aranha-rails 0.1.0
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/lib/aranha/rails.rb +9 -0
- data/lib/aranha/rails/engine.rb +17 -0
- data/lib/aranha/rails/fixtures_download.rb +72 -0
- data/lib/aranha/rails/manager.rb +41 -0
- data/lib/aranha/rails/version.rb +7 -0
- data/lib/tasks/aranha.rake +24 -0
- metadata +163 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: ea03bcdec3dd45159d259277c82e9caa7d6aa8469499abfff9567101a7d23e6f
|
4
|
+
data.tar.gz: e25011f06e74adc37e3192e6a5fa80e849430b4b8dd0ebc7ddb0e1af3cc7ff98
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 458bf075dec14c64b8c63065a81bfde264420940161f7d7475ee84bf1712a86ddb04dc10f45d06d346c0fe9c9963e19d1a756898cd02505c07fe078b017576b4
|
7
|
+
data.tar.gz: 6be3e41fb8f7abd3cf950bcfd55f9d0c36778c124d34e1cd0e12bd44ef5944864b164299358f176157488842228cf8d98650330718d6fa771cfa1b8b4bf468ed
|
data/lib/aranha/rails.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'active_scaffold'
|
4
|
+
|
5
|
+
module Aranha
|
6
|
+
module Rails
|
7
|
+
class Engine < ::Rails::Engine
|
8
|
+
isolate_namespace ::Aranha
|
9
|
+
|
10
|
+
initializer :append_migrations do |app|
|
11
|
+
config.paths['db/migrate'].expanded.each do |expanded_path|
|
12
|
+
app.config.paths['db/migrate'] << expanded_path
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/parsers/base'
|
4
|
+
require 'aranha/parsers/source_address'
|
5
|
+
require 'aranha/parsers/source_target_fixtures'
|
6
|
+
|
7
|
+
module Aranha
|
8
|
+
module Rails
|
9
|
+
class FixturesDownload
|
10
|
+
attr_reader :pending
|
11
|
+
|
12
|
+
def initialize(options)
|
13
|
+
@prefix = options.fetch(:prefix)
|
14
|
+
@prefix = '' if @prefix.blank?
|
15
|
+
@download = options.fetch(:download)
|
16
|
+
@pending = options.fetch(:pending)
|
17
|
+
end
|
18
|
+
|
19
|
+
def run
|
20
|
+
url_files.each do |f|
|
21
|
+
Rails.logger.info(relative_path(f))
|
22
|
+
download(url(f), target(f)) if @download
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def url_files
|
29
|
+
Dir["#{fixtures_root}/**/*.url"].select { |path| select_path?(path) }
|
30
|
+
end
|
31
|
+
|
32
|
+
def select_path?(path)
|
33
|
+
return false unless match_prefix_pattern(path)
|
34
|
+
|
35
|
+
!pending || !source_exist?(path)
|
36
|
+
end
|
37
|
+
|
38
|
+
def match_prefix_pattern(path)
|
39
|
+
relative_path(path).start_with?(@prefix)
|
40
|
+
end
|
41
|
+
|
42
|
+
def fixtures_root
|
43
|
+
Rails.root.to_s
|
44
|
+
end
|
45
|
+
|
46
|
+
def download(url, target)
|
47
|
+
Rails.logger.info "Baixando \"#{url}\"..."
|
48
|
+
content = ::Aranha::Parsers::Base.new(url).content
|
49
|
+
raise "Content is blank for \"#{url}\"" if content.blank?
|
50
|
+
|
51
|
+
File.open(target, 'wb') { |file| file.write(content) }
|
52
|
+
end
|
53
|
+
|
54
|
+
def url(file)
|
55
|
+
::Aranha::Parsers::SourceAddress.from_file(file)
|
56
|
+
end
|
57
|
+
|
58
|
+
def target(file)
|
59
|
+
File.expand_path(File.basename(file, '.url') + '.source.html', File.dirname(file))
|
60
|
+
end
|
61
|
+
|
62
|
+
def relative_path(path)
|
63
|
+
path.sub(%r{^#{Regexp.quote(fixtures_root)}/}, '')
|
64
|
+
end
|
65
|
+
|
66
|
+
def source_exist?(path)
|
67
|
+
stf = ::Aranha::Parsers::SourceTargetFixtures.new(::File.dirname(path))
|
68
|
+
stf.source_file(::File.basename(path, '.url')).present?
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/manager'
|
4
|
+
require 'singleton'
|
5
|
+
|
6
|
+
module Aranha
|
7
|
+
module Rails
|
8
|
+
class Manager < ::Aranha::Manager
|
9
|
+
include ::Singleton
|
10
|
+
|
11
|
+
def add_address(url, processor, extra_data = nil)
|
12
|
+
a = ::Aranha::Address.find_or_initialize_by(url: ::Aranha::Address.sanitize_url(url))
|
13
|
+
a.processor = processor
|
14
|
+
a.extra_data = extra_data.to_yaml
|
15
|
+
a.save!
|
16
|
+
end
|
17
|
+
|
18
|
+
def addresses_count
|
19
|
+
::Aranha::Address.count
|
20
|
+
end
|
21
|
+
|
22
|
+
def clear_expired_addresses
|
23
|
+
q = ::Aranha::Address.by_created_at_lt(Time.zone.now - 12.hours)
|
24
|
+
::Rails.logger.info("Addresses expired: #{q.count}")
|
25
|
+
q.destroy_all
|
26
|
+
end
|
27
|
+
|
28
|
+
def log_info(message)
|
29
|
+
::Rails.logger.info(message)
|
30
|
+
end
|
31
|
+
|
32
|
+
def log_warn(message)
|
33
|
+
::Rails.logger.warn(message)
|
34
|
+
end
|
35
|
+
|
36
|
+
def unprocessed_addresses
|
37
|
+
::Aranha::Address.unprocessed
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
namespace(:aranha) do
|
4
|
+
desc 'Process Aranha\'s addresses.'
|
5
|
+
task process: :environment do
|
6
|
+
::Aranha::Processor.new
|
7
|
+
end
|
8
|
+
|
9
|
+
desc 'Remove all registered Aranha\'s addresses.'
|
10
|
+
task clear: :environment do
|
11
|
+
Rails.logger.info("Addresses deleted: #{::Aranha::Address.destroy_all.count}")
|
12
|
+
end
|
13
|
+
|
14
|
+
namespace :fixtures do
|
15
|
+
desc 'Download remote content for fixtures.'
|
16
|
+
task download: :environment do
|
17
|
+
::Aranha::Rails::FixturesDownload.new(
|
18
|
+
prefix: ENV['PREFIX'],
|
19
|
+
download: ENV['DOWNLOAD'].present?,
|
20
|
+
pending: ENV['PENDING'].present?
|
21
|
+
).run
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,163 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: aranha-rails
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Put here the authors
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2020-11-28 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: active_scaffold
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '3.5'
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 3.5.5
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - "~>"
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '3.5'
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 3.5.5
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: aranha
|
35
|
+
requirement: !ruby/object:Gem::Requirement
|
36
|
+
requirements:
|
37
|
+
- - "~>"
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: '0.15'
|
40
|
+
type: :runtime
|
41
|
+
prerelease: false
|
42
|
+
version_requirements: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - "~>"
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '0.15'
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: aranha-parsers
|
49
|
+
requirement: !ruby/object:Gem::Requirement
|
50
|
+
requirements:
|
51
|
+
- - "~>"
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0.6'
|
54
|
+
type: :runtime
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - "~>"
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '0.6'
|
61
|
+
- !ruby/object:Gem::Dependency
|
62
|
+
name: eac_rails_utils
|
63
|
+
requirement: !ruby/object:Gem::Requirement
|
64
|
+
requirements:
|
65
|
+
- - "~>"
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: '0.12'
|
68
|
+
- - ">="
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: 0.12.1
|
71
|
+
type: :runtime
|
72
|
+
prerelease: false
|
73
|
+
version_requirements: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - "~>"
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0.12'
|
78
|
+
- - ">="
|
79
|
+
- !ruby/object:Gem::Version
|
80
|
+
version: 0.12.1
|
81
|
+
- !ruby/object:Gem::Dependency
|
82
|
+
name: eac_ruby_utils
|
83
|
+
requirement: !ruby/object:Gem::Requirement
|
84
|
+
requirements:
|
85
|
+
- - "~>"
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0.52'
|
88
|
+
type: :runtime
|
89
|
+
prerelease: false
|
90
|
+
version_requirements: !ruby/object:Gem::Requirement
|
91
|
+
requirements:
|
92
|
+
- - "~>"
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: '0.52'
|
95
|
+
- !ruby/object:Gem::Dependency
|
96
|
+
name: rails
|
97
|
+
requirement: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - "~>"
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: 5.1.7
|
102
|
+
type: :runtime
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
requirements:
|
106
|
+
- - "~>"
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
version: 5.1.7
|
109
|
+
- !ruby/object:Gem::Dependency
|
110
|
+
name: eac_ruby_gem_support
|
111
|
+
requirement: !ruby/object:Gem::Requirement
|
112
|
+
requirements:
|
113
|
+
- - "~>"
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '0.1'
|
116
|
+
- - ">="
|
117
|
+
- !ruby/object:Gem::Version
|
118
|
+
version: 0.1.2
|
119
|
+
type: :development
|
120
|
+
prerelease: false
|
121
|
+
version_requirements: !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - "~>"
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0.1'
|
126
|
+
- - ">="
|
127
|
+
- !ruby/object:Gem::Version
|
128
|
+
version: 0.1.2
|
129
|
+
description:
|
130
|
+
email:
|
131
|
+
executables: []
|
132
|
+
extensions: []
|
133
|
+
extra_rdoc_files: []
|
134
|
+
files:
|
135
|
+
- lib/aranha/rails.rb
|
136
|
+
- lib/aranha/rails/engine.rb
|
137
|
+
- lib/aranha/rails/fixtures_download.rb
|
138
|
+
- lib/aranha/rails/manager.rb
|
139
|
+
- lib/aranha/rails/version.rb
|
140
|
+
- lib/tasks/aranha.rake
|
141
|
+
homepage:
|
142
|
+
licenses: []
|
143
|
+
metadata: {}
|
144
|
+
post_install_message:
|
145
|
+
rdoc_options: []
|
146
|
+
require_paths:
|
147
|
+
- lib
|
148
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - ">="
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0'
|
153
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
154
|
+
requirements:
|
155
|
+
- - ">="
|
156
|
+
- !ruby/object:Gem::Version
|
157
|
+
version: '0'
|
158
|
+
requirements: []
|
159
|
+
rubygems_version: 3.0.8
|
160
|
+
signing_key:
|
161
|
+
specification_version: 4
|
162
|
+
summary: Put here de description.
|
163
|
+
test_files: []
|