scrap_kit 0.1.2 → 0.1.7
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/.github/workflows/run_tests.yml +20 -0
- data/CHANGELOG.md +23 -0
- data/Gemfile.lock +17 -9
- data/lib/scrap_kit/recipe.rb +16 -4
- data/lib/scrap_kit/version.rb +1 -1
- data/scrap_kit.gemspec +3 -2
- metadata +27 -13
- data/.github/workflows/publish_gem.yml +0 -17
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 9b98409a1148b80bc3f7a908779d3881f36fe3f8a8de2e1726135ea6488e24b2
|
4
|
+
data.tar.gz: a5b66ae5611527e93bee6167dfd4d365822f4122258054c781b09a290644ad80
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 863a0c56ada01470ff55e655c8a1dfa2159d05aa3da5cf3107c7a48509ee31e292bd383955d4e45c2b5f1962f7ea659b5d893c6cd5a8d63fd4d72000b975f137
|
7
|
+
data.tar.gz: 9a1345ee740fbfcab5b984be2ecb9c6b57a23a715bd19e7cc77c002cc4e0a4115cb9eeed52c6cd1672f4ff7b6eb9c7082d4bc4173b5c5d3e37f2fa17db2bfce8
|
@@ -0,0 +1,20 @@
|
|
1
|
+
name: Run tests
|
2
|
+
|
3
|
+
on: [push]
|
4
|
+
|
5
|
+
jobs:
|
6
|
+
test:
|
7
|
+
|
8
|
+
runs-on: ubuntu-latest
|
9
|
+
|
10
|
+
steps:
|
11
|
+
- uses: actions/checkout@v1
|
12
|
+
- name: Setup Ruby
|
13
|
+
uses: actions/setup-ruby@v1
|
14
|
+
with:
|
15
|
+
ruby-version: '2.7.1'
|
16
|
+
- name: Build and run tests
|
17
|
+
run: |
|
18
|
+
gem install bundler
|
19
|
+
bundle update --conservative --jobs 4 --retry 3
|
20
|
+
bundle exec rake spec
|
data/CHANGELOG.md
CHANGED
@@ -1,5 +1,27 @@
|
|
1
1
|
# Changelog
|
2
2
|
|
3
|
+
## [0.1.7] 2020-08-28
|
4
|
+
- Match selector condition by regexp or exact value
|
5
|
+
|
6
|
+
## [0.1.6] 2020-08-28
|
7
|
+
- Update activesupport requirement from = 6.0.2.1 to ~> 6.0
|
8
|
+
- Fix bug when matching selector condition
|
9
|
+
|
10
|
+
## [0.1.5] 2020-08-08
|
11
|
+
|
12
|
+
### Changed/Added
|
13
|
+
- Add `webdrivers` as dependency
|
14
|
+
|
15
|
+
## [0.1.4] 2020-07-12
|
16
|
+
|
17
|
+
### Changed/Added
|
18
|
+
- Add support for `<input />` elements
|
19
|
+
|
20
|
+
## [0.1.3] 2020-06-18
|
21
|
+
|
22
|
+
### Changed/Added
|
23
|
+
- Moved development dependencies as dependencies
|
24
|
+
|
3
25
|
## [0.1.2] 2020-06-18
|
4
26
|
|
5
27
|
### Changed/Added
|
@@ -9,6 +31,7 @@
|
|
9
31
|
|
10
32
|
### Changed/Added
|
11
33
|
- Update activesupport requirement from = 6.0.2.1 to = 6.0.3.1
|
34
|
+
- Update rake requirement from ~> 10.0 to ~> 13.0
|
12
35
|
|
13
36
|
## [0.1.0] 2020-02-09
|
14
37
|
|
data/Gemfile.lock
CHANGED
@@ -1,25 +1,31 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
scrap_kit (0.1.
|
4
|
+
scrap_kit (0.1.7)
|
5
|
+
activesupport (~> 6.0)
|
6
|
+
watir (~> 6.16.5)
|
7
|
+
webdrivers (~> 4.0)
|
5
8
|
|
6
9
|
GEM
|
7
10
|
remote: https://rubygems.org/
|
8
11
|
specs:
|
9
|
-
activesupport (6.0.3.
|
12
|
+
activesupport (6.0.3.2)
|
10
13
|
concurrent-ruby (~> 1.0, >= 1.0.2)
|
11
14
|
i18n (>= 0.7, < 2)
|
12
15
|
minitest (~> 5.1)
|
13
16
|
tzinfo (~> 1.1)
|
14
17
|
zeitwerk (~> 2.2, >= 2.2.2)
|
15
18
|
childprocess (3.0.0)
|
16
|
-
concurrent-ruby (1.1.
|
19
|
+
concurrent-ruby (1.1.7)
|
17
20
|
diff-lcs (1.3)
|
18
|
-
i18n (1.8.
|
21
|
+
i18n (1.8.5)
|
19
22
|
concurrent-ruby (~> 1.0)
|
23
|
+
mini_portile2 (2.4.0)
|
20
24
|
minitest (5.14.1)
|
25
|
+
nokogiri (1.10.10)
|
26
|
+
mini_portile2 (~> 2.4.0)
|
21
27
|
rake (13.0.1)
|
22
|
-
regexp_parser (1.
|
28
|
+
regexp_parser (1.7.1)
|
23
29
|
rspec (3.9.0)
|
24
30
|
rspec-core (~> 3.9.0)
|
25
31
|
rspec-expectations (~> 3.9.0)
|
@@ -33,7 +39,7 @@ GEM
|
|
33
39
|
diff-lcs (>= 1.2.0, < 2.0)
|
34
40
|
rspec-support (~> 3.9.0)
|
35
41
|
rspec-support (3.9.2)
|
36
|
-
rubyzip (2.
|
42
|
+
rubyzip (2.3.0)
|
37
43
|
selenium-webdriver (3.142.7)
|
38
44
|
childprocess (>= 0.5, < 4.0)
|
39
45
|
rubyzip (>= 1.2.2)
|
@@ -43,18 +49,20 @@ GEM
|
|
43
49
|
watir (6.16.5)
|
44
50
|
regexp_parser (~> 1.2)
|
45
51
|
selenium-webdriver (~> 3.6)
|
46
|
-
|
52
|
+
webdrivers (4.4.1)
|
53
|
+
nokogiri (~> 1.6)
|
54
|
+
rubyzip (>= 1.3.0)
|
55
|
+
selenium-webdriver (>= 3.0, < 4.0)
|
56
|
+
zeitwerk (2.4.0)
|
47
57
|
|
48
58
|
PLATFORMS
|
49
59
|
ruby
|
50
60
|
|
51
61
|
DEPENDENCIES
|
52
|
-
activesupport (= 6.0.3.1)
|
53
62
|
bundler (~> 2.0)
|
54
63
|
rake (~> 13.0)
|
55
64
|
rspec (~> 3.0)
|
56
65
|
scrap_kit!
|
57
|
-
watir (~> 6.16.5)
|
58
66
|
|
59
67
|
BUNDLED WITH
|
60
68
|
2.1.4
|
data/lib/scrap_kit/recipe.rb
CHANGED
@@ -1,4 +1,5 @@
|
|
1
1
|
require "active_support/core_ext/hash"
|
2
|
+
require "webdrivers/chromedriver"
|
2
3
|
require "watir"
|
3
4
|
|
4
5
|
module ScrapKit
|
@@ -44,17 +45,28 @@ module ScrapKit
|
|
44
45
|
end
|
45
46
|
|
46
47
|
elements.filter do |element|
|
47
|
-
condition_key = condition.keys
|
48
|
-
condition_value = condition.values
|
48
|
+
condition_key = condition.keys.first.to_s
|
49
|
+
condition_value = condition.values.first
|
49
50
|
found_element = element.element(css: condition_key)
|
50
|
-
found_element
|
51
|
+
extracted_value = extract_value_from_element(found_element)
|
52
|
+
extracted_value.match(condition_value) || extracted_value == condition_value
|
51
53
|
end
|
52
54
|
end
|
53
55
|
end
|
54
56
|
|
57
|
+
def extract_value_from_element(element)
|
58
|
+
if element&.respond_to?(:tag_name)
|
59
|
+
if element.tag_name.downcase == "input"
|
60
|
+
return element.attribute_value(:value)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
element&.text_content
|
65
|
+
end
|
66
|
+
|
55
67
|
def extract_attribute(browser_or_element, selector_or_hash)
|
56
68
|
if selector_or_hash.is_a?(String)
|
57
|
-
browser_or_element.element(css: selector_or_hash)
|
69
|
+
extract_value_from_element(browser_or_element.element(css: selector_or_hash))
|
58
70
|
elsif selector_or_hash.is_a?(Hash)
|
59
71
|
selector = selector_or_hash[:selector]
|
60
72
|
selector_for_children_attributes = selector_or_hash[:children_attributes]
|
data/lib/scrap_kit/version.rb
CHANGED
data/scrap_kit.gemspec
CHANGED
@@ -31,6 +31,7 @@ Gem::Specification.new do |spec|
|
|
31
31
|
spec.add_development_dependency "bundler", "~> 2.0"
|
32
32
|
spec.add_development_dependency "rake", "~> 13.0"
|
33
33
|
spec.add_development_dependency "rspec", "~> 3.0"
|
34
|
-
spec.
|
35
|
-
spec.
|
34
|
+
spec.add_dependency "watir", "~> 6.16.5"
|
35
|
+
spec.add_dependency "webdrivers", "~> 4.0"
|
36
|
+
spec.add_dependency "activesupport", "~> 6.0"
|
36
37
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scrap_kit
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Gustavo Leon
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-08-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -53,33 +53,47 @@ dependencies:
|
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '3.0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: watir
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- -
|
59
|
+
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: 6.
|
62
|
-
type: :
|
61
|
+
version: 6.16.5
|
62
|
+
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- -
|
66
|
+
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: 6.
|
68
|
+
version: 6.16.5
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
70
|
+
name: webdrivers
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
73
|
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version:
|
76
|
-
type: :
|
75
|
+
version: '4.0'
|
76
|
+
type: :runtime
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
80
|
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version:
|
82
|
+
version: '4.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: activesupport
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '6.0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '6.0'
|
83
97
|
description: Run JSON-based recipes to scrap web sites.
|
84
98
|
email:
|
85
99
|
- hpneo@hotmail.com
|
@@ -87,7 +101,7 @@ executables: []
|
|
87
101
|
extensions: []
|
88
102
|
extra_rdoc_files: []
|
89
103
|
files:
|
90
|
-
- ".github/workflows/
|
104
|
+
- ".github/workflows/run_tests.yml"
|
91
105
|
- ".gitignore"
|
92
106
|
- ".rspec"
|
93
107
|
- ".rubocop.yml"
|