--- a/progs/crawler2.scala Sun Sep 07 08:37:44 2014 +0100
+++ b/progs/crawler2.scala Sat Sep 13 04:30:25 2014 +0100
@@ -12,7 +12,7 @@
}
// regexes for URLs and "my" domain
-val http_pattern = """\"https?://[^\"]*\"""".r
+val http_pattern = """"https?://[^"]*"""".r
val my_urls = """urbanc""".r
def unquote(s: String) = s.drop(1).dropRight(1)
@@ -33,8 +33,8 @@
}
}
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
+// starting URL for the crawler
+val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc"""
// can now deal with depth 3 and beyond
crawl(startURL, 3)