scruber 0.1.1
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 +15 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/Gemfile +6 -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/exe/scruber +4 -0
- data/lib/scruber/app_searcher.rb +31 -0
- data/lib/scruber/cli/project_generator.rb +47 -0
- data/lib/scruber/cli/templates/Gemfile.tt +6 -0
- data/lib/scruber/cli/templates/application.tt +18 -0
- data/lib/scruber/cli/templates/bin/scruber.tt +6 -0
- data/lib/scruber/cli/templates/boot.tt +3 -0
- data/lib/scruber/cli/templates/gitignore.tt +12 -0
- data/lib/scruber/cli/templates/initializers/proxies.tt +10 -0
- data/lib/scruber/cli/templates/initializers/user_agents.tt +14 -0
- data/lib/scruber/cli/templates/scrapers/sample.tt +7 -0
- data/lib/scruber/cli.rb +40 -0
- data/lib/scruber/core/configuration.rb +30 -0
- data/lib/scruber/core/crawler.rb +92 -0
- data/lib/scruber/core/extensions/base.rb +26 -0
- data/lib/scruber/core/extensions/csv_output.rb +62 -0
- data/lib/scruber/core/extensions/loop.rb +39 -0
- data/lib/scruber/core/page_format/base.rb +11 -0
- data/lib/scruber/core/page_format/html.rb +13 -0
- data/lib/scruber/core/page_format/xml.rb +13 -0
- data/lib/scruber/core/page_format.rb +33 -0
- data/lib/scruber/fetcher.rb +34 -0
- data/lib/scruber/fetcher_adapters/abstract_adapter.rb +119 -0
- data/lib/scruber/fetcher_adapters/typhoeus_fetcher.rb +78 -0
- data/lib/scruber/helpers/dictionary_reader/csv.rb +27 -0
- data/lib/scruber/helpers/dictionary_reader/xml.rb +23 -0
- data/lib/scruber/helpers/dictionary_reader.rb +33 -0
- data/lib/scruber/helpers/fetcher_agent.rb +40 -0
- data/lib/scruber/helpers/fetcher_agent_adapters/abstract_adapter.rb +69 -0
- data/lib/scruber/helpers/fetcher_agent_adapters/memory.rb +41 -0
- data/lib/scruber/helpers/proxy_rotator.rb +125 -0
- data/lib/scruber/helpers/user_agent_rotator.rb +91 -0
- data/lib/scruber/queue.rb +34 -0
- data/lib/scruber/queue_adapters/abstract_adapter.rb +112 -0
- data/lib/scruber/queue_adapters/memory.rb +70 -0
- data/lib/scruber/version.rb +3 -0
- data/lib/scruber.rb +69 -0
- data/scruber.gemspec +43 -0
- metadata +233 -0
@@ -0,0 +1,91 @@
|
|
1
|
+
module Scruber
|
2
|
+
module Helpers
|
3
|
+
class UserAgentRotator
|
4
|
+
|
5
|
+
class UserAgent
|
6
|
+
attr_accessor :name, :tags
|
7
|
+
|
8
|
+
def initialize(name, options={})
|
9
|
+
@name = name
|
10
|
+
raise Scruber::ArgumentError.new("You need to specify name") if @name.blank?
|
11
|
+
@tags = options.fetch(:tags){ [] } || []
|
12
|
+
if !@tags.is_a?(Array)
|
13
|
+
@tags = [@tags]
|
14
|
+
end
|
15
|
+
@tags = @tags.compact.map(&:to_sym)
|
16
|
+
end
|
17
|
+
|
18
|
+
def id
|
19
|
+
@name
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
class Configuration
|
24
|
+
include Scruber::Core::Extensions::Loop::CoreMethods
|
25
|
+
|
26
|
+
attr_reader :user_agents, :tags
|
27
|
+
|
28
|
+
def initialize
|
29
|
+
@tags = :all
|
30
|
+
@user_agents = []
|
31
|
+
end
|
32
|
+
|
33
|
+
def configure(&block)
|
34
|
+
instance_eval &block
|
35
|
+
end
|
36
|
+
|
37
|
+
def clean
|
38
|
+
@user_agents = []
|
39
|
+
end
|
40
|
+
|
41
|
+
def add(name, options={})
|
42
|
+
ua = UserAgent.new(name, options)
|
43
|
+
@user_agents.push ua
|
44
|
+
end
|
45
|
+
|
46
|
+
def set_filter(tags)
|
47
|
+
@tags = tags
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
class << self
|
52
|
+
attr_writer :configuration
|
53
|
+
attr_accessor :cursor
|
54
|
+
|
55
|
+
def configuration
|
56
|
+
@configuration ||= Configuration.new
|
57
|
+
end
|
58
|
+
|
59
|
+
def configure(&block)
|
60
|
+
configuration.configure(&block)
|
61
|
+
end
|
62
|
+
|
63
|
+
def next(tags=nil)
|
64
|
+
raise Scruber::ArgumentError.new("UserAgent rotator not configured") if @configuration.nil?
|
65
|
+
tags = @configuration.tags if tags.blank?
|
66
|
+
user_agents = get_collection(tags)
|
67
|
+
if @cursor.nil? || @cursor >= user_agents.count-1
|
68
|
+
@cursor = 0
|
69
|
+
else
|
70
|
+
@cursor += 1
|
71
|
+
end
|
72
|
+
user_agents[@cursor].name
|
73
|
+
end
|
74
|
+
|
75
|
+
private
|
76
|
+
|
77
|
+
def get_collection(tags)
|
78
|
+
if tags == :all
|
79
|
+
@configuration.user_agents
|
80
|
+
else
|
81
|
+
if !tags.is_a?(Array)
|
82
|
+
tags = [tags]
|
83
|
+
end
|
84
|
+
tags = tags.compact.map(&:to_sym)
|
85
|
+
@configuration.user_agents.select{|ua| tags.all?{|t| ua.tags.include?(t) } }
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
module Scruber
|
2
|
+
module Queue
|
3
|
+
class << self
|
4
|
+
attr_writer :adapter
|
5
|
+
|
6
|
+
def new(options={})
|
7
|
+
adapter.new(::Scruber.configuration.queue_options.merge(options))
|
8
|
+
end
|
9
|
+
|
10
|
+
def adapter
|
11
|
+
unless @adapter
|
12
|
+
@adapter = ::Scruber.configuration.queue_adapter || _adapters.keys.first
|
13
|
+
end
|
14
|
+
raise Scruber::ArgumentError.new("Adapter not found") unless @adapter
|
15
|
+
_adapters[@adapter]
|
16
|
+
end
|
17
|
+
|
18
|
+
def add_adapter(label, claz)
|
19
|
+
unless claz.method_defined?(:add)
|
20
|
+
raise NoMethodError, "add is not declared in the #{label.inspect}"
|
21
|
+
end
|
22
|
+
_adapters[label] = claz
|
23
|
+
end
|
24
|
+
|
25
|
+
def [](label)
|
26
|
+
_adapters[label]
|
27
|
+
end
|
28
|
+
|
29
|
+
def _adapters
|
30
|
+
@_adapters ||= {}
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
@@ -0,0 +1,112 @@
|
|
1
|
+
module Scruber
|
2
|
+
module QueueAdapters
|
3
|
+
class AbstractAdapter
|
4
|
+
|
5
|
+
class Page
|
6
|
+
attr_accessor :url,
|
7
|
+
:method,
|
8
|
+
:user_agent,
|
9
|
+
:post_body,
|
10
|
+
:headers,
|
11
|
+
:fetcher_agent_id,
|
12
|
+
:proxy_id,
|
13
|
+
:response_body,
|
14
|
+
:response_code,
|
15
|
+
:response_headers,
|
16
|
+
:response_total_time,
|
17
|
+
:retry_at,
|
18
|
+
:fetched_at,
|
19
|
+
:retry_count,
|
20
|
+
:max_retry_times,
|
21
|
+
:enqueued_at,
|
22
|
+
:page_type,
|
23
|
+
:queue,
|
24
|
+
:priority,
|
25
|
+
:processed_at,
|
26
|
+
:options
|
27
|
+
|
28
|
+
def initialize(queue, url, options={})
|
29
|
+
@queue = queue
|
30
|
+
@url = url
|
31
|
+
@method = options.fetch(:method) { :get }
|
32
|
+
@user_agent = options.fetch(:user_agent) { nil }
|
33
|
+
@post_body = options.fetch(:post_body) { nil }
|
34
|
+
@headers = options.fetch(:headers) { {} }
|
35
|
+
@fetcher_agent_id = options.fetch(:fetcher_agent_id) { nil }
|
36
|
+
@proxy_id = options.fetch(:proxy_id) { nil }
|
37
|
+
@response_body = options.fetch(:response_body) { nil }
|
38
|
+
@response_code = options.fetch(:response_code) { nil }
|
39
|
+
@response_headers = options.fetch(:response_headers) { {} }
|
40
|
+
@response_total_time = options.fetch(:response_total_time) { nil }
|
41
|
+
@retry_at = options.fetch(:retry_at) { 0 }
|
42
|
+
@fetched_at = options.fetch(:fetched_at) { 0 }
|
43
|
+
@retry_count = options.fetch(:retry_count) { 0 }
|
44
|
+
@max_retry_times = options.fetch(:max_retry_times) { nil }
|
45
|
+
@enqueued_at = options.fetch(:enqueued_at) { 0 }
|
46
|
+
@page_type = options.fetch(:page_type) { :seed }
|
47
|
+
# @queue = options.fetch(:queue) { 'default' }
|
48
|
+
@priority = options.fetch(:priority) { 0 }
|
49
|
+
@processed_at = options.fetch(:processed_at) { 0 }
|
50
|
+
@options = options
|
51
|
+
|
52
|
+
@_fetcher_agent = false
|
53
|
+
@_proxy = false
|
54
|
+
end
|
55
|
+
|
56
|
+
def fetcher_agent
|
57
|
+
if @_fetcher_agent == false
|
58
|
+
@_fetcher_agent = (@fetcher_agent_id ? Scruber::Helpers::FetcherAgent.find(@fetcher_agent_id) : nil)
|
59
|
+
else
|
60
|
+
@_fetcher_agent
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
def proxy
|
65
|
+
if @_proxy == false
|
66
|
+
@_proxy = (@proxy_id ? Scruber::Helpers::ProxyRotator.find(@proxy_id) : nil)
|
67
|
+
else
|
68
|
+
@_proxy
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
def response_cookies
|
73
|
+
cookies = self.response_headers['Set-Cookie']
|
74
|
+
if cookies.blank?
|
75
|
+
[]
|
76
|
+
else
|
77
|
+
if cookies.is_a?(Array)
|
78
|
+
cookies
|
79
|
+
else
|
80
|
+
[cookies]
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
def save
|
86
|
+
raise NotImplementedError
|
87
|
+
end
|
88
|
+
|
89
|
+
def [](k)
|
90
|
+
instance_variable_get("@#{k.to_s}")
|
91
|
+
end
|
92
|
+
|
93
|
+
end
|
94
|
+
|
95
|
+
def initialize(options={})
|
96
|
+
@options = options
|
97
|
+
end
|
98
|
+
|
99
|
+
def add(url, options={})
|
100
|
+
raise NotImplementedError
|
101
|
+
end
|
102
|
+
|
103
|
+
def fetch_pending(count=nil)
|
104
|
+
raise NotImplementedError
|
105
|
+
end
|
106
|
+
|
107
|
+
def fetch_downloaded(count=nil)
|
108
|
+
raise NotImplementedError
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
112
|
+
end
|
@@ -0,0 +1,70 @@
|
|
1
|
+
module Scruber
|
2
|
+
module QueueAdapters
|
3
|
+
class Memory < AbstractAdapter
|
4
|
+
attr_reader :error_pages
|
5
|
+
|
6
|
+
class Page < Scruber::QueueAdapters::AbstractAdapter::Page
|
7
|
+
def save
|
8
|
+
if self.fetched_at > 0
|
9
|
+
@queue.add_downloaded self
|
10
|
+
elsif self.retry_count >= self.max_retry_times.to_i
|
11
|
+
@queue.add_error_page self
|
12
|
+
else
|
13
|
+
@queue.push self
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
def initialize(options={})
|
19
|
+
super(options)
|
20
|
+
@queue = []
|
21
|
+
@downloaded_pages = []
|
22
|
+
@error_pages = []
|
23
|
+
end
|
24
|
+
|
25
|
+
def push(url_or_page, options={})
|
26
|
+
if url_or_page.is_a?(Page)
|
27
|
+
@queue.push url_or_page
|
28
|
+
else
|
29
|
+
@queue.push Page.new(self, url_or_page, options)
|
30
|
+
end
|
31
|
+
end
|
32
|
+
alias_method :add, :push
|
33
|
+
|
34
|
+
def queue_size
|
35
|
+
@queue.count
|
36
|
+
end
|
37
|
+
|
38
|
+
def fetch_downloaded(count=nil)
|
39
|
+
if count.nil?
|
40
|
+
@downloaded_pages.shift
|
41
|
+
else
|
42
|
+
@downloaded_pages.shift(count)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def fetch_pending(count=nil)
|
47
|
+
if count.nil?
|
48
|
+
@queue.shift
|
49
|
+
else
|
50
|
+
@queue.shift(count)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def add_downloaded(page)
|
55
|
+
@downloaded_pages.push page
|
56
|
+
end
|
57
|
+
|
58
|
+
def add_error_page(page)
|
59
|
+
@error_pages.push page
|
60
|
+
end
|
61
|
+
|
62
|
+
def has_work?
|
63
|
+
@queue.count > 0 || @downloaded_pages.count > 0
|
64
|
+
end
|
65
|
+
|
66
|
+
end
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
Scruber::Queue.add_adapter(:memory, Scruber::QueueAdapters::Memory)
|
data/lib/scruber.rb
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
require "scruber/version"
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'http-cookie'
|
4
|
+
require 'pickup'
|
5
|
+
require 'csv'
|
6
|
+
require 'active_support'
|
7
|
+
require 'active_support/core_ext/object'
|
8
|
+
require 'active_support/core_ext/hash'
|
9
|
+
|
10
|
+
require "scruber/fetcher"
|
11
|
+
require "scruber/fetcher_adapters/abstract_adapter"
|
12
|
+
require "scruber/fetcher_adapters/typhoeus_fetcher"
|
13
|
+
|
14
|
+
require "scruber/queue"
|
15
|
+
require "scruber/queue_adapters/abstract_adapter"
|
16
|
+
require "scruber/queue_adapters/memory"
|
17
|
+
|
18
|
+
require "scruber/core/page_format"
|
19
|
+
require "scruber/core/page_format/base"
|
20
|
+
require "scruber/core/page_format/xml"
|
21
|
+
require "scruber/core/page_format/html"
|
22
|
+
|
23
|
+
require "scruber/core/extensions/base"
|
24
|
+
require "scruber/core/extensions/loop"
|
25
|
+
require "scruber/core/extensions/csv_output"
|
26
|
+
|
27
|
+
# require "scruber/core/configuration"
|
28
|
+
# require "scruber/core/configuration"
|
29
|
+
|
30
|
+
module Scruber
|
31
|
+
class ArgumentError < ::ArgumentError; end
|
32
|
+
module Core
|
33
|
+
autoload :Configuration, "scruber/core/configuration"
|
34
|
+
autoload :Crawler, "scruber/core/crawler"
|
35
|
+
end
|
36
|
+
|
37
|
+
module Helpers
|
38
|
+
autoload :UserAgentRotator, "scruber/helpers/user_agent_rotator"
|
39
|
+
autoload :ProxyRotator, "scruber/helpers/proxy_rotator"
|
40
|
+
autoload :FetcherAgent, "scruber/helpers/fetcher_agent"
|
41
|
+
module FetcherAgentAdapters
|
42
|
+
autoload :AbstractAdapter, "scruber/helpers/fetcher_agent_adapters/abstract_adapter"
|
43
|
+
autoload :Memory, "scruber/helpers/fetcher_agent_adapters/memory"
|
44
|
+
end
|
45
|
+
autoload :DictionaryReader, "scruber/helpers/dictionary_reader"
|
46
|
+
module DictionaryReader
|
47
|
+
autoload :Xml, "scruber/helpers/dictionary_reader/xml"
|
48
|
+
autoload :Csv, "scruber/helpers/dictionary_reader/csv"
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
class << self
|
53
|
+
attr_writer :configuration
|
54
|
+
|
55
|
+
def run(options={}, &block)
|
56
|
+
raise "You need a block to build!" unless block_given?
|
57
|
+
|
58
|
+
Core::Crawler.new(options).run(&block)
|
59
|
+
end
|
60
|
+
|
61
|
+
def configuration
|
62
|
+
@configuration ||= Core::Configuration.new
|
63
|
+
end
|
64
|
+
|
65
|
+
def configure(&block)
|
66
|
+
yield configuration
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
data/scruber.gemspec
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "scruber/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "scruber"
|
8
|
+
spec.version = Scruber::VERSION
|
9
|
+
spec.authors = ["Ivan Goncharov"]
|
10
|
+
spec.email = ["revis0r.mob@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Crawling framework}
|
13
|
+
spec.description = %q{Crawling framework}
|
14
|
+
spec.homepage = "https://github.com/scruber/scruber"
|
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 " \
|
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 "typhoeus", "1.1.2"
|
34
|
+
spec.add_dependency "pickup", "0.0.11"
|
35
|
+
spec.add_dependency "nokogiri", "1.8.2"
|
36
|
+
spec.add_dependency "http-cookie", "1.0.3"
|
37
|
+
spec.add_dependency "activesupport", "5.1.5"
|
38
|
+
spec.add_runtime_dependency "thor", "0.20.0"
|
39
|
+
spec.add_development_dependency "bundler", "~> 1.15"
|
40
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
41
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
42
|
+
spec.add_development_dependency "webmock", "3.0.1"
|
43
|
+
end
|
metadata
ADDED
@@ -0,0 +1,233 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scruber
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ivan Goncharov
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-03-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: typhoeus
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.1.2
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 1.1.2
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: pickup
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.0.11
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.0.11
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: nokogiri
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 1.8.2
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 1.8.2
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: http-cookie
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 1.0.3
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 1.0.3
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: activesupport
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 5.1.5
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 5.1.5
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: thor
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 0.20.0
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 0.20.0
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: bundler
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '1.15'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '1.15'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rake
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '10.0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '10.0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: rspec
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '3.0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - "~>"
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '3.0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: webmock
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - '='
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: 3.0.1
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - '='
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: 3.0.1
|
153
|
+
description: Crawling framework
|
154
|
+
email:
|
155
|
+
- revis0r.mob@gmail.com
|
156
|
+
executables:
|
157
|
+
- scruber
|
158
|
+
extensions: []
|
159
|
+
extra_rdoc_files: []
|
160
|
+
files:
|
161
|
+
- ".gitignore"
|
162
|
+
- ".rspec"
|
163
|
+
- ".travis.yml"
|
164
|
+
- Gemfile
|
165
|
+
- LICENSE.txt
|
166
|
+
- README.md
|
167
|
+
- Rakefile
|
168
|
+
- bin/console
|
169
|
+
- bin/setup
|
170
|
+
- exe/scruber
|
171
|
+
- lib/scruber.rb
|
172
|
+
- lib/scruber/app_searcher.rb
|
173
|
+
- lib/scruber/cli.rb
|
174
|
+
- lib/scruber/cli/project_generator.rb
|
175
|
+
- lib/scruber/cli/templates/Gemfile.tt
|
176
|
+
- lib/scruber/cli/templates/application.tt
|
177
|
+
- lib/scruber/cli/templates/bin/scruber.tt
|
178
|
+
- lib/scruber/cli/templates/boot.tt
|
179
|
+
- lib/scruber/cli/templates/gitignore.tt
|
180
|
+
- lib/scruber/cli/templates/initializers/proxies.tt
|
181
|
+
- lib/scruber/cli/templates/initializers/user_agents.tt
|
182
|
+
- lib/scruber/cli/templates/scrapers/sample.tt
|
183
|
+
- lib/scruber/core/configuration.rb
|
184
|
+
- lib/scruber/core/crawler.rb
|
185
|
+
- lib/scruber/core/extensions/base.rb
|
186
|
+
- lib/scruber/core/extensions/csv_output.rb
|
187
|
+
- lib/scruber/core/extensions/loop.rb
|
188
|
+
- lib/scruber/core/page_format.rb
|
189
|
+
- lib/scruber/core/page_format/base.rb
|
190
|
+
- lib/scruber/core/page_format/html.rb
|
191
|
+
- lib/scruber/core/page_format/xml.rb
|
192
|
+
- lib/scruber/fetcher.rb
|
193
|
+
- lib/scruber/fetcher_adapters/abstract_adapter.rb
|
194
|
+
- lib/scruber/fetcher_adapters/typhoeus_fetcher.rb
|
195
|
+
- lib/scruber/helpers/dictionary_reader.rb
|
196
|
+
- lib/scruber/helpers/dictionary_reader/csv.rb
|
197
|
+
- lib/scruber/helpers/dictionary_reader/xml.rb
|
198
|
+
- lib/scruber/helpers/fetcher_agent.rb
|
199
|
+
- lib/scruber/helpers/fetcher_agent_adapters/abstract_adapter.rb
|
200
|
+
- lib/scruber/helpers/fetcher_agent_adapters/memory.rb
|
201
|
+
- lib/scruber/helpers/proxy_rotator.rb
|
202
|
+
- lib/scruber/helpers/user_agent_rotator.rb
|
203
|
+
- lib/scruber/queue.rb
|
204
|
+
- lib/scruber/queue_adapters/abstract_adapter.rb
|
205
|
+
- lib/scruber/queue_adapters/memory.rb
|
206
|
+
- lib/scruber/version.rb
|
207
|
+
- scruber.gemspec
|
208
|
+
homepage: https://github.com/scruber/scruber
|
209
|
+
licenses:
|
210
|
+
- MIT
|
211
|
+
metadata:
|
212
|
+
allowed_push_host: https://rubygems.org
|
213
|
+
post_install_message:
|
214
|
+
rdoc_options: []
|
215
|
+
require_paths:
|
216
|
+
- lib
|
217
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
218
|
+
requirements:
|
219
|
+
- - ">="
|
220
|
+
- !ruby/object:Gem::Version
|
221
|
+
version: '0'
|
222
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
223
|
+
requirements:
|
224
|
+
- - ">="
|
225
|
+
- !ruby/object:Gem::Version
|
226
|
+
version: '0'
|
227
|
+
requirements: []
|
228
|
+
rubyforge_project:
|
229
|
+
rubygems_version: 2.6.14
|
230
|
+
signing_key:
|
231
|
+
specification_version: 4
|
232
|
+
summary: Crawling framework
|
233
|
+
test_files: []
|