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
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
其他回答
克里斯的回答很好，很优雅，但如果值未定义就失败了。简单的改进就能让它稳固:
function htmlDecode(value) {
return (typeof value === 'undefined') ? '' : $('<div/>').html(value).text();
}
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 & Like Mike'));
其他答案都有问题。
document.createElement('div')方法(包括使用jQuery的方法)执行传递给它的任何javascript(一个安全问题)，DOMParser.parseFromString()方法修饰空白。这是一个纯javascript解决方案，没有任何问题:
function htmlDecode(html) {
var textarea = document.createElement("textarea");
html= html.replace(/\r/g, String.fromCharCode(0xe000)); // Replace "\r" with reserved unicode character.
textarea.innerHTML = html;
var result = textarea.value;
return result.replace(new RegExp(String.fromCharCode(0xe000), 'g'), '\r');
}
TextArea是专门用来避免执行js代码。它通过了这些:
htmlDecode('<& >'); // returns "<& >" with non-breaking space.
htmlDecode(' '); // returns " "
htmlDecode('<img src="dummy" onerror="alert(\'xss\')">'); // Does not execute alert()
htmlDecode('\r\n') // returns "\r\n", doesn't lose the \r like other solutions.
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
// decode-html.js v1
function decodeHtml(html) {
const textarea = document.createElement('textarea');
textarea.innerHTML = html;
const decodedHtml = textarea.textContent;
textarea.remove();
return decodedHtml;
};
// encode-html.js v1
function encodeHtml(html) {
const textarea = document.createElement('textarea');
textarea.textContent = html;
const encodedHtml = textarea.innerHTML;
textarea.remove();
return encodedHtml;
};
// example of use:
let htmlDecoded = 'one & two & three';
let htmlEncoded = 'one & two & three';
console.log(1, htmlDecoded);
console.log(2, encodeHtml(htmlDecoded));
console.log(3, htmlEncoded);
console.log(4, decodeHtml(htmlEncoded));
