--- a/progs/crawler1.scala Thu Apr 16 19:15:46 2020 +0100
+++ b/progs/crawler1.scala Wed May 06 15:37:31 2020 +0100
@@ -10,18 +10,20 @@
Try(Source.fromURL(url)("ISO-8859-1").take(10000).mkString).
getOrElse { println(s" Problem with: $url"); ""}
}
-get_page("https://nms.kcl.ac.uk/christiana.urban/")
+
+// e.g. get_page("https://nms.kcl.ac.uk/christiana.urban/")
+
// regex for URLs
val http_pattern = """"https?://[^"]*"""".r /*@\label{httpline}@*/
-// drops the first and last character from a string
+// drops the first and last characters 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}@*/
-// naive version of crawl - searches until a given depth,
-// visits pages potentially more than once
+// a very naive version of crawl - searches until a given
+// depth, visits pages potentially more than once
def crawl(url: String, n: Int) : Unit = {
if (n == 0) ()
else {
@@ -31,6 +33,7 @@
}
// some starting URLs for the crawler
+
val startURL = """https://nms.kcl.ac.uk/christian.urban/"""
//val startURL = """https://nms.kcl.ac.uk/luc.moreau/"""