app4.scala
author Christian Urban <urbanc@in.tum.de>
Tue, 09 Oct 2012 13:34:30 +0100
changeset 22 1efa38ee7237
parent 13 6d554a18b81e
permissions -rw-r--r--
added

val http_pattern = """\"https?://[^\"]*\"""".r
val my_urls = """urbanc""".r
val email_pattern = 
  """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r

def crawl(url: String, n: Int) : Unit = {
  if (n == 0) ()
  else {
    println("Visiting: " + n + " " + url)
    val page = get_page(url)
    println(email_pattern.findAllIn(page).mkString("\n"))
    for (u <- get_all_URLs(page)) crawl(u, n - 1)
  }
}