rumba-crawler 0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.travis.yml +5 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +86 -0
- data/Rakefile +4 -0
- data/lib/rumba/crawler.rb +28 -0
- data/lib/rumba/crawler/exceptions.rb +8 -0
- data/lib/rumba/crawler/models.rb +6 -0
- data/lib/rumba/crawler/parser.rb +72 -0
- data/lib/rumba/crawler/version.rb +5 -0
- data/rumba-crawler.gemspec +29 -0
- data/spec/crawler/parser_spec.rb +101 -0
- data/spec/crawler_spec.rb +23 -0
- data/spec/spec_helper.rb +9 -0
- metadata +160 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: d37db998d18c3cfbe4e350026c474f37a05e2469
|
4
|
+
data.tar.gz: 1df7bf2ad9d67e46440bd5a0fa57e6b73893a52d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 92455f66a6efcfc923b4d0d9f760f405418f9673e65dad7908e00ea0b103c5b2f0f103eabc9c6bb1fbcbbb90dfddc0ecf7189e87b0b5df24b23658515f6aa097
|
7
|
+
data.tar.gz: a8dc4d46b1a2db70b222ad383cebcd756a5e2e2dcc866a35da78cab04dea11a113722f69b79022b69a70829f8271e80ea4f583a1ca5715f1c7c42d7cc857f97c
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Volodymyr Ladnik
|
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 +1,86 @@
|
|
1
|
+
# Rumba::Crawler
|
2
|
+
[![Dependency Status](https://gemnasium.com/vladnik/rumba-crawler.png)](https://gemnasium.com/vladnik/rumba-crawler)
|
3
|
+
[![Build Status](https://travis-ci.org/vladnik/rumba-crawler.png?branch=master)](https://travis-ci.org/vladnik/rumba-crawler)
|
4
|
+
[![Code Climate](https://codeclimate.com/github/vladnik/rumba-crawler.png)](https://codeclimate.com/github/vladnik/rumba-crawler)
|
5
|
+
|
6
|
+
Web crawler with JSON-based DSL and EventMachine-powered page fetching
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
gem 'rumba-crawler'
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install rumba-crawler
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
Gem supports ```"css", "root" and "regexp"``` service keys:
|
24
|
+
* css: CSS locator for node
|
25
|
+
* root: custom root for current node (parent node is used by default )
|
26
|
+
* regexp: regular expression to extract data
|
27
|
+
|
28
|
+
If you have multiple objects of the same type, put object description into ```[ ]```.
|
29
|
+
|
30
|
+
Besides it supports shortcut for ```"css"``` attribute, so if you don't have any nested nodes(leaf node)
|
31
|
+
and you don't need ```"root" and "regexp"``` keys, you can omit "css" key and provide locator as string value
|
32
|
+
(```"name": "span.name"``` in example).
|
33
|
+
|
34
|
+
Map your models to page structure like this:
|
35
|
+
```json
|
36
|
+
[
|
37
|
+
{
|
38
|
+
"game": {
|
39
|
+
"css":".games",
|
40
|
+
"teams":[
|
41
|
+
{
|
42
|
+
"css": ".teams",
|
43
|
+
"name": "span.name",
|
44
|
+
"scores": {
|
45
|
+
"css":".score",
|
46
|
+
"regexp":"[0-9]+"
|
47
|
+
},
|
48
|
+
"sport": {
|
49
|
+
"css":"#sport",
|
50
|
+
"root":"body"
|
51
|
+
}
|
52
|
+
}
|
53
|
+
]
|
54
|
+
}
|
55
|
+
}
|
56
|
+
]
|
57
|
+
```
|
58
|
+
This will allow you to extract data from page for current model structure:
|
59
|
+
```ruby
|
60
|
+
class Game
|
61
|
+
# has_many :teams
|
62
|
+
def teams=(array_value)
|
63
|
+
array_value.each do |value|
|
64
|
+
Team.find_or_create(value)
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
class Team
|
69
|
+
# belongs_to :game
|
70
|
+
# belongs_to :sport
|
71
|
+
attr_writer :name, :scores
|
72
|
+
def sport=(value)
|
73
|
+
Sport.find_or_create(value)
|
74
|
+
end
|
75
|
+
end
|
76
|
+
class Sport
|
77
|
+
# has_many :teams
|
78
|
+
end
|
79
|
+
```
|
80
|
+
## Contributing
|
81
|
+
|
82
|
+
1. Fork it
|
83
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
84
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
85
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
86
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
require "date"
|
2
|
+
require "json"
|
3
|
+
require "em-http-request"
|
4
|
+
require "nokogiri"
|
5
|
+
require "rumba/crawler/version"
|
6
|
+
require "rumba/crawler/exceptions"
|
7
|
+
require "rumba/crawler/models"
|
8
|
+
require "rumba/crawler/parser"
|
9
|
+
|
10
|
+
module Rumba
|
11
|
+
module Crawler
|
12
|
+
|
13
|
+
def self.get_data(url, query)
|
14
|
+
EventMachine.run {
|
15
|
+
http = EventMachine::HttpRequest.new(url).get query: query
|
16
|
+
http.errback { raise Exceptions::BadResponse; EventMachine.stop }
|
17
|
+
http.callback {
|
18
|
+
if http.response_header.status >= 400
|
19
|
+
raise Exceptions::BadResponse
|
20
|
+
else
|
21
|
+
yield(http.response)
|
22
|
+
end
|
23
|
+
EventMachine.stop
|
24
|
+
}
|
25
|
+
}
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
module Rumba
|
2
|
+
module Crawler
|
3
|
+
class Parser
|
4
|
+
include Rumba::Crawler::Models
|
5
|
+
# Service Keys
|
6
|
+
SK = ['css', 'root', 'regexp']
|
7
|
+
|
8
|
+
def process(response, template)
|
9
|
+
template = JSON.parse(template)
|
10
|
+
@doc = Nokogiri::HTML(response)
|
11
|
+
if template.is_a? Array
|
12
|
+
parse_multi(@doc, template.first)
|
13
|
+
else
|
14
|
+
parse_node(@doc, template, template.keys.first)
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
def parse_multi(doc, template)
|
19
|
+
result = []
|
20
|
+
template.each do |key, value|
|
21
|
+
get_node(doc, value).each do |node|
|
22
|
+
result << create_object(key, node, value)
|
23
|
+
end
|
24
|
+
end
|
25
|
+
return result
|
26
|
+
end
|
27
|
+
|
28
|
+
def parse_node(doc, template, name)
|
29
|
+
node = get_node(doc, template).first
|
30
|
+
if leaf_node?(template)
|
31
|
+
get_content(node, template)
|
32
|
+
else
|
33
|
+
create_object(name, node, template)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
def create_object(name, node, template)
|
38
|
+
object = send(name)
|
39
|
+
template.reject{|key, _| SK.include?(key)}.each do |key, value|
|
40
|
+
if value.is_a? Array
|
41
|
+
object.send("#{key}=", parse_multi(node, value.first))
|
42
|
+
else
|
43
|
+
object.send("#{key}=", parse_node(node, value, key))
|
44
|
+
end
|
45
|
+
end
|
46
|
+
return object
|
47
|
+
end
|
48
|
+
|
49
|
+
def get_content(node, template)
|
50
|
+
if template['regexp']
|
51
|
+
/#{template['regexp']}/i.match(node.content).to_s
|
52
|
+
else
|
53
|
+
node.content
|
54
|
+
end
|
55
|
+
end
|
56
|
+
|
57
|
+
def get_node(doc, template)
|
58
|
+
if template.is_a?(String)
|
59
|
+
doc.css(template)
|
60
|
+
elsif template['root']
|
61
|
+
@doc.css(template['root']).css(template['css'])
|
62
|
+
else
|
63
|
+
doc.css(template['css'])
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
def leaf_node?(template)
|
68
|
+
template.is_a?(String) || template.reject{|key, _| SK.include?(key)}.empty?
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'rumba/crawler/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "rumba-crawler"
|
8
|
+
spec.version = Rumba::Crawler::VERSION
|
9
|
+
spec.authors = ["Volodymyr Ladnik"]
|
10
|
+
spec.email = ["Volodymyr.UA@gmail.com"]
|
11
|
+
spec.summary = %q{Web crawler with JSON-based DSL and EventMachine-powered page fetching}
|
12
|
+
spec.description = spec.summary
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_dependency "json", "~> 1.8.0"
|
22
|
+
spec.add_dependency "em-http-request", "~> 1.0.3"
|
23
|
+
spec.add_dependency "nokogiri", "~> 1.5.9"
|
24
|
+
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
26
|
+
spec.add_development_dependency "rake"
|
27
|
+
spec.add_development_dependency "rspec"
|
28
|
+
spec.add_development_dependency "webmock"
|
29
|
+
end
|
@@ -0,0 +1,101 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
module Rumba::Crawler
|
4
|
+
describe Parser do
|
5
|
+
let(:parser) { Parser.new }
|
6
|
+
|
7
|
+
describe '#process' do
|
8
|
+
it "invokes parse_multi for Array template" do
|
9
|
+
Nokogiri::HTML::Document.stub(parse: :parsed_doc)
|
10
|
+
parser.should_receive(:parse_multi).with(:parsed_doc, 'games').and_return([:result])
|
11
|
+
parser.process('<html><html>','["games"]').should eq [:result]
|
12
|
+
end
|
13
|
+
|
14
|
+
it "invokes parse_node for Object template" do
|
15
|
+
Nokogiri::HTML::Document.stub(parse: :parsed_doc)
|
16
|
+
parser.should_receive(:parse_node).with(:parsed_doc, {"game" => 123}, 'game').and_return(:result)
|
17
|
+
parser.process('<html><html>','{"game": 123}').should eq :result
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
describe '#parse_multi' do
|
22
|
+
it "creates object for every matching HTML node" do
|
23
|
+
parser.stub(get_node: [:node, :node])
|
24
|
+
parser.should_receive(:create_object).with(:key, :node, :value).twice.and_return(:result)
|
25
|
+
parser.parse_multi(:doc, {key: :value}).should eq [:result, :result]
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
describe '#parse_node' do
|
30
|
+
it "gets content for template leaf node" do
|
31
|
+
parser.stub(get_node: [:node])
|
32
|
+
parser.stub(leaf_node?: true)
|
33
|
+
parser.should_receive(:get_content).with(:node, :template).and_return('some content')
|
34
|
+
parser.parse_node(:doc, :template, :name).should eq 'some content'
|
35
|
+
end
|
36
|
+
it "creates object for template parent node" do
|
37
|
+
parser.stub(get_node: [:node])
|
38
|
+
parser.stub(leaf_node?: false)
|
39
|
+
parser.should_receive(:create_object).with(:name, :node, :template).and_return(:object)
|
40
|
+
parser.parse_node(:doc, :template, :name).should eq :object
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
describe "#create_object" do
|
45
|
+
it "creates an object" do
|
46
|
+
parser.should_receive(:name).and_return(:object)
|
47
|
+
parser.create_object(:name, :node, {'css' => 'body'}).should eq :object
|
48
|
+
end
|
49
|
+
it "invokes a setter with parse_multi method for object attributes with Array value" do
|
50
|
+
object = double("object")
|
51
|
+
object.should_receive(:name=).with(:result)
|
52
|
+
parser.should_receive(:parse_multi).with(:node, 'attr').and_return(:result)
|
53
|
+
parser.stub(game: object)
|
54
|
+
parser.create_object(:game, :node, {'css' => 'body', 'name' => ['attr']})
|
55
|
+
end
|
56
|
+
it "invokes a setter with parse_node method for object other attributes" do
|
57
|
+
object = double("object")
|
58
|
+
object.should_receive(:name=).with(:result)
|
59
|
+
parser.should_receive(:parse_node).with(:node, {"attr"=>"value"}, "name").and_return(:result)
|
60
|
+
parser.stub(game: object)
|
61
|
+
parser.create_object(:game, :node, {'css' => 'body', 'name' => {'attr' => 'value'}})
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
describe "#get_content" do
|
66
|
+
it "get node content" do
|
67
|
+
node = double("node")
|
68
|
+
node.should_receive(:content).and_return('some content')
|
69
|
+
parser.get_content(node, {}).should eq 'some content'
|
70
|
+
end
|
71
|
+
it "uses provided regexp to extract content" do
|
72
|
+
node = double("node")
|
73
|
+
node.should_receive(:content).and_return('content123')
|
74
|
+
parser.get_content(node, {'regexp' => '[a-z]+'}).should eq 'content'
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
describe "#get_node" do
|
79
|
+
it "uses css locator provided" do
|
80
|
+
node = double("node")
|
81
|
+
node.should_receive(:css).with('locator').and_return(:node)
|
82
|
+
parser.get_node(node, {'css' => 'locator'}).should eq :node
|
83
|
+
end
|
84
|
+
it "uses shortcut css locator" do
|
85
|
+
node = double("node")
|
86
|
+
node.should_receive(:css).with('locator').and_return(:node)
|
87
|
+
parser.get_node(node, 'locator').should eq :node
|
88
|
+
end
|
89
|
+
end
|
90
|
+
|
91
|
+
describe "#leaf_node?" do
|
92
|
+
it "identifies shortcut locator" do
|
93
|
+
parser.leaf_node?('locator').should eq true
|
94
|
+
end
|
95
|
+
it "identifies non-service attributes" do
|
96
|
+
parser.leaf_node?({'css' => 'locator'}).should eq true
|
97
|
+
parser.leaf_node?({'name' => 'locator'}).should eq false
|
98
|
+
end
|
99
|
+
end
|
100
|
+
end
|
101
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
module Rumba::Crawler
|
4
|
+
describe '#get_data' do
|
5
|
+
it "makes GET request to specified url with specified parameters" do
|
6
|
+
stub = stub_request(:get, "http://example.com/?date=now").to_return(status: 200, body: '', headers: {})
|
7
|
+
Rumba::Crawler.get_data('http://example.com', {date: 'now'}) { |response| }
|
8
|
+
stub.should have_been_requested
|
9
|
+
end
|
10
|
+
|
11
|
+
it "invokes callback method with response data" do
|
12
|
+
callback = double("callback")
|
13
|
+
callback.should_receive(:process_response).with('response data')
|
14
|
+
stub_request(:get, "http://example.com/?date=now").to_return(status: 200, body: 'response data', headers: {})
|
15
|
+
Rumba::Crawler.get_data('http://example.com', {date: 'now'}) { |response| callback.process_response(response)}
|
16
|
+
end
|
17
|
+
|
18
|
+
it "should raise exception on bad response" do
|
19
|
+
stub_request(:get, "http://example.com/?date=now").to_return(status: 400)
|
20
|
+
expect {Rumba::Crawler.get_data('http://example.com', {date: 'now'}) { |response| }}.to raise_error(Exceptions::BadResponse)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,160 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rumba-crawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: '0.1'
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Volodymyr Ladnik
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-06-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: json
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.8.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 1.8.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: em-http-request
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.0.3
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.0.3
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: nokogiri
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 1.5.9
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 1.5.9
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: bundler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.3'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.3'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rake
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
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: rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
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: webmock
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '>='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
description: Web crawler with JSON-based DSL and EventMachine-powered page fetching
|
112
|
+
email:
|
113
|
+
- Volodymyr.UA@gmail.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- .gitignore
|
119
|
+
- .travis.yml
|
120
|
+
- Gemfile
|
121
|
+
- LICENSE.txt
|
122
|
+
- README.md
|
123
|
+
- Rakefile
|
124
|
+
- lib/rumba/crawler.rb
|
125
|
+
- lib/rumba/crawler/exceptions.rb
|
126
|
+
- lib/rumba/crawler/models.rb
|
127
|
+
- lib/rumba/crawler/parser.rb
|
128
|
+
- lib/rumba/crawler/version.rb
|
129
|
+
- rumba-crawler.gemspec
|
130
|
+
- spec/crawler/parser_spec.rb
|
131
|
+
- spec/crawler_spec.rb
|
132
|
+
- spec/spec_helper.rb
|
133
|
+
homepage: ''
|
134
|
+
licenses:
|
135
|
+
- MIT
|
136
|
+
metadata: {}
|
137
|
+
post_install_message:
|
138
|
+
rdoc_options: []
|
139
|
+
require_paths:
|
140
|
+
- lib
|
141
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - '>='
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
147
|
+
requirements:
|
148
|
+
- - '>='
|
149
|
+
- !ruby/object:Gem::Version
|
150
|
+
version: '0'
|
151
|
+
requirements: []
|
152
|
+
rubyforge_project:
|
153
|
+
rubygems_version: 2.0.3
|
154
|
+
signing_key:
|
155
|
+
specification_version: 4
|
156
|
+
summary: Web crawler with JSON-based DSL and EventMachine-powered page fetching
|
157
|
+
test_files:
|
158
|
+
- spec/crawler/parser_spec.rb
|
159
|
+
- spec/crawler_spec.rb
|
160
|
+
- spec/spec_helper.rb
|