Parsing xml file from url and loop to get all urls in it using node.js

Question

Parsing xml file from url and loop to get all urls in it using node.js

I'm using node module xml2js. My xml file is of the form.:

<?xml version="1.0" encoding="UTF-8" ?>
<?xml-stylesheet type="text/xsl"?>
    <?xml-stylesheet type="text/css" media="screen" href="some url" ?>
        <rss xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" version="2.0">
            <channel>
                <item>
                    <pubDate>Fri, 19 Sep 2014 18:00:08 GMT</pubDate>
                    <guid isPermaLink="false">http://www.example0.com</guid>
                </item>
                <item>
                    <pubDate>Fri, 19 Sep 2014 17:52:25 GMT</pubDate>
                    <guid isPermaLink="false">http://www.example1.com</guid>
                </item>
            </channel>
        </rss>

I want to get all the urls under <item><guid isPermaLink="false"> as an array.

I'm trying out the code, but it is for a locally stored xml file. Also, I'm unable to get the urls.:

var fs = require('fs'),
    xml2js = require('xml2js');

var parser = new xml2js.Parser();
parser.addListener('end', function(result) {
    console.dir(result);
    console.log('Done.');
});
fs.readFile(__dirname + '/foo.xml', function(err, data) {
    parser.parseString(data);
});

javascript
xml
node.js

Answer 1

You can use the sax-js module to extract URLs you need. The module you mentioned uses sax-js internally.

Here is the code (rough cuts):

'use strict';

var sax = require('sax');
var fs = require('fs');

var filePath = __dirname + '/' + 'foo.xml';
var isTextPending = false;

var saxStream = sax.createStream(true);
saxStream.on('error', function (e) {
  console.error(e);
});

saxStream.ontext = function (text) {
  if(isTextPending) {
    console.log(text);
    isTextPending = false;
  }
};

saxStream.on('opentag', function (node) {
  if(node.name === 'guid' && node.attributes.isPermaLink === 'false') {
    isTextPending = true;
  }
});

fs.createReadStream(filePath)
  .pipe(saxStream);

And the output is:

http://www.example0.com
http://www.example1.com

UPD:

To fetch XML from the internet to process it, use the request module:

var request = require('request');

var href = 'http://SOME_URL.xml';

request(href)
  .pipe(saxStream);