dmm-crawler 0.0.7 → 0.1.0
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/CHANGELOG.md +5 -2
- data/Gemfile.lock +1 -1
- data/lib/dmm-crawler/ranking.rb +13 -1
- data/lib/dmm-crawler/version.rb +1 -1
- data/spec/dmm-crawler/ranking_spec.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: fb28829797ace3b0102362683982bcdfca075a56
|
4
|
+
data.tar.gz: c4a8628acd41839ed5a51fcf4c258618e6131092
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 719401d375387a33ec83b2ba7da3ee6b358c3b7172b455f742c2a09e99d7ed0e675fd907f91198eca45f1bf49ebf0310c8c238c449d99e2eb1a8360b812f6706
|
7
|
+
data.tar.gz: ba6651b43f241a5f3c5d2b8665cc58160f9168e4a17eec011281a21372dda1f269ea442f05cebbe580fc18fd17cc5f908ad125b2d3dfd984678cbfb439191eb8
|
data/CHANGELOG.md
CHANGED
@@ -1,11 +1,14 @@
|
|
1
1
|
# Change logs
|
2
2
|
|
3
|
-
## 0.0
|
3
|
+
## 0.1.0
|
4
|
+
- Add an attribute raw data of description that include HTML tag.
|
5
|
+
|
6
|
+
## 0.0.7
|
4
7
|
### Critical bug fix
|
5
8
|
- Replace url with image_url
|
9
|
+
- Fix the bug where description is empty.
|
6
10
|
|
7
11
|
## 0.0.6
|
8
|
-
- Fix the bug where description is empty.
|
9
12
|
- Refactor codes related to attributes for the art.
|
10
13
|
|
11
14
|
## 0.0.5
|
data/Gemfile.lock
CHANGED
data/lib/dmm-crawler/ranking.rb
CHANGED
@@ -14,12 +14,13 @@ module DMMCrawler
|
|
14
14
|
Attribute.new(element).to_a
|
15
15
|
end
|
16
16
|
|
17
|
-
arts.map.with_index(1) do |(title, title_link, image_url, description, tags), rank|
|
17
|
+
arts.map.with_index(1) do |(title, title_link, image_url, description, description_raw, tags), rank|
|
18
18
|
{
|
19
19
|
title: "#{rank}位: #{title}",
|
20
20
|
title_link: title_link,
|
21
21
|
image_url: image_url,
|
22
22
|
description: description,
|
23
|
+
description_raw: description_raw,
|
23
24
|
tags: tags
|
24
25
|
}
|
25
26
|
end
|
@@ -37,6 +38,7 @@ module DMMCrawler
|
|
37
38
|
title_link,
|
38
39
|
image_url,
|
39
40
|
description,
|
41
|
+
description_raw,
|
40
42
|
tags
|
41
43
|
]
|
42
44
|
end
|
@@ -59,7 +61,17 @@ module DMMCrawler
|
|
59
61
|
@element.search('.rank-desc').text.nil? ? fetch_description : @element.search('.rank-desc').text
|
60
62
|
end
|
61
63
|
|
64
|
+
def description_raw
|
65
|
+
@element.search('.rank-desc').text.nil? ? fetch_description_raw : @element.search('.rank-desc').to_s
|
66
|
+
end
|
67
|
+
|
62
68
|
def fetch_description
|
69
|
+
url = File.join(BASE_URL, @element.search('.rank-name a').first.attributes['href'].value)
|
70
|
+
page = @agent.get(url)
|
71
|
+
page.search('.summary .summary__txt').text
|
72
|
+
end
|
73
|
+
|
74
|
+
def fetch_description_raw
|
63
75
|
url = File.join(BASE_URL, @element.search('.rank-name a').first.attributes['href'].value)
|
64
76
|
page = @agent.get(url)
|
65
77
|
page.search('.summary .summary__txt').to_s.gsub(/\sclass=".*"/, '')
|
data/lib/dmm-crawler/version.rb
CHANGED
@@ -21,7 +21,7 @@ describe DMMCrawler::Ranking do
|
|
21
21
|
let(:term) { '24' }
|
22
22
|
|
23
23
|
it { is_expected.not_to be_empty }
|
24
|
-
it { is_expected.to all(include(:title, :title_link, :image_url, :description, :tags)) }
|
24
|
+
it { is_expected.to all(include(:title, :title_link, :image_url, :description, :description_raw, :tags)) }
|
25
25
|
end
|
26
26
|
|
27
27
|
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: 0.0
|
4
|
+
version: 0.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Satoshi Ohmori
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-05-
|
11
|
+
date: 2017-05-29 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|