changeset 7 | 73cf4406b773 |
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/app2.scala Thu Sep 27 11:59:41 2012 +0100 @@ -0,0 +1,16 @@ +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) + } +} +