scraypa 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.
@@ -0,0 +1,18 @@
1
+ module Scraypa
2
+ class VisitFactory
3
+ def self.build(params={})
4
+ if params[:config] && params[:config].use_capybara
5
+ if [:poltergeist, :poltergeist_billy].include? params[:config].driver
6
+ VisitCapybaraPoltergeist.new(params)
7
+ elsif params[:config].driver == :headless_chromium
8
+ VisitCapybaraHeadlessChromium.new(params)
9
+ else
10
+ raise CapybaraDriverUnsupported,
11
+ "Currently no support for capybara driver: #{params[:config].driver}"
12
+ end
13
+ else
14
+ VisitRestClient.new(params)
15
+ end
16
+ end
17
+ end
18
+ end
@@ -0,0 +1,13 @@
1
+ module Scraypa
2
+ class VisitInterface
3
+ def initialize(params)
4
+ raise "Scraypa::Configuration object required by Visit interface. " +
5
+ "Got: #{args[0].class}" unless
6
+ params && params[:config].is_a?(Scraypa::Configuration)
7
+ end
8
+
9
+ def execute
10
+ raise NotImplementedError, 'execute action not implemented.'
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,39 @@
1
+ require 'rest-client'
2
+
3
+ module Scraypa
4
+ class VisitRestClient < VisitInterface
5
+ def initialize params={}
6
+ super(params)
7
+ @config = params[:config]
8
+ @tor_proxy = params[:tor_proxy]
9
+ @user_agent_retriever = params[:user_agent_retriever]
10
+ end
11
+
12
+ def execute params={}
13
+ @config.tor && @tor_proxy ?
14
+ visit_get_response_through_tor(params) :
15
+ visit_get_response(params)
16
+ end
17
+
18
+ private
19
+
20
+ def visit_get_response_through_tor params={}
21
+ @tor_proxy.proxy do
22
+ return visit_get_response params
23
+ end
24
+ end
25
+
26
+ def visit_get_response params={}
27
+ RestClient::Request.execute add_user_agent_to(params)
28
+ end
29
+
30
+ def add_user_agent_to params
31
+ @user_agent_retriever ?
32
+ params.merge({
33
+ headers: {
34
+ user_agent: @user_agent_retriever.user_agent
35
+ }
36
+ }) : params
37
+ end
38
+ end
39
+ end
@@ -0,0 +1,42 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'scraypa/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = "scraypa"
8
+ spec.version = Scraypa::VERSION
9
+ spec.authors = ["joshweir"]
10
+ spec.email = ["joshua.weir@gmail.com"]
11
+
12
+ spec.summary = %q{Web scraper with support for proxy, Tor and javascript.}
13
+ #spec.description = %q{TODO: Write a longer description or delete this line.}
14
+ spec.homepage = "https://github.com/joshweir/scraypa"
15
+ spec.license = "MIT"
16
+
17
+ spec.files = `git ls-files -z`.split("\x0").reject do |f|
18
+ f.match(%r{^(test|spec|features)/})
19
+ end
20
+ spec.bindir = "exe"
21
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
22
+ spec.require_paths = ["lib"]
23
+
24
+ spec.add_development_dependency "bundler", "~> 1.14"
25
+ spec.add_development_dependency "rake", "~> 10.0"
26
+ spec.add_development_dependency "rspec", "~> 3.0"
27
+ spec.add_development_dependency "rspec-rails", "~> 3.5"
28
+ spec.add_development_dependency "webmock"
29
+ spec.add_development_dependency "puffing-billy"
30
+ spec.add_development_dependency "gem-release"
31
+ spec.add_development_dependency "rb-fsevent"
32
+ spec.add_development_dependency "guard-rspec"
33
+ spec.add_dependency "activesupport"
34
+ spec.add_dependency "rest-client"
35
+ spec.add_dependency "useragents", "0.1.4"
36
+ spec.add_dependency "capybara", "~> 2.4.4"
37
+ spec.add_dependency "chromedriver-helper"
38
+ spec.add_dependency "tormanager"
39
+ spec.add_dependency "selenium-webdriver"
40
+ spec.add_dependency "poltergeist"
41
+ spec.add_dependency "phantomjs"
42
+ end
metadata ADDED
@@ -0,0 +1,322 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: scraypa
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.1
5
+ platform: ruby
6
+ authors:
7
+ - joshweir
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2017-09-25 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: bundler
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '1.14'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.14'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rake
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '10.0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '10.0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rspec
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '3.0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '3.0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: rspec-rails
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - "~>"
60
+ - !ruby/object:Gem::Version
61
+ version: '3.5'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - "~>"
67
+ - !ruby/object:Gem::Version
68
+ version: '3.5'
69
+ - !ruby/object:Gem::Dependency
70
+ name: webmock
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: puffing-billy
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: gem-release
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: rb-fsevent
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - ">="
116
+ - !ruby/object:Gem::Version
117
+ version: '0'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - ">="
123
+ - !ruby/object:Gem::Version
124
+ version: '0'
125
+ - !ruby/object:Gem::Dependency
126
+ name: guard-rspec
127
+ requirement: !ruby/object:Gem::Requirement
128
+ requirements:
129
+ - - ">="
130
+ - !ruby/object:Gem::Version
131
+ version: '0'
132
+ type: :development
133
+ prerelease: false
134
+ version_requirements: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - ">="
137
+ - !ruby/object:Gem::Version
138
+ version: '0'
139
+ - !ruby/object:Gem::Dependency
140
+ name: activesupport
141
+ requirement: !ruby/object:Gem::Requirement
142
+ requirements:
143
+ - - ">="
144
+ - !ruby/object:Gem::Version
145
+ version: '0'
146
+ type: :runtime
147
+ prerelease: false
148
+ version_requirements: !ruby/object:Gem::Requirement
149
+ requirements:
150
+ - - ">="
151
+ - !ruby/object:Gem::Version
152
+ version: '0'
153
+ - !ruby/object:Gem::Dependency
154
+ name: rest-client
155
+ requirement: !ruby/object:Gem::Requirement
156
+ requirements:
157
+ - - ">="
158
+ - !ruby/object:Gem::Version
159
+ version: '0'
160
+ type: :runtime
161
+ prerelease: false
162
+ version_requirements: !ruby/object:Gem::Requirement
163
+ requirements:
164
+ - - ">="
165
+ - !ruby/object:Gem::Version
166
+ version: '0'
167
+ - !ruby/object:Gem::Dependency
168
+ name: useragents
169
+ requirement: !ruby/object:Gem::Requirement
170
+ requirements:
171
+ - - '='
172
+ - !ruby/object:Gem::Version
173
+ version: 0.1.4
174
+ type: :runtime
175
+ prerelease: false
176
+ version_requirements: !ruby/object:Gem::Requirement
177
+ requirements:
178
+ - - '='
179
+ - !ruby/object:Gem::Version
180
+ version: 0.1.4
181
+ - !ruby/object:Gem::Dependency
182
+ name: capybara
183
+ requirement: !ruby/object:Gem::Requirement
184
+ requirements:
185
+ - - "~>"
186
+ - !ruby/object:Gem::Version
187
+ version: 2.4.4
188
+ type: :runtime
189
+ prerelease: false
190
+ version_requirements: !ruby/object:Gem::Requirement
191
+ requirements:
192
+ - - "~>"
193
+ - !ruby/object:Gem::Version
194
+ version: 2.4.4
195
+ - !ruby/object:Gem::Dependency
196
+ name: chromedriver-helper
197
+ requirement: !ruby/object:Gem::Requirement
198
+ requirements:
199
+ - - ">="
200
+ - !ruby/object:Gem::Version
201
+ version: '0'
202
+ type: :runtime
203
+ prerelease: false
204
+ version_requirements: !ruby/object:Gem::Requirement
205
+ requirements:
206
+ - - ">="
207
+ - !ruby/object:Gem::Version
208
+ version: '0'
209
+ - !ruby/object:Gem::Dependency
210
+ name: tormanager
211
+ requirement: !ruby/object:Gem::Requirement
212
+ requirements:
213
+ - - ">="
214
+ - !ruby/object:Gem::Version
215
+ version: '0'
216
+ type: :runtime
217
+ prerelease: false
218
+ version_requirements: !ruby/object:Gem::Requirement
219
+ requirements:
220
+ - - ">="
221
+ - !ruby/object:Gem::Version
222
+ version: '0'
223
+ - !ruby/object:Gem::Dependency
224
+ name: selenium-webdriver
225
+ requirement: !ruby/object:Gem::Requirement
226
+ requirements:
227
+ - - ">="
228
+ - !ruby/object:Gem::Version
229
+ version: '0'
230
+ type: :runtime
231
+ prerelease: false
232
+ version_requirements: !ruby/object:Gem::Requirement
233
+ requirements:
234
+ - - ">="
235
+ - !ruby/object:Gem::Version
236
+ version: '0'
237
+ - !ruby/object:Gem::Dependency
238
+ name: poltergeist
239
+ requirement: !ruby/object:Gem::Requirement
240
+ requirements:
241
+ - - ">="
242
+ - !ruby/object:Gem::Version
243
+ version: '0'
244
+ type: :runtime
245
+ prerelease: false
246
+ version_requirements: !ruby/object:Gem::Requirement
247
+ requirements:
248
+ - - ">="
249
+ - !ruby/object:Gem::Version
250
+ version: '0'
251
+ - !ruby/object:Gem::Dependency
252
+ name: phantomjs
253
+ requirement: !ruby/object:Gem::Requirement
254
+ requirements:
255
+ - - ">="
256
+ - !ruby/object:Gem::Version
257
+ version: '0'
258
+ type: :runtime
259
+ prerelease: false
260
+ version_requirements: !ruby/object:Gem::Requirement
261
+ requirements:
262
+ - - ">="
263
+ - !ruby/object:Gem::Version
264
+ version: '0'
265
+ description:
266
+ email:
267
+ - joshua.weir@gmail.com
268
+ executables: []
269
+ extensions: []
270
+ extra_rdoc_files: []
271
+ files:
272
+ - ".gitignore"
273
+ - ".rspec"
274
+ - ".travis.yml"
275
+ - Gemfile
276
+ - Guardfile
277
+ - LICENSE.txt
278
+ - README.md
279
+ - Rakefile
280
+ - bin/console
281
+ - bin/setup
282
+ - lib/scraypa.rb
283
+ - lib/scraypa/configuration.rb
284
+ - lib/scraypa/driver_resetter.rb
285
+ - lib/scraypa/throttle.rb
286
+ - lib/scraypa/user_agent/user_agent_abstract.rb
287
+ - lib/scraypa/user_agent/user_agent_common_aliases_lists.rb
288
+ - lib/scraypa/user_agent/user_agent_factory.rb
289
+ - lib/scraypa/user_agent/user_agent_iterator.rb
290
+ - lib/scraypa/user_agent/user_agent_random.rb
291
+ - lib/scraypa/version.rb
292
+ - lib/scraypa/visit/visit_capabara_headless_chromium.rb
293
+ - lib/scraypa/visit/visit_capabara_poltergeist.rb
294
+ - lib/scraypa/visit/visit_factory.rb
295
+ - lib/scraypa/visit/visit_interface.rb
296
+ - lib/scraypa/visit/visit_rest_client.rb
297
+ - scraypa.gemspec
298
+ homepage: https://github.com/joshweir/scraypa
299
+ licenses:
300
+ - MIT
301
+ metadata: {}
302
+ post_install_message:
303
+ rdoc_options: []
304
+ require_paths:
305
+ - lib
306
+ required_ruby_version: !ruby/object:Gem::Requirement
307
+ requirements:
308
+ - - ">="
309
+ - !ruby/object:Gem::Version
310
+ version: '0'
311
+ required_rubygems_version: !ruby/object:Gem::Requirement
312
+ requirements:
313
+ - - ">="
314
+ - !ruby/object:Gem::Version
315
+ version: '0'
316
+ requirements: []
317
+ rubyforge_project:
318
+ rubygems_version: 2.5.1
319
+ signing_key:
320
+ specification_version: 4
321
+ summary: Web scraper with support for proxy, Tor and javascript.
322
+ test_files: []