Extract the text out of HTML string using JavaScript
Create an element, store the HTML in it, and get its textContent:
function extractContent(s) {
var span = document.createElement('span');
span.innerHTML = s;
return span.textContent || span.innerText;
};
alert(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>"));Here's a version that allows you to have spaces between nodes, although you'd probably want that for block-level elements only:
function extractContent(s, space) {
var span= document.createElement('span');
span.innerHTML= s;
if(space) {
var children= span.querySelectorAll('*');
for(var i = 0 ; i < children.length ; i++) {
if(children[i].textContent)
children[i].textContent+= ' ';
else
children[i].innerText+= ' ';
}
}
return [span.textContent || span.innerText].toString().replace(/ +/g,' ');
};
console.log(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>. Nice to <em>see</em><strong><em>you!</em></strong>"));
console.log(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>. Nice to <em>see</em><strong><em>you!</em></strong>",true));One line (more precisely, one statement) version:
function extractContent(html) {
return new DOMParser()
.parseFromString(html, "text/html")
.documentElement.textContent;
}
textContext is a very good technique for achieving desired results but sometimes we don't want to load DOM. So simple workaround will be following regular expression:
let htmlString = "<p>Hello</p><a href='http://w3c.org'>W3C</a>"
let plainText = htmlString.replace(/<[^>]+>/g, '');