klepto 0.4.8 → 0.4.9
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/klepto/parser.rb +16 -0
- data/lib/klepto/structure.rb +5 -1
- data/lib/klepto/version.rb +1 -1
- data/spec/lib/klepto/bot_spec.rb +15 -0
- data/spec/spec_helper.rb +11 -0
- metadata +12 -11
data/lib/klepto/structure.rb
CHANGED
@@ -29,8 +29,13 @@ module Klepto
|
|
29
29
|
options[:attr] ||= nil
|
30
30
|
options[:default] ||= nil
|
31
31
|
options[:limit] ||= nil
|
32
|
+
options[:parser] ||= nil
|
32
33
|
selector = args.shift
|
33
34
|
|
35
|
+
if !block_given? && options[:parser]
|
36
|
+
block = options[:parser].new
|
37
|
+
end
|
38
|
+
|
34
39
|
Klepto.logger.debug("\t\tDefining attribute: #{meth} -> #{selector}")
|
35
40
|
|
36
41
|
if options[:as] == :collection
|
@@ -48,7 +53,6 @@ module Klepto
|
|
48
53
|
result = _context.first( options[:syntax], selector )
|
49
54
|
Klepto.logger.debug("\t\t\tAs: resource, Result? #{!result.nil?}")
|
50
55
|
@_hash[meth] = Structure.build(result, self, &block)
|
51
|
-
|
52
56
|
elsif block
|
53
57
|
result = selector ?
|
54
58
|
_context.send( options[:match], options[:syntax], selector ) : _context
|
data/lib/klepto/version.rb
CHANGED
data/spec/lib/klepto/bot_spec.rb
CHANGED
@@ -247,6 +247,21 @@ describe Klepto::Bot do
|
|
247
247
|
end
|
248
248
|
end
|
249
249
|
|
250
|
+
describe 'structuring with a Parser' do
|
251
|
+
before(:each) do
|
252
|
+
@bot = Klepto::Bot.new("https://twitter.com/justinbieber"){
|
253
|
+
name 'h1.fullname', parser: TextParser
|
254
|
+
links 'span.url a', :match => :all, :parser => HrefParser
|
255
|
+
}
|
256
|
+
@structure = @bot.resources
|
257
|
+
end
|
258
|
+
|
259
|
+
it 'should structure the data' do
|
260
|
+
@structure.first[:name].should match(/Justin/i)
|
261
|
+
@structure.first[:links].first.should match(/^http:/i)
|
262
|
+
end
|
263
|
+
end
|
264
|
+
|
250
265
|
describe 'creating a bot with a node limit' do
|
251
266
|
before(:each) do
|
252
267
|
@bot = Klepto::Bot.new("https://twitter.com/justinbieber"){
|
data/spec/spec_helper.rb
CHANGED
@@ -7,6 +7,7 @@ SimpleCov.start do
|
|
7
7
|
end
|
8
8
|
|
9
9
|
require 'klepto'
|
10
|
+
require 'klepto/parser'
|
10
11
|
require 'vcr'
|
11
12
|
require 'orm/active_record'
|
12
13
|
|
@@ -33,4 +34,14 @@ RSpec.configure do |config|
|
|
33
34
|
config.after(:all) { TestMigration.down }
|
34
35
|
config.treat_symbols_as_metadata_keys_with_true_values = true
|
35
36
|
#config.filter_run_including :only => true
|
37
|
+
end
|
38
|
+
|
39
|
+
class TextParser
|
40
|
+
include Klepto::Parser
|
41
|
+
end
|
42
|
+
class HrefParser
|
43
|
+
include Klepto::Parser
|
44
|
+
def call(node)
|
45
|
+
node[:href]
|
46
|
+
end
|
36
47
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: klepto
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.4.
|
4
|
+
version: 0.4.9
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -13,7 +13,7 @@ date: 2013-05-30 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: poltergeist
|
16
|
-
requirement: &
|
16
|
+
requirement: &70325624163420 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - =
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: 1.1.0
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *70325624163420
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: capybara
|
27
|
-
requirement: &
|
27
|
+
requirement: &70325624162920 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - =
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: 2.0.2
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *70325624162920
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70325624162460 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ~>
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: 1.5.6
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *70325624162460
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: activesupport
|
49
|
-
requirement: &
|
49
|
+
requirement: &70325624162080 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :runtime
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *70325624162080
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: multi_json
|
60
|
-
requirement: &
|
60
|
+
requirement: &70325624161540 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,7 +65,7 @@ dependencies:
|
|
65
65
|
version: '1.0'
|
66
66
|
type: :runtime
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *70325624161540
|
69
69
|
description: Tearing up web pages into ActiveRecord resources
|
70
70
|
email:
|
71
71
|
- github@coryodaniel.com
|
@@ -86,6 +86,7 @@ files:
|
|
86
86
|
- lib/klepto/bot.rb
|
87
87
|
- lib/klepto/browser.rb
|
88
88
|
- lib/klepto/config.rb
|
89
|
+
- lib/klepto/parser.rb
|
89
90
|
- lib/klepto/structure.rb
|
90
91
|
- lib/klepto/tasks.rb
|
91
92
|
- lib/klepto/version.rb
|