http_utilities 1.0.1

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.
Files changed (49) hide show
  1. checksums.yaml +7 -0
  2. data/Gemfile +22 -0
  3. data/README +15 -0
  4. data/Rakefile +87 -0
  5. data/VERSION +1 -0
  6. data/http_utilities.gemspec +78 -0
  7. data/lib/generators/active_record/http_utilities_generator.rb +21 -0
  8. data/lib/generators/active_record/templates/migration.rb +34 -0
  9. data/lib/generators/active_record/templates/proxy.rb +3 -0
  10. data/lib/generators/helpers/file_helper.rb +35 -0
  11. data/lib/generators/helpers/orm_helpers.rb +15 -0
  12. data/lib/generators/http_utilities/http_utilities_generator.rb +25 -0
  13. data/lib/generators/templates/http_utilities.rb +2 -0
  14. data/lib/generators/templates/user_agents.yml +3419 -0
  15. data/lib/http_utilities/http/adapters/curb.rb +107 -0
  16. data/lib/http_utilities/http/adapters/net_http.rb +130 -0
  17. data/lib/http_utilities/http/adapters/open_uri.rb +46 -0
  18. data/lib/http_utilities/http/client.rb +22 -0
  19. data/lib/http_utilities/http/cookies.rb +49 -0
  20. data/lib/http_utilities/http/format.rb +26 -0
  21. data/lib/http_utilities/http/get.rb +67 -0
  22. data/lib/http_utilities/http/logger.rb +11 -0
  23. data/lib/http_utilities/http/mechanize/client.rb +197 -0
  24. data/lib/http_utilities/http/post.rb +32 -0
  25. data/lib/http_utilities/http/proxy_support.rb +88 -0
  26. data/lib/http_utilities/http/request.rb +20 -0
  27. data/lib/http_utilities/http/response.rb +50 -0
  28. data/lib/http_utilities/http/url.rb +48 -0
  29. data/lib/http_utilities/http/user_agent.rb +3380 -0
  30. data/lib/http_utilities/jobs/resque/proxies/check_proxies_job.rb +15 -0
  31. data/lib/http_utilities/jobs/resque/proxies/check_proxy_job.rb +21 -0
  32. data/lib/http_utilities/jobs/sidekiq/proxies/check_proxies_job.rb +17 -0
  33. data/lib/http_utilities/jobs/sidekiq/proxies/check_proxy_job.rb +22 -0
  34. data/lib/http_utilities/proxies/proxy_checker.rb +122 -0
  35. data/lib/http_utilities/proxies/proxy_module.rb +70 -0
  36. data/lib/http_utilities/proxies/proxy_seeder.rb +104 -0
  37. data/lib/http_utilities/railtie.rb +11 -0
  38. data/lib/http_utilities.rb +47 -0
  39. data/lib/tasks/http_utilities_tasks.rake +19 -0
  40. data/spec/database.yml.example +10 -0
  41. data/spec/http_utilities/client_spec.rb +145 -0
  42. data/spec/http_utilities/mechanize_client_spec.rb +35 -0
  43. data/spec/http_utilities/proxy_checker_spec.rb +11 -0
  44. data/spec/http_utilities/proxy_seeder_spec.rb +24 -0
  45. data/spec/http_utilities/proxy_spec.rb +114 -0
  46. data/spec/models.rb +6 -0
  47. data/spec/schema.rb +30 -0
  48. data/spec/spec_helper.rb +50 -0
  49. metadata +209 -0
@@ -0,0 +1,24 @@
1
+ require File.expand_path('../../spec_helper', __FILE__)
2
+
3
+ describe HttpUtilities::Proxies::ProxySeeder do
4
+
5
+ describe "when initialized" do
6
+ before(:each) do
7
+ @seeder = HttpUtilities::Proxies::ProxySeeder.new
8
+ end
9
+
10
+ it "should parse proxies from text files" do
11
+ proxy_data = @seeder.parse_proxies
12
+ proxy_data.should_not be_nil
13
+ end
14
+
15
+ #Can only be tested on mysql, sqlite will fail with ConstraintExceptions (since it does not support on duplicate key update ...)
16
+ if (ENV['DB'] == 'mysql')
17
+ it "should import parsed proxies using activerecord-import" do
18
+ @seeder.seed
19
+ ::Proxy.count.should > 0
20
+ end
21
+ end
22
+
23
+ end
24
+ end
@@ -0,0 +1,114 @@
1
+ require File.expand_path('../../spec_helper', __FILE__)
2
+
3
+ describe Proxy do
4
+
5
+ describe "when initialized" do
6
+ before(:each) do
7
+ clean_database!
8
+ @proxy = Proxy.new
9
+ end
10
+
11
+ it "should respond to proxy address module instance method" do
12
+ @proxy.should respond_to(:proxy_address)
13
+ end
14
+
15
+ it "should correctly return a formatted proxy address" do
16
+ @proxy.host = "127.0.0.1"
17
+ @proxy.port = 80
18
+
19
+ @proxy.proxy_address.should == "127.0.0.1:80"
20
+ @proxy.proxy_address(include_http = true).should == "http://127.0.0.1:80"
21
+ end
22
+
23
+ it "should correctly return formatted proxy credentials" do
24
+ @proxy.username = "usr"
25
+ @proxy.password = "passw"
26
+
27
+ @proxy.proxy_credentials.should == "usr:passw"
28
+ end
29
+ end
30
+
31
+ describe "in a class context" do
32
+ it "should respond to get random proxy module class method" do
33
+ Proxy.should respond_to(:get_random_proxy)
34
+ end
35
+
36
+ it "should respond to format proxy address module class method" do
37
+ Proxy.should respond_to(:format_proxy_address)
38
+ end
39
+
40
+ it "should respond to format proxy credentials module class method" do
41
+ Proxy.should respond_to(:format_proxy_credentials)
42
+ end
43
+
44
+ it "should respond to should_be_checked-scope" do
45
+ Proxy.should respond_to(:should_be_checked)
46
+ end
47
+ end
48
+
49
+ describe "when fetching proxies" do
50
+ before(:each) do
51
+ clean_database!
52
+
53
+ data = {:host => "127.0.0.1",
54
+ :port => 80,
55
+ :protocol => 'http',
56
+ :proxy_type => 'public',
57
+ :category => 'L1',
58
+ :valid_proxy => true,
59
+ :last_checked_at => 1.week.ago
60
+ }
61
+
62
+ #Http Proxies
63
+ Proxy.create(data)
64
+ Proxy.create(data.merge!({:port => 81, :proxy_type => 'shared'}))
65
+ Proxy.create(data.merge!({:port => 82, :proxy_type => 'private'}))
66
+
67
+ #Socks Proxies
68
+ Proxy.create(data.merge!({:port => 83, :protocol => 'socks', :proxy_type => 'public'}))
69
+ Proxy.create(data.merge!({:port => 84, :protocol => 'socks', :proxy_type => 'shared'}))
70
+ Proxy.create(data.merge!({:port => 85, :protocol => 'socks', :proxy_type => 'private'}))
71
+ end
72
+
73
+ it "should return proxies that should be checked (using default parameters)" do
74
+ proxies = Proxy.should_be_checked
75
+ proxies.should_not be_nil
76
+ proxies.size.should == 6
77
+ end
78
+
79
+ [:http, :socks].each do |protocol|
80
+ it "should return #{protocol.to_s} proxies that should be checked" do
81
+ proxies = Proxy.should_be_checked(protocol)
82
+ proxies.should_not be_nil
83
+ proxies.size.should == 3
84
+ end
85
+
86
+ [:public, :shared, :private].each do |proxy_type|
87
+ it "should return #{proxy_type.to_s} #{protocol.to_s} proxies that should be checked" do
88
+ proxies = Proxy.should_be_checked(protocol, proxy_type)
89
+ proxies.should_not be_nil
90
+ proxies.size.should == 1
91
+ end
92
+ end
93
+ end
94
+
95
+ [:http, :socks].each do |protocol|
96
+ it "should return a random #{protocol.to_s} proxy" do
97
+ random_proxy = Proxy.get_random_proxy(protocol)
98
+ random_proxy.should_not be_nil
99
+ random_proxy.protocol.should == protocol.to_s
100
+ end
101
+
102
+ [:public, :shared, :private].each do |proxy_type|
103
+ it "should return a random #{proxy_type.to_s} #{protocol.to_s} proxy" do
104
+ random_proxy = Proxy.get_random_proxy(protocol, proxy_type)
105
+ random_proxy.should_not be_nil
106
+ random_proxy.protocol.should == protocol.to_s
107
+ random_proxy.proxy_type.should == proxy_type.to_s
108
+ end
109
+ end
110
+ end
111
+
112
+ end
113
+
114
+ end
data/spec/models.rb ADDED
@@ -0,0 +1,6 @@
1
+ require "active_record"
2
+ require File.expand_path('../../lib/http_utilities/proxies/proxy_module', __FILE__)
3
+
4
+ class Proxy < ActiveRecord::Base
5
+ include HttpUtilities::Proxies::ProxyModule
6
+ end
data/spec/schema.rb ADDED
@@ -0,0 +1,30 @@
1
+ ActiveRecord::Schema.define :version => 0 do
2
+ execute "DROP TABLE IF EXISTS proxies"
3
+
4
+ create_table :proxies do |t|
5
+
6
+ t.string :host, :null => false
7
+ t.integer :port, :null => false
8
+ t.string :username
9
+ t.string :password
10
+
11
+ t.string :protocol, :null => false, :default => 'http'
12
+ t.string :proxy_type, :null => false, :defaut => 'public'
13
+ t.string :category
14
+
15
+ t.datetime :last_checked_at
16
+ t.boolean :valid_proxy, :null => false, :default => false
17
+ t.integer :successful_attempts, :null => false, :default => 0
18
+ t.integer :failed_attempts, :null => false, :default => 0
19
+
20
+ t.timestamps
21
+ end
22
+
23
+ add_index :proxies, [:host, :port], :unique => true, :name => 'index_unique_proxy'
24
+ add_index :proxies, :protocol, :name => 'index_protocol'
25
+ add_index :proxies, :proxy_type, :name => 'index_proxy_type'
26
+ add_index :proxies, :category, :name => 'index_category'
27
+ add_index :proxies, :valid_proxy, :name => 'index_valid_proxy'
28
+ add_index :proxies, :successful_attempts, :name => 'index_successful_attempts'
29
+ add_index :proxies, :failed_attempts, :name => 'index_failed_attempts'
30
+ end
@@ -0,0 +1,50 @@
1
+ $LOAD_PATH << "." unless $LOAD_PATH.include?(".")
2
+
3
+ begin
4
+ require "rubygems"
5
+ require "bundler"
6
+
7
+ if Gem::Version.new(Bundler::VERSION) <= Gem::Version.new("0.9.5")
8
+ raise RuntimeError, "Your bundler version is too old." +
9
+ "Run `gem install bundler` to upgrade."
10
+ end
11
+
12
+ # Set up load paths for all bundled gems
13
+ Bundler.setup
14
+ rescue Bundler::GemNotFound
15
+ raise RuntimeError, "Bundler couldn't find some gems." +
16
+ "Did you run \`bundlee install\`?"
17
+ end
18
+
19
+ require "active_record"
20
+ require "logger"
21
+ Bundler.require
22
+
23
+ require File.expand_path('../../lib/http_utilities', __FILE__)
24
+
25
+ ENV['DB'] ||= 'sqlite3'
26
+
27
+ database_yml = File.expand_path('../database.yml', __FILE__)
28
+ if File.exists?(database_yml)
29
+ active_record_configuration = YAML.load_file(database_yml)[ENV['DB']]
30
+
31
+ ActiveRecord::Base.establish_connection(active_record_configuration)
32
+ ActiveRecord::Base.logger = Logger.new(File.join(File.dirname(__FILE__), "debug.log"))
33
+
34
+ ActiveRecord::Base.silence do
35
+ ActiveRecord::Migration.verbose = false
36
+ load(File.dirname(__FILE__) + '/schema.rb')
37
+ load(File.dirname(__FILE__) + '/models.rb')
38
+ end
39
+ else
40
+ raise "Please create #{database_yml} first to configure your database. Take a look at: #{database_yml}.example"
41
+ end
42
+
43
+ def clean_database!
44
+ models = [Proxy]
45
+ models.each do |model|
46
+ ActiveRecord::Base.connection.execute "DELETE FROM #{model.table_name}"
47
+ end
48
+ end
49
+
50
+ clean_database!
metadata ADDED
@@ -0,0 +1,209 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: http_utilities
3
+ version: !ruby/object:Gem::Version
4
+ version: 1.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Sebastian Johnsson
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2012-11-22 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: 1.5.5
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - '>='
25
+ - !ruby/object:Gem::Version
26
+ version: 1.5.5
27
+ - !ruby/object:Gem::Dependency
28
+ name: mechanize
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - '>='
32
+ - !ruby/object:Gem::Version
33
+ version: '2.5'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - '>='
39
+ - !ruby/object:Gem::Version
40
+ version: '2.5'
41
+ - !ruby/object:Gem::Dependency
42
+ name: multi_xml
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - '>='
46
+ - !ruby/object:Gem::Version
47
+ version: '0.5'
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - '>='
53
+ - !ruby/object:Gem::Version
54
+ version: '0.5'
55
+ - !ruby/object:Gem::Dependency
56
+ name: activerecord-import
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :runtime
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - '>='
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: rails
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: sqlite3
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
+ - !ruby/object:Gem::Dependency
112
+ name: mysql2
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - '>='
116
+ - !ruby/object:Gem::Version
117
+ version: 0.3.11
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - '>='
123
+ - !ruby/object:Gem::Version
124
+ version: 0.3.11
125
+ description: Wrapper for common Http Libraries (Net:HTTP/Open URI/Curl)
126
+ email:
127
+ executables: []
128
+ extensions: []
129
+ extra_rdoc_files: []
130
+ files:
131
+ - Gemfile
132
+ - README
133
+ - Rakefile
134
+ - VERSION
135
+ - http_utilities.gemspec
136
+ - lib/generators/active_record/http_utilities_generator.rb
137
+ - lib/generators/active_record/templates/migration.rb
138
+ - lib/generators/active_record/templates/proxy.rb
139
+ - lib/generators/helpers/file_helper.rb
140
+ - lib/generators/helpers/orm_helpers.rb
141
+ - lib/generators/http_utilities/http_utilities_generator.rb
142
+ - lib/generators/templates/http_utilities.rb
143
+ - lib/generators/templates/user_agents.yml
144
+ - lib/http_utilities.rb
145
+ - lib/http_utilities/http/adapters/curb.rb
146
+ - lib/http_utilities/http/adapters/net_http.rb
147
+ - lib/http_utilities/http/adapters/open_uri.rb
148
+ - lib/http_utilities/http/client.rb
149
+ - lib/http_utilities/http/cookies.rb
150
+ - lib/http_utilities/http/format.rb
151
+ - lib/http_utilities/http/get.rb
152
+ - lib/http_utilities/http/logger.rb
153
+ - lib/http_utilities/http/mechanize/client.rb
154
+ - lib/http_utilities/http/post.rb
155
+ - lib/http_utilities/http/proxy_support.rb
156
+ - lib/http_utilities/http/request.rb
157
+ - lib/http_utilities/http/response.rb
158
+ - lib/http_utilities/http/url.rb
159
+ - lib/http_utilities/http/user_agent.rb
160
+ - lib/http_utilities/jobs/resque/proxies/check_proxies_job.rb
161
+ - lib/http_utilities/jobs/resque/proxies/check_proxy_job.rb
162
+ - lib/http_utilities/jobs/sidekiq/proxies/check_proxies_job.rb
163
+ - lib/http_utilities/jobs/sidekiq/proxies/check_proxy_job.rb
164
+ - lib/http_utilities/proxies/proxy_checker.rb
165
+ - lib/http_utilities/proxies/proxy_module.rb
166
+ - lib/http_utilities/proxies/proxy_seeder.rb
167
+ - lib/http_utilities/railtie.rb
168
+ - lib/tasks/http_utilities_tasks.rake
169
+ - spec/database.yml.example
170
+ - spec/http_utilities/client_spec.rb
171
+ - spec/http_utilities/mechanize_client_spec.rb
172
+ - spec/http_utilities/proxy_checker_spec.rb
173
+ - spec/http_utilities/proxy_seeder_spec.rb
174
+ - spec/http_utilities/proxy_spec.rb
175
+ - spec/models.rb
176
+ - spec/schema.rb
177
+ - spec/spec_helper.rb
178
+ homepage: http://github.com/Agiley/http_utilities
179
+ licenses: []
180
+ metadata: {}
181
+ post_install_message:
182
+ rdoc_options: []
183
+ require_paths:
184
+ - lib
185
+ required_ruby_version: !ruby/object:Gem::Requirement
186
+ requirements:
187
+ - - '>='
188
+ - !ruby/object:Gem::Version
189
+ version: '0'
190
+ required_rubygems_version: !ruby/object:Gem::Requirement
191
+ requirements:
192
+ - - '>='
193
+ - !ruby/object:Gem::Version
194
+ version: 1.3.5
195
+ requirements: []
196
+ rubyforge_project:
197
+ rubygems_version: 2.0.3
198
+ signing_key:
199
+ specification_version: 2
200
+ summary: Wrapper for common Http Libraries (Net:HTTP/Open URI/Curl)
201
+ test_files:
202
+ - spec/http_utilities/client_spec.rb
203
+ - spec/http_utilities/mechanize_client_spec.rb
204
+ - spec/http_utilities/proxy_checker_spec.rb
205
+ - spec/http_utilities/proxy_seeder_spec.rb
206
+ - spec/http_utilities/proxy_spec.rb
207
+ - spec/models.rb
208
+ - spec/schema.rb
209
+ - spec/spec_helper.rb