Question

I am currently working on an HTML utility. I want to extract the font-family used in the HTML Code using Javascript. I found this piece of Regular Expression which can find only the normal fonts:

font-family\s*?:.*?(;|(?=""|'|;))

i.e font-family:Arial, Helvetica, sans-serif

I am not able to match font families like:

font-family: 'Lucida Sans', 'Lucida Sans Unicode', 'Lucida Grande', sans-serif;

Are there any methods available to extract the fonts/font families?

Answer 1

Finally I got it sorted out..

function demo(input,output) {
var div = document.createElement("div");
try {
    div.innerHTML = input;
} catch (e) {
    alert(e.message);
    return;
}
// images
var images = div.getElementsByTagName("IMG");
//console.log(images);

// font-family
var fontfamily = [];
var ffstack = [div];
while (ffstack.length) {
    var ff = ffstack.pop();
    if (ff.style && ff.style.fontFamily) {
            fontfamily.push(ff.style.fontFamily);
    }
    if (ff.childNodes) {
        for (var i = 0; i < ff.childNodes.length; i++) {
            ffstack.push(ff.childNodes[i]);
        }
    }
}
//console.log(fontfamily);
document.getElementById("resultBlock").style.display = "block";
var vArray = Duplicates(fontfamily);
var fontss = vArray.join("\n\n");
output.value =fontss;

}

function Duplicates(arr) {
var i,
lenn = arr.length,
    out = [],
    obj = {};

for (i = 0; i < lenn; i++) {
    obj[arr[i]] = 0;
}
for (i in obj) {
    out.push(i);
}
return out;

}