我如何编码和解码HTML实体使用JavaScript或JQuery?

var varTitle = "Chris' corner";

我希望它是:

var varTitle = "Chris' corner";

当前回答

这是另一个版本:

函数convertHTMLEntity(文本){ const span = document.createElement('span'); 返回文本 .replace (/ & [# A-Za-z0-9] +, / gi(实体、位置、文本)= > { 跨度。innerHTML =实体; 返回span.innerText; }); } console.log (convertHTMLEntity(“大& lt;& # 163;500 '));

其他回答

为了在列表中添加另一个“受Robert K的启发”,这里是另一个不剥离HTML标签的安全版本。它不是通过HTML解析器运行整个字符串,而是只提取实体并转换它们。

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;
    }
})();

这是另一个版本:

函数convertHTMLEntity(文本){ const span = document.createElement('span'); 返回文本 .replace (/ & [# A-Za-z0-9] +, / gi(实体、位置、文本)= > { 跨度。innerHTML =实体; 返回span.innerText; }); } console.log (convertHTMLEntity(“大& lt;& # 163;500 '));

向页面中注入不受信任的HTML是危险的,如如何使用jQuery解码HTML实体中所述。

一种替代方法是使用PHP html_entity_decode的纯javascript实现(来自http://phpjs.org/functions/html_entity_decode:424)。这个例子应该是这样的:

var varTitle = html_entity_decode("Chris' corner");

因为@Robert K和@mattcasey都有很好的代码,我想在这里贡献一个CoffeeScript版本,以防将来有人会使用它:

    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)

请参阅https://jsfiddle.net/tigerhawkvok/t9pn1dn5/7/或https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d(包括编译过的JS,可能比这个答案更新了)

受Robert K的解决方案的启发,这个版本不剥离HTML标记,而且同样安全。

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;
})();