diff -r 0debe6f41396 -r 546f2090ce12 progs/crawler1.scala
--- a/progs/crawler1.scala	Tue Sep 20 12:47:46 2016 +0100
+++ b/progs/crawler1.scala	Fri Sep 23 15:22:33 2016 +0100
@@ -7,18 +7,18 @@
 
 // gets the first 10K of a web-page
 def get_page(url: String) : String = {
-  Try(Source.fromURL(url).take(10000).mkString) getOrElse 
+  Try(Source.fromURL(url)("ISO-8859-1").take(10000).mkString) getOrElse 
     { println(s"  Problem with: $url"); ""}
 }
 
 // regex for URLs
-val http_pattern = """"https?://[^"]*"""".r (*@\label{httpline}@*) 
+val http_pattern = """"https?://[^"]*"""".r /*@\label{httpline}@*/ 
 
 // drops the first and last character from a string
 def unquote(s: String) = s.drop(1).dropRight(1)
 
 def get_all_URLs(page: String) : Set[String] = 
-  http_pattern.findAllIn(page).map(unquote).toSet (*@\label{findallline}@*) 
+  http_pattern.findAllIn(page).map(unquote).toSet /*@\label{findallline}@*/
 
 
 // naive version of crawl - searches until a given depth,
@@ -32,8 +32,9 @@
 }
 
 // some starting URLs for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc"""
+//val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc"""
 //val startURL = """http://www.inf.kcl.ac.uk/staff/mcburney"""
+val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/bsc-projects-16.html"""
 
 crawl(startURL, 2)