--- a/progs/crawler1.scala Thu Sep 26 10:36:24 2013 +0100
+++ b/progs/crawler1.scala Thu Sep 26 10:39:23 2013 +0100
@@ -1,8 +1,11 @@
+// A crawler which checks whether there
+// are problems with links in web-pages
+
import io.Source
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"); ""}
@@ -11,6 +14,7 @@
// regex for URLs
val http_pattern = """\"https?://[^\"]*\"""".r
+// 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] = {
@@ -32,7 +36,5 @@
//val startURL = """http://www.inf.kcl.ac.uk/staff/mml/"""
-// call on the command line
crawl(startURL, 2)
-crawl("""http://www.inf.kcl.ac.uk/staff/urbanc/bsc-projects-13.html""", 2)