progs/app2.scala
author Christian Urban <christian dot urban at kcl dot ac dot uk>
Tue, 24 Sep 2013 01:56:53 +0100
changeset 96 9fcd3de53c06
parent 93 4794759139ea
child 97 60a3ba90dd53
permissions -rw-r--r--
updated

val http_pattern = """\"https?://[^\"]*\"""".r

def unquote(s: String) = s.drop(1).dropRight(1)

def get_all_URLs(page: String) : Set[String] = {
  http_pattern.findAllIn(page).map(unquote).toSet
}

def crawl(url: String, n: Int) : Unit = {
  if (n == 0) ()
  else {
    println(s"Visiting: $n $url")
    for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
  }
}