Extracts data from http://www.nuforc.org and writes it to a .CSV file

Driver.scala

import java.io.{File, PrintWriter}

import org.jsoup.Jsoup
import org.jsoup.nodes.Element
import collection.JavaConversions._

/**
 * Created by josh on 3/20/15.
 * 
 * Extracts data from http://www.nuforc.org and writes it to a .CSV file
 */
object Driver {

  val indexURL = "http://www.nuforc.org/webreports/ndxevent.html"
  val numPages = 50

  def getPageURLs = {
    Jsoup.connect(indexURL).get()
      .select("table a")
      .map(_.attr("abs:href"))
      .toVector
  }

  case class RowData(date: String, city: String, state: String, shape: String, duration: String, summary: String)

  def getRowData(row: Element) = {
    val data = row
      .select("td")
      .map(_.text())
      .toVector
    RowData(data.head, data(1), data(2), data(3), data(4), data(5))
  }

  def getData(url: String) = {
    println(s"Extracting data from $url")
    Jsoup.connect(url).get()
      .select("tr:not(:first-child)")
      .map(getRowData)
      .toVector
  }

  def writeCsv(data: Vector[RowData]): Unit = {
    println("Writing .CSV file")
    val p = new PrintWriter(new File("./data.csv"))
    data.foreach(row => p.println(row.productIterator.mkString("\t")))
    p.close()
  }

  def main(args: Array[String]) {
    val urls = getPageURLs
    val data = urls
      .take(numPages)
      .flatMap(getData)
    println(s"${data.size} entries extracted")
    writeCsv(data)
  }

}