CODEWITHSUNDEEP
javascriptphantomjs
Amon
Amon

Reputation: 3

PhantomJS Iterating through HTML page elements

can anybody please help me with this issue?

I'm scraping a local HTML file with PhantomJS and I'm trying to show the content of the HTML tags with class "test" on my screen. I do get the content of the first tag, but somehow I don't get the next one.

-= HTML / index.html =-

<!doctype html>
<html>
    <head>
        <meta charset="UTF-8">
        <title>Document</title>
    </head>
    <body>
        <div id="parent-id">
            <p>hello word 1</p>
            <p class="test">hello word 2</p>
            <p class="test">hello word 3</p>
            <p>hello word 4</p>
        </div>
    </body>
</html>

-= PhantomJS / test2.js =-

var fs = require('fs');
var page = require('webpage').create();

page.settings.userAgent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:49.0) Gecko/20100101 Firefox/49.0';
page.viewportSize = {width:1200, height:1024};

page.onConsoleMessage = function (msg) {
    //console.log(msg);
}

page.open('http://localhost/index.html', function(status) {
    if (status == 'success') {
        var products = page.evaluate(function() {
            return document.getElementsByClassName('test')
        });

        for(var i = 0; i < products.length; ++i) {
            if(products[i]) {
                console.log(products[i].innerHTML);
            }
        }

        phantom.exit();
    } else {
        console.log('Unable to load the address!');
        phantom.exit();
    }
});

when I run phantomjs "test2.js" I got:

hello word 2

While I would expect to get:

hello word 2
hello word 3

Upvotes: 0

Views: 1310

Answers (1)

a-bobkov
a-bobkov

Reputation: 724

You should not return elements from page context. Return simple values. This example works for your index.html:

page.open('http://localhost/index.html', function(status) {
    if (status == 'success') {
        var products = page.evaluate(function() {
            return [].map.call(document.getElementsByClassName('test'), function(elem) {
                return elem.innerHTML;
            });
        });

        for(var i = 0; i < products.length; ++i) {
            if(products[i]) {
                console.log(products[i]);
            }
        }

        phantom.exit();
    } else {
        console.log('Unable to load the address!');
        phantom.exit();
    }
});

Upvotes: 1

Related Questions