author | Christian Urban <urbanc@in.tum.de> |
Mon, 29 Oct 2012 12:31:31 +0000 | |
changeset 49 | d2c6852ca8da |
parent 7 | 73cf4406b773 |
permissions | -rw-r--r-- |
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("Visiting: " + n + " " + url) for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1) } }