medusa-crawler 1.0.0.pre.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- checksums.yaml.gz.sig +0 -0
- data.tar.gz.sig +0 -0
- data/CHANGELOG.md +20 -0
- data/CONTRIBUTORS.md +22 -0
- data/LICENSE.txt +20 -0
- data/README.md +48 -0
- data/Rakefile +24 -0
- data/VERSION +1 -0
- data/bin/medusa +4 -0
- data/lib/medusa.rb +2 -0
- data/lib/medusa/cli.rb +24 -0
- data/lib/medusa/cli/count.rb +22 -0
- data/lib/medusa/cli/cron.rb +90 -0
- data/lib/medusa/cli/pagedepth.rb +32 -0
- data/lib/medusa/cli/serialize.rb +35 -0
- data/lib/medusa/cli/url_list.rb +41 -0
- data/lib/medusa/cookie_store.rb +35 -0
- data/lib/medusa/core.rb +305 -0
- data/lib/medusa/exceptions.rb +5 -0
- data/lib/medusa/http.rb +202 -0
- data/lib/medusa/page.rb +229 -0
- data/lib/medusa/page_store.rb +160 -0
- data/lib/medusa/storage.rb +8 -0
- data/lib/medusa/storage/base.rb +81 -0
- data/lib/medusa/storage/exceptions.rb +15 -0
- data/lib/medusa/storage/moneta.rb +42 -0
- data/lib/medusa/tentacle.rb +39 -0
- data/lib/medusa/version.rb +3 -0
- data/spec/fakeweb_helper.rb +85 -0
- data/spec/medusa_helper.rb +5 -0
- data/spec/medusa_spec.rb +14 -0
- data/spec/spec_helper.rb +104 -0
- metadata +187 -0
- metadata.gz.sig +0 -0
@@ -0,0 +1,42 @@
|
|
1
|
+
require 'moneta'
|
2
|
+
require 'forwardable'
|
3
|
+
|
4
|
+
module Medusa
|
5
|
+
module Storage
|
6
|
+
class Moneta
|
7
|
+
extend Forwardable
|
8
|
+
|
9
|
+
def_delegators :@moneta, :[], :[]=, :delete, :key?, :clear, :close
|
10
|
+
|
11
|
+
alias has_key? key?
|
12
|
+
|
13
|
+
def initialize(name, options = {})
|
14
|
+
default_options = { threadsafe: true, prefix: 'medusa' }
|
15
|
+
@moneta = ::Moneta.new(name, default_options.merge(options))
|
16
|
+
end
|
17
|
+
|
18
|
+
def each
|
19
|
+
@moneta.each_key do |k|
|
20
|
+
yield k, @moneta.fetch(k)
|
21
|
+
end
|
22
|
+
self
|
23
|
+
end
|
24
|
+
|
25
|
+
def size
|
26
|
+
current_size = @moneta.each_key.size
|
27
|
+
|
28
|
+
return @moneta.each_key.reduce(0) { |size, k| size + 1 } if current_size.nil?
|
29
|
+
return current_size
|
30
|
+
end
|
31
|
+
|
32
|
+
def keys
|
33
|
+
@moneta.each_key.to_a.sort
|
34
|
+
end
|
35
|
+
|
36
|
+
def merge!(hash)
|
37
|
+
@moneta.merge!(hash) unless hash.empty?
|
38
|
+
self
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
require 'medusa/http'
|
2
|
+
|
3
|
+
module Medusa
|
4
|
+
class Tentacle
|
5
|
+
|
6
|
+
#
|
7
|
+
# Create a new Tentacle
|
8
|
+
#
|
9
|
+
def initialize(link_queue, page_queue, opts = {})
|
10
|
+
@link_queue = link_queue
|
11
|
+
@page_queue = page_queue
|
12
|
+
@http = Medusa::HTTP.new(opts)
|
13
|
+
@opts = opts
|
14
|
+
end
|
15
|
+
|
16
|
+
#
|
17
|
+
# Gets links from @link_queue, and returns the fetched
|
18
|
+
# Page objects into @page_queue
|
19
|
+
#
|
20
|
+
def run
|
21
|
+
loop do
|
22
|
+
link, referer, depth = @link_queue.deq
|
23
|
+
|
24
|
+
break if link == :END
|
25
|
+
|
26
|
+
@http.fetch_pages(link, referer, depth).each { |page| @page_queue << page }
|
27
|
+
|
28
|
+
delay
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
private
|
33
|
+
|
34
|
+
def delay
|
35
|
+
sleep @opts[:delay] if @opts[:delay] > 0
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
end
|
@@ -0,0 +1,85 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'webmock/rspec'
|
4
|
+
|
5
|
+
WebMock.disable_net_connect!
|
6
|
+
|
7
|
+
module Medusa
|
8
|
+
AUTH = ['user', 'pass']
|
9
|
+
SPEC_DOMAIN = "http://www.example.com/"
|
10
|
+
AUTH_SPEC_DOMAIN = "http://#{AUTH.join(':')}@#{URI.parse(SPEC_DOMAIN).host}/"
|
11
|
+
|
12
|
+
class FakePage
|
13
|
+
attr_accessor :links
|
14
|
+
attr_accessor :hrefs
|
15
|
+
attr_accessor :body
|
16
|
+
|
17
|
+
def initialize(name = '', options = {})
|
18
|
+
@name = name
|
19
|
+
@links = []
|
20
|
+
@hrefs = []
|
21
|
+
@redirect = nil
|
22
|
+
@auth = false
|
23
|
+
@base = ''
|
24
|
+
|
25
|
+
@links = [options[:links]].flatten if options.has_key?(:links)
|
26
|
+
@hrefs = [options[:hrefs]].flatten if options.has_key?(:hrefs)
|
27
|
+
@redirect = options[:redirect] if options.has_key?(:redirect)
|
28
|
+
@auth = options[:auth] if options.has_key?(:auth)
|
29
|
+
@base = options[:base] if options.has_key?(:base)
|
30
|
+
@content_type = options[:content_type] || "text/html"
|
31
|
+
@body = options[:body]
|
32
|
+
|
33
|
+
create_body unless @body
|
34
|
+
add_to_fakeweb
|
35
|
+
end
|
36
|
+
|
37
|
+
def url
|
38
|
+
SPEC_DOMAIN + @name
|
39
|
+
end
|
40
|
+
|
41
|
+
def auth_url
|
42
|
+
AUTH_SPEC_DOMAIN + @name
|
43
|
+
end
|
44
|
+
|
45
|
+
private
|
46
|
+
|
47
|
+
def create_body
|
48
|
+
if @base
|
49
|
+
@body = "<html><head><base href=\"#{@base}\"></head><body>"
|
50
|
+
else
|
51
|
+
@body = "<html><body>"
|
52
|
+
end
|
53
|
+
@links.each{|l| @body += "<a href=\"#{SPEC_DOMAIN}#{l}\"></a>"} if @links
|
54
|
+
@hrefs.each{|h| @body += "<a href=\"#{h}\"></a>"} if @hrefs
|
55
|
+
@body += "</body></html>"
|
56
|
+
end
|
57
|
+
|
58
|
+
def add_to_fakeweb
|
59
|
+
options = {body: @body, status: [200, 'OK'], headers: {'Content-Type' => @content_type}}
|
60
|
+
|
61
|
+
if @redirect
|
62
|
+
options[:status] = [301, 'Moved Permanently']
|
63
|
+
|
64
|
+
# only prepend SPEC_DOMAIN if a relative url (without an http scheme) was specified
|
65
|
+
redirect_url = (@redirect =~ /http/) ? @redirect : SPEC_DOMAIN + @redirect
|
66
|
+
options[:headers]['Location'] = redirect_url
|
67
|
+
|
68
|
+
# register the page this one redirects to
|
69
|
+
WebMock.stub_request(:get, redirect_url).to_return(body: '', status: [200, 'OK'], headers: {'Content-Type' => @content_type})
|
70
|
+
end
|
71
|
+
|
72
|
+
if @auth
|
73
|
+
unautorized_options = {body: 'Unauthorized', status: [401, 'Unauthorized']}
|
74
|
+
|
75
|
+
WebMock.stub_request(:get, url).to_return(unautorized_options)
|
76
|
+
WebMock.stub_request(:get, url).with(basic_auth: AUTH).to_return(options)
|
77
|
+
else
|
78
|
+
WebMock.stub_request(:get, url).to_return(options)
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
#default root
|
85
|
+
Medusa::FakePage.new
|
data/spec/medusa_spec.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
|
2
|
+
RSpec.describe Medusa do
|
3
|
+
|
4
|
+
it "should have a version" do
|
5
|
+
expect(Medusa.const_defined?('VERSION')).to be true
|
6
|
+
end
|
7
|
+
|
8
|
+
it "should return a Medusa::Core from the crawl, which has a PageStore" do
|
9
|
+
result = Medusa.crawl(SPEC_DOMAIN)
|
10
|
+
expect(result).to be_an_instance_of(Medusa::Core)
|
11
|
+
expect(result.pages).to be_an_instance_of(Medusa::PageStore)
|
12
|
+
end
|
13
|
+
|
14
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,104 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'medusa_helper'
|
4
|
+
|
5
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
6
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
7
|
+
# The generated `.rspec` file contains `--require spec_helper` which will cause
|
8
|
+
# this file to always be loaded, without a need to explicitly require it in any
|
9
|
+
# files.
|
10
|
+
#
|
11
|
+
# Given that it is always loaded, you are encouraged to keep this file as
|
12
|
+
# light-weight as possible. Requiring heavyweight dependencies from this file
|
13
|
+
# will add to the boot time of your test suite on EVERY test run, even for an
|
14
|
+
# individual file that may not need all of that loaded. Instead, consider making
|
15
|
+
# a separate helper file that requires the additional dependencies and performs
|
16
|
+
# the additional setup, and require it from the spec files that actually need
|
17
|
+
# it.
|
18
|
+
#
|
19
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
20
|
+
RSpec.configure do |config|
|
21
|
+
# rspec-expectations config goes here. You can use an alternate
|
22
|
+
# assertion/expectation library such as wrong or the stdlib/minitest
|
23
|
+
# assertions if you prefer.
|
24
|
+
config.expect_with :rspec do |expectations|
|
25
|
+
# This option will default to `true` in RSpec 4. It makes the `description`
|
26
|
+
# and `failure_message` of custom matchers include text for helper methods
|
27
|
+
# defined using `chain`, e.g.:
|
28
|
+
# be_bigger_than(2).and_smaller_than(4).description
|
29
|
+
# # => "be bigger than 2 and smaller than 4"
|
30
|
+
# ...rather than:
|
31
|
+
# # => "be bigger than 2"
|
32
|
+
expectations.include_chain_clauses_in_custom_matcher_descriptions = true
|
33
|
+
end
|
34
|
+
|
35
|
+
# rspec-mocks config goes here. You can use an alternate test double
|
36
|
+
# library (such as bogus or mocha) by changing the `mock_with` option here.
|
37
|
+
config.mock_with :rspec do |mocks|
|
38
|
+
# Prevents you from mocking or stubbing a method that does not exist on
|
39
|
+
# a real object. This is generally recommended, and will default to
|
40
|
+
# `true` in RSpec 4.
|
41
|
+
mocks.verify_partial_doubles = true
|
42
|
+
end
|
43
|
+
|
44
|
+
# This option will default to `:apply_to_host_groups` in RSpec 4 (and will
|
45
|
+
# have no way to turn it off -- the option exists only for backwards
|
46
|
+
# compatibility in RSpec 3). It causes shared context metadata to be
|
47
|
+
# inherited by the metadata hash of host groups and examples, rather than
|
48
|
+
# triggering implicit auto-inclusion in groups with matching metadata.
|
49
|
+
config.shared_context_metadata_behavior = :apply_to_host_groups
|
50
|
+
|
51
|
+
# The settings below are suggested to provide a good initial experience
|
52
|
+
# with RSpec, but feel free to customize to your heart's content.
|
53
|
+
|
54
|
+
# This allows you to limit a spec run to individual examples or groups
|
55
|
+
# you care about by tagging them with `:focus` metadata. When nothing
|
56
|
+
# is tagged with `:focus`, all examples get run. RSpec also provides
|
57
|
+
# aliases for `it`, `describe`, and `context` that include `:focus`
|
58
|
+
# metadata: `fit`, `fdescribe` and `fcontext`, respectively.
|
59
|
+
config.filter_run_when_matching :focus
|
60
|
+
|
61
|
+
# Allows RSpec to persist some state between runs in order to support
|
62
|
+
# the `--only-failures` and `--next-failure` CLI options. We recommend
|
63
|
+
# you configure your source control system to ignore this file.
|
64
|
+
config.example_status_persistence_file_path = "spec/examples.txt"
|
65
|
+
|
66
|
+
# Limits the available syntax to the non-monkey patched syntax that is
|
67
|
+
# recommended. For more details, see:
|
68
|
+
# - http://rspec.info/blog/2012/06/rspecs-new-expectation-syntax/
|
69
|
+
# - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
|
70
|
+
# - http://rspec.info/blog/2014/05/notable-changes-in-rspec-3/#zero-monkey-patching-mode
|
71
|
+
config.disable_monkey_patching!
|
72
|
+
|
73
|
+
# This setting enables warnings. It's recommended, but in some cases may
|
74
|
+
# be too noisy due to issues in dependencies.
|
75
|
+
# config.warnings = true
|
76
|
+
|
77
|
+
# Many RSpec users commonly either run the entire suite or an individual
|
78
|
+
# file, and it's useful to allow more verbose output when running an
|
79
|
+
# individual spec file.
|
80
|
+
if config.files_to_run.one?
|
81
|
+
# Use the documentation formatter for detailed output,
|
82
|
+
# unless a formatter has already been configured
|
83
|
+
# (e.g. via a command-line flag).
|
84
|
+
config.default_formatter = "doc"
|
85
|
+
end
|
86
|
+
|
87
|
+
# Print the 10 slowest examples and example groups at the
|
88
|
+
# end of the spec run, to help surface which specs are running
|
89
|
+
# particularly slow.
|
90
|
+
config.profile_examples = 10
|
91
|
+
|
92
|
+
# Run specs in random order to surface order dependencies. If you find an
|
93
|
+
# order dependency and want to debug it, you can fix the order by providing
|
94
|
+
# the seed, which is printed after each run.
|
95
|
+
# --seed 1234
|
96
|
+
config.order = :random
|
97
|
+
|
98
|
+
# Seed global randomization in this process using the `--seed` CLI option.
|
99
|
+
# Setting this allows you to use `--seed` to deterministically reproduce
|
100
|
+
# test failures related to randomization by passing the same `--seed` value
|
101
|
+
# as the one that triggered the failure.
|
102
|
+
Kernel.srand config.seed
|
103
|
+
|
104
|
+
end
|
metadata
ADDED
@@ -0,0 +1,187 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: medusa-crawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0.pre.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Mauro Asprea
|
8
|
+
- Chris Kite
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain:
|
12
|
+
- |
|
13
|
+
-----BEGIN CERTIFICATE-----
|
14
|
+
MIIERDCCAqygAwIBAgIBATANBgkqhkiG9w0BAQsFADAmMSQwIgYDVQQDDBttYXVy
|
15
|
+
b2FzcHJlYS9EQz1nbWFpbC9EQz1jb20wHhcNMjAwODA2MTEwNDAzWhcNMjEwODA2
|
16
|
+
MTEwNDAzWjAmMSQwIgYDVQQDDBttYXVyb2FzcHJlYS9EQz1nbWFpbC9EQz1jb20w
|
17
|
+
ggGiMA0GCSqGSIb3DQEBAQUAA4IBjwAwggGKAoIBgQDNsvJN5orxdj+eEUiSttpC
|
18
|
+
6N6IeTK/btk65TAbZlY7/9MVIHM/Ya3tUSWoQA6KURsksV+lUbJm0MC4pwm5y46T
|
19
|
+
p+Q6/eDz8gmofian4X+y3inyzYqmvbM2t2mPcO+Mj1NjSfGn56jqk0ey32xL7cz3
|
20
|
+
YZqx9LnkUUuqzn4QM+R8LfGUWXe9nlkMoLoNGw+X1XB8bPYoQo2YpofILEWcCLJl
|
21
|
+
NnFjcjIzQuE3NDaPIBX/cXPDpvuKNVXw51My35pQb5uW4Aa7sRZAz1MCDoFA1+XO
|
22
|
+
9czVf+zE+YsMtuqruWOI08TEPD2kMeiDqMc1fbPkLN9Rhe2Nxj8fTK1Ptyz0mQJL
|
23
|
+
x5cQZT2XK+nmZKiU/z+91XU17BNd+LEERU6ZmjkGQKUH/Gj060kQWMnw2sOsZJS9
|
24
|
+
VVU/raletJxhODeQbShcrxUR6VSGDkgQa4G/rqtPjUQ9AXYeNeVBg2aE4DRTRFhy
|
25
|
+
gYsyE9DbAluV7BcJWO+GKntyXqhu14dnATCfSFI3WMsCAwEAAaN9MHswCQYDVR0T
|
26
|
+
BAIwADALBgNVHQ8EBAMCBLAwHQYDVR0OBBYEFAjiCg2cEkNDWhG4P1PgDwATcmgR
|
27
|
+
MCAGA1UdEQQZMBeBFW1hdXJvYXNwcmVhQGdtYWlsLmNvbTAgBgNVHRIEGTAXgRVt
|
28
|
+
YXVyb2FzcHJlYUBnbWFpbC5jb20wDQYJKoZIhvcNAQELBQADggGBAG4S5uDseGtN
|
29
|
+
EqxvogGfJ+h7Pg5pdDsMVFWXOPN9IztSHE+88Ypv9b97zNk/vBztj3nwkUuhEczv
|
30
|
+
GZeI9/F72j1+8ARWdNgHalsrTHcFWaGEYNkm06EGh21dtO939Uqjg9auv9thDD/C
|
31
|
+
4jlEii1EvaGIaMhEdONAiRyOj0gEagw1AU5ItSxoWHFaaCEQSqXRskZMpw6fDZrE
|
32
|
+
jnJPYx5I8axku6D+/nlP3GeuMNwlqzTg1YblLDanzEdI7Yet41MgMwLcor6Z4BXb
|
33
|
+
xKDzHfGjkQfEpEvwzqSi0rAbrMv68FRybNxgB/3gwgSiEaeFeE4CFX0gm1F3m28m
|
34
|
+
Z9rgjNU1SA9dSTGLY14K3rjtn71PMlP64Ci+QJ0HA8V0+cpx1Lkn3WsywgILV16a
|
35
|
+
g4G6EZGbKCMwJDC0Wtmrygr7+THZVQlBs0ljTdrN8GXsuI9W52VlZctZQXEuoboH
|
36
|
+
mpXw1d3WewNciml1VaOG782DKqZvT0i19V5LnZzoGzmU2q3ZJw7jCw==
|
37
|
+
-----END CERTIFICATE-----
|
38
|
+
date: 2020-08-06 00:00:00.000000000 Z
|
39
|
+
dependencies:
|
40
|
+
- !ruby/object:Gem::Dependency
|
41
|
+
name: moneta
|
42
|
+
requirement: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - "~>"
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '1.3'
|
47
|
+
- - ">="
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: 1.3.0
|
50
|
+
type: :runtime
|
51
|
+
prerelease: false
|
52
|
+
version_requirements: !ruby/object:Gem::Requirement
|
53
|
+
requirements:
|
54
|
+
- - "~>"
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '1.3'
|
57
|
+
- - ">="
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: 1.3.0
|
60
|
+
- !ruby/object:Gem::Dependency
|
61
|
+
name: nokogiri
|
62
|
+
requirement: !ruby/object:Gem::Requirement
|
63
|
+
requirements:
|
64
|
+
- - "~>"
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
version: '1.3'
|
67
|
+
- - ">="
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: 1.3.0
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
requirements:
|
74
|
+
- - "~>"
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '1.3'
|
77
|
+
- - ">="
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: 1.3.0
|
80
|
+
- !ruby/object:Gem::Dependency
|
81
|
+
name: robotex
|
82
|
+
requirement: !ruby/object:Gem::Requirement
|
83
|
+
requirements:
|
84
|
+
- - "~>"
|
85
|
+
- !ruby/object:Gem::Version
|
86
|
+
version: '1.0'
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 1.0.0
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.0'
|
97
|
+
- - ">="
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: 1.0.0
|
100
|
+
description: |-
|
101
|
+
== Medusa: a ruby crawler framework
|
102
|
+
|
103
|
+
Medusa is a ruby framework to crawl and collect useful information about the pages it visits.
|
104
|
+
It is versatile, allowing you to write your own specialized tasks quickly and easily.
|
105
|
+
|
106
|
+
#### Features
|
107
|
+
|
108
|
+
- Choose the links to follow on each page with `focus_crawl()`
|
109
|
+
- Multi-threaded design for high performance
|
110
|
+
- Tracks 301 HTTP redirects
|
111
|
+
- Allows exclusion of URLs based on regular expressions
|
112
|
+
- HTTPS support
|
113
|
+
- Records response time for each page
|
114
|
+
- Obey robots.txt
|
115
|
+
- In-memory or persistent storage of pages during crawl using Moneta adapters.
|
116
|
+
- Inherits OpenURI behavior (redirects, automatic charset and encoding detection, proxy configuration options).
|
117
|
+
email:
|
118
|
+
executables:
|
119
|
+
- medusa
|
120
|
+
extensions: []
|
121
|
+
extra_rdoc_files:
|
122
|
+
- README.md
|
123
|
+
files:
|
124
|
+
- CHANGELOG.md
|
125
|
+
- CONTRIBUTORS.md
|
126
|
+
- LICENSE.txt
|
127
|
+
- README.md
|
128
|
+
- Rakefile
|
129
|
+
- VERSION
|
130
|
+
- bin/medusa
|
131
|
+
- lib/medusa.rb
|
132
|
+
- lib/medusa/cli.rb
|
133
|
+
- lib/medusa/cli/count.rb
|
134
|
+
- lib/medusa/cli/cron.rb
|
135
|
+
- lib/medusa/cli/pagedepth.rb
|
136
|
+
- lib/medusa/cli/serialize.rb
|
137
|
+
- lib/medusa/cli/url_list.rb
|
138
|
+
- lib/medusa/cookie_store.rb
|
139
|
+
- lib/medusa/core.rb
|
140
|
+
- lib/medusa/exceptions.rb
|
141
|
+
- lib/medusa/http.rb
|
142
|
+
- lib/medusa/page.rb
|
143
|
+
- lib/medusa/page_store.rb
|
144
|
+
- lib/medusa/storage.rb
|
145
|
+
- lib/medusa/storage/base.rb
|
146
|
+
- lib/medusa/storage/exceptions.rb
|
147
|
+
- lib/medusa/storage/moneta.rb
|
148
|
+
- lib/medusa/tentacle.rb
|
149
|
+
- lib/medusa/version.rb
|
150
|
+
- spec/fakeweb_helper.rb
|
151
|
+
- spec/medusa_helper.rb
|
152
|
+
- spec/medusa_spec.rb
|
153
|
+
- spec/spec_helper.rb
|
154
|
+
homepage: https://github.com/brutuscat/medusa-crawler
|
155
|
+
licenses:
|
156
|
+
- MIT
|
157
|
+
metadata:
|
158
|
+
bug_tracker_uri: https://github.com/brutuscat/medusa-crawler/issues
|
159
|
+
source_code_uri: https://github.com/brutuscat/medusa-crawler/tree/v1.0.0.pre.1
|
160
|
+
post_install_message:
|
161
|
+
rdoc_options:
|
162
|
+
- "-m"
|
163
|
+
- README.md
|
164
|
+
- "-t"
|
165
|
+
- Medusa
|
166
|
+
require_paths:
|
167
|
+
- lib
|
168
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
169
|
+
requirements:
|
170
|
+
- - ">="
|
171
|
+
- !ruby/object:Gem::Version
|
172
|
+
version: '0'
|
173
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
174
|
+
requirements:
|
175
|
+
- - ">"
|
176
|
+
- !ruby/object:Gem::Version
|
177
|
+
version: 1.3.1
|
178
|
+
requirements: []
|
179
|
+
rubygems_version: 3.1.2
|
180
|
+
signing_key:
|
181
|
+
specification_version: 4
|
182
|
+
summary: Medusa is a ruby crawler framework
|
183
|
+
test_files:
|
184
|
+
- spec/spec_helper.rb
|
185
|
+
- spec/medusa_helper.rb
|
186
|
+
- spec/fakeweb_helper.rb
|
187
|
+
- spec/medusa_spec.rb
|