ginspider 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +49 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +39 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/ginspider.gemspec +36 -0
- data/lib/ginspider.rb +2 -0
- data/lib/ginspider.rb.bak +13 -0
- data/lib/ginspider/analysis.rb +28 -0
- data/lib/ginspider/http.rb +44 -0
- data/lib/ginspider/main.rb +27 -0
- data/lib/ginspider/version.rb +3 -0
- metadata +146 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 29fa6c15ccb053fa0634bbfa9507de6a1d5a63a4
|
4
|
+
data.tar.gz: ba3dbf3cbade0a9234e52f81ed5c3b553f25175d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 8562aa005f132860a2038670e505edb00ce2021c33eb041dff6f25ad4a5ae730468583669bf70a68449398e9a57f32b1272c1c18fe717f7753291007f7de3503
|
7
|
+
data.tar.gz: 143b860949224be710f653d373f4fb2c64af49875421dc9123afe64d9a3cbe2c04772ec6220f592a3d776d4cfdafaca369302a6aa4cc21abf7e97b2abf56a7e6
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, and in the interest of
|
4
|
+
fostering an open and welcoming community, we pledge to respect all people who
|
5
|
+
contribute through reporting issues, posting feature requests, updating
|
6
|
+
documentation, submitting pull requests or patches, and other activities.
|
7
|
+
|
8
|
+
We are committed to making participation in this project a harassment-free
|
9
|
+
experience for everyone, regardless of level of experience, gender, gender
|
10
|
+
identity and expression, sexual orientation, disability, personal appearance,
|
11
|
+
body size, race, ethnicity, age, religion, or nationality.
|
12
|
+
|
13
|
+
Examples of unacceptable behavior by participants include:
|
14
|
+
|
15
|
+
* The use of sexualized language or imagery
|
16
|
+
* Personal attacks
|
17
|
+
* Trolling or insulting/derogatory comments
|
18
|
+
* Public or private harassment
|
19
|
+
* Publishing other's private information, such as physical or electronic
|
20
|
+
addresses, without explicit permission
|
21
|
+
* Other unethical or unprofessional conduct
|
22
|
+
|
23
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
24
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
25
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
26
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
27
|
+
threatening, offensive, or harmful.
|
28
|
+
|
29
|
+
By adopting this Code of Conduct, project maintainers commit themselves to
|
30
|
+
fairly and consistently applying these principles to every aspect of managing
|
31
|
+
this project. Project maintainers who do not follow or enforce the Code of
|
32
|
+
Conduct may be permanently removed from the project team.
|
33
|
+
|
34
|
+
This code of conduct applies both within project spaces and in public spaces
|
35
|
+
when an individual is representing the project or its community.
|
36
|
+
|
37
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
38
|
+
reported by contacting a project maintainer at gin.lance.inside@hotmail.com. All
|
39
|
+
complaints will be reviewed and investigated and will result in a response that
|
40
|
+
is deemed necessary and appropriate to the circumstances. Maintainers are
|
41
|
+
obligated to maintain confidentiality with regard to the reporter of an
|
42
|
+
incident.
|
43
|
+
|
44
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
45
|
+
version 1.3.0, available at
|
46
|
+
[http://contributor-covenant.org/version/1/3/0/][version]
|
47
|
+
|
48
|
+
[homepage]: http://contributor-covenant.org
|
49
|
+
[version]: http://contributor-covenant.org/version/1/3/0/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 lancegin
|
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 +1,39 @@
|
|
1
|
+
# Ginspider
|
2
|
+
|
3
|
+
Ginspider is a powerful gem to analyze the common websites, it will be easier to get the HTTP request data.
|
4
|
+
|
5
|
+
The main ruby code in the file `lib/ginspider`. To experiment with that code, run `bin/console` for an interactive prompt.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'ginspider'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install ginspider
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
useages
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
## Contributing
|
32
|
+
|
33
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/LanceGin/ginspider. 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.
|
34
|
+
|
35
|
+
|
36
|
+
## License
|
37
|
+
|
38
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
39
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "ginspider"
|
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/ginspider.gemspec
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'ginspider/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ginspider"
|
8
|
+
spec.version = Ginspider::VERSION
|
9
|
+
spec.authors = ["lancegin"]
|
10
|
+
spec.email = ["gin.lance.inside@hotmail.com"]
|
11
|
+
|
12
|
+
spec.summary = "to analyze some websites"
|
13
|
+
# spec.description = %q{TODO: Write a longer description or delete this line.}
|
14
|
+
spec.homepage = "https://github.com/LanceGin/GinSpider"
|
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'] = "https://rubygems.org"
|
21
|
+
else
|
22
|
+
raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
|
23
|
+
end
|
24
|
+
|
25
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
26
|
+
spec.bindir = "exe"
|
27
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
28
|
+
spec.require_paths = ["lib"]
|
29
|
+
|
30
|
+
spec.add_development_dependency "bundler", "~> 1.12"
|
31
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
32
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
33
|
+
spec.add_development_dependency "awesome_print", "~> 1.7"
|
34
|
+
spec.add_development_dependency "http", "~> 2.0"
|
35
|
+
spec.add_development_dependency "nokogiri", "~> 1.6"
|
36
|
+
end
|
data/lib/ginspider.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'ginspider/http'
|
3
|
+
|
4
|
+
module Ginspider
|
5
|
+
|
6
|
+
class Analysis
|
7
|
+
|
8
|
+
#
|
9
|
+
# return nokogiri response
|
10
|
+
#
|
11
|
+
def self.noko_res(url)
|
12
|
+
res_body = Http.res_body(url)
|
13
|
+
@noko_res = get_noko_res(res_body)
|
14
|
+
return @noko_res
|
15
|
+
end
|
16
|
+
|
17
|
+
private
|
18
|
+
#
|
19
|
+
# generate a nokogiri response
|
20
|
+
#
|
21
|
+
def self.get_noko_res(res_body)
|
22
|
+
noko_res = Nokogiri::HTML(res_body.to_s)
|
23
|
+
return noko_res
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require 'http'
|
2
|
+
|
3
|
+
module Ginspider
|
4
|
+
|
5
|
+
class Http
|
6
|
+
|
7
|
+
#
|
8
|
+
# return the basic response of the http request
|
9
|
+
#
|
10
|
+
def self.basic_res(url)
|
11
|
+
@basic_res = get_basic_res(url)
|
12
|
+
return @basic_res
|
13
|
+
end
|
14
|
+
|
15
|
+
#
|
16
|
+
# return thr response body of the http request
|
17
|
+
#
|
18
|
+
def self.res_body(url)
|
19
|
+
@res_body = get_res_body(url)
|
20
|
+
return @res_body
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
#
|
26
|
+
# get the basic response of an HTTP request
|
27
|
+
#
|
28
|
+
def self.get_basic_res(url)
|
29
|
+
basic_res = HTTP.get(url)
|
30
|
+
return basic_res
|
31
|
+
end
|
32
|
+
|
33
|
+
#
|
34
|
+
# get the response body
|
35
|
+
#
|
36
|
+
def self.get_res_body(url)
|
37
|
+
basic_res = get_basic_res(url)
|
38
|
+
res_body = basic_res.body
|
39
|
+
return res_body
|
40
|
+
end
|
41
|
+
|
42
|
+
end
|
43
|
+
|
44
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'awesome_print'
|
2
|
+
require 'ginspider/version'
|
3
|
+
require 'ginspider/http'
|
4
|
+
require 'ginspider/analysis'
|
5
|
+
|
6
|
+
module Ginspider
|
7
|
+
|
8
|
+
#
|
9
|
+
# the main method to crawl a website
|
10
|
+
#
|
11
|
+
def Ginspider.crawl(url, options = {})
|
12
|
+
Main.crawl(url, options)
|
13
|
+
end
|
14
|
+
|
15
|
+
class Main
|
16
|
+
|
17
|
+
#
|
18
|
+
# define the main crawler
|
19
|
+
#
|
20
|
+
def self.crawl(url, options = {})
|
21
|
+
noko_res = Analysis.noko_res(url)
|
22
|
+
ap noko_res.css(options["element"]).text
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,146 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ginspider
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- lancegin
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-07-08 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: '1.12'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.12'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: awesome_print
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.7'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.7'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: http
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '2.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '2.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: nokogiri
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.6'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.6'
|
97
|
+
description:
|
98
|
+
email:
|
99
|
+
- gin.lance.inside@hotmail.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".gitignore"
|
105
|
+
- ".rspec"
|
106
|
+
- ".travis.yml"
|
107
|
+
- CODE_OF_CONDUCT.md
|
108
|
+
- Gemfile
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
- Rakefile
|
112
|
+
- bin/console
|
113
|
+
- bin/setup
|
114
|
+
- ginspider.gemspec
|
115
|
+
- lib/ginspider.rb
|
116
|
+
- lib/ginspider.rb.bak
|
117
|
+
- lib/ginspider/analysis.rb
|
118
|
+
- lib/ginspider/http.rb
|
119
|
+
- lib/ginspider/main.rb
|
120
|
+
- lib/ginspider/version.rb
|
121
|
+
homepage: https://github.com/LanceGin/GinSpider
|
122
|
+
licenses:
|
123
|
+
- MIT
|
124
|
+
metadata:
|
125
|
+
allowed_push_host: https://rubygems.org
|
126
|
+
post_install_message:
|
127
|
+
rdoc_options: []
|
128
|
+
require_paths:
|
129
|
+
- lib
|
130
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
131
|
+
requirements:
|
132
|
+
- - ">="
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
version: '0'
|
135
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
136
|
+
requirements:
|
137
|
+
- - ">="
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: '0'
|
140
|
+
requirements: []
|
141
|
+
rubyforge_project:
|
142
|
+
rubygems_version: 2.6.6
|
143
|
+
signing_key:
|
144
|
+
specification_version: 4
|
145
|
+
summary: to analyze some websites
|
146
|
+
test_files: []
|