app4.scala
changeset 7 73cf4406b773
child 13 6d554a18b81e
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/app4.scala	Thu Sep 27 11:59:41 2012 +0100
@@ -0,0 +1,15 @@
+val http_pattern = """\"https?://[^\"]*\"""".r
+val my_urls = """urbanc""".r
+val email_pattern = 
+  """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
+
+def crawl(url: String, n: Int) : Unit = {
+  if (n == 0) ()
+  //else if (my_urls.findFirstIn(url) == None) ()
+  else {
+    println("Visiting: " + n + " " + url)
+    val page = get_page(url)
+    println(email_pattern.findAllIn(page).mkString("\n"))
+    for (u <- get_all_URLs(page)) crawl(u, n - 1)
+  }
+}