changeset 92 | e85600529ca5 |
parent 91 | 47f86885d481 |
child 93 | 4794759139ea |
--- a/app2.scala Sun Dec 23 00:38:56 2012 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,16 +0,0 @@ -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) - } -} -