sosowa 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +27 -0
- data/Rakefile +2 -0
- data/lib/sosowa/parser.rb +58 -0
- data/lib/sosowa/scheme.rb +102 -0
- data/lib/sosowa/version.rb +3 -0
- data/lib/sosowa.rb +22 -0
- data/sosowa.gemspec +18 -0
- metadata +67 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Oame
|
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
|
+
# Sosowa
|
2
|
+
|
3
|
+
Sosowa Parser for Ruby 1.9.x
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
gem install sosowa
|
8
|
+
|
9
|
+
## Usage
|
10
|
+
|
11
|
+
require "sosowa"
|
12
|
+
|
13
|
+
# 最新版から最初のSSを持ってくる
|
14
|
+
novel = Sosowa.get.first
|
15
|
+
puts novel.text
|
16
|
+
|
17
|
+
# 作品集番号156の1320873807を持ってくる
|
18
|
+
novel = Sosowa.get(:log => 156, :key => 1320873807)
|
19
|
+
puts novel.text
|
20
|
+
|
21
|
+
## Contributing
|
22
|
+
|
23
|
+
1. Fork it
|
24
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
25
|
+
3. Commit your changes (`git commit -am 'Added 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 +1,58 @@
|
|
1
|
+
module Sosowa
|
2
|
+
class Parser
|
3
|
+
|
4
|
+
def initialize
|
5
|
+
@agent = Mechanize.new
|
6
|
+
@agent.user_agent = "Sosowa Ruby #{Sosowa::VERSION}"
|
7
|
+
end
|
8
|
+
|
9
|
+
def fetch_index(log)
|
10
|
+
page = @agent.get("#{Sosowa::BASE_URL}/?log=#{log}")
|
11
|
+
indexes = []
|
12
|
+
tr = page.search("tr")
|
13
|
+
tr = tr[1, tr.size-1]
|
14
|
+
num = 1
|
15
|
+
tr.each do |tr|
|
16
|
+
if (tr/%{td[@class="tags"]}).size > 0
|
17
|
+
#tags = (tr/%{td[@class="tags"]})[0].inner_html.to_s.toutf8.strip.gsub(/^.+?: /, "").split(/\s/)
|
18
|
+
#indexes[num-1] << tags
|
19
|
+
else
|
20
|
+
title = tr.search(%{td[@class="title cell_title"] > a}).inner_html.to_s.toutf8.strip
|
21
|
+
tags = tr.search(%{td[@class="title cell_title"] > a})[0].attributes["title"].value.split(" / ")
|
22
|
+
key = tr.search(%{td[@class="title cell_title"] > a})[0].attributes["href"].value.gsub(/^.+key=(.+?)&.+$/, '\1').to_i
|
23
|
+
author = tr.search(%{td[@class="cell_author"]}).inner_html.to_s.toutf8.strip
|
24
|
+
created_at = Time.parse(tr.search(%{td[@class="cell_created"]}).inner_html.to_s.toutf8.strip)
|
25
|
+
updated_at = Time.parse(tr.search(%{td[@class="cell_lastup"]}).inner_html.to_s.toutf8.strip)
|
26
|
+
eval = tr.search(%{td[@class="cell_eval"]}).inner_html.to_s.toutf8.strip.split("/")
|
27
|
+
review_count = eval[1].to_i
|
28
|
+
comment_count = eval[0].to_i
|
29
|
+
point = tr.search(%{td[@class="cell_point"]}).inner_html.to_s.toutf8.strip.to_i
|
30
|
+
rate = tr.search(%{td[@class="cell_rate"]}).inner_html.to_s.toutf8.strip.to_f
|
31
|
+
size = tr.search(%{td[@class="cell_size"]}).inner_html.to_s.toutf8.strip
|
32
|
+
index = {
|
33
|
+
:log => log,
|
34
|
+
:key => key,
|
35
|
+
:title => title,
|
36
|
+
:author => author,
|
37
|
+
:created_at => created_at,
|
38
|
+
:updated_at => updated_at,
|
39
|
+
:review_count => review_count,
|
40
|
+
:comment_count => comment_count,
|
41
|
+
:point => point,
|
42
|
+
:tags => tags,
|
43
|
+
:rate => rate,
|
44
|
+
:size => size
|
45
|
+
}
|
46
|
+
indexes << Index.new(index)
|
47
|
+
end
|
48
|
+
num += 1
|
49
|
+
end
|
50
|
+
return indexes
|
51
|
+
end
|
52
|
+
|
53
|
+
def fetch_novel(log, key)
|
54
|
+
novel = Novel.new(:log => log, :key => key)
|
55
|
+
return novel
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
@@ -0,0 +1,102 @@
|
|
1
|
+
module Sosowa
|
2
|
+
class Scheme
|
3
|
+
protected
|
4
|
+
|
5
|
+
def method_missing(action, *args)
|
6
|
+
return @element[action.to_s.to_sym] rescue nil
|
7
|
+
end
|
8
|
+
|
9
|
+
public
|
10
|
+
|
11
|
+
def params() @element.keys.map{|k|k.to_sym} ; end
|
12
|
+
alias_method :available_methods, :params
|
13
|
+
end
|
14
|
+
|
15
|
+
class Novel < Scheme
|
16
|
+
def initialize(args)
|
17
|
+
@log = args[:log] || 0
|
18
|
+
@key = args[:key]
|
19
|
+
@agent = Mechanize.new
|
20
|
+
@page = nil
|
21
|
+
@element = fetch(@log, @key)
|
22
|
+
end
|
23
|
+
|
24
|
+
def fetch(log, key)
|
25
|
+
@page = @agent.get("#{Sosowa::BASE_URL}/?mode=read&log=#{log}&key=#{key}")
|
26
|
+
tags = (@page/%{dl[@class="info"][1] > dd > a}).map{|t| t.inner_html.to_s.toutf8 }
|
27
|
+
text = (@page/%{div[@class="contents ss"]})[0].inner_html.to_s.toutf8
|
28
|
+
ps = (@page/%{div[@class="aft"]})[0].inner_html.to_s.toutf8
|
29
|
+
author_name = (@page/%{div[@class="author"] b})[0].inner_html.to_s.toutf8
|
30
|
+
author_email, author_website = (@page/%{div[@class="author"] a}).map{|e| e.attributes["href"].value}
|
31
|
+
author = Author.new(:name => author_name, :email => (author_email ? author_email.gsub(/^mailto:/, "") : nil), :website => author_website)
|
32
|
+
header = (@page/%{div[@class="header"] > span})[0].inner_html.to_s.toutf8.split(/\r?\n/).map{|n| n.strip}.reject{|n| n == ""}.map{|n| n.split(": ")}
|
33
|
+
review = header[3][1].split("/")
|
34
|
+
comments = []
|
35
|
+
comment_element = (@page/%{div[@class="comments"] > dl > *})
|
36
|
+
comment_element[1, comment_element.size-1].each_slice(2) do |element|
|
37
|
+
bobj = element[0].search("b").map{|n| n.inner_html.to_s.toutf8.strip}
|
38
|
+
point = element[0].search("span").inner_html.to_s.toutf8.to_i
|
39
|
+
id = element[0].inner_html.to_s.toutf8.split(/\r?\n/).map{|n| n.strip}[1].to_i
|
40
|
+
comment = Comment.new(
|
41
|
+
:id => id,
|
42
|
+
:point => point,
|
43
|
+
:name => bobj[0],
|
44
|
+
:created_at => Time.parse(bobj[1].gsub(/[^\/\d\s:]/, "")),
|
45
|
+
:text => element[1].inner_html.to_s.toutf8.strip
|
46
|
+
)
|
47
|
+
comments << comment
|
48
|
+
end
|
49
|
+
novel = {
|
50
|
+
:text => text,
|
51
|
+
:ps => ps,
|
52
|
+
:author => author,
|
53
|
+
:tags => tags,
|
54
|
+
:log => log,
|
55
|
+
:key => key,
|
56
|
+
:created_at => Time.parse(header[1][1]),
|
57
|
+
:updated_at => Time.parse(header[2][1]),
|
58
|
+
:review_count => review[1].to_i,
|
59
|
+
:comment_count => review[0].to_i,
|
60
|
+
:point => header[4][1].to_i,
|
61
|
+
:rate => header[5][1].to_f,
|
62
|
+
:comments => comments
|
63
|
+
}
|
64
|
+
return novel
|
65
|
+
end
|
66
|
+
|
67
|
+
def simple_rating(point)
|
68
|
+
form = @page.forms[0]
|
69
|
+
form.click_button(form.button_with(:value => point.to_s))
|
70
|
+
end
|
71
|
+
|
72
|
+
def comment(text, params)
|
73
|
+
form = @page.forms[1]
|
74
|
+
form.field_with(:name => "name").value = params[:name] || nil
|
75
|
+
form.field_with(:name => "body").value = text
|
76
|
+
form.field_with(:name => "pass").value = params[:pass] || nil
|
77
|
+
form.field_with(:name => "mail").value = params[:mail] || nil
|
78
|
+
form.field_with(:name => "point").option_with(:value => (params[:point].to_s || "0")).select
|
79
|
+
form.click_button
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
class Comment < Scheme
|
84
|
+
|
85
|
+
end
|
86
|
+
|
87
|
+
class Author < Scheme
|
88
|
+
|
89
|
+
end
|
90
|
+
|
91
|
+
class Index < Scheme
|
92
|
+
def initialize(element)
|
93
|
+
super(@element)
|
94
|
+
@element = element
|
95
|
+
end
|
96
|
+
|
97
|
+
def fetch
|
98
|
+
Novel.new(:log => @element[:log], :key => @element[:key])
|
99
|
+
end
|
100
|
+
alias_method :get, :fetch
|
101
|
+
end
|
102
|
+
end
|
data/lib/sosowa.rb
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
$LOAD_PATH.unshift(File.expand_path("../", __FILE__))
|
2
|
+
require "kconv"
|
3
|
+
require "mechanize"
|
4
|
+
require "time"
|
5
|
+
require "cgi"
|
6
|
+
require "sosowa/version"
|
7
|
+
require "sosowa/scheme"
|
8
|
+
require "sosowa/parser"
|
9
|
+
|
10
|
+
module Sosowa
|
11
|
+
BASE_URL = "http://coolier.sytes.net:8080/sosowa/ssw_l"
|
12
|
+
|
13
|
+
def self.get(args={})
|
14
|
+
args[:log] ||= 0
|
15
|
+
parser = Parser.new
|
16
|
+
if args.has_key?(:key)
|
17
|
+
parser.fetch_novel(args[:log], args[:key])
|
18
|
+
else
|
19
|
+
parser.fetch_index(args[:log])
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
data/sosowa.gemspec
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/sosowa/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Oame"]
|
6
|
+
gem.email = ["oame@oameya.com"]
|
7
|
+
gem.description = %q{Sosowa Parser for Ruby}
|
8
|
+
gem.summary = %q{Sosowa Parser for Ruby.}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "sosowa"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = Sosowa::VERSION
|
17
|
+
gem.add_dependency "mechanize"
|
18
|
+
end
|
metadata
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: sosowa
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Oame
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-07-09 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: mechanize
|
16
|
+
requirement: &70129465130960 !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: *70129465130960
|
25
|
+
description: Sosowa Parser for Ruby
|
26
|
+
email:
|
27
|
+
- oame@oameya.com
|
28
|
+
executables: []
|
29
|
+
extensions: []
|
30
|
+
extra_rdoc_files: []
|
31
|
+
files:
|
32
|
+
- .gitignore
|
33
|
+
- Gemfile
|
34
|
+
- LICENSE
|
35
|
+
- README.md
|
36
|
+
- Rakefile
|
37
|
+
- lib/sosowa.rb
|
38
|
+
- lib/sosowa/parser.rb
|
39
|
+
- lib/sosowa/scheme.rb
|
40
|
+
- lib/sosowa/version.rb
|
41
|
+
- sosowa.gemspec
|
42
|
+
homepage: ''
|
43
|
+
licenses: []
|
44
|
+
post_install_message:
|
45
|
+
rdoc_options: []
|
46
|
+
require_paths:
|
47
|
+
- lib
|
48
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
55
|
+
none: false
|
56
|
+
requirements:
|
57
|
+
- - ! '>='
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: '0'
|
60
|
+
requirements: []
|
61
|
+
rubyforge_project:
|
62
|
+
rubygems_version: 1.8.10
|
63
|
+
signing_key:
|
64
|
+
specification_version: 3
|
65
|
+
summary: Sosowa Parser for Ruby.
|
66
|
+
test_files: []
|
67
|
+
has_rdoc:
|