rcrawler 0.0.1
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 +17 -0
- data/Gemfile +9 -0
- data/LICENSE.txt +22 -0
- data/README.md +49 -0
- data/Rakefile +9 -0
- data/lib/rcrawler.rb +20 -0
- data/lib/rcrawler/crawl.rb +17 -0
- data/lib/rcrawler/driver.rb +23 -0
- data/lib/rcrawler/version.rb +5 -0
- data/rcrawler.gemspec +29 -0
- data/spec/spec_helper.rb +15 -0
- metadata +154 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 06cb51462ed7694164d649bc33f28102ae5ed66a
|
4
|
+
data.tar.gz: fc4017fd01b7140517b1e13bcbda221ac672eb77
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2408c89221e3c7d4b9e6f11f1d2015d4471efe3492369ded48ba4a202fce1c30b74894201ccdd7af5cd6e94cfe8ea9090a1a11c38f3352f7929804884a7eb2a2
|
7
|
+
data.tar.gz: 6c77a1d1fab7789c3920524c746e8f1f7070a78df0b27f02a6db059eb1695a4c616389eb40939b9d6dc88d95e3ff4c7dd065b2aa01cb097ec326143612275cbe
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 i2bskn
|
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 +1,49 @@
|
|
1
|
+
# Rcrawler
|
2
|
+
|
3
|
+
The wrapper of capybara for crawler.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'rcrawler'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install rcrawler
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
```ruby
|
22
|
+
require "rcrawler"
|
23
|
+
|
24
|
+
RCrawler.crawl do
|
25
|
+
# Some capybara dsl
|
26
|
+
visit("https://example.com/login")
|
27
|
+
page.fill_in("name", with: "user")
|
28
|
+
page.fill_in("password", with: "secret")
|
29
|
+
page.click_button("send")
|
30
|
+
page.save_screenshot("/tmp/example.png")
|
31
|
+
|
32
|
+
# Screenshot shortcut
|
33
|
+
# visit(arg[0]) and page.save_screenshot(arg[1])
|
34
|
+
screenshot("http://example.com", "/tmp/example.png")
|
35
|
+
|
36
|
+
# Nokogiri
|
37
|
+
# doc is return Nokogiri::HTML(page.html)
|
38
|
+
visit("http://example.com")
|
39
|
+
doc.css("a.some_link").each {|a| puts a.attr("href")}
|
40
|
+
end
|
41
|
+
```
|
42
|
+
|
43
|
+
## Contributing
|
44
|
+
|
45
|
+
1. Fork it
|
46
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
47
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
48
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
49
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/lib/rcrawler.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
require "capybara"
|
4
|
+
require "capybara/dsl"
|
5
|
+
require "capybara-webkit"
|
6
|
+
require "nokogiri"
|
7
|
+
require "headless"
|
8
|
+
|
9
|
+
require "rcrawler/version"
|
10
|
+
require "rcrawler/driver"
|
11
|
+
require "rcrawler/crawl"
|
12
|
+
|
13
|
+
module RCrawler
|
14
|
+
class << self
|
15
|
+
def crawl(&block)
|
16
|
+
c = Crawl.new
|
17
|
+
c.instance_eval &block
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
module RCrawler
|
4
|
+
class Crawl < BasicObject
|
5
|
+
def initialize
|
6
|
+
@driver = Driver.new
|
7
|
+
end
|
8
|
+
|
9
|
+
def method_missing(action, *args)
|
10
|
+
if @driver.respond_to? action
|
11
|
+
@driver.send(action, *args)
|
12
|
+
else
|
13
|
+
super
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
module RCrawler
|
4
|
+
class Driver
|
5
|
+
Capybara.default_driver = :webkit
|
6
|
+
include Capybara::DSL
|
7
|
+
attr_accessor :headless
|
8
|
+
|
9
|
+
def initialize(options={})
|
10
|
+
@headless = options.fetch(:headless, Headless.new)
|
11
|
+
@headless.start if @headless
|
12
|
+
end
|
13
|
+
|
14
|
+
def screenshot(url, file_path)
|
15
|
+
visit(url)
|
16
|
+
page.save_screenshot(file_path)
|
17
|
+
end
|
18
|
+
|
19
|
+
def doc
|
20
|
+
Nokogiri::HTML(page.html)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/rcrawler.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'rcrawler/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "rcrawler"
|
8
|
+
spec.version = RCrawler::VERSION
|
9
|
+
spec.authors = ["i2bskn"]
|
10
|
+
spec.email = ["i2bskn@gmail.com"]
|
11
|
+
spec.description = %q{The wrapper of capybara for crawler}
|
12
|
+
spec.summary = %q{The wrapper of capybara for crawler}
|
13
|
+
spec.homepage = "https://github.com/i2bskn/rcrawler"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
|
25
|
+
spec.add_dependency "capybara"
|
26
|
+
spec.add_dependency "capybara-webkit"
|
27
|
+
spec.add_dependency "nokogiri"
|
28
|
+
spec.add_dependency "headless"
|
29
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
# require "simplecov"
|
2
|
+
# require "coveralls"
|
3
|
+
# Coveralls.wear!
|
4
|
+
|
5
|
+
# SimpleCov.formatter = SimpleCov::Formatter::HTMLFormatter
|
6
|
+
# SimpleCov.start do
|
7
|
+
# add_filter "spec"
|
8
|
+
# add_filter ".bundle"
|
9
|
+
# end
|
10
|
+
|
11
|
+
require "rcrawler"
|
12
|
+
|
13
|
+
RSpec.configure do |config|
|
14
|
+
config.order = "random"
|
15
|
+
end
|
metadata
ADDED
@@ -0,0 +1,154 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rcrawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- i2bskn
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-07-02 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: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
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: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
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: capybara
|
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
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: capybara-webkit
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '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: '0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: headless
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '>='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
description: The wrapper of capybara for crawler
|
112
|
+
email:
|
113
|
+
- i2bskn@gmail.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- .gitignore
|
119
|
+
- Gemfile
|
120
|
+
- LICENSE.txt
|
121
|
+
- README.md
|
122
|
+
- Rakefile
|
123
|
+
- lib/rcrawler.rb
|
124
|
+
- lib/rcrawler/crawl.rb
|
125
|
+
- lib/rcrawler/driver.rb
|
126
|
+
- lib/rcrawler/version.rb
|
127
|
+
- rcrawler.gemspec
|
128
|
+
- spec/spec_helper.rb
|
129
|
+
homepage: https://github.com/i2bskn/rcrawler
|
130
|
+
licenses:
|
131
|
+
- MIT
|
132
|
+
metadata: {}
|
133
|
+
post_install_message:
|
134
|
+
rdoc_options: []
|
135
|
+
require_paths:
|
136
|
+
- lib
|
137
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
138
|
+
requirements:
|
139
|
+
- - '>='
|
140
|
+
- !ruby/object:Gem::Version
|
141
|
+
version: '0'
|
142
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
143
|
+
requirements:
|
144
|
+
- - '>='
|
145
|
+
- !ruby/object:Gem::Version
|
146
|
+
version: '0'
|
147
|
+
requirements: []
|
148
|
+
rubyforge_project:
|
149
|
+
rubygems_version: 2.0.2
|
150
|
+
signing_key:
|
151
|
+
specification_version: 4
|
152
|
+
summary: The wrapper of capybara for crawler
|
153
|
+
test_files:
|
154
|
+
- spec/spec_helper.rb
|