参阅https://jsfiddle.net/tigerhawkvok/t9pn1dn5/7/或https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d（包括已编译的JS，可能与此答案相比可能已更新）
答案 15 :(得分：0)
要在没有jquery的纯javascript中执行此操作或预定义所有内容，您可以通过元素innerHTML和innerText（/ textContent）属性循环编码的html字符串，以用于所需的每个解码步骤：
<html>
<head>
<title>For every decode step, cycle through innerHTML and innerText </title>
<script>
function decode(str) {
var d = document.createElement("div");
d.innerHTML = str;
return typeof d.innerText !== 'undefined' ? d.innerText : d.textContent;
}
</script>
</head>
<body>
<script>
var encodedString = "<p>name</p><p><span style=\"font-size:xx-small;\">ajde</span></p><p><em>da</em></p>";
</script>
<input type=button onclick="document.body.innerHTML=decode(encodedString)"/>
</body>
</html>
答案 16 :(得分：-1)
我认为这与所选择的解决方案完全相反。
var decoded = $("<div/>").text(encodedStr).html();
尝试一下：）
答案 17 :(得分：-1)
您还询问了如何对它们进行编码 - 您可以使用服务器端功能，也可以创建自己的对象来进行映射，例如： clj: A function to convert extended character ?