diff -r b606c9439fa6 -r 6e7da958ba8c app1.scala
--- a/app1.scala	Wed Sep 26 02:08:55 2012 +0100
+++ b/app1.scala	Wed Sep 26 02:50:44 2012 +0100
@@ -1,7 +1,3 @@
-import io.Source
-import scala.util.matching.Regex
-
-// gets the first ~10K of a page
 def get_page(url: String) : String = { 
   try {
     Source.fromURL(url).take(10000).mkString  
@@ -14,27 +10,3 @@
   }
 }
 
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
-
-// regex for URLs
-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
-}
-
-// naive version - seraches until a given depth
-// visits pages potentially more than once
-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)
-  }
-}
-
-crawl(startURL, 2)
-