dmm-crawler 0.0.5 → 0.0.6
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 +4 -0
- data/Gemfile.lock +1 -1
- data/lib/dmm-crawler/agent.rb +8 -5
- data/lib/dmm-crawler/ranking.rb +50 -9
- data/lib/dmm-crawler/version.rb +1 -1
- 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: 9348e5bbc1d9fdd3687fa75aad5f99c5ddd26eef
|
4
|
+
data.tar.gz: acda09a89a2d16b311422d54e61f5df157b0b2f4
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: be3d69e605d26e625eff51f373e5c6cbf4f9ac0182f93ad981d56fb366e441a4c062b0e0b187725679589c75bf90c11cdcc019385b6faa582bd5612011aa8332
|
7
|
+
data.tar.gz: 5695dd753f88ba79580a6258e40b00d6e98b37f031717831966c398d0a2751dac04b7f001db94dc928d5d2e2b30c9500c2a7143c09eb06042cce145859e36830
|
data/CHANGELOG.md
CHANGED
data/Gemfile.lock
CHANGED
data/lib/dmm-crawler/agent.rb
CHANGED
@@ -1,11 +1,14 @@
|
|
1
|
+
require 'singleton'
|
2
|
+
|
1
3
|
module DMMCrawler
|
2
4
|
class Agent
|
3
|
-
|
5
|
+
include Singleton
|
4
6
|
|
5
|
-
def
|
6
|
-
|
7
|
-
|
8
|
-
|
7
|
+
def agent
|
8
|
+
agent = ::Mechanize.new
|
9
|
+
agent.request_headers = { 'Accept-Encoding' => '' }
|
10
|
+
agent.ignore_bad_chunking = true
|
11
|
+
agent
|
9
12
|
end
|
10
13
|
end
|
11
14
|
end
|
data/lib/dmm-crawler/ranking.rb
CHANGED
@@ -5,19 +5,13 @@ module DMMCrawler
|
|
5
5
|
def initialize(arguments)
|
6
6
|
@term = discriminate_term(arguments[:term])
|
7
7
|
@submedia = discriminate_submedia(arguments[:submedia])
|
8
|
-
@url = "
|
9
|
-
@agent = Agent.
|
8
|
+
@url = File.join(BASE_URL, "/dc/doujin/-/ranking-all/=/sort=popular/submedia=#{@submedia}/term=#{@term}")
|
9
|
+
@agent = Agent.instance.agent
|
10
10
|
end
|
11
11
|
|
12
12
|
def arts
|
13
13
|
arts = page.search('.rank-rankListItem.fn-setPurchaseChange').map do |element|
|
14
|
-
|
15
|
-
element.search('.rank-name').first.text.strip,
|
16
|
-
element.search('img').last.attributes['src'].value,
|
17
|
-
"#{BASE_URL}#{element.search('.rank-name').first.search('a').first.attributes.first[1].value}",
|
18
|
-
element.search('.rank-desc').text,
|
19
|
-
element.search('.rank-labelListItem').map { |e| e.search('a').text.strip }
|
20
|
-
]
|
14
|
+
Attribute.new(element).to_a
|
21
15
|
end
|
22
16
|
|
23
17
|
arts.map.with_index(1) do |(title, image_url, title_link, description, tags), rank|
|
@@ -31,6 +25,53 @@ module DMMCrawler
|
|
31
25
|
end
|
32
26
|
end
|
33
27
|
|
28
|
+
class Attribute
|
29
|
+
def initialize(element)
|
30
|
+
@element = element
|
31
|
+
@agent = Agent.instance.agent
|
32
|
+
end
|
33
|
+
|
34
|
+
def to_a
|
35
|
+
[
|
36
|
+
title,
|
37
|
+
title_link,
|
38
|
+
image_url,
|
39
|
+
description,
|
40
|
+
tags
|
41
|
+
]
|
42
|
+
end
|
43
|
+
|
44
|
+
private
|
45
|
+
|
46
|
+
def title
|
47
|
+
@element.search('.rank-name').first.text.strip
|
48
|
+
end
|
49
|
+
|
50
|
+
def image_url
|
51
|
+
@element.search('img').last.attributes['src'].value
|
52
|
+
end
|
53
|
+
|
54
|
+
def title_link
|
55
|
+
File.join(BASE_URL, @element.search('.rank-name').first.search('a').first.attributes.first[1].value)
|
56
|
+
end
|
57
|
+
|
58
|
+
def description
|
59
|
+
@element.search('.rank-desc').text.nil? ? fetch_description : @element.search('.rank-desc').text
|
60
|
+
end
|
61
|
+
|
62
|
+
def fetch_description
|
63
|
+
url = File.join(BASE_URL, @element.search('.rank-name a').first.attributes['href'].value)
|
64
|
+
page = @agent.get(url)
|
65
|
+
page.search('.summary .summary__txt').to_s.gsub(/\sclass=".*"/, '')
|
66
|
+
end
|
67
|
+
|
68
|
+
def tags
|
69
|
+
@element.search('.rank-labelListItem').map { |e| e.search('a').text.strip }
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
private_constant :Attribute
|
74
|
+
|
34
75
|
private
|
35
76
|
|
36
77
|
def page
|
data/lib/dmm-crawler/version.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: 0.0.
|
4
|
+
version: 0.0.6
|
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: 2017-05-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|
@@ -139,7 +139,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
139
139
|
version: '0'
|
140
140
|
requirements: []
|
141
141
|
rubyforge_project:
|
142
|
-
rubygems_version: 2.
|
142
|
+
rubygems_version: 2.6.12
|
143
143
|
signing_key:
|
144
144
|
specification_version: 4
|
145
145
|
summary: Show DMM and DMM.R18's crawled data
|