我有一些与XML-RPC后端通信的JavaScript代码。 XML-RPC返回如下形式的字符串:

<img src='myimage.jpg'>

然而,当我使用JavaScript将字符串插入到HTML中时,它们会逐字呈现。我看到的不是图像,而是字符串:

<img src='myimage.jpg'>

我猜想HTML是通过XML-RPC通道转义的。

如何在JavaScript中解除字符串转义?我尝试了这个页面上的技巧,但没有成功:http://paulschreiber.com/blog/2008/09/20/javascript-how-to-unescape-html-entities/

诊断这个问题的其他方法是什么?


当前回答

我知道这里有很多好的答案,但由于我实现了一个有点不同的方法,我想分享一下。

这段代码是一种非常安全的安全方法,因为转义处理程序依赖于浏览器,而不是函数。因此,如果将来发现新的漏洞,将覆盖此解决方案。

const decodeHTMLEntities = text => {
    // Create a new element or use one from cache, to save some element creation overhead
    const el = decodeHTMLEntities.__cache_data_element 
             = decodeHTMLEntities.__cache_data_element 
               || document.createElement('div');
    
    const enc = text
        // Prevent any mixup of existing pattern in text
        .replace(/⪪/g, '⪪#')
        // Encode entities in special format. This will prevent native element encoder to replace any amp characters
        .replace(/&([a-z1-8]{2,31}|#x[0-9a-f]+|#\d+);/gi, '⪪$1⪫');

    // Encode any HTML tags in the text to prevent script injection
    el.textContent = enc;

    // Decode entities from special format, back to their original HTML entities format
    el.innerHTML = el.innerHTML
        .replace(/⪪([a-z1-8]{2,31}|#x[0-9a-f]+|#\d+)⪫/gi, '&$1;')
        .replace(/#⪫/g, '⪫');
   
    // Get the decoded HTML entities
    const dec = el.textContent;
    
    // Clear the element content, in order to preserve a bit of memory (it is just the text may be pretty big)
    el.textContent = '';

    return dec;
}

// Example
console.log(decodeHTMLEntities("<script>alert('&awconint;&CounterClockwiseContourIntegral;&#x02233;&#8755;⪪#x02233⪫');</script>"));
// Prints: <script>alert('∳∳∳∳⪪##x02233⪫');</script>

顺便说一下,我选择使用字符⪪和⪫,因为它们很少被使用,因此通过匹配它们影响性能的几率显著降低。

其他回答

首先创建一个<span id="decodeIt" style="display:none;></span>在身体某处

接下来,将要解码为innerHTML的字符串赋值如下:

document.getElementById("decodeIt").innerHTML=stringtodecode

最后,

stringtodecode=document.getElementById("decodeIt").innerText

下面是整个代码:

var stringtodecode="<B>Hello</B> world<br>";
document.getElementById("decodeIt").innerHTML=stringtodecode;
stringtodecode=document.getElementById("decodeIt").innerText
var encodedStr = 'hello &amp; world';

var parser = new DOMParser;
var dom = parser.parseFromString(
    '<!doctype html><body>' + encodedStr,
    'text/html');
var decodedString = dom.body.textContent;

console.log(decodedString);
var htmlEnDeCode = (function() {
    var charToEntityRegex,
        entityToCharRegex,
        charToEntity,
        entityToChar;

    function resetCharacterEntities() {
        charToEntity = {};
        entityToChar = {};
        // add the default set
        addCharacterEntities({
            '&amp;'     :   '&',
            '&gt;'      :   '>',
            '&lt;'      :   '<',
            '&quot;'    :   '"',
            '&#39;'     :   "'"
        });
    }

    function addCharacterEntities(newEntities) {
        var charKeys = [],
            entityKeys = [],
            key, echar;
        for (key in newEntities) {
            echar = newEntities[key];
            entityToChar[key] = echar;
            charToEntity[echar] = key;
            charKeys.push(echar);
            entityKeys.push(key);
        }
        charToEntityRegex = new RegExp('(' + charKeys.join('|') + ')', 'g');
        entityToCharRegex = new RegExp('(' + entityKeys.join('|') + '|&#[0-9]{1,5};' + ')', 'g');
    }

    function htmlEncode(value){
        var htmlEncodeReplaceFn = function(match, capture) {
            return charToEntity[capture];
        };

        return (!value) ? value : String(value).replace(charToEntityRegex, htmlEncodeReplaceFn);
    }

    function htmlDecode(value) {
        var htmlDecodeReplaceFn = function(match, capture) {
            return (capture in entityToChar) ? entityToChar[capture] : String.fromCharCode(parseInt(capture.substr(2), 10));
        };

        return (!value) ? value : String(value).replace(entityToCharRegex, htmlDecodeReplaceFn);
    }

    resetCharacterEntities();

    return {
        htmlEncode: htmlEncode,
        htmlDecode: htmlDecode
    };
})();

这是ExtJS的源代码。

对于只说一句话的男人:

const htmlDecode = innerHTML => Object.assign(document.createElement('textarea'), {innerHTML}).value;

console.log(htmlDecode('Complicated - Dimitri Vegas &amp; Like Mike'));

不客气只是一个信使……全部归功于ourcodeworld.com,链接如下。

window.htmlentities = {
        /**
         * Converts a string to its html characters completely.
         *
         * @param {String} str String with unescaped HTML characters
         **/
        encode : function(str) {
            var buf = [];

            for (var i=str.length-1;i>=0;i--) {
                buf.unshift(['&#', str[i].charCodeAt(), ';'].join(''));
            }

            return buf.join('');
        },
        /**
         * Converts an html characterSet into its original character.
         *
         * @param {String} str htmlSet entities
         **/
        decode : function(str) {
            return str.replace(/&#(\d+);/g, function(match, dec) {
                return String.fromCharCode(dec);
            });
        }
    };

出处:https://ourcodeworld.com/articles/read/188/encode-and-decode-html-entities-using-pure-javascript