HTML Entity Decode [duplicate]

2018-12-31 02:00发布

This question already has an answer here:

How do I encode and decode HTML entities using JavaScript or JQuery?

var varTitle = "Chris' corner";

I want it to be:

var varTitle = "Chris' corner";

18条回答
怪性笑人.
2楼-- · 2018-12-31 02:32

Inspired by Robert K's solution, strips html tags and prevents executing scripts and eventhandlers like: <img src=fake onerror="prompt(1)"> Tested on latest Chrome, FF, IE (should work from IE9, but haven't tested).

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;
    })();

Simply call:

decodeEntities('<img src=fake onerror="prompt(1)">');
decodeEntities("<script>alert('aaa!')</script>");
查看更多
孤独寂梦人
3楼-- · 2018-12-31 02:34

A more functional approach to @William Lahti's answer:

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
  })
}
查看更多
妖精总统
4楼-- · 2018-12-31 02:35

Like Robert K said, don't use jQuery.html().text() to decode html entities as it's unsafe because user input should never have access to the DOM. Read about XSS for why this is unsafe.

Instead try the Underscore.js utility-belt library which comes with escape and unescape methods:

_.escape(string)

Escapes a string for insertion into HTML, replacing &, <, >, ", `, and ' characters.

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

_.unescape(string)

The opposite of escape, replaces &amp;, &lt;, &gt;, &quot;, &#96; and &#x27; with their unescaped counterparts.

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

To support decoding more characters, just copy the Underscore unescape method and add more characters to the map.

查看更多
还给你的自由
5楼-- · 2018-12-31 02:35

To do it in pure javascript without jquery or predefining everything you can cycle the encoded html string through an elements innerHTML and innerText(/textContent) properties for every decode step that is required:

<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>
查看更多
忆尘夕之涩
6楼-- · 2018-12-31 02:36

jQuery provides a way to encode and decode html entities.

If you use a "<div/>" tag, it will strip out all the html.

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

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

If you use a "<textarea/>" tag, it will preserve the html tags.

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

function htmlEncode(value) {
    return $('<textarea/>').text(value).html();
}
查看更多
冷夜・残月
7楼-- · 2018-12-31 02:37

Here is a full version

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;
}

Usage

htmldecode("&sum;&nbsp;&gt;&euro;");
查看更多
登录 后发表回答