Escuelita de Scala - Parte 4b - Indexamiento

gistfile1.scala

// RM: https://github.com/molekilla/ScalaRegPubRobot/blob/master/src/com/ecyware/web/robot/RegPubStorage.scala
 
def saveOrUpdate(items:Map[String,Object])  {
   // webdata is database
   // regpub is collection
   val ficha = if ( items.containsKey("ficha") ) Some(items("ficha").toString) else None
   
   if ( ficha.isDefined ) { 
       val document = items.asDBObject
       val existingItems = mongoCollection.find(document) 
       if ( existingItems.length == 0 )
       {
         mongoCollection += document
         println(String.format("Ficha added: %s", ficha.get))
       }
RM: ElasticSearch index
       this.indexRegPubDocument(document, ficha.get)
   }
 }
// RM: https://github.com/molekilla/ScalaRegPubRobot/blob/master/src/com/ecyware/web/robot/RegPubParser.scala
def parseCompany(url:String, html:String):Store =
  {
    if ( url.endsWith("&ID=0"))
    {
      Store("", Map.empty[String, String])
    }
    try {
    val document = Jsoup.parse(html)
    val page = document.select("div[id=CONSULTA]").select("table[border=0]").toSeq()
    
    // Ficha y Documento
    val fichaDocumentoTable = page.get(0).toTableCellsSeq 
    var nombre = page.get(2).toTableCellsSeq
    val tomoTable = page.get(3).toTableCellsSeq
    val fechaRegistroTable = page.get(4).toTableCellsSeq
    val escrituraTable = page.get(5).toTableCellsSeq
    val notariaTable = page.get(6).toTableCellsSeq
    val provinciaNotariaTable = page.get(7).toTableCellsSeq
    val domicilioTable = page.get(8).toTableCellsSeq
    val prendaTable = page.get(9).toTableCellsSeq
    val tasaUnicaTable = page.get(11).toTableCellsSeq
    val tasaUnicaAgenteResidente = page.get(12).toTableCellsSeq().get(1).text.trim
    val diarioTable = page.get(14).toTableCellsSeq()
    

    val idMap = Map(
        "ficha" -> fichaDocumentoTable.get(1).text.trim,
        "documento" -> fichaDocumentoTable.get(3).text.trim,
        "nombre" -> nombre.get(0).text.trim,
        "tomo" -> tomoTable.get(1).text.trim,
        "folio" -> tomoTable.get(3).text.trim,
        "asiento" -> tomoTable.get(5).text.trim,
        "fechaRegistro" ->  fechaRegistroTable.get(1).text.trim,
        "estado" -> fechaRegistroTable.get(3).text.trim,
        "fechaEscritura" -> escrituraTable.get(3).text.trim,
        "escritura" -> escrituraTable.get(1).text.trim,
        "notaria" -> (notariaTable.get(1).text.trim + " " + notariaTable.get(2).text.trim),
        "provinciaNotaria" -> provinciaNotariaTable.get(1).text.trim,
        "duracion" -> domicilioTable.get(1).text.trim,
        "domicilio" -> domicilioTable.get(3).text.trim,
        "prenda" -> (prendaTable.get(1).text.trim() + prendaTable.get(2).text.trim),
        "tasaUnicaBoleta" -> tasaUnicaTable.get(1).text.trim,
        "tasaUnicaFechaPago" -> tasaUnicaTable.get(3).text.trim,
        "tasaUnicaAgenteResidente" -> tasaUnicaAgenteResidente,
        "diarioTomo" -> diarioTable.get(1).text.trim,
        "diarioAsiento" -> diarioTable.get(3).text.trim,
        "dignatarios" -> page.getDignatarios,
        "subscriptores" -> page.getSubscribers,
        "directores" -> page.getDirectors
        ) ++ page.getMicro
    Store(url, idMap)
    }
    catch {
      case e: Exception =>
        Store("", Map.empty[String, String])
    }

  }