torimochi 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +40 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/torimochi.rb +12 -0
- data/lib/torimochi/node.rb +35 -0
- data/lib/torimochi/page.rb +26 -0
- data/lib/torimochi/scrapable.rb +19 -0
- data/lib/torimochi/version.rb +3 -0
- data/torimochi.gemspec +37 -0
- metadata +100 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4d3cef6425297166c1464e162cf36728c7bb1f80
|
4
|
+
data.tar.gz: 87c5d646591c1b3fbab59f75a14373e53c9e9e99
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: eb36813910d2816ed5c06bd0b21c2e8c1c6e9251569f60d76ae75bb004ee100ef027a1eb300037467de6036479529d1dfa938c8ebf0de789a20d12e960c814f8
|
7
|
+
data.tar.gz: 55b9b2dd7bbad340c79efad73037e7333cc1aff213737cea2d4e45f4c23a357b5b447b88751cff81f53ed8d07ece948b3e72ea381f537558ea529f5e6e009750
|
data/.gitignore
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at TODO: Write your email address. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 TODO: Write your name
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
# Torimochi
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/torimochi`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'torimochi'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install torimochi
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/tetsuya-ogawa/torimochi. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
36
|
+
|
37
|
+
|
38
|
+
## License
|
39
|
+
|
40
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "torimochi"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/torimochi.rb
ADDED
@@ -0,0 +1,12 @@
|
|
1
|
+
require 'torimochi/version'
|
2
|
+
require 'mechanize'
|
3
|
+
require 'torimochi/page'
|
4
|
+
require 'torimochi/node'
|
5
|
+
|
6
|
+
DEFAULT_URL = 'https://www.google.co.jp/'
|
7
|
+
|
8
|
+
module Torimochi
|
9
|
+
def self.new(url = DEFAULT_URL) # Torimochi.new
|
10
|
+
Torimochi::Page.new(url)
|
11
|
+
end
|
12
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
module Torimochi
|
2
|
+
class Node
|
3
|
+
attr_reader :node
|
4
|
+
def initialize(node)
|
5
|
+
@node = node
|
6
|
+
end
|
7
|
+
|
8
|
+
def title
|
9
|
+
title = @node.search('a')
|
10
|
+
NKF.nkf('-wxm0', exclusion_tag(title.children.to_html))
|
11
|
+
end
|
12
|
+
|
13
|
+
def url
|
14
|
+
url = @node.search('a').attr('href').value
|
15
|
+
URI.decode_www_form(url)[0][1]
|
16
|
+
end
|
17
|
+
|
18
|
+
def discription
|
19
|
+
discription = @node.search('span.st')
|
20
|
+
NKF.nkf('-wxm0', exclusion_tag(discription.children.to_html))
|
21
|
+
end
|
22
|
+
|
23
|
+
def normal? # 一番上にある変な奴はアブノーマルってことに。あとで命名変更
|
24
|
+
!discription.empty?
|
25
|
+
end
|
26
|
+
|
27
|
+
def search(param)
|
28
|
+
@node.search(param)
|
29
|
+
end
|
30
|
+
|
31
|
+
def exclusion_tag(str)
|
32
|
+
str.gsub(/\R|<b>|<\/b>|<br>|<\/br>/, '')
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
require 'torimochi/scrapable'
|
2
|
+
module Torimochi
|
3
|
+
class Page
|
4
|
+
include Scrapable
|
5
|
+
|
6
|
+
attr_accessor :url, :agent, :page
|
7
|
+
|
8
|
+
def initialize(url)
|
9
|
+
@url = url
|
10
|
+
@agent = Mechanize.new
|
11
|
+
@page = @agent.get(url)
|
12
|
+
end
|
13
|
+
|
14
|
+
def forms
|
15
|
+
@page.forms
|
16
|
+
end
|
17
|
+
|
18
|
+
def links
|
19
|
+
@page.links
|
20
|
+
end
|
21
|
+
|
22
|
+
def search_form_by(name)
|
23
|
+
forms.select{|form| form.name == name}
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module Scrapable
|
2
|
+
def search_by(kw)
|
3
|
+
return unless self.page
|
4
|
+
self.page = self.page.form_with(action: '/search') do |form|
|
5
|
+
form.q = kw
|
6
|
+
end.submit
|
7
|
+
end
|
8
|
+
|
9
|
+
def scraping(args, row = nil)
|
10
|
+
return unless self.page || block_given?
|
11
|
+
nodes = self.page.search(args)
|
12
|
+
nodes.each_with_index do |node, index|
|
13
|
+
t_node = Torimochi::Node.new(node)
|
14
|
+
next unless t_node.normal?
|
15
|
+
yield t_node
|
16
|
+
break if row && index == row
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
data/torimochi.gemspec
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'torimochi/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "torimochi"
|
8
|
+
spec.version = Torimochi::VERSION
|
9
|
+
spec.authors = ["Tetsuya Ogawa"]
|
10
|
+
spec.email = ["tetsuya.ogawa87@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{search scraping}
|
13
|
+
spec.description = %q{search scraping}
|
14
|
+
spec.homepage = "https://github.com/tetsuya-ogawa/torimochi"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
# if spec.respond_to?(:metadata)
|
20
|
+
# spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
|
21
|
+
# else
|
22
|
+
# raise "RubyGems 2.0 or newer is required to protect against " \
|
23
|
+
# "public gem pushes."
|
24
|
+
# end
|
25
|
+
|
26
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
27
|
+
f.match(%r{^(test|spec|features)/})
|
28
|
+
end
|
29
|
+
spec.bindir = "exe"
|
30
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
31
|
+
spec.require_paths = ["lib"]
|
32
|
+
|
33
|
+
spec.add_dependency "mechanize"
|
34
|
+
|
35
|
+
spec.add_development_dependency "bundler", "~> 1.13"
|
36
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
37
|
+
end
|
metadata
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: torimochi
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Tetsuya Ogawa
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-06-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: mechanize
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.13'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.13'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
description: search scraping
|
56
|
+
email:
|
57
|
+
- tetsuya.ogawa87@gmail.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- ".gitignore"
|
63
|
+
- CODE_OF_CONDUCT.md
|
64
|
+
- Gemfile
|
65
|
+
- LICENSE.txt
|
66
|
+
- README.md
|
67
|
+
- Rakefile
|
68
|
+
- bin/console
|
69
|
+
- bin/setup
|
70
|
+
- lib/torimochi.rb
|
71
|
+
- lib/torimochi/node.rb
|
72
|
+
- lib/torimochi/page.rb
|
73
|
+
- lib/torimochi/scrapable.rb
|
74
|
+
- lib/torimochi/version.rb
|
75
|
+
- torimochi.gemspec
|
76
|
+
homepage: https://github.com/tetsuya-ogawa/torimochi
|
77
|
+
licenses:
|
78
|
+
- MIT
|
79
|
+
metadata: {}
|
80
|
+
post_install_message:
|
81
|
+
rdoc_options: []
|
82
|
+
require_paths:
|
83
|
+
- lib
|
84
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - ">="
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '0'
|
89
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
90
|
+
requirements:
|
91
|
+
- - ">="
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
requirements: []
|
95
|
+
rubyforge_project:
|
96
|
+
rubygems_version: 2.5.2
|
97
|
+
signing_key:
|
98
|
+
specification_version: 4
|
99
|
+
summary: search scraping
|
100
|
+
test_files: []
|