--- a/progs/crawler1.scala Sat May 05 10:31:00 2018 +0100
+++ b/progs/crawler1.scala Fri Jun 01 15:28:37 2018 +0100
@@ -20,7 +20,6 @@
def get_all_URLs(page: String) : Set[String] =
http_pattern.findAllIn(page).map(unquote).toSet /*@\label{findallline}@*/
-
// naive version of crawl - searches until a given depth,
// visits pages potentially more than once
def crawl(url: String, n: Int) : Unit = {
@@ -32,9 +31,8 @@
}
// 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/mcburney"""
+val startURL = """https://nms.kcl.ac.uk/christian.urban/"""
+//val startURL = """https://nms.kcl.ac.uk/luc.moreau/"""
+crawl(startURL, 3)
-crawl(startURL, 2)
-