Javascript HTML实体解码
如何使用JavaScript或JQuery对HTML实体进行编码和解码Javascript HTML实体解码,javascript,jquery,html,Javascript,Jquery,Html,如何使用JavaScript或JQuery对HTML实体进行编码和解码 var varTitle = "Chris' corner"; 我希望它是: var varTitle = "Chris' corner"; 您可以尝试以下方法: var varTitle = html_entity_decode("Chris' corner"); var Title=$('').html(“Chris'corner”).text(); 控制台日志(标题
var varTitle = "Chris' corner";
我希望它是:
var varTitle = "Chris' corner";
您可以尝试以下方法:
var varTitle = html_entity_decode("Chris' corner");
var Title=$('').html(“Chris'corner”).text();
控制台日志(标题)代码>
将不受信任的HTML注入页面是危险的,如中所述
另一种方法是使用PHP的html_实体_解码(from)的纯JavaScript实现。然后,示例将类似于:
var varTitle = html_entity_decode("Chris' corner");
我建议不要使用被接受为答案的jQuery代码。虽然它不会将要解码的字符串插入到页面中,但它确实会创建脚本和HTML元素等内容。这比我们需要的代码多得多。相反,我建议使用更安全、更优化的函数
var decodeEntities = (function() {
// this prevents any overhead from creating the object each time
var element = document.createElement('div');
function decodeHTMLEntities (str) {
if(str && typeof str === 'string') {
// strip script/html tags
str = str.replace(/<script[^>]*>([\S\s]*?)<\/script>/gmi, '');
str = str.replace(/<\/?\w(?:[^"'>]|"[^"]*"|'[^']*')*>/gmi, '');
element.innerHTML = str;
str = element.textContent;
element.textContent = '';
}
return str;
}
return decodeHTMLEntities;
})();
我知道我玩游戏有点晚了,但我想我可以提供以下代码片段作为我如何使用jQuery解码HTML实体的示例:
var varTitleE = "Chris' corner";
var varTitleD = $("<div/>").html(varTitleE).text();
console.log(varTitleE + " vs. " + varTitleD);
正如Robert K所说,不要使用jQuery.html().text()对html实体进行解码,因为这是不安全的,因为用户输入不应该访问DOM。了解这是不安全的原因
请尝试以下工具和方法提供的实用皮带库:
转义字符串以插入HTML,替换&
、
、“
、`
和
字符
_.escape('Curly, Larry & Moe');
=> "Curly, Larry & Moe"
与escape相反的是,它取代了,,,,,“,,,,&96代码>和'代码>及其未替换的对应项
_.unescape('Curly, Larry & Moe');
=> "Curly, Larry & Moe"
要支持解码更多字符,只需复制下划线方法并向地图添加更多字符。受Robert K的解决方案启发,此版本不剥离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;
})();
下面是一个不需要创建div的快速方法,它可以解码“最常见”的HTML转义字符:
function decodeHTMLEntities(text) {
var entities = [
['amp', '&'],
['apos', '\''],
['#x27', '\''],
['#x2F', '/'],
['#39', '\''],
['#47', '/'],
['lt', '<'],
['gt', '>'],
['nbsp', ' '],
['quot', '"']
];
for (var i = 0, max = entities.length; i < max; ++i)
text = text.replace(new RegExp('&'+entities[i][0]+';', 'g'), entities[i][1]);
return text;
}
函数解码属性(文本){
var实体=[
[‘amp’、‘和’],
[apos','\''],
[#x27','\''],
[#x2F','/'],
['#39', '\''],
['#47', '/'],
[lt',''],
['nbsp',''],
['quot','“']
];
对于(变量i=0,max=entities.length;i
我认为这与所选择的解决方案正好相反
var decoded = $("<div/>").text(encodedStr).html();
var decoded=$(“”).text(encodedStr.html();
试试看:)要在纯javascript中执行此操作,而无需jquery或预定义所有内容,您可以通过元素innerHTML和innerText(/textContent)属性循环编码的html字符串,以执行所需的每个解码步骤:
<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 = "<p>name</p><p><span style=\"font-size:xx-small;\">ajde</span></p><p><em>da</em></p>";
</script>
<input type=button onclick="document.body.innerHTML=decode(encodedString)"/>
</body>
</html>
对于每个解码步骤,循环浏览innerHTML和innerText
函数解码(str){
var d=document.createElement(“div”);
d、 innerHTML=str;
返回d.innerText的类型!=“未定义”?d.innerText:d.textContent;
}
var encodedString=“pname/ppspan style=\”字体大小:xx小;\“ajde/span/ppemda/em/p”;
受Robert K解决方案的启发,剥离html标记并阻止执行脚本和事件处理程序,如:
在最新的Chrome、FF、IE上测试(应该可以从IE9开始工作,但尚未测试)
简单地说:
decodeEntities('<img src=fake onerror="prompt(1)">');
decodeEntities("<script>alert('aaa!')</script>");
解码实体(“”);
解码实体(“警报('aaa!'”);
jQuery提供了一种编码和解码html实体的方法
如果使用“”标记,它将删除所有html
function htmlDecode(value) {
return $("<div/>").html(value).text();
}
function htmlEncode(value) {
return $('<div/>').text(value).html();
}
函数htmlDecode(值){
返回$(“”).html(值).text();
}
函数htmlEncode(值){
返回$('').text(value.html();
}
如果使用“”标记,它将保留html标记
function htmlDecode(value) {
return $("<textarea/>").html(value).text();
}
function htmlEncode(value) {
return $('<textarea/>').text(value).html();
}
函数htmlDecode(值){
返回$(“”).html(值).text();
}
函数htmlEncode(值){
返回$('').text(value.html();
}
要在列表中添加另一个“灵感来源于Robert K”,这里是另一个安全版本,它不剥离HTML标记。它不通过HTML解析器运行整个字符串,而是只提取实体并转换实体
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;
}
})();
因为@Robert K和@mattcasey都有很好的代码,我想我会在这里提供一个咖啡脚本版本,以防将来有人使用它:
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(/\&#/mg, '&#') # The rest, for double-encodings
string = string.replace(/\"/mg, '"')
string = string.replace(/\"e;/mg, '"')
string = string.replace(/\_/mg, '_')
string = string.replace(/\'/mg, "'")
string = string.replace(/\"/mg, '"')
string = string.replace(/\>/mg, '>')
string = string.replace(/\</mg, '<')
string
# Run it
tmp = fixHtmlEncodings(this)
decodeHTMLEntities(tmp)
String::unescape=(strict=false)->
###
#获取转义文本,并返回未转义的版本
#
#@param string str |要使用的字符串
#@param bool strict |粘贴模式将删除所有HTML
#
#在这里测试它:
# https://jsfiddle.net/tigerhawkvok/t9pn1dn5/
#
#代码:https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d
###
#创建一个虚拟元素
元素=document.createElement(“div”)
DecodeThMLentities=(str)->
如果str?和typeof str为“string”
除非严格是真的
#转义HTML标记
str=escape(str)。替换(/%26/g,,&')。替换(/%23/g,,#')。替换(/%3B/g,,;'))
其他的
str=str.replace(/]*>([\S\S]*?)/gmi',)
str=str.replace(/'))
string=string.replace(/\&60;/mg),这是一个完整的版本
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;
}
对于@William Lahti的答案,更实用的方法是:
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
})
}
var实体={
"amp":"&",
“apos”:“\”,
“#x27”:“\”,
“#x2F”:“/”,
'#39': '\'',
'#47': '/',
“lt”:”,
“nbsp”:”,
‘quot’:‘quot’
}
函数属性(文本){
返回文本。替换(/&([^;]+);/gm,函数(匹配,实体){
返回实体[实体]| |匹配
})
}
这是我最喜欢的解码HTML字符的方法。使用此代码的优点是标记也被保留
function decodeHtml(html) {
var txt = document.createElement("textarea");
txt.innerHTML = html;
return txt.value;
}
例如:
输入:
Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>
Entity:XSS:alert的错误尝试('new\nline?')
输出:
Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>
Entity:XSS:alert的错误尝试('new\nline?')
这里是另一个版本:
函数转换属性(文本){
const span=document.createElement('span');
返回文本
.更换(/&[#A-Za-z0-9]+;/g
function decodeHtml(html) {
var txt = document.createElement("textarea");
txt.innerHTML = html;
return txt.value;
}
Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>
Entity: Bad attempt at XSS:<script>alert('new\nline?')</script><br>