scraping 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/.travis.yml +5 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +114 -0
- data/Rakefile +10 -0
- data/lib/scraping.rb +55 -0
- data/lib/scraping/dsl.rb +19 -0
- data/lib/scraping/rules/element.rb +26 -0
- data/lib/scraping/rules/elements.rb +29 -0
- data/lib/scraping/rules/elements_of.rb +26 -0
- data/lib/scraping/version.rb +3 -0
- data/scraping.gemspec +27 -0
- metadata +113 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b9aff8bf11dbde49763faa84c830518cb308daab
|
4
|
+
data.tar.gz: ba701a4490c085c2278ff93efbdeb244a9b74b12
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b6bc072d8df959e32b8cd5230db684ebffdb08d23ce3a2633a683042eed6f92a5f0c8e61b4c35ecd570975461d417a93f6941b1688d328eafb76cf958f247627
|
7
|
+
data.tar.gz: 0149081ebc7cd6073e2a178f10c1904e46a3e3cab8e2fa9f35fc82387b1a7938d4f48428a9eb58d1adc835680c5dc0248b76bd562fb7b1e8288cc24efca46154
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 Ray Zane
|
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 +1,114 @@
|
|
1
|
+
# Scraping
|
2
|
+
|
3
|
+
A really simple HTML scraping DSL.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'scraping'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
## Usage
|
18
|
+
|
19
|
+
#### A simple example
|
20
|
+
|
21
|
+
```ruby
|
22
|
+
class Person
|
23
|
+
include Scraping
|
24
|
+
element :name, 'h1'
|
25
|
+
end
|
26
|
+
|
27
|
+
person = Person.scrape('<h1>Millard Fillmore</h1>')
|
28
|
+
person.name #=> 'Millard Fillmore'
|
29
|
+
```
|
30
|
+
|
31
|
+
#### More complex data structures
|
32
|
+
|
33
|
+
You can also scrape arrays, objects, and arrays of objects. `elements` and `elements_of` can be deeply nested.
|
34
|
+
|
35
|
+
```ruby
|
36
|
+
class YouCan
|
37
|
+
include Scraping
|
38
|
+
elements :scrape, '.scrape'
|
39
|
+
|
40
|
+
elements :also_scrape, '.also-scrape li' do
|
41
|
+
element :name, 'a'
|
42
|
+
element :link, 'a/@href'
|
43
|
+
elements :numbers, 'span'
|
44
|
+
end
|
45
|
+
|
46
|
+
elements_of :nested_scrape do
|
47
|
+
element :data, '.data'
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
you_can = YouCan.scrape(<<-EOF)
|
52
|
+
<p class="scrape">
|
53
|
+
<span>Arrays</span>
|
54
|
+
<span>Too</span>
|
55
|
+
</p>
|
56
|
+
|
57
|
+
<ul class="also-scrape">
|
58
|
+
<li>
|
59
|
+
<a href="example.com">Meek Mill</a>
|
60
|
+
<span>1</span>
|
61
|
+
<span>2</span>
|
62
|
+
</li>
|
63
|
+
<li><a href="test.com">Drake</a></li>
|
64
|
+
<ul>
|
65
|
+
|
66
|
+
<p class="data">Beef</p>
|
67
|
+
EOF
|
68
|
+
|
69
|
+
you_can.scrape #=> ['Arrays', 'Too']
|
70
|
+
|
71
|
+
you_can.also_scrape.first.name #=> 'Meek Mill'
|
72
|
+
you_can.also_scrape.first.link #=> 'example.com'
|
73
|
+
you_can.also_scrape.first.numbers #=> ['1', '2']
|
74
|
+
|
75
|
+
you_can.nested_scrape.data #=> 'Beef'
|
76
|
+
```
|
77
|
+
|
78
|
+
#### Customizing extraction
|
79
|
+
|
80
|
+
Any block given to `#element` will allow you to customize the value extracted from the found node.
|
81
|
+
|
82
|
+
Using `as: :something` would call a method named `#extract_something`.
|
83
|
+
|
84
|
+
```ruby
|
85
|
+
class Advanced
|
86
|
+
element :first_name, '.name' do |node|
|
87
|
+
node.text.split(', ').first
|
88
|
+
end
|
89
|
+
|
90
|
+
element :birthday, '.birthday', as: :date
|
91
|
+
|
92
|
+
private
|
93
|
+
|
94
|
+
def extract_date(node)
|
95
|
+
Date.parse(node.text)
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
advanced = Advanced.new(<<-EOF)
|
100
|
+
<h1 class="name">Millard Fillmore</h1>
|
101
|
+
<h2 class="birthday">7-1-1800</h2>
|
102
|
+
EOF
|
103
|
+
|
104
|
+
advanced.first_name #=> 'Millard'
|
105
|
+
advanced.birthday #=> #<Date: 1800-01-07>
|
106
|
+
```
|
107
|
+
|
108
|
+
## Contributing
|
109
|
+
|
110
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/scraping.
|
111
|
+
|
112
|
+
## License
|
113
|
+
|
114
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/lib/scraping.rb
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'scraping/version'
|
3
|
+
require 'scraping/dsl'
|
4
|
+
require 'scraping/rules/element'
|
5
|
+
require 'scraping/rules/elements_of'
|
6
|
+
require 'scraping/rules/elements'
|
7
|
+
|
8
|
+
module Scraping
|
9
|
+
def self.included(base)
|
10
|
+
base.extend ClassMethods
|
11
|
+
|
12
|
+
base.class_eval do
|
13
|
+
attr_reader :page
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
def initialize(page)
|
18
|
+
@page = page
|
19
|
+
end
|
20
|
+
|
21
|
+
def scrape
|
22
|
+
self.class.rules.each do |name, rule|
|
23
|
+
public_send("#{name}=", rule.call(self, page))
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
module ClassMethods
|
28
|
+
include DSL
|
29
|
+
|
30
|
+
# Make the rules inheritable, but prevent mutation
|
31
|
+
# of the original hash
|
32
|
+
def inherited(subclass)
|
33
|
+
subclass.instance_variable_set(:@rules, rules.clone)
|
34
|
+
end
|
35
|
+
|
36
|
+
def element(name, *)
|
37
|
+
attr_accessor name
|
38
|
+
super
|
39
|
+
end
|
40
|
+
|
41
|
+
def elements_of(name)
|
42
|
+
attr_accessor name
|
43
|
+
super
|
44
|
+
end
|
45
|
+
|
46
|
+
def elements(name, *)
|
47
|
+
attr_accessor name
|
48
|
+
super
|
49
|
+
end
|
50
|
+
|
51
|
+
def scrape(html)
|
52
|
+
new(Nokogiri::HTML(html)).tap(&:scrape)
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
data/lib/scraping/dsl.rb
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
module Scraping
|
2
|
+
module DSL
|
3
|
+
def rules
|
4
|
+
@rules ||= {}
|
5
|
+
end
|
6
|
+
|
7
|
+
def element(name, selector, options = {}, &block)
|
8
|
+
rules[name] = Rules::Element.new(name, selector, options, &block)
|
9
|
+
end
|
10
|
+
|
11
|
+
def elements_of(name, &block)
|
12
|
+
rules[name] = Rules::ElementsOf.new(name).evaluate(&block)
|
13
|
+
end
|
14
|
+
|
15
|
+
def elements(name, selector, options = {}, &block)
|
16
|
+
rules[name] = Rules::Elements.new(name, selector, options).evaluate(&block)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
module Scraping
|
2
|
+
module Rules
|
3
|
+
class Element
|
4
|
+
attr_reader :name, :selector, :options, :extract
|
5
|
+
|
6
|
+
def initialize(name, selector, options = {}, &extract)
|
7
|
+
@name = name
|
8
|
+
@selector = selector
|
9
|
+
@options = options
|
10
|
+
@extract = extract if block_given?
|
11
|
+
end
|
12
|
+
|
13
|
+
def call(scraper, node)
|
14
|
+
item = node.at(selector)
|
15
|
+
|
16
|
+
if item && options[:as]
|
17
|
+
scraper.send("extract_#{options[:as]}", item)
|
18
|
+
elsif item && extract
|
19
|
+
scraper.instance_exec(item, &extract)
|
20
|
+
elsif item
|
21
|
+
item.text
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
module Scraping
|
2
|
+
module Rules
|
3
|
+
class Elements
|
4
|
+
attr_reader :name, :selector, :rule, :options
|
5
|
+
|
6
|
+
def initialize(name, selector, options = {})
|
7
|
+
@name = name
|
8
|
+
@selector = selector
|
9
|
+
@options = options
|
10
|
+
end
|
11
|
+
|
12
|
+
def evaluate(&block)
|
13
|
+
if block_given?
|
14
|
+
@rule = ElementsOf.new(name).evaluate(&block)
|
15
|
+
else
|
16
|
+
@rule = Element.new(name, '.', options)
|
17
|
+
end
|
18
|
+
|
19
|
+
self
|
20
|
+
end
|
21
|
+
|
22
|
+
def call(scraper, node)
|
23
|
+
node.search(selector).map do |item|
|
24
|
+
rule.call(scraper, item)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
require 'ostruct'
|
2
|
+
|
3
|
+
module Scraping
|
4
|
+
module Rules
|
5
|
+
class ElementsOf
|
6
|
+
include DSL
|
7
|
+
attr_reader :name
|
8
|
+
|
9
|
+
def initialize(name)
|
10
|
+
@name = name
|
11
|
+
end
|
12
|
+
|
13
|
+
def evaluate(&block)
|
14
|
+
instance_eval(&block)
|
15
|
+
self
|
16
|
+
end
|
17
|
+
|
18
|
+
def call(scraper, node)
|
19
|
+
rules.inject(OpenStruct.new) do |obj, (name, rule)|
|
20
|
+
obj[name] = rule.call(scraper, node)
|
21
|
+
obj
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
data/scraping.gemspec
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'scraping/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "scraping"
|
8
|
+
spec.version = Scraping::VERSION
|
9
|
+
spec.authors = ["Ray Zane"]
|
10
|
+
spec.email = ["ray@promptworks.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{A DSL for scraping HTML into objects}
|
13
|
+
spec.description = %q{A DSL for scraping HTML into objects}
|
14
|
+
spec.homepage = "https://github.com/rzane/scraping"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_dependency 'nokogiri'
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.12"
|
25
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
26
|
+
spec.add_development_dependency "minitest", "~> 5.0"
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,113 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scraping
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ray Zane
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-05-25 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
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: '1.12'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.12'
|
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
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: minitest
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '5.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '5.0'
|
69
|
+
description: A DSL for scraping HTML into objects
|
70
|
+
email:
|
71
|
+
- ray@promptworks.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- ".travis.yml"
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- lib/scraping.rb
|
83
|
+
- lib/scraping/dsl.rb
|
84
|
+
- lib/scraping/rules/element.rb
|
85
|
+
- lib/scraping/rules/elements.rb
|
86
|
+
- lib/scraping/rules/elements_of.rb
|
87
|
+
- lib/scraping/version.rb
|
88
|
+
- scraping.gemspec
|
89
|
+
homepage: https://github.com/rzane/scraping
|
90
|
+
licenses:
|
91
|
+
- MIT
|
92
|
+
metadata: {}
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options: []
|
95
|
+
require_paths:
|
96
|
+
- lib
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
|
+
requirements:
|
104
|
+
- - ">="
|
105
|
+
- !ruby/object:Gem::Version
|
106
|
+
version: '0'
|
107
|
+
requirements: []
|
108
|
+
rubyforge_project:
|
109
|
+
rubygems_version: 2.4.8
|
110
|
+
signing_key:
|
111
|
+
specification_version: 4
|
112
|
+
summary: A DSL for scraping HTML into objects
|
113
|
+
test_files: []
|