progs/app2.scala
changeset 93 4794759139ea
parent 92 e85600529ca5
child 96 9fcd3de53c06
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app2.scala	Sat Jun 15 09:23:18 2013 -0400
@@ -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)
+  }
+}
+