yoyakutopten_scraper 0.0.2
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 +7 -0
- data/.gitignore +19 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +27 -0
- data/Rakefile +1 -0
- data/lib/test.rb +14 -0
- data/lib/yoyakutopten_scraper.rb +12 -0
- data/lib/yoyakutopten_scraper/app.rb +72 -0
- data/lib/yoyakutopten_scraper/bonus.rb +35 -0
- data/lib/yoyakutopten_scraper/constant.rb +8 -0
- data/lib/yoyakutopten_scraper/ranking.rb +70 -0
- data/lib/yoyakutopten_scraper/util.rb +5 -0
- data/lib/yoyakutopten_scraper/version.rb +3 -0
- data/yoyakutopten_scraper.gemspec +26 -0
- metadata +115 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f2a680e79e875eba5b048a093dbb1816d430f388
|
4
|
+
data.tar.gz: 31969cc6a82f9258a250288010942b0c81a09ed5
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 3a397e45fd3a773e6b060fa7d49d6aca825dbf7789cb4bddf2a9e795b2d5040d57d3308a273dcefe25ec18f45e812a979ab853db3742bf3b764d6d91f4fb0592
|
7
|
+
data.tar.gz: 1a36aabf32e8ad59f22f3b920020771fb43e17dfb701276c10e4d3899cfb8d3747cb12c326a8516ec0a815b6078274ea17b9b88ed708f9e2b195ead2d03ba229
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 ryysd
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# YoyakutoptenScraper
|
2
|
+
|
3
|
+
scraper for https://yoyaku-top10.jp.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'yoyakutopten_scraper'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install yoyakutopten_scraper
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
## Contributing
|
22
|
+
|
23
|
+
1. Fork it ( http://github.com/<my-github-username>/yoyakutopten_scraper/fork )
|
24
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
25
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
26
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
27
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/test.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
require 'yoyakutopten_scraper'
|
2
|
+
|
3
|
+
ranking = YoyakutoptenScraper::Ranking.new os_type: :ios, feed: :daily
|
4
|
+
ranking.update
|
5
|
+
|
6
|
+
app = ranking.results.first
|
7
|
+
|
8
|
+
app_detail = YoyakutoptenScraper::App.new app_id: app[:app_id], os_type: app[:os_type]
|
9
|
+
bonus_detail = YoyakutoptenScraper::Bonus.new bonus_id: app[:bonus_id], os_type: app[:os_type]
|
10
|
+
|
11
|
+
app_detail.update
|
12
|
+
p app_detail
|
13
|
+
bonus_detail.update
|
14
|
+
p bonus_detail
|
@@ -0,0 +1,12 @@
|
|
1
|
+
require "yoyakutopten_scraper/version"
|
2
|
+
require 'typhoeus'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
require 'yoyakutopten_scraper/util'
|
6
|
+
require 'yoyakutopten_scraper/constant'
|
7
|
+
require 'yoyakutopten_scraper/ranking'
|
8
|
+
require 'yoyakutopten_scraper/app'
|
9
|
+
require 'yoyakutopten_scraper/bonus'
|
10
|
+
|
11
|
+
module YoyakutoptenScraper
|
12
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
module YoyakutoptenScraper
|
2
|
+
class App
|
3
|
+
def initialize(app_id:, os_type:)
|
4
|
+
@app_id = app_id
|
5
|
+
@os_type = os_type
|
6
|
+
end
|
7
|
+
|
8
|
+
def parse(html)
|
9
|
+
detail = (html.css '.app_detail_box').first
|
10
|
+
icon = (detail.css '.app_detail_img').first
|
11
|
+
title = (detail.css 'h1').first
|
12
|
+
publisher = (detail.css '.app_company').first
|
13
|
+
release = ((detail.css '.app_released').first.css 'dd').last
|
14
|
+
reservation = (detail.css '.app_booking').first
|
15
|
+
current_reserved = (reservation.css 'li')[1]
|
16
|
+
max_reserved = (reservation.css 'li')[2]
|
17
|
+
|
18
|
+
video = (html.css '.app_detail_movie').first
|
19
|
+
|
20
|
+
unless video.nil?
|
21
|
+
video_frame = (video.css 'iframe').first
|
22
|
+
video_url = video_frame.get_attribute 'src'
|
23
|
+
end
|
24
|
+
|
25
|
+
screenshot_container = (html.css '.gallery_wrap').first
|
26
|
+
screenshots = screenshot_container.css '.item'
|
27
|
+
screenshot_urls = screenshots.map do |ss|
|
28
|
+
rel_url = (ss.css 'img').first.get_attribute 'src'
|
29
|
+
YoyakutoptenScraper.make_absolute_url rel_url
|
30
|
+
end
|
31
|
+
|
32
|
+
description = (html.css '.app_description').first
|
33
|
+
|
34
|
+
bonus_detail = (html.css '.bonus_detail').first
|
35
|
+
unless bonus_detail.nil?
|
36
|
+
bonus = ((bonus_detail.css '.btn_bounus').first.css 'a').first
|
37
|
+
|
38
|
+
bonus_rel_url = bonus.get_attribute 'href'
|
39
|
+
bonus_rel_url.match %r!/[a-zA-Z]+/[a-zA-Z]+/(\w+)!
|
40
|
+
bonus_url = YoyakutoptenScraper.make_absolute_url bonus_rel_url
|
41
|
+
bonus_id = $1
|
42
|
+
else
|
43
|
+
bonus_id = ''
|
44
|
+
bonus_url = ''
|
45
|
+
end
|
46
|
+
|
47
|
+
@title = title.text
|
48
|
+
@icon = (YoyakutoptenScraper.make_absolute_url (icon.get_attribute 'src'))
|
49
|
+
@publisher = publisher.text
|
50
|
+
@release = release.text
|
51
|
+
@current_reserved = current_reserved.text
|
52
|
+
@max_reserved = max_reserved.text
|
53
|
+
@screenshot_urls = screenshot_urls
|
54
|
+
@description = description.text
|
55
|
+
@video_url = video_url
|
56
|
+
@bonus_id = bonus_id
|
57
|
+
@bonus_url = bonus_url
|
58
|
+
@website_url = (YoyakutoptenScraper.make_absolute_url ("#{YoyakutoptenScraper::PC_PREFIX}/#{@app_id}"))
|
59
|
+
end
|
60
|
+
|
61
|
+
def update
|
62
|
+
query = "#{YoyakutoptenScraper::HOST}/#{YoyakutoptenScraper::PC_PREFIX}/#{@app_id}"
|
63
|
+
user_agents = YoyakutoptenScraper::USER_AGENTS[@os_type]
|
64
|
+
request = Typhoeus::Request.new query,
|
65
|
+
method: 'get',
|
66
|
+
headers: {:"User-Agent" => user_agents},
|
67
|
+
followlocation: true
|
68
|
+
response = request.run
|
69
|
+
self.parse (Nokogiri::HTML.parse response.body)
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
module YoyakutoptenScraper
|
2
|
+
class Bonus
|
3
|
+
def initialize(bonus_id:, os_type:)
|
4
|
+
@bonus_id = bonus_id
|
5
|
+
@os_type = os_type
|
6
|
+
end
|
7
|
+
|
8
|
+
def parse(html)
|
9
|
+
img = ((html.css '.app_detail_bonus_imgArea').first.css 'img').first
|
10
|
+
description = (html.css '.app_description').first
|
11
|
+
|
12
|
+
detail = (html.css '.reserv_detail').first
|
13
|
+
reserved_num = (detail.css '.reserv_detail_num').first
|
14
|
+
current_reserved = (reserved_num.css 'li')[1]
|
15
|
+
max_reserved = (reserved_num.css 'li')[2]
|
16
|
+
|
17
|
+
@img_url = (img.get_attribute 'src')
|
18
|
+
@description = description.text
|
19
|
+
@current_reserved = current_reserved.text
|
20
|
+
@max_reserved = max_reserved.text
|
21
|
+
end
|
22
|
+
|
23
|
+
def update
|
24
|
+
query = "#{YoyakutoptenScraper::HOST}/#{YoyakutoptenScraper::MOBILE_PREFIX}/#{@bonus_id}/bonus"
|
25
|
+
user_agents = YoyakutoptenScraper::USER_AGENTS[@os_type]
|
26
|
+
request = Typhoeus::Request.new query,
|
27
|
+
method: 'get',
|
28
|
+
headers: {:"User-Agent" => user_agents},
|
29
|
+
followlocation: true
|
30
|
+
|
31
|
+
response = request.run
|
32
|
+
self.parse (Nokogiri::HTML.parse response.body)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,8 @@
|
|
1
|
+
module YoyakutoptenScraper
|
2
|
+
HOST = 'https://yoyaku-top10.jp'.freeze
|
3
|
+
PC_PREFIX = 'u/a'
|
4
|
+
MOBILE_PREFIX = 'sp/r'
|
5
|
+
ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; U; Android 1.6; ja-jp; IS01 Build/S3082) AppleWebKit/528.5+ (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1'
|
6
|
+
IOS_USER_AGENT = 'Mozilla/5.0 (iPhone; CPU iPhone OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10A403 Safari/8536.25'
|
7
|
+
USER_AGENTS = {ios: IOS_USER_AGENT, android: ANDROID_USER_AGENT}
|
8
|
+
end
|
@@ -0,0 +1,70 @@
|
|
1
|
+
module YoyakutoptenScraper
|
2
|
+
class Ranking
|
3
|
+
TYPE = [:daily, :total, :new]
|
4
|
+
attr_accessor :feed, :os_type, :results
|
5
|
+
|
6
|
+
def initialize(feed:, os_type:, options: {})
|
7
|
+
@feed = feed
|
8
|
+
@os_type = os_type
|
9
|
+
end
|
10
|
+
|
11
|
+
def parse(html)
|
12
|
+
apps = html.css '.rank_content'
|
13
|
+
|
14
|
+
@results = apps.map do |app|
|
15
|
+
title = (app.css '.rank_title').first
|
16
|
+
price = (app.css '.rank_price').first
|
17
|
+
banner = ((app.css '.rank_bnr').first.css 'a').first
|
18
|
+
banner_img = (banner.css 'img').first
|
19
|
+
|
20
|
+
info = (app.css '.bg_rank_summary').first
|
21
|
+
release = ((info.css '.rank_released').first.css 'li').last
|
22
|
+
|
23
|
+
detail_rel_url = banner.get_attribute 'href'
|
24
|
+
detail_rel_url.match %r!/[a-zA-Z]+/[a-zA-Z]+/(\w+)!
|
25
|
+
detail_url = YoyakutoptenScraper.make_absolute_url detail_rel_url
|
26
|
+
app_id = $1
|
27
|
+
|
28
|
+
special = (info.css '.btn_special').first
|
29
|
+
|
30
|
+
unless special.nil?
|
31
|
+
bonus = (special.css 'a').first
|
32
|
+
bonus_rel_url = bonus.get_attribute 'href'
|
33
|
+
bonus_rel_url.match %r!/[a-zA-Z]+/[a-zA-Z]+/(\w+)!
|
34
|
+
bonus_url = YoyakutoptenScraper.make_absolute_url bonus_rel_url
|
35
|
+
bonus_id = $1
|
36
|
+
else
|
37
|
+
bonus_id = ''
|
38
|
+
bonus_url = ''
|
39
|
+
end
|
40
|
+
|
41
|
+
banner_rel_url = (banner_img.get_attribute 'src')
|
42
|
+
banner_url = YoyakutoptenScraper.make_absolute_url banner_rel_url
|
43
|
+
|
44
|
+
{
|
45
|
+
title: title.text,
|
46
|
+
price: (price.text == 'FREE' ? 0 : price.text),
|
47
|
+
detail_url: detail_url,
|
48
|
+
banner_img_url: banner_url,
|
49
|
+
app_id: app_id,
|
50
|
+
release: release.text,
|
51
|
+
bonus_id: bonus_id,
|
52
|
+
bonus_url: bonus_url,
|
53
|
+
os_type: @os_type
|
54
|
+
}
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def update
|
59
|
+
query = "#{YoyakutoptenScraper::HOST}/pc/r/#{@os_type}/#{@feed}"
|
60
|
+
user_agents = YoyakutoptenScraper::USER_AGENTS[@os_type]
|
61
|
+
request = Typhoeus::Request.new query,
|
62
|
+
method: 'get',
|
63
|
+
headers: {:"User-Agent" => user_agents},
|
64
|
+
followlocation: true
|
65
|
+
|
66
|
+
response = request.run
|
67
|
+
self.parse (Nokogiri::HTML.parse response.body)
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'yoyakutopten_scraper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "yoyakutopten_scraper"
|
8
|
+
spec.version = YoyakutoptenScraper::VERSION
|
9
|
+
spec.authors = ["ryysd"]
|
10
|
+
spec.email = ["ry.ysd01@gmail.com"]
|
11
|
+
spec.summary = %q{scraper for https://yoyaku-top10.jp.}
|
12
|
+
spec.description = %q{scraper for https://yoyaku-top10.jp.}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.5"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
|
24
|
+
spec.add_dependency 'nokogiri'
|
25
|
+
spec.add_dependency 'typhoeus'
|
26
|
+
end
|
metadata
ADDED
@@ -0,0 +1,115 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: yoyakutopten_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- ryysd
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-03 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.5'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.5'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: nokogiri
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: typhoeus
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: scraper for https://yoyaku-top10.jp.
|
70
|
+
email:
|
71
|
+
- ry.ysd01@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- Gemfile
|
78
|
+
- LICENSE.txt
|
79
|
+
- README.md
|
80
|
+
- Rakefile
|
81
|
+
- lib/test.rb
|
82
|
+
- lib/yoyakutopten_scraper.rb
|
83
|
+
- lib/yoyakutopten_scraper/app.rb
|
84
|
+
- lib/yoyakutopten_scraper/bonus.rb
|
85
|
+
- lib/yoyakutopten_scraper/constant.rb
|
86
|
+
- lib/yoyakutopten_scraper/ranking.rb
|
87
|
+
- lib/yoyakutopten_scraper/util.rb
|
88
|
+
- lib/yoyakutopten_scraper/version.rb
|
89
|
+
- yoyakutopten_scraper.gemspec
|
90
|
+
homepage: ''
|
91
|
+
licenses:
|
92
|
+
- MIT
|
93
|
+
metadata: {}
|
94
|
+
post_install_message:
|
95
|
+
rdoc_options: []
|
96
|
+
require_paths:
|
97
|
+
- lib
|
98
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - ">="
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '0'
|
103
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
104
|
+
requirements:
|
105
|
+
- - ">="
|
106
|
+
- !ruby/object:Gem::Version
|
107
|
+
version: '0'
|
108
|
+
requirements: []
|
109
|
+
rubyforge_project:
|
110
|
+
rubygems_version: 2.2.0
|
111
|
+
signing_key:
|
112
|
+
specification_version: 4
|
113
|
+
summary: scraper for https://yoyaku-top10.jp.
|
114
|
+
test_files: []
|
115
|
+
has_rdoc:
|