aikatsu_calendar 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/.rspec +1 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +1 -0
- data/Rakefile +3 -0
- data/aikatsu_calendar.gemspec +26 -0
- data/lib/aikatsu_calendar.rb +6 -0
- data/lib/aikatsu_calendar/scraper.rb +110 -0
- data/lib/aikatsu_calendar/version.rb +3 -0
- data/spec/aikatsu_calendar/scraper_spec.rb +120 -0
- metadata +122 -0
data/.gitignore
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--colour
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 furugomu
|
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 @@
|
|
1
|
+
`AikatsuCalendar::Scraper.scrape()`
|
data/Rakefile
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'aikatsu_calendar/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "aikatsu_calendar"
|
8
|
+
spec.version = AikatsuCalendar::VERSION
|
9
|
+
spec.authors = ["furugomu"]
|
10
|
+
spec.email = ["furugomu@gmail.com"]
|
11
|
+
spec.description = %q{Aikatsu calendar}
|
12
|
+
spec.summary = %q{Ai! Katsu!}
|
13
|
+
spec.homepage = "https://github.com/furugomu/aikatsu_calendar"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_dependency "nokogiri"
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
24
|
+
spec.add_development_dependency "rake"
|
25
|
+
spec.add_development_dependency "rspec"
|
26
|
+
end
|
@@ -0,0 +1,110 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# -*- encoding: UTF-8 -*-
|
3
|
+
|
4
|
+
require 'nokogiri'
|
5
|
+
require 'uri'
|
6
|
+
require 'json'
|
7
|
+
require 'open-uri'
|
8
|
+
|
9
|
+
module AikatsuCalendar
|
10
|
+
class Scraper
|
11
|
+
attr_accessor :year, :month, :day, :schedules
|
12
|
+
|
13
|
+
def self.scrape(path=AikatsuCalendar::URL)
|
14
|
+
scraper = new()
|
15
|
+
doc = open(path) {|f| Nokogiri::HTML.parse(f) }
|
16
|
+
scraper.feed(doc)
|
17
|
+
scraper.schedules.uniq do |x|
|
18
|
+
[x[:type], x[:content], x[:date_from], x[:date_until]]
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def initialize
|
23
|
+
@schedules = []
|
24
|
+
end
|
25
|
+
|
26
|
+
def feed(doc)
|
27
|
+
container = doc.at_css(".info-schedule")
|
28
|
+
container.css('table').each do |table|
|
29
|
+
feed_table(table)
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def feed_table(table)
|
34
|
+
# 年と月
|
35
|
+
text = table.at_css('th').text
|
36
|
+
m = text.match(/(\d+)年(\d+)月/) or raise ValueError, text
|
37
|
+
@year = m[1].to_i
|
38
|
+
@month = m[2].to_i
|
39
|
+
|
40
|
+
table.css('tr')[1..-1].each do |tr|
|
41
|
+
feed_row(tr)
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def feed_row(tr)
|
46
|
+
# 日付
|
47
|
+
text = tr.at_css('td').text
|
48
|
+
m = text.match(/(\d+)日/) or raise ValueError, text
|
49
|
+
@day = m[1].to_i
|
50
|
+
|
51
|
+
tr.css('p').each do |p|
|
52
|
+
feed_item(p)
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
def feed_item(p)
|
57
|
+
@schedules << parse_item(p)
|
58
|
+
end
|
59
|
+
|
60
|
+
def parse_item(p)
|
61
|
+
# 日付
|
62
|
+
text = p.text
|
63
|
+
re = /(?: ※)?(\d+)年(\d+)月(\d+)日~(?:(\d+)年)?(\d+)月(\d+)日/
|
64
|
+
m = text.match(re)
|
65
|
+
if m
|
66
|
+
year_until = (m[4] || m[1]).to_i
|
67
|
+
date_from = Time.local(m[1].to_i, m[2].to_i, m[3].to_i)
|
68
|
+
date_until = Time.local(year_until, m[5].to_i, m[6].to_i)
|
69
|
+
else
|
70
|
+
date_from = date_until = Time.local(@year, @month, @day)
|
71
|
+
end
|
72
|
+
# 日付をとっぱらう
|
73
|
+
text = text.sub(re, '')
|
74
|
+
|
75
|
+
# URL
|
76
|
+
url = nil
|
77
|
+
if (a = p.at_css('a[href]'))
|
78
|
+
base = 'http://www.aikatsu.com/calender/'
|
79
|
+
url = URI.join(base, a.attr(:href)).to_s
|
80
|
+
end
|
81
|
+
|
82
|
+
# type
|
83
|
+
type = class_to_type(p.attr(:class))
|
84
|
+
|
85
|
+
{
|
86
|
+
type: type,
|
87
|
+
date_from: date_from,
|
88
|
+
date_until: date_until,
|
89
|
+
content: text.strip,
|
90
|
+
link: url,
|
91
|
+
}
|
92
|
+
end
|
93
|
+
|
94
|
+
def class_to_type(s)
|
95
|
+
if s =~ /schedule-(\w+)/
|
96
|
+
$1
|
97
|
+
else
|
98
|
+
nil
|
99
|
+
end
|
100
|
+
end
|
101
|
+
|
102
|
+
def to_json(pretty=false)
|
103
|
+
if pretty
|
104
|
+
JSON.pretty_generate(@schedules)
|
105
|
+
else
|
106
|
+
JSON.dump(@schedules)
|
107
|
+
end
|
108
|
+
end
|
109
|
+
end
|
110
|
+
end
|
@@ -0,0 +1,120 @@
|
|
1
|
+
#!ruby
|
2
|
+
# -*- encoding: UTF-8 -*-
|
3
|
+
|
4
|
+
require 'aikatsu_calendar'
|
5
|
+
|
6
|
+
def html(s)
|
7
|
+
Nokogiri::HTML::DocumentFragment.parse(s.strip).children.first
|
8
|
+
end
|
9
|
+
|
10
|
+
describe AikatsuCalendar::Scraper do
|
11
|
+
let(:aical) { AikatsuCalendar::Scraper.new }
|
12
|
+
subject { aical }
|
13
|
+
before do
|
14
|
+
aical.year = 2000; aical.month = 10; aical.day = 10
|
15
|
+
end
|
16
|
+
|
17
|
+
describe 'feed_table' do
|
18
|
+
let(:table) do
|
19
|
+
html(<<-HTML)
|
20
|
+
<table cellspacing="0" class="apr">
|
21
|
+
<tbody>
|
22
|
+
<tr>
|
23
|
+
<th colspan="3">2013年4月</th>
|
24
|
+
</tr>
|
25
|
+
</tbody>
|
26
|
+
</table>
|
27
|
+
HTML
|
28
|
+
end
|
29
|
+
before do
|
30
|
+
aical.feed_table(table)
|
31
|
+
end
|
32
|
+
its(:year) { should == 2013 }
|
33
|
+
its(:month) { should == 4 }
|
34
|
+
end
|
35
|
+
|
36
|
+
describe 'feed_row' do
|
37
|
+
let(:tr) do
|
38
|
+
html(<<-HTML)
|
39
|
+
<tr>
|
40
|
+
<td class="schedule-day"><span>03日</span><span class="schedule-week">水</span></td>
|
41
|
+
<td><p>x</p></td>
|
42
|
+
</tr>
|
43
|
+
HTML
|
44
|
+
end
|
45
|
+
before do
|
46
|
+
aical.feed_row(tr)
|
47
|
+
end
|
48
|
+
its(:day) { should == 3 }
|
49
|
+
end
|
50
|
+
|
51
|
+
describe 'parse_item' do
|
52
|
+
let(:p) { html('<p class="schedule-game clearfix">いちごちゃん</p>') }
|
53
|
+
subject { aical.parse_item(p) }
|
54
|
+
|
55
|
+
it 'content' do
|
56
|
+
subject[:content].should == p.text
|
57
|
+
end
|
58
|
+
it 'date_from' do
|
59
|
+
subject[:date_from].should == Time.local(aical.year, aical.month, aical.day)
|
60
|
+
end
|
61
|
+
it 'date_until' do
|
62
|
+
subject[:date_until].should == Time.local(aical.year, aical.month, aical.day)
|
63
|
+
end
|
64
|
+
it 'type' do
|
65
|
+
subject[:type].should == 'game'
|
66
|
+
end
|
67
|
+
|
68
|
+
context '中に日付が書かれている(※あり)' do
|
69
|
+
let(:p) { html('<p class="schedule-game">あおいちゃん ※2013年2月14日~2014年3月31日</p>') }
|
70
|
+
it 'content' do
|
71
|
+
subject[:content].should == 'あおいちゃん'
|
72
|
+
end
|
73
|
+
it 'date_from' do
|
74
|
+
subject[:date_from].should == Time.local(2013, 2, 14)
|
75
|
+
end
|
76
|
+
it 'date_until' do
|
77
|
+
subject[:date_until].should == Time.local(2014, 3, 31)
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
context '中に日付が書かれている(終了年が無い)' do
|
82
|
+
let(:p) { html('<p class="schedule-game">蘭ちゃん ※2013年2月14日~3月31日</p>') }
|
83
|
+
it 'content' do
|
84
|
+
subject[:content].should == '蘭ちゃん'
|
85
|
+
end
|
86
|
+
it 'date_from' do
|
87
|
+
subject[:date_from].should == Time.local(2013, 2, 14)
|
88
|
+
end
|
89
|
+
it 'date_until' do
|
90
|
+
subject[:date_until].should == Time.local(2013, 3, 31)
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
context '中に日付が書かれている(※なし)' do
|
95
|
+
let(:p) do
|
96
|
+
html(<<-HTML)
|
97
|
+
<p class="schedule-game">
|
98
|
+
<span>2013年2月14日~2014年3月31日</span>
|
99
|
+
おとめちゃん</p>
|
100
|
+
HTML
|
101
|
+
end
|
102
|
+
it 'content' do
|
103
|
+
subject[:content].should == 'おとめちゃん'
|
104
|
+
end
|
105
|
+
it 'date_from' do
|
106
|
+
subject[:date_from].should == Time.local(2013, 2, 14)
|
107
|
+
end
|
108
|
+
it 'date_until' do
|
109
|
+
subject[:date_until].should == Time.local(2014, 3, 31)
|
110
|
+
end
|
111
|
+
end
|
112
|
+
|
113
|
+
context 'リンクがある' do
|
114
|
+
let(:p) { html('<p class="schedule-magazine"><a href="../magazine/magazine15.html">ちゃお4月号</a></p>') }
|
115
|
+
it 'link' do
|
116
|
+
subject[:link].should == 'http://www.aikatsu.com/magazine/magazine15.html'
|
117
|
+
end
|
118
|
+
end
|
119
|
+
end
|
120
|
+
end
|
metadata
ADDED
@@ -0,0 +1,122 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: aikatsu_calendar
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- furugomu
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-04-08 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: bundler
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ~>
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '1.3'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '1.3'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rake
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: rspec
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
description: Aikatsu calendar
|
79
|
+
email:
|
80
|
+
- furugomu@gmail.com
|
81
|
+
executables: []
|
82
|
+
extensions: []
|
83
|
+
extra_rdoc_files: []
|
84
|
+
files:
|
85
|
+
- .gitignore
|
86
|
+
- .rspec
|
87
|
+
- Gemfile
|
88
|
+
- LICENSE.txt
|
89
|
+
- README.md
|
90
|
+
- Rakefile
|
91
|
+
- aikatsu_calendar.gemspec
|
92
|
+
- lib/aikatsu_calendar.rb
|
93
|
+
- lib/aikatsu_calendar/scraper.rb
|
94
|
+
- lib/aikatsu_calendar/version.rb
|
95
|
+
- spec/aikatsu_calendar/scraper_spec.rb
|
96
|
+
homepage: https://github.com/furugomu/aikatsu_calendar
|
97
|
+
licenses:
|
98
|
+
- MIT
|
99
|
+
post_install_message:
|
100
|
+
rdoc_options: []
|
101
|
+
require_paths:
|
102
|
+
- lib
|
103
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
104
|
+
none: false
|
105
|
+
requirements:
|
106
|
+
- - ! '>='
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
version: '0'
|
109
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
110
|
+
none: false
|
111
|
+
requirements:
|
112
|
+
- - ! '>='
|
113
|
+
- !ruby/object:Gem::Version
|
114
|
+
version: '0'
|
115
|
+
requirements: []
|
116
|
+
rubyforge_project:
|
117
|
+
rubygems_version: 1.8.23
|
118
|
+
signing_key:
|
119
|
+
specification_version: 3
|
120
|
+
summary: Ai! Katsu!
|
121
|
+
test_files:
|
122
|
+
- spec/aikatsu_calendar/scraper_spec.rb
|