diff -r 0debe6f41396 -r 546f2090ce12 progs/crawler2.scala
--- a/progs/crawler2.scala	Tue Sep 20 12:47:46 2016 +0100
+++ b/progs/crawler2.scala	Fri Sep 23 15:22:33 2016 +0100
@@ -7,13 +7,13 @@
 
 // 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"); ""}
 }
 
 // regexes for URLs and "my" domain
 val http_pattern = """"https?://[^"]*"""".r
-val my_urls = """urbanc""".r       (*@\label{myurlline}@*) 
+val my_urls = """urbanc""".r       /*@\label{myurlline}@*/
 
 def unquote(s: String) = s.drop(1).dropRight(1)
 
@@ -21,11 +21,11 @@
   http_pattern.findAllIn(page).map(unquote).toSet
 
 def crawl(url: String, n: Int) : Unit = {
-  if (n == 0) ()                   (*@\label{changestartline}@*) 
+  if (n == 0) ()                   /*@\label{changestartline}@*/
   else if (my_urls.findFirstIn(url) == None) { 
     println(s"Visiting: $n $url")
     get_page(url); () 
-  }                                (*@\label{changeendline}@*) 
+  }                                /*@\label{changeendline}@*/
   else {
     println(s"Visiting: $n $url")
     for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)