--- a/progs/crawler3.scala Tue Mar 22 17:09:24 2016 +0000
+++ b/progs/crawler3.scala Wed Apr 06 11:51:33 2016 +0100
@@ -12,7 +12,7 @@
// regexes for URLs, for "my" domain and for email addresses
val http_pattern = """"https?://[^"]*"""".r
-val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
+val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r (*@\label{emailline}@*)
def unquote(s: String) = s.drop(1).dropRight(1)
@@ -27,7 +27,7 @@
else {
println(s"Visiting: $n $url")
val page = get_page(url)
- print_str(email_pattern.findAllIn(page).mkString("\n"))
+ print_str(email_pattern.findAllIn(page).mkString("\n")) (*@\label{mainline}@*)
for (u <- get_all_URLs(page).par) crawl(u, n - 1)
}
}