kabutops 0.0.12 → 0.0.13
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.
- checksums.yaml +4 -4
- data/README.md +1 -1
- data/lib/kabutops/crawler.rb +9 -0
- data/lib/kabutops/recipe.rb +2 -2
- data/lib/kabutops/recipe_item.rb +21 -3
- data/lib/kabutops/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2079759508e14efc73da0711fefa3bafa7e2cffa
|
4
|
+
data.tar.gz: 0034b70dbeca4dafd3471125f47392a4c7e98693
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5315b48bff4207c58ff56242120cf6c9feb5297b29d668607241238ff9f1e0f01df16bf0ed45367b927690f6c55480b212761aec3dda0261a6af3ade1676e6b7
|
7
|
+
data.tar.gz: c00e64003cd9b3bb26685ed74dd16052e9b952cfa5e89baf0cf36f35d4d2cca77e3ee618c50d68f82d3e15aa2d239d45aebadea33b774ec507813ce15abfeb51
|
data/README.md
CHANGED
data/lib/kabutops/crawler.rb
CHANGED
@@ -75,6 +75,8 @@ module Kabutops
|
|
75
75
|
|
76
76
|
page = crawl(resource)
|
77
77
|
|
78
|
+
return if page.nil?
|
79
|
+
|
78
80
|
adapters.each do |adapter|
|
79
81
|
adapter.process(resource, page)
|
80
82
|
end
|
@@ -113,6 +115,13 @@ module Kabutops
|
|
113
115
|
page = Nokogiri::HTML(content) if page.nil?
|
114
116
|
self.class.notify(:after_crawl, resource, page)
|
115
117
|
page
|
118
|
+
rescue Mechanize::ResponseCodeError => e
|
119
|
+
if e.response_code.to_i == 404
|
120
|
+
nil
|
121
|
+
else
|
122
|
+
p e.response_code
|
123
|
+
raise
|
124
|
+
end
|
116
125
|
end
|
117
126
|
|
118
127
|
def agent
|
data/lib/kabutops/recipe.rb
CHANGED
@@ -17,8 +17,8 @@ module Kabutops
|
|
17
17
|
@items[name] = RecipeItem.new(:recipe, recipe)
|
18
18
|
@nested = true
|
19
19
|
else
|
20
|
-
type, value = args[0..
|
21
|
-
@items[name] = RecipeItem.new(type, value)
|
20
|
+
type, value, convert_to = args[0..2]
|
21
|
+
@items[name] = RecipeItem.new(type, value, convert_to)
|
22
22
|
end
|
23
23
|
end
|
24
24
|
|
data/lib/kabutops/recipe_item.rb
CHANGED
@@ -5,27 +5,45 @@ module Kabutops
|
|
5
5
|
class RecipeItem
|
6
6
|
attr_reader :type, :value
|
7
7
|
|
8
|
-
def initialize type, value
|
8
|
+
def initialize type, value, convert_to=nil
|
9
9
|
@type = type
|
10
10
|
@value = value
|
11
|
+
@convert_to = convert_to
|
11
12
|
end
|
12
13
|
|
13
14
|
def process resource, page
|
15
|
+
convert(get(resource, page))
|
16
|
+
end
|
17
|
+
|
18
|
+
protected
|
19
|
+
|
20
|
+
def get resource, page
|
14
21
|
case @type
|
15
22
|
when :var
|
16
23
|
resource[@value]
|
17
24
|
when :recipe
|
18
25
|
@value.process(resource, page)
|
19
26
|
when :css
|
20
|
-
page.css(@value).text
|
27
|
+
page.css(@value).text.gsub(/\u00a0/, ' ').strip
|
21
28
|
when :xpath
|
22
|
-
page.xpath(@value).text
|
29
|
+
page.xpath(@value).text.gsub(/\u00a0/, ' ').strip
|
23
30
|
when :lambda, :proc
|
24
31
|
@value.call(resource, page)
|
25
32
|
else
|
26
33
|
raise "unknown recipe item type '#{item.type}'"
|
27
34
|
end
|
28
35
|
end
|
36
|
+
|
37
|
+
def convert v
|
38
|
+
return nil if v.nil?
|
39
|
+
|
40
|
+
case @convert_to
|
41
|
+
when nil then v
|
42
|
+
when :int then v[/\d+/].to_i
|
43
|
+
when :float then v[/\d+(\.\d+)?/].to_f
|
44
|
+
end
|
45
|
+
end
|
29
46
|
end
|
30
47
|
|
48
|
+
|
31
49
|
end
|
data/lib/kabutops/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: kabutops
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.13
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Rene Klacan
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-07-
|
11
|
+
date: 2014-07-17 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|