Extract the text out of HTML string using JavaScri

I am trying to get the inner text of HTML string, using a JS function(the string is passed as an argument). Here is the code:

function extractContent(value) {
    var content_holder = "";

    for(var i=0;i<value.length;i++) {
        if(value.charAt(i) === '>') {
            continue;
            while(value.charAt(i) != '<') {
                content_holder += value.charAt(i);
            }
        }

    }
    console.log(content_holder);
}

extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");

The problem is that nothing gets printed on the console(content_holder stays empty). I think the problem is caused by the "===" operator..

标签： javascript html string text extract

7条回答

叛逆

2楼-- · 2019-02-04 18:05

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));

0人赞添加讨论(0) 举报

来，给爷笑一个

3楼-- · 2019-02-04 18:09

You could temporarily write it out to a block level element that is positioned off the page .. some thing like this:

HTML:

<div id="tmp" style="position:absolute;top:-400px;left:-400px;">
</div>

JavaScript:

<script type="text/javascript">
function extractContent(value){
        var div=document.getElementById('tmp');
        div.innerHTML=value;
        console.log(div.children[0].innerHTML);//console out p
}

extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");
</script>

0人赞添加讨论(0) 举报

地球回转人心会变

4楼-- · 2019-02-04 18:13

One line (more precisely, one statement) version:

function extractContent(html) {

    return (new DOMParser).parseFromString(html, "text/html") . 
        documentElement . textContent;

}

0人赞添加讨论(0) 举报

祖国的老花朵

5楼-- · 2019-02-04 18:14

you need array to hold values

  function extractContent(value) {
var content_holder = new Array();

for(var i=0;i<value.length;i++) {
    if(value.charAt(i) === '>') {
        continue;
        while(value.charAt(i) != '<') {
            content_holder.push(value.charAt(i));
            console.log(content_holder[i]);
        }
    }
}
}extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");

0人赞添加讨论(0) 举报

虎瘦雄心在

6楼-- · 2019-02-04 18:16

Try This:-

<!DOCTYPE html>
<html>
<body>
<script type="text/javascript">
function extractContent(value){
        var div = document.createElement('div')
        div.innerHTML=value;
        var text= div.textContent;            
        return text;
}
window.onload=function()
{
   alert(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>"));
};
</script>
</body>
</html>

0人赞添加讨论(0) 举报

Melony?

7楼-- · 2019-02-04 18:21

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, '');

0人赞添加讨论(0) 举报

1 2 下一页

Extract the text out of HTML string using JavaScri

采纳回答

编辑标签

举报内容

检举类型

检举原因

检举说明(必填)

打开微信“扫一扫”，打开网页后点击屏幕右上角分享按钮

付费偷看金额在0.1-10元之间