JavaScript DOMParser access innerHTML and other properties

I am using the following code to parse a string into DOM:

var doc = new DOMParser().parseFromString(string, 'text/xml');

Where string is something like <!DOCTYPE html><html><head></head><body>content</body></html>.

typeof doc gives me object. If I do something like doc.querySelector('body') I get a DOM object back. But if I try to access any properties, like you normally can, it gives me undefined:

doc.querySelector('body').innerHTML; // undefined

The same goes for other properties, e.g. id. The attribute retrieval on the other hand goes fine doc.querySelector('body').getAttribute('id');.

Is there a magic function to have access to those properties?

Your current method fails, because HTML properties are not defined for the given XML document. If you supply the text/html MIME-type, the method should work.

var string = '<!DOCTYPE html><html><head></head><body>content</body></html>';
var doc = new DOMParser().parseFromString(string, 'text/html');
doc.body.innerHTML; // or doc.querySelector('body').innerHTML
// ^ Returns "content"

The code below enables the text/html MIME-type for browsers which do not natively support it yet. Is retrieved from the Mozilla Developer Network:

/* 
 * DOMParser HTML extension 
 * 2012-02-02 
 * 
 * By Eli Grey, http://eligrey.com 
 * Public domain. 
 * NO WARRANTY EXPRESSED OR IMPLIED. USE AT YOUR OWN RISK. 
 */  

/*! @source https://gist.github.com/1129031 */  
/*global document, DOMParser*/  

(function(DOMParser) {  
    "use strict";  
    var DOMParser_proto = DOMParser.prototype  
      , real_parseFromString = DOMParser_proto.parseFromString;

    // Firefox/Opera/IE throw errors on unsupported types  
    try {  
        // WebKit returns null on unsupported types  
        if ((new DOMParser).parseFromString("", "text/html")) {  
            // text/html parsing is natively supported  
            return;  
        }  
    } catch (ex) {}  

    DOMParser_proto.parseFromString = function(markup, type) {  
        if (/^\s*text\/html\s*(?:;|$)/i.test(type)) {  
            var doc = document.implementation.createHTMLDocument("")
              , doc_elt = doc.documentElement
              , first_elt;

            doc_elt.innerHTML = markup;
            first_elt = doc_elt.firstElementChild;

            if (doc_elt.childElementCount === 1
                && first_elt.localName.toLowerCase() === "html") {  
                doc.replaceChild(first_elt, doc_elt);  
            }  

            return doc;  
        } else {  
            return real_parseFromString.apply(this, arguments);  
        }  
    };  
}(DOMParser));

Try something like this:

const fragment = document.createRange().createContextualFragment(html);

whereas html is the string you want to convert.

JavaScript DOMParser access innerHTML and other properties

Related

Recent Posts