progs/crawler2.scala
changeset 399 5c1fbb39c93e
parent 303 4439c56d96cf
child 415 4ae59fd3b174
--- a/progs/crawler2.scala	Tue Mar 22 17:09:24 2016 +0000
+++ b/progs/crawler2.scala	Wed Apr 06 11:51:33 2016 +0100
@@ -13,7 +13,7 @@
 
 // regexes for URLs and "my" domain
 val http_pattern = """"https?://[^"]*"""".r
-val my_urls = """urbanc""".r
+val my_urls = """urbanc""".r (*@\label{myurlline}@*) 
 
 def unquote(s: String) = s.drop(1).dropRight(1)
 
@@ -21,11 +21,11 @@
   http_pattern.findAllIn(page).map(unquote).toSet
 
 def crawl(url: String, n: Int) : Unit = {
-  if (n == 0) ()
+  if (n == 0) () (*@\label{changestartline}@*) 
   else if (my_urls.findFirstIn(url) == None) { 
     println(s"Visiting: $n $url")
     get_page(url); () 
-  }
+  } (*@\label{changeendline}@*) 
   else {
     println(s"Visiting: $n $url")
     for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)