HTML实体解码[重复]

2020/10/09 04:41 · javascript ·  · 0评论

如何使用JavaScript或JQuery编码和解码HTML实体?

var varTitle = "Chris' corner";

我希望它是:

var varTitle = "Chris' corner";

您可以尝试类似:

var Title = $('<textarea />').html("Chris&apos; corner").text();
console.log(Title);
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>

JS提琴手

更具交互性的版本:

$('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>

JS提琴手

我建议不要使用被接受为答案的jQuery代码。虽然它没有将要解码的字符串插入页面,但确实会导致创建脚本和HTML元素之类的东西。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;
})();

http://jsfiddle.net/LYteC/4/

要使用此功能,只需调用decodeEntities("&amp;"),它将使用与jQuery版本相同的基础技术,但无需jQuery的开销,并且在清除输入中的HTML标记之后。请参阅Mike Samuel对已接受答案的评论,以了解如何过滤HTML标记。

通过在项目中添加以下行,可以轻松地将此函数用作jQuery插件。

jQuery.decodeEntities = decodeEntities;

就像Robert K所说的那样,不要使用jQuery.html()。text()来解码html实体,因为它不安全,因为用户输入永远都不能访问DOM。了解有关XSS为何不安全的信息。

而是尝试使用带有转义unescape方法Underscore.js实用程序带库

_.escape(字符串)

逸出用于插入HTML,替换字符串&<>"`,和'字符。

_.escape('Curly, Larry & Moe');
=> "Curly, Larry &amp; Moe"

_.unescape(字符串)

逃跑的对面,更换&amp;&lt;&gt;&quot;&#96;&#x27;与他们同行的转义。

_.unescape('Curly, Larry &amp; Moe');
=> "Curly, Larry & Moe"

要支持解码更多字符,只需复制Underscore unescape方法并向地图添加更多字符。

这是一种不需要创建div的快速方法,它可以解码“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;
}

原作者在这里回答

这是我最喜欢的解码HTML字符的方式。使用此代码的优点是还保留了标签。

function decodeHtml(html) {
    var txt = document.createElement("textarea");
    txt.innerHTML = html;
    return txt.value;
}

示例:http//jsfiddle.net/k65s3/

输入:

Entity:&nbsp;Bad attempt at XSS:<script>alert('new\nline?')</script><br>

输出:

Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>

受Robert K解决方案的启发,此版本不剥离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;
})();

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 &lt; &#163; 500'));

jQuery提供了一种编码和解码html实体的方法。

如果使用“ <div />”标记,它将去除所有html。

function htmlDecode(value) {
    return $("<div/>").html(value).text();
}

function htmlEncode(value) {
    return $('<div/>').text(value).html();
}

如果使用“ <textarea />”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();
}

要将另一个“受Robert K启发”的列表添加到列表中,这是另一个不剥离HTML标签的安全版本它没有通过HTML解析器运行整个字符串,而是仅提取实体并将其转换。

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;
    }
})();

如何使用jQuery解码HTML实体中所述,将不可信的HTML注入页面是危险的

一种替代方法是使用纯JavaScript的PHP的html_entity_decode实现(来自http://phpjs.org/functions/html_entity_decode:424)。该示例将类似于:

var varTitle = html_entity_decode("Chris&apos; corner");

受罗伯特·K(Robert K)解决方案的启发,剥离html标签并阻止执行脚本和事件处理程序,例如:<img src=fake onerror="prompt(1)">
在最新的Chrome,FF,IE上进行了测试(应在IE9上运行,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>");

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("&sum;&nbsp;&gt;&euro;");

@William Lahti的答案的更实用的方法:

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
  })
}

我知道我对游戏有些迟了,但是我想我可以提供以下片段作为示例,说明如何使用jQuery解码HTML实体:

var varTitleE = "Chris&apos; corner";
var varTitleD = $("<div/>").html(varTitleE).text();

console.log(varTitleE + " vs. " + varTitleD);​​​​​​​​​​​

不要忘记启动检查器/调试器以查看控制台结果-或只需替换console.log(...)w / alert(...)

就是说,这是我的控制台通过Google Chrome检查器读取的内容:

Chris&apos; corner vs. Chris' corner

因为@Robert K和@mattcasey都具有良好的代码,所以我想在这里提供CoffeeScript版本,以防将来任何人使用它:

    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(/\&amp;#/mg, '&#') # The rest, for double-encodings
        string = string.replace(/\&quot;/mg, '"')
        string = string.replace(/\&quote;/mg, '"')
        string = string.replace(/\&#95;/mg, '_')
        string = string.replace(/\&#39;/mg, "'")
        string = string.replace(/\&#34;/mg, '"')
        string = string.replace(/\&#62;/mg, '>')
        string = string.replace(/\&#60;/mg, '<')
        string
      # Run it
      tmp = fixHtmlEncodings(this)
      decodeHTMLEntities(tmp)

参见https://jsfiddle.net/tigerhawkvok/t9pn1dn5/7/https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d(包含已编译的JS,与该答案相比可能进行了更新)

要使用纯JavaScript而不使用jquery或不预先定义所有内容,您可以针对每个所需的解码步骤,通过元素innerHTML和innerText(/ textContent)属性循环编码的html字符串:

<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 = "&lt;p&gt;name&lt;/p&gt;&lt;p&gt;&lt;span style=\"font-size:xx-small;\"&gt;ajde&lt;/span&gt;&lt;/p&gt;&lt;p&gt;&lt;em&gt;da&lt;/em&gt;&lt;/p&gt;";
    </script>
    <input type=button onclick="document.body.innerHTML=decode(encodedString)"/>
  </body>
</html>

我认为这与选择的解决方案完全相反。

var decoded = $("<div/>").text(encodedStr).html();

试试吧 :)

本文地址:http://javascript.askforanswer.com/htmlshitijiemazhongfu.html
文章标签: ,   ,  
版权声明:本文为原创文章,版权归 javascript 所有,欢迎分享本文,转载请保留出处!

文件下载

老薛主机终身7折优惠码boke112

上一篇:
下一篇:

评论已关闭!