dmm-crawler 0.2.1 → 0.2.3
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/.gitignore +1 -0
- data/CHANGELOG.md +13 -0
- data/dmm-crawler.gemspec +5 -5
- data/lib/dmm-crawler/attributes.rb +1 -1
- data/lib/dmm-crawler/ranking.rb +10 -4
- data/lib/dmm-crawler/version.rb +1 -1
- data/spec/dmm-crawler/ranking_spec.rb +2 -1
- metadata +23 -24
- data/Gemfile.lock +0 -84
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 653778e42cde0643d26e9e7e24c4f7b7aefff105
|
4
|
+
data.tar.gz: 715a8a7937cb7b4351f11718fcf0327ef85700c0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: cadd766510e0de7319ec516a708ec6d9b3ce315f79d6fa5c52ac1ca3f0b31c65acd276230932c051b0ccdb99cfb689e915bb0f02c76ea06c67d3b172705fb1f8
|
7
|
+
data.tar.gz: d9b31e5c90c5141c0ca7a26d6a64d48343fa920ee3ebd475aece738d769536a0cccaa478d864c36814eeaf4907f7e654396f6e1feafd24940d4867b03fef30b8
|
data/.gitignore
CHANGED
data/CHANGELOG.md
CHANGED
@@ -1,5 +1,18 @@
|
|
1
1
|
# Change logs
|
2
2
|
|
3
|
+
## 0.2.3
|
4
|
+
- Do not lock gem versions in 'dmm-crawler.gemspec'.
|
5
|
+
- Change the author name element due to it is not found.
|
6
|
+
|
7
|
+
### Security Changes
|
8
|
+
- Lock the RuboCop version over `0.49.0`.
|
9
|
+
|
10
|
+
### Breaking Changes
|
11
|
+
- Reduce the ranking size to ten.
|
12
|
+
|
13
|
+
## 0.2.2
|
14
|
+
- Do not manage 'Gemfile.lock'.
|
15
|
+
|
3
16
|
## 0.2.1
|
4
17
|
- Add an attribute for author.
|
5
18
|
|
data/dmm-crawler.gemspec
CHANGED
@@ -19,9 +19,9 @@ Gem::Specification.new do |spec|
|
|
19
19
|
|
20
20
|
spec.add_runtime_dependency 'mechanize'
|
21
21
|
|
22
|
-
spec.add_development_dependency 'bundler'
|
23
|
-
spec.add_development_dependency 'rake'
|
24
|
-
spec.add_development_dependency 'rubocop', '
|
25
|
-
spec.add_development_dependency 'pry'
|
26
|
-
spec.add_development_dependency 'rspec'
|
22
|
+
spec.add_development_dependency 'bundler'
|
23
|
+
spec.add_development_dependency 'rake'
|
24
|
+
spec.add_development_dependency 'rubocop', '< 0.49.0'
|
25
|
+
spec.add_development_dependency 'pry'
|
26
|
+
spec.add_development_dependency 'rspec'
|
27
27
|
end
|
data/lib/dmm-crawler/ranking.rb
CHANGED
@@ -8,10 +8,11 @@ module DMMCrawler
|
|
8
8
|
end
|
9
9
|
|
10
10
|
def arts
|
11
|
-
arts = page.search('.rank-rankListItem.fn-setPurchaseChange').map do |element|
|
12
|
-
|
13
|
-
|
14
|
-
|
11
|
+
arts = page.search('.rank-rankListItem.fn-setPurchaseChange').take(10).map do |element|
|
12
|
+
sleep_each do
|
13
|
+
url = File.join(BASE_URL, element.search('.rank-name a').first.attributes['href'].value)
|
14
|
+
Attributes.new(url).to_a
|
15
|
+
end
|
15
16
|
end
|
16
17
|
|
17
18
|
arts.map.with_index(1) do |(title, title_link, image_url, submedia, author, informations, tags), rank|
|
@@ -42,5 +43,10 @@ module DMMCrawler
|
|
42
43
|
return agent if agent.is_a?(Mechanize)
|
43
44
|
raise TypeError
|
44
45
|
end
|
46
|
+
|
47
|
+
def sleep_each
|
48
|
+
sleep rand(0.7..1.3)
|
49
|
+
yield
|
50
|
+
end
|
45
51
|
end
|
46
52
|
end
|
data/lib/dmm-crawler/version.rb
CHANGED
@@ -13,7 +13,7 @@ describe DMMCrawler::Ranking do
|
|
13
13
|
|
14
14
|
let(:term) { '24' }
|
15
15
|
|
16
|
-
it { is_expected.to be
|
16
|
+
it { is_expected.to be 10 }
|
17
17
|
end
|
18
18
|
|
19
19
|
context 'with 24 argument' do
|
@@ -22,6 +22,7 @@ describe DMMCrawler::Ranking do
|
|
22
22
|
let(:term) { '24' }
|
23
23
|
|
24
24
|
it { is_expected.to all(include(:title, :title_link, :image_url, :submedia, :author, :informations, :tags)) }
|
25
|
+
it { is_expected.to all(satisfy { |art| art.all? { |_k, v| v != '' } }) }
|
25
26
|
end
|
26
27
|
|
27
28
|
context 'with not registered argument' do
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dmm-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Satoshi Ohmori
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-
|
11
|
+
date: 2017-12-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|
@@ -28,72 +28,72 @@ dependencies:
|
|
28
28
|
name: bundler
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - "
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - "
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: rake
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - "
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '0'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - "
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
54
|
+
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: rubocop
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - "
|
59
|
+
- - "<"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version:
|
61
|
+
version: 0.49.0
|
62
62
|
type: :development
|
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:
|
68
|
+
version: 0.49.0
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: pry
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- -
|
73
|
+
- - ">="
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version: 0
|
75
|
+
version: '0'
|
76
76
|
type: :development
|
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: 0
|
82
|
+
version: '0'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: rspec
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
|
-
- -
|
87
|
+
- - ">="
|
88
88
|
- !ruby/object:Gem::Version
|
89
|
-
version:
|
89
|
+
version: '0'
|
90
90
|
type: :development
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
|
-
- -
|
94
|
+
- - ">="
|
95
95
|
- !ruby/object:Gem::Version
|
96
|
-
version:
|
96
|
+
version: '0'
|
97
97
|
description: Show DMM and DMM.R18's crawled data. e.g. ranking
|
98
98
|
email:
|
99
99
|
- sachin21dev@gmail.com
|
@@ -107,7 +107,6 @@ files:
|
|
107
107
|
- ".travis.yml"
|
108
108
|
- CHANGELOG.md
|
109
109
|
- Gemfile
|
110
|
-
- Gemfile.lock
|
111
110
|
- LICENSE.txt
|
112
111
|
- README.md
|
113
112
|
- Rakefile
|
@@ -141,7 +140,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
141
140
|
version: '0'
|
142
141
|
requirements: []
|
143
142
|
rubyforge_project:
|
144
|
-
rubygems_version: 2.
|
143
|
+
rubygems_version: 2.6.11
|
145
144
|
signing_key:
|
146
145
|
specification_version: 4
|
147
146
|
summary: Show DMM and DMM.R18's crawled data
|
data/Gemfile.lock
DELETED
@@ -1,84 +0,0 @@
|
|
1
|
-
PATH
|
2
|
-
remote: .
|
3
|
-
specs:
|
4
|
-
dmm-crawler (0.2.1)
|
5
|
-
mechanize
|
6
|
-
|
7
|
-
GEM
|
8
|
-
remote: https://rubygems.org/
|
9
|
-
specs:
|
10
|
-
ast (2.3.0)
|
11
|
-
coderay (1.1.1)
|
12
|
-
diff-lcs (1.3)
|
13
|
-
domain_name (0.5.20170404)
|
14
|
-
unf (>= 0.0.5, < 1.0.0)
|
15
|
-
http-cookie (1.0.3)
|
16
|
-
domain_name (~> 0.5)
|
17
|
-
mechanize (2.7.5)
|
18
|
-
domain_name (~> 0.5, >= 0.5.1)
|
19
|
-
http-cookie (~> 1.0)
|
20
|
-
mime-types (>= 1.17.2)
|
21
|
-
net-http-digest_auth (~> 1.1, >= 1.1.1)
|
22
|
-
net-http-persistent (~> 2.5, >= 2.5.2)
|
23
|
-
nokogiri (~> 1.6)
|
24
|
-
ntlm-http (~> 0.1, >= 0.1.1)
|
25
|
-
webrobots (>= 0.0.9, < 0.2)
|
26
|
-
method_source (0.8.2)
|
27
|
-
mime-types (3.1)
|
28
|
-
mime-types-data (~> 3.2015)
|
29
|
-
mime-types-data (3.2016.0521)
|
30
|
-
mini_portile2 (2.3.0)
|
31
|
-
net-http-digest_auth (1.4.1)
|
32
|
-
net-http-persistent (2.9.4)
|
33
|
-
nokogiri (1.8.1)
|
34
|
-
mini_portile2 (~> 2.3.0)
|
35
|
-
ntlm-http (0.1.1)
|
36
|
-
parser (2.4.0.0)
|
37
|
-
ast (~> 2.2)
|
38
|
-
powerpack (0.1.1)
|
39
|
-
pry (0.10.4)
|
40
|
-
coderay (~> 1.1.0)
|
41
|
-
method_source (~> 0.8.1)
|
42
|
-
slop (~> 3.4)
|
43
|
-
rainbow (2.2.1)
|
44
|
-
rake (10.5.0)
|
45
|
-
rspec (3.5.0)
|
46
|
-
rspec-core (~> 3.5.0)
|
47
|
-
rspec-expectations (~> 3.5.0)
|
48
|
-
rspec-mocks (~> 3.5.0)
|
49
|
-
rspec-core (3.5.4)
|
50
|
-
rspec-support (~> 3.5.0)
|
51
|
-
rspec-expectations (3.5.0)
|
52
|
-
diff-lcs (>= 1.2.0, < 2.0)
|
53
|
-
rspec-support (~> 3.5.0)
|
54
|
-
rspec-mocks (3.5.0)
|
55
|
-
diff-lcs (>= 1.2.0, < 2.0)
|
56
|
-
rspec-support (~> 3.5.0)
|
57
|
-
rspec-support (3.5.0)
|
58
|
-
rubocop (0.47.1)
|
59
|
-
parser (>= 2.3.3.1, < 3.0)
|
60
|
-
powerpack (~> 0.1)
|
61
|
-
rainbow (>= 1.99.1, < 3.0)
|
62
|
-
ruby-progressbar (~> 1.7)
|
63
|
-
unicode-display_width (~> 1.0, >= 1.0.1)
|
64
|
-
ruby-progressbar (1.8.1)
|
65
|
-
slop (3.6.0)
|
66
|
-
unf (0.1.4)
|
67
|
-
unf_ext
|
68
|
-
unf_ext (0.0.7.4)
|
69
|
-
unicode-display_width (1.1.3)
|
70
|
-
webrobots (0.1.2)
|
71
|
-
|
72
|
-
PLATFORMS
|
73
|
-
ruby
|
74
|
-
|
75
|
-
DEPENDENCIES
|
76
|
-
bundler (~> 1.14)
|
77
|
-
dmm-crawler!
|
78
|
-
pry (= 0.10.4)
|
79
|
-
rake (~> 10.0)
|
80
|
-
rspec (= 3.5.0)
|
81
|
-
rubocop (~> 0.47)
|
82
|
-
|
83
|
-
BUNDLED WITH
|
84
|
-
1.16.0.pre.2
|