--- a/progs/crawler2.scala Sat May 05 10:31:00 2018 +0100
+++ b/progs/crawler2.scala Fri Jun 01 15:28:37 2018 +0100
@@ -13,7 +13,8 @@
// regexes for URLs and "my" domain
val http_pattern = """"https?://[^"]*"""".r
-val my_urls = """urbanc""".r /*@\label{myurlline}@*/
+val my_urls = """urban""".r /*@\label{myurlline}@*/
+//val my_urls = """kcl.ac.uk""".r
def unquote(s: String) = s.drop(1).dropRight(1)
@@ -28,15 +29,16 @@
} /*@\label{changeendline}@*/
else {
println(s"Visiting: $n $url")
- for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
+ for (u <- get_all_URLs(get_page(url)).par) crawl(u, n - 1)
}
}
// starting URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc"""
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/bsc-projects-16.html"""
+val startURL = """https://nms.kcl.ac.uk/christian.urban/"""
+//val startURL = """https://nms.kcl.ac.uk/christian.urban/bsc-projects-17.html"""
+
// can now deal with depth 3 and beyond
-crawl(startURL, 2)
+crawl(startURL, 3)