Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place.

1
require 'uri'
2

3
class Anemone::Extractors::Generic < Anemone::Extractors::Base
4

5
  def run
6
    URI.extract( doc.to_s, %w(http https) ).map do |u|
7
      #
8
      # This extractor needs to be a tiny bit intelligent because
9
      # due to its generic nature it'll inevitably match some garbage.
10
      #
11
      # For example, if some JS code contains:
12
      #
13
      #	var = 'http://blah.com?id=1'
14
      #
15
      # or
16
      #
17
      #	var = { 'http://blah.com?id=1', 1 }
18
      #
19
      #
20
      # The URI.extract call will match:
21
      #
22
      #	http://blah.com?id=1'
23
      #
24
      # and
25
      #
26
      #	http://blah.com?id=1',
27
      #
28
      # respectively.
29
      #
30
      if !includes_quotes?( u )
31
        u
32
      else
33
        if html.include?( "'#{u}" )
34
          u.split( '\'' ).first
35
        elsif html.include?( "\"#{u}" )
36
          u.split( '"' ).first
37
        else
38
          u
39
        end
40
      end
41
    end
42
  rescue
43
    []
44
  end
45

46
  def includes_quotes?( url )
47
    url.include?( '\'' ) || url.include?( '"' )
48
  end
49

50
end
51

52