read-xml-stream.coffee

http      = require 'http'
through   = require 'through'
XmlStream = require 'xml-stream'

http.get 'http://example.com/file.xml', (res) ->
  res.setEncoding 'utf-8'
  res.on 'error', console.error

  # create a stream to clean non-ascii characters, because
  # XmlStream fails to parse XMLs with some chars (pasted from MS Word, mostly)
  tr = through (buffer) ->
    data = buffer.toString().replace(/[^\x00-\xFF]/g, '')
    @emit 'data', data

  # pipe for new stream
  res.pipe tr

  # process xml
  xml = new XmlStream(tr)

  xml.collect 'node subnode' #collect elements to array
  xml.on 'updateElement: node', (node) ->
    # output for testing
    console.log JSON.stringify node, null, ' '