有人知道一个简单的方法来转义HTML从字符串在jQuery?我需要能够传递一个任意字符串,并有它正确转义显示在HTML页面(防止JavaScript/HTML注入攻击)。我确信可以通过扩展jQuery来实现这一点,但目前我对框架的了解还不够,无法实现这一点。
当前回答
因为你使用的是jQuery,你可以设置元素的text属性:
// before:
// <div class="someClass">text</div>
var someHtmlString = "<script>alert('hi!');</script>";
// set a DIV's text:
$("div.someClass").text(someHtmlString);
// after:
// <div class="someClass"><script>alert('hi!');</script></div>
// get the text in a string:
var escaped = $("<div>").text(someHtmlString).html();
// value:
// <script>alert('hi!');</script>
其他回答
(function(undefined){
var charsToReplace = {
'&': '&',
'<': '<',
'>': '>'
};
var replaceReg = new RegExp("[" + Object.keys(charsToReplace).join("") + "]", "g");
var replaceFn = function(tag){ return charsToReplace[tag] || tag; };
var replaceRegF = function(replaceMap) {
return (new RegExp("[" + Object.keys(charsToReplace).concat(Object.keys(replaceMap)).join("") + "]", "gi"));
};
var replaceFnF = function(replaceMap) {
return function(tag){ return replaceMap[tag] || charsToReplace[tag] || tag; };
};
String.prototype.htmlEscape = function(replaceMap) {
if (replaceMap === undefined) return this.replace(replaceReg, replaceFn);
return this.replace(replaceRegF(replaceMap), replaceFnF(replaceMap));
};
})();
没有全局变量,一些内存优化。 用法:
"some<tag>and&symbol©".htmlEscape({'©': '©'})
结果是:
"some<tag>and&symbol©"
我增强了mustache.js示例,将escapeHTML()方法添加到字符串对象中。
var __entityMap = {
"&": "&",
"<": "<",
">": ">",
'"': '"',
"'": ''',
"/": '/'
};
String.prototype.escapeHTML = function() {
return String(this).replace(/[&<>"'\/]/g, function (s) {
return __entityMap[s];
});
}
这样就很容易使用"Some <text>, more Text&Text".escapeHTML()
经过最后的测试,我可以推荐最快和完全跨浏览器兼容的原生javaScript (DOM)解决方案:
function HTMLescape(html){
return document.createElement('div')
.appendChild(document.createTextNode(html))
.parentNode
.innerHTML
}
如果你重复多次,你可以用一次准备好的变量来做:
//prepare variables
var DOMtext = document.createTextNode("test");
var DOMnative = document.createElement("span");
DOMnative.appendChild(DOMtext);
//main work for each case
function HTMLescape(html){
DOMtext.nodeValue = html;
return DOMnative.innerHTML
}
看看我最后的性能比较(堆栈问题)。
一个速度优化版本:
function escapeHtml(s) { let out = ""; let p2 = 0; for (let p = 0; p < s.length; p++) { let r; switch (s.charCodeAt(p)) { case 34: r = """; break; // " case 38: r = "&" ; break; // & case 39: r = "'" ; break; // ' case 60: r = '<' ; break; // < case 62: r = '>' ; break; // > default: continue; } if (p2 < p) { out += s.substring(p2, p); } out += r; p2 = p + 1; } if (p2 == 0) { return s; } if (p2 < s.length) { out += s.substring(p2); } return out; } const s = "Hello <World>!"; document.write(escapeHtml(s)); console.log(escapeHtml(s));
如果你走的是正则表达式路线,上面tghw的例子中就有一个错误。
<!-- WON'T WORK - item[0] is an index, not an item -->
var escaped = html;
var findReplace = [[/&/g, "&"], [/</g, "<"], [/>/g,">"], [/"/g,
"""]]
for(var item in findReplace) {
escaped = escaped.replace(item[0], item[1]);
}
<!-- WORKS - findReplace[item[]] correctly references contents -->
var escaped = html;
var findReplace = [[/&/g, "&"], [/</g, "<"], [/>/g, ">"], [/"/g, """]]
for(var item in findReplace) {
escaped = escaped.replace(findReplace[item[0]], findReplace[item[1]]);
}