jobparser 0.4.2 → 0.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/jobparser/facets/deadline.rb +24 -0
- data/lib/jobparser/facets/facet.rb +3 -1
- data/lib/jobparser/parsehtml.rb +4 -0
- data/lib/jobparser/parser.rb +2 -1
- data/lib/jobparser/parseschema.rb +4 -0
- data/lib/jobparser/specialcases.rb +11 -0
- data/lib/jobparser/version.rb +1 -1
- data/lib/jobparser.rb +1 -0
- metadata +3 -2
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'date'
|
2
|
+
|
3
|
+
module JobParser
|
4
|
+
module Facets
|
5
|
+
class Deadline < Facet
|
6
|
+
def parse
|
7
|
+
special_case_result = use_special_case(:deadline)
|
8
|
+
return special_case_result unless special_case_result.nil?
|
9
|
+
|
10
|
+
regex = /(Apply before|Closing Date):\s*(.+)$/i
|
11
|
+
loop_over_elements { |name, elem|
|
12
|
+
regex.match(elem.content) { |m|
|
13
|
+
return Cleaner.strip_all_white_space(m[2])
|
14
|
+
}
|
15
|
+
}
|
16
|
+
|
17
|
+
regex.match(@plain_text) { |m|
|
18
|
+
# return Cleaner.strip_all_white_space(m[2])
|
19
|
+
}
|
20
|
+
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
data/lib/jobparser/parsehtml.rb
CHANGED
data/lib/jobparser/parser.rb
CHANGED
@@ -38,6 +38,17 @@ module JobParser
|
|
38
38
|
}
|
39
39
|
salary
|
40
40
|
}
|
41
|
+
},
|
42
|
+
"bfi.org.uk" => {
|
43
|
+
:deadline => Proc.new { |doc|
|
44
|
+
match = ""
|
45
|
+
doc.css(".block-container>p").each do |p|
|
46
|
+
/The closing date for this position is (.+)\./.match(p.content) { |m|
|
47
|
+
match = m[1]
|
48
|
+
}
|
49
|
+
end
|
50
|
+
match
|
51
|
+
}
|
41
52
|
}
|
42
53
|
}
|
43
54
|
end
|
data/lib/jobparser/version.rb
CHANGED
data/lib/jobparser.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: jobparser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.5.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-07-
|
12
|
+
date: 2013-07-31 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bundler
|
@@ -100,6 +100,7 @@ extra_rdoc_files: []
|
|
100
100
|
files:
|
101
101
|
- lib/jobparser/cleaner.rb
|
102
102
|
- lib/jobparser/facets/apply.rb
|
103
|
+
- lib/jobparser/facets/deadline.rb
|
103
104
|
- lib/jobparser/facets/facet.rb
|
104
105
|
- lib/jobparser/facets/location.rb
|
105
106
|
- lib/jobparser/facets/salary.rb
|