equal
deleted
inserted
replaced
3 |
3 |
4 import io.Source |
4 import io.Source |
5 import scala.util.matching.Regex |
5 import scala.util.matching.Regex |
6 import scala.util._ |
6 import scala.util._ |
7 |
7 |
8 // gets the first ~10K of a web-page |
8 // gets the first 10K of a web-page |
9 def get_page(url: String) : String = { |
9 def get_page(url: String) : String = { |
10 Try(Source.fromURL(url).take(10000).mkString) getOrElse |
10 Try(Source.fromURL(url).take(10000).mkString) getOrElse |
11 { println(s" Problem with: $url"); ""} |
11 { println(s" Problem with: $url"); ""} |
12 } |
12 } |
13 |
13 |
16 |
16 |
17 // drops the first and last character from a string |
17 // drops the first and last character from a string |
18 def unquote(s: String) = s.drop(1).dropRight(1) |
18 def unquote(s: String) = s.drop(1).dropRight(1) |
19 |
19 |
20 def get_all_URLs(page: String) : Set[String] = { |
20 def get_all_URLs(page: String) : Set[String] = { |
21 (http_pattern.findAllIn(page)).map { unquote(_) }.toSet |
21 http_pattern.findAllIn(page).map(unquote).toSet |
22 } |
22 } |
23 |
23 |
24 // naive version - seraches until a given depth |
24 // naive version - seraches until a given depth |
25 // visits pages potentially more than once |
25 // visits pages potentially more than once |
26 def crawl(url: String, n: Int) : Unit = { |
26 def crawl(url: String, n: Int) : Unit = { |
33 |
33 |
34 // staring URL for the crawler |
34 // staring URL for the crawler |
35 val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/""" |
35 val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/""" |
36 //val startURL = """http://www.inf.kcl.ac.uk/staff/mml/""" |
36 //val startURL = """http://www.inf.kcl.ac.uk/staff/mml/""" |
37 |
37 |
38 |
|
39 crawl(startURL, 2) |
38 crawl(startURL, 2) |
40 |
39 |