Sunday 21 May 2017

Unable to parse xml to json properly

I'm trying to parse a xml to json & i'm using xml2js in nodejs. Below is my code

var chai = require('chai');
var chaiHttp = require('chai-http');
var request = chai.request;
var should = chai.should();
var expect = chai.expect;
var assert = chai.assert;
var supertest = require('supertest');
var fs = require('fs');
var xmlLocation = "./configdata/xmlDoc.xml";

var xml2js = require('xml2js');
var parser = new xml2js.Parser();

//Plugin for HTTP, etc.
chai.use(chaiHttp);
process.env['NODE_TLS_REJECT_UNAUTHORIZED'] = '0';

//xmlFile = JSON.parse(fs.readFileSync(xmlData, 'utf8'));


describe("Test : ", function () {

    it("convert xml to json", function (done) {

        r = fs.readFileSync(xmlLocation, 'UTF-8');
        parser.parseString(r, function (err, parsedData) {
            if (err) throw err;
            else {
                fs.writeFile("jsonData.json", JSON.stringify(parsedData), function (err, response) {
                });
            }
        });

        done();
    });

})

My sample xml file :

<?xml version="1.0" encoding="UTF-8" ?>
<ALEXA>
    <SD TITLE="A" FLAGS="" HOST="davidwalsh.name">
        <TITLE TEXT="David Walsh Blog :: PHP, MySQL, CSS, Javascript, MooTools, and Everything Else"/>
        <LINKSIN NUM="1102"/>
        <SPEED TEXT="1421" PCT="51"/>
    </SD>
    <SD>
        <POPULARITY URL="davidwalsh.name/" TEXT="7131"/>
        <REACH RANK="5952"/>
        <RANK DELTA="-1648"/>
    </SD>
</ALEXA>

I'm getting the below output :

{
  "ALEXA": {
    "SD": [
      {
        "$": {
          "TITLE": "A",
          "FLAGS": "",
          "HOST": "davidwalsh.name"
        },
        "TITLE": [
          {
            "$": {
              "TEXT": "David Walsh Blog :: PHP, MySQL, CSS, Javascript, MooTools, and Everything Else"
            }
          }
        ],
        "LINKSIN": [
          {
            "$": {
              "NUM": "1102"
            }
          }
        ],
        "SPEED": [
          {
            "$": {
              "TEXT": "1421",
              "PCT": "51"
            }
          }
        ]
      },
      {
        "POPULARITY": [
          {
            "$": {
              "URL": "davidwalsh.name/",
              "TEXT": "7131"
            }
          }
        ],
        "REACH": [
          {
            "$": {
              "RANK": "5952"
            }
          }
        ],
        "RANK": [
          {
            "$": {
              "DELTA": "-1648"
            }
          }
        ]
      }
    ]
  }
}

'$' is getting added to the parsed json. How to avoid it..??

Looking for a solution. Thanks in advance.



via Sandeep Teja Mummoji

No comments:

Post a Comment