--- a/progs/crawler2.scala Thu Sep 26 10:36:24 2013 +0100
+++ b/progs/crawler2.scala Thu Sep 26 10:39:23 2013 +0100
@@ -5,7 +5,7 @@
import scala.util.matching.Regex
import scala.util._
-// gets the first ~10K of a page
+// gets the first ~10K of a web-page
def get_page(url: String) : String = {
Try(Source.fromURL(url).take(10000).mkString) getOrElse
{ println(s" Problem with: $url"); ""}
@@ -28,7 +28,7 @@
// visits pages potentially more than once
def crawl(url: String, n: Int) : Unit = {
if (n == 0) ()
- //else if (my_urls.findFirstIn(url) == None) ()
+ else if (my_urls.findFirstIn(url) == None) ()
else {
println(s"Visiting: $n $url")
for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)