author | Christian Urban <christian.urban@kcl.ac.uk> |
Sat, 09 Nov 2024 06:31:45 +0000 | |
changeset 973 | f25d338d16c9 |
parent 722 | 14914b57e207 |
permissions | -rw-r--r-- |
242
35104ee14f87
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
112
diff
changeset
|
1 |
// A crawler which checks whether there are |
35104ee14f87
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
112
diff
changeset
|
2 |
// dead links in web-pages |
101
4758a6155878
links
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
99
diff
changeset
|
3 |
|
1 | 4 |
import io.Source |
5 |
import scala.util.matching.Regex |
|
96
9fcd3de53c06
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
6 |
import scala.util._ |
1 | 7 |
|
112
95ee5cc5c05d
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
101
diff
changeset
|
8 |
// gets the first 10K of a web-page |
99
91145f6d9b0e
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
96
diff
changeset
|
9 |
def get_page(url: String) : String = { |
428
a47c4227a0c6
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
427
diff
changeset
|
10 |
Try(Source.fromURL(url)("ISO-8859-1").take(10000).mkString). |
a47c4227a0c6
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
427
diff
changeset
|
11 |
getOrElse { println(s" Problem with: $url"); ""} |
99
91145f6d9b0e
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
96
diff
changeset
|
12 |
} |
722 | 13 |
|
14 |
// e.g. get_page("https://nms.kcl.ac.uk/christiana.urban/") |
|
15 |
||
1 | 16 |
// regex for URLs |
427
546f2090ce12
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
421
diff
changeset
|
17 |
val http_pattern = """"https?://[^"]*"""".r /*@\label{httpline}@*/ |
1 | 18 |
|
722 | 19 |
// drops the first and last characters from a string |
1 | 20 |
def unquote(s: String) = s.drop(1).dropRight(1) |
21 |
||
254
dcd4688690ce
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
242
diff
changeset
|
22 |
def get_all_URLs(page: String) : Set[String] = |
427
546f2090ce12
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
421
diff
changeset
|
23 |
http_pattern.findAllIn(page).map(unquote).toSet /*@\label{findallline}@*/ |
254
dcd4688690ce
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
242
diff
changeset
|
24 |
|
722 | 25 |
// a very naive version of crawl - searches until a given |
26 |
// depth, visits pages potentially more than once |
|
1 | 27 |
def crawl(url: String, n: Int) : Unit = { |
28 |
if (n == 0) () |
|
29 |
else { |
|
95
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
30 |
println(s"Visiting: $n $url") |
1 | 31 |
for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1) |
32 |
} |
|
33 |
} |
|
34 |
||
242
35104ee14f87
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
112
diff
changeset
|
35 |
// some starting URLs for the crawler |
722 | 36 |
|
550 | 37 |
val startURL = """https://nms.kcl.ac.uk/christian.urban/""" |
38 |
//val startURL = """https://nms.kcl.ac.uk/luc.moreau/""" |
|
7 | 39 |
|
561 | 40 |
crawl(startURL, 2) |
432
55be90b2a642
added pictures
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
428
diff
changeset
|
41 |