Better way of extracting text from HTML in Javascript - javascript

I'm trying to scrape text from an HTML string by using container.innerText || container.textContent where container is the element from which I want to extract text.
Usually, the text I want to extract is located in <p> tags. So for the HTML below as an example:
<div id="container">
<p>This is the first sentence.</p>
<p>This is the second sentence.</p>
</div>
Using
var container = document.getElementById("container");
var text = container.innerText || container.textContent; // the text I want
will return This is the first sentence.This is the second sentence. without a space between the first period and the start of the second sentence.
My overall goal is to parse text using the Stanford CoreNLP, but its parser cannot detect that these are 2 sentences because they are not separated by a space. Is there a better way of extracting text from HTML such that the sentences are separated by a space character?
The HTML I'm parsing will have the text I want mostly in <p> tags, but the HTML may also contain <img>, <a>, and other tags embeeded between <p> tags.

As a dirty hack, try using this:
container.innerHTML.replace(/<.*?>/g," ").replace(/ +/g," ");
This will replace all tags with a space, then collapse multiple spaces into a single one.
Note that if there is a > inside an attribute value, this will mess you up. Avoiding this problem will require more elaborate parsing, such as looping through all text nodes and putting them together.
Longer but more robust method:
function recurse(result, node) {
var c = node.childNodes, l = c.length, i;
for( i=0; i<l; i++) {
if( c[i].nodeType == 3) result += c.nodeValue + " ";
if( c[i].nodeType == 1) result = recurse(result, c[i]);
}
return result;
}
recurse(container);
Assuming I haven't made a stupid mistake, this will perform a depth-first search for text nodes, appending their contents to the result as it goes.

jQuery has the method text() that does what you want. Will this work for you?
I'm not sure if it fits for everything that's in your container but it works in my example. It will also take the text of a <a>-tag and appends it to the text.
Update 20.12.2020
If you're not using jQuery. You could implement the text method with vanilla js like this:
const nodes = Array.from(document.querySelectorAll("#container"));
const text = nodes
.filter((node) => !!node.textContent)
.map((node) => node.textContent)
.join(" ");
Using querySelectorAll("#container") to get every node in the container. Using Array.from so we can work with Array methods like filter, map & join.
Finally, generate the text by filtering out elements with-out textContent. Then use map to get each text and use join to add a space separator between the text.
$(function() {
var textToParse = $('#container').text();
$('#output').html(textToParse);
});
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<div id="container">
<p>This is the first sentence.</p>
<p>This is the second sentence.</p>
<img src="http://placehold.it/200x200" alt="Nice picture"></img>
<p>Third sentence.</p>
</div>
<h2>output:</h2>
<div id="output"></div>

You can use the following function to extract and process the text as shown. It basically goes through all the children nodes of the target element and the child nodes of the child nodes and so on ... adding spaces at appropriate points:
function getInnerText( sel ) {
var txt = '';
$( sel ).contents().each(function() {
var children = $(this).children();
txt += ' ' + this.nodeType === 3 ? this.nodeValue : children.length ? getInnerText( this ) : $(this).text();
});
return txt;
}
function getInnerText( sel ) {
var txt = '';
$( sel ).contents().each(function() {
var children = $(this).children();
txt += ' ' + this.nodeType === 3 ?
this.nodeValue : children.length ?
getInnerText( this ) : $(this).text();
});
return txt;
}
alert( getInnerText( '#container' ) );
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js"></script>
<div id="container">
Some other sentence
<p>This is the first sentence.</p>
<p>This is the second sentence.</p>
</div>

You may use jQuery to traverse down the elements.
Here is the code :
$(document).ready(function()
{
var children = $("#container").find("*");
var text = "";
while (children.html() != undefined)
{
text += children.html()+"\n";
children = children.next();
}
alert(text);
});
Here is the fiddle : http://jsfiddle.net/69wezyc5/

Related

How to make a word count that contains html tags using javascript?

Hi I would like to do a Word Count in my RTE (Rich Text Editor) with javascript can also use with jquery. But it should not count the html tags and repeating white spaces.
Sample Text:
<p>11 22 33</p><p>44</p>5<br></div>
The javascript should display 5 only.
Is there any javascript code for this and that is also fast to calculate the Word Count?
Thanks!
Try something like this:
You get the html in the div then you remove all tags and replace them with spaces. You remove (trim) all left and right spaces and finally you split the string into an array. The length is your answer.
var cont = $("#content").html();
cont = cont.replace(/<[^>]*>/g," ");
cont = cont.replace(/\s+/g, ' ');
cont = cont.trim();
var n = cont.split(" ").length
alert(n);
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js"></script>
<div id="content">
<p>11 22 33</p><p>44</p>5<br></div>
var words = [];
function getWords(elements) {
elements.contents().each(function() {
if ($(this).contents().length > 0) return getWords($(this));
if ($(this).text()) words = words.concat($(this).text().split(" "));
})
}
getWords($('<div>').html('<p>11 22 33</p><p>44</p>5<br></div>'));
console.log(words,words.length);
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
You can do something tricky by using jQuery by creating an element with the content.
var str = '<p>11 22 33</p><p>44</p>5<br></div>';
var len = 0;
// create a temporary jQuery object with the content
$('<div/>', {
html: str
})
// get al child nodes including text node
.contents()
// iterate over the elements
.each(function() {
// now get number or words using match and add
len += (this.textContent.match(/[\w\d]+/g) || '').length;
});
console.log(len);
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
You can use Countable.js for live word counting, although it doesn't ignore HTML tags.

Jquery selector to do text() but without class or id?

<h1>
<br>
USA
<br>
<br>
<p style="margin-top:13px;" class="glyphicon glyphicon-chevron-down"></p>
<br>
<br>
Canada
</h1>
Without changing the HTML above, how can I get the value of Canada with jQuery selector?
If you want to get the last text-node value, then try this
var h1 = document.querySelector("h1");
var childNodes = h1.childNodes;
console.log(childNodes[childNodes.length -1 ].nodeValue);
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<h1><br>USA<br><br><p style="margin-top:13px;" class="glyphicon glyphicon-chevron-down"></p><br><br>Canada </h1>
Equivalent jquery would be
var h1 = $("h1")[0];
If the markup style is consistent -- not prone to change, you can use xpath.
https://developer.mozilla.org/en-US/docs/Web/XPath
You can also do something like this:
var value = $('h1').contents().filter(function() {
return this.nodeType == 3;
})[1];
Here i use nodeType == 3, which selects text nodes.
https://jsfiddle.net/54tw4nw0/
Here you go:
var afterP;
var text = $('h1').contents().filter(function() {
if (this.nodeName == "P") {
afterP = true
}
return afterP && this.nodeType == 3;
}).text();
console.log(text);
Solution copied & enhanced from Get the text after span element using jquery
Try :
var text = $("h1").html();
alert(text.substring(text.lastIndexOf("<br>") +4));
Working Fiddle

window.getSelection() on a semantic element like <strong>

Let's say I have this html
<strong>Link</strong>
and I want to replace this with something else programatically. I select this with the mouse and call
var sel = window.getSelection()
The content of sel is however a text, and its parentNode is the link node a (and its parentNode is the <strong> element I was looking for).
Can I get semantic elements like e.g. strong, b, em in a selection?
Use case: I want to select some text in a wysiwyg editor (html) and replace it with a link.
You can use the jQuery selector feature to search in the string for particular tag:
$('#btn').on('click', function() {
var sel = getSelectionHtml();
alert(sel.toString())
var anchor = $(sel).find('a');
var id = anchor.attr('id');
// here DOM manipulation starts
$('#' + id).html('Click here');
});
function getSelectionHtml() {
var html = "";
if (typeof window.getSelection != "undefined") {
var sel = window.getSelection();
if (sel.rangeCount) {
var container = document.createElement("div");
for (var i = 0, len = sel.rangeCount; i < len; ++i) {
container.appendChild(sel.getRangeAt(i).cloneContents());
}
html = container.innerHTML;
}
}
else if (typeof document.selection != "undefined") {
if (document.selection.type == "Text") {
html = document.selection.createRange().htmlText;
}
}
return html;
}
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<span>This is sample text</span>
<br/>
<br/>
<strong>Link</strong>
<span>This is another text</span>
<br/>
<br/>
<span>Select two above lines and click the button below</span>
<br/>
<br/>
<input type="button" id="btn" value="Click to see selected HTML" />
The function used to obtain HTML selection was reused from this page
Are you sure that there wouldn't be other <strong> tags on the page? This isn't unique at all, so you would be running a risk of selecting/replacing the wrong element. You could do something where you're finding the first or closest, but this may still be risky (could even grab this in a text-based ad that you're running).
That said, if you feel comfortable with the approach, you could try something like this instead:
document.getElementsByTagName("strong")[0].innerHTML = "<a href='url'>Some words</a>";
That would grab the first <strong> tag on the page and inject the link for you.

Stack at getting elements with javascript

I have the following html elements from which I have to get some specific texts,
example "John Doe"
I'm a newbie in javascript but have been playing with getElementById etc but I can't seem to get this one right.
<div id="name">
<p><span id="nameheading">name: </span> John Doe</p>
</div>
Bellow is What I have tried:
function askInformation()
{
var nameHeading = document.getElementById("nameheading");
var paragraph = document.getElementsByTagName("p").item(0).innerHTML ;
var name = paragraph[4];
console.log(name); // prints letter (n)
}
I need help please
If you want to get the text following the span in the following:
<div id="name">
<p><span id="nameheading">name: </span> John Doe</p>
</div>
You can use something like:
// Get a reference to the span
var span = document.getElementById('nameheading');
// Get the following text
var text = span.nextSibling.data;
However that is highly dependent on the internal structure, it may be best to loop over text node children and collect the content of all of them. You may also want to trim leading and trailing white space.
You could also get a reference to the parent DIV and use a function like the following that collects the text children and ignores child elements:
// Return the text of the child text nodes of an element,
// but not descendant element text nodes
function getChildText(element) {
var children = element.childNodes;
var text = '';
for (var i=0, iLen=children.length; i<iLen; i++) {
if (children[i].nodeType == '3') {
text += children[i].data;
}
}
return text;
}
var text = getChildText(document.getElementById('name').getElementsByTagName('p')[0]);
or more concisely for hosts that support the querySelector interface:
var text = getChildText(document.querySelector('#name p'));
var paragraph = document.getElementsByTagName("p").item(0).innerHTML ;
var name = paragraph.replace('<span id="nameheading">name: </span>','').trim(); // John Doe

How get text between two closed tags

I'm looking for a jQuery solution
<pre><marker id="markerStart"></marker>
aaaaa
<span style='font-family:monospace;background-color:#a0a0a0;'>bbb</span>bb
cc<marker id="markerEnd"></marker>ccc
</pre>
How get text between <marker> tags? Should be the following result:
aaaaabbbbbcc
Example 2 (markerEnd inside SPAN tag):
<pre><marker id="markerStart"></marker>
aaaaa
<span style='font-family:monospace;background-color:#a0a0a0;'>b<marker id="markerEnd"></marker>bb</span>bb
ccccc
</pre>
expected result: aaaaab
Thanks.
You can get all elements between two nodes like this:
$('marker:first').nextUntil('marker').text()
However, since you need to include text nodes, you need to write
var contents = $('pre').contents(),
start = contents.filter('marker:first'),
end = start.nextAll('marker:first'),
startIndex = contents.index(start),
endIndex = contents.index(end);
alert(contents.filter(function(i) {
return i > startIndex && i < endIndex;
}).text());
http://jsfiddle.net/SLaks/2jEps/
Here you go:
function textBetween(id1, id2) {
var node = document.getElementById(id1).nextSibling,
text = '';
while ( node && node.id !== id2 ) {
text += node.textContent.trim();
node = node.nextSibling;
}
return text;
}
Call this to get your text:
textBetween('markerStart', 'markerEnd')
Live demo: http://jsfiddle.net/simevidas/yxVxy/4/

Categories

Resources