dmm-crawler 0.1.2 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +3 -0
- data/Gemfile.lock +1 -1
- data/lib/dmm-crawler/attributes.rb +15 -1
- data/lib/dmm-crawler/ranking.rb +6 -2
- data/lib/dmm-crawler/version.rb +1 -1
- data/spec/dmm-crawler/ranking_spec.rb +1 -2
- data/spec/spec_helper.rb +1 -0
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: d81d554887372647840ee289931bb8e48fdf7773
|
4
|
+
data.tar.gz: cb08a2dbecf8d0a05d622e263a028d4a30ee8078
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 9cc563c97f1391290b6a9d43b57053bc8b661336f49a42b43e6c140f0538b083349e0e8136925348fd13720383fe958a8a40f54c8eefb87a478216bb4caaa6dc
|
7
|
+
data.tar.gz: '01795b372af4159cda9661d50dcb76f30fa1ab1cacb34337572d89425abe5d2243e20c9d54e252c4fac8e41f6c12f2a78855f6f4e96fb7d91736511f34ee1313'
|
data/CHANGELOG.md
CHANGED
data/Gemfile.lock
CHANGED
@@ -15,6 +15,7 @@ module DMMCrawler
|
|
15
15
|
description,
|
16
16
|
description_raw,
|
17
17
|
submedia,
|
18
|
+
informations,
|
18
19
|
tags
|
19
20
|
]
|
20
21
|
end
|
@@ -51,7 +52,7 @@ module DMMCrawler
|
|
51
52
|
@element.search('.summary .summary__txt').text
|
52
53
|
else
|
53
54
|
@element.search('.rank-desc').text
|
54
|
-
end
|
55
|
+
end.strip
|
55
56
|
end
|
56
57
|
|
57
58
|
def description_raw
|
@@ -74,6 +75,19 @@ module DMMCrawler
|
|
74
75
|
.delete('-')
|
75
76
|
end
|
76
77
|
|
78
|
+
def informations
|
79
|
+
keys = extract_text(@element.search('.m-productInformation .productInformation__item .informationList__ttl'))
|
80
|
+
values = extract_text(@element.search('.m-productInformation .productInformation__item .informationList__txt'))
|
81
|
+
|
82
|
+
keys.zip(values).map { |key, value| { key: key, value: value } }
|
83
|
+
end
|
84
|
+
|
85
|
+
def extract_text(elements)
|
86
|
+
elements
|
87
|
+
.select { |element| element.text.strip != 'ジャンル' }
|
88
|
+
.map { |element| element.children.text.strip }
|
89
|
+
end
|
90
|
+
|
77
91
|
def tags
|
78
92
|
if art_page?
|
79
93
|
@element.search('.genreTagList .genreTagList__item a').map { |e| e.text.strip }
|
data/lib/dmm-crawler/ranking.rb
CHANGED
@@ -9,10 +9,13 @@ module DMMCrawler
|
|
9
9
|
|
10
10
|
def arts
|
11
11
|
arts = page.search('.rank-rankListItem.fn-setPurchaseChange').map do |element|
|
12
|
-
|
12
|
+
sleep 1
|
13
|
+
url = File.join(BASE_URL, element.search('.rank-name a').first.attributes['href'].value)
|
14
|
+
page = @agent.get(url)
|
15
|
+
Attributes.new(page, @submedia).to_a
|
13
16
|
end
|
14
17
|
|
15
|
-
arts.map.with_index(1) do |(title, title_link, image_url, description, description_raw, submedia, tags), rank|
|
18
|
+
arts.map.with_index(1) do |(title, title_link, image_url, description, description_raw, submedia, informations, tags), rank|
|
16
19
|
{
|
17
20
|
title: "#{rank}位: #{title}",
|
18
21
|
title_link: title_link,
|
@@ -20,6 +23,7 @@ module DMMCrawler
|
|
20
23
|
description: description,
|
21
24
|
description_raw: description_raw,
|
22
25
|
submedia: submedia,
|
26
|
+
informations: informations,
|
23
27
|
tags: tags
|
24
28
|
}
|
25
29
|
end
|
data/lib/dmm-crawler/version.rb
CHANGED
@@ -20,8 +20,7 @@ describe DMMCrawler::Ranking do
|
|
20
20
|
|
21
21
|
let(:term) { '24' }
|
22
22
|
|
23
|
-
it { is_expected.
|
24
|
-
it { is_expected.to all(include(:title, :title_link, :image_url, :description, :description_raw, :submedia, :tags)) }
|
23
|
+
it { is_expected.to all(include(:title, :title_link, :image_url, :description, :description_raw, :submedia, :informations, :tags)) }
|
25
24
|
end
|
26
25
|
|
27
26
|
context 'with not registered argument' do
|
data/spec/spec_helper.rb
CHANGED
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: 0.1.
|
4
|
+
version: 0.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Satoshi Ohmori
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-06-
|
11
|
+
date: 2017-06-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|
@@ -140,7 +140,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
140
140
|
version: '0'
|
141
141
|
requirements: []
|
142
142
|
rubyforge_project:
|
143
|
-
rubygems_version: 2.6.
|
143
|
+
rubygems_version: 2.6.10
|
144
144
|
signing_key:
|
145
145
|
specification_version: 4
|
146
146
|
summary: Show DMM and DMM.R18's crawled data
|