active_scraper 0.0.1

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.
checksums.yaml ADDED
@@ -0,0 +1,15 @@
1
+ ---
2
+ !binary "U0hBMQ==":
3
+ metadata.gz: !binary |-
4
+ ODhmOGY2MGY0MWNjZmExNGM5MzA5ZGQwZmFhNjg0ZDQxZTMzOGQwNw==
5
+ data.tar.gz: !binary |-
6
+ NWQ5ZDQwYzZlNTg5MjY2YjdmZjFkN2Q4MmEzMjdmOGYwNjE0OWQ2NQ==
7
+ SHA512:
8
+ metadata.gz: !binary |-
9
+ NjY1NWFjOTg5OGI1NWFlOTgzZjNjZGNiNjk2OGJkZDIyMTRjMmQwNWU3MjY3
10
+ MTIyMDNlZDJiZWMwZjNhZDM4NTk1Njk5MjdkNmRiYTNlZDEzZDZmNjdhYjRl
11
+ ZjFjNmVlMTVjYjI5MDE0MGYyNTdlNTEyZmEzMmI3N2QwYTNhNGY=
12
+ data.tar.gz: !binary |-
13
+ YzIyNWE4M2JhODc0MmY3OWQ1ZDFkNmYwNjA1M2M5MDZiNDAyMGVlYmU2MTVl
14
+ NDk5Y2ZiNTg1OGFkZmZkYmJhOGQyYjUyODA4NTg2ZDliNjhhMmQyZTNhZmEx
15
+ YzQwYWU1NzdlZWE2MjRiMTM2YjUwNzM3NjM5YWM2NDk3YmU4NDk=
data/MIT-LICENSE ADDED
@@ -0,0 +1,20 @@
1
+ Copyright 2013 YOURNAME
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining
4
+ a copy of this software and associated documentation files (the
5
+ "Software"), to deal in the Software without restriction, including
6
+ without limitation the rights to use, copy, modify, merge, publish,
7
+ distribute, sublicense, and/or sell copies of the Software, and to
8
+ permit persons to whom the Software is furnished to do so, subject to
9
+ the following conditions:
10
+
11
+ The above copyright notice and this permission notice shall be
12
+ included in all copies or substantial portions of the Software.
13
+
14
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
18
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
19
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
20
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/Rakefile ADDED
@@ -0,0 +1,23 @@
1
+ begin
2
+ require 'bundler/setup'
3
+ rescue LoadError
4
+ puts 'You must `gem install bundler` and `bundle install` to run rake tasks'
5
+ end
6
+
7
+ require 'rdoc/task'
8
+
9
+ RDoc::Task.new(:rdoc) do |rdoc|
10
+ rdoc.rdoc_dir = 'rdoc'
11
+ rdoc.title = 'ActiveScraper'
12
+ rdoc.options << '--line-numbers'
13
+ rdoc.rdoc_files.include('README.rdoc')
14
+ rdoc.rdoc_files.include('lib/**/*.rb')
15
+ end
16
+
17
+ APP_RAKEFILE = File.expand_path("../spec/dummy/Rakefile", __FILE__)
18
+ load 'rails/tasks/engine.rake'
19
+
20
+
21
+
22
+ Bundler::GemHelper.install_tasks
23
+
@@ -0,0 +1,15 @@
1
+ /*
2
+ * This is a manifest file that'll be compiled into application.css, which will include all the files
3
+ * listed below.
4
+ *
5
+ * Any CSS and SCSS file within this directory, lib/assets/stylesheets, vendor/assets/stylesheets,
6
+ * or vendor/assets/stylesheets of plugins, if any, can be referenced here using a relative path.
7
+ *
8
+ * You're free to add application-wide styles to this file and they'll appear at the bottom of the
9
+ * compiled file so the styles you add here take precedence over styles defined in any styles
10
+ * defined in the other CSS/SCSS files in this directory. It is generally better to create a new
11
+ * file per style scope.
12
+ *
13
+ *= require_tree .
14
+ *= require_self
15
+ */
@@ -0,0 +1,4 @@
1
+ module ActiveScraper
2
+ class ApplicationController < ActionController::Base
3
+ end
4
+ end
@@ -0,0 +1,4 @@
1
+ module ActiveScraper
2
+ module ApplicationHelper
3
+ end
4
+ end
@@ -0,0 +1,47 @@
1
+ module ActiveScraper
2
+ class AgnosticResponseObject < SimpleDelegator
3
+
4
+ attr_reader :code, :headers, :body, :content_type
5
+
6
+ def initialize(obj)
7
+ if obj.class == (HTTParty::Response)
8
+ # use the Net::HTTPResponse instead
9
+ obj = obj.response
10
+ end
11
+
12
+ response_obj = if obj.is_a?(Net::HTTPResponse)
13
+ @body = obj.body
14
+ @content_type = obj.content_type
15
+ @headers = obj.each_header.inject({}){|h, (k, v)| h[k] = v; h }
16
+ @code = obj.code.to_i
17
+ elsif obj.is_a?(ActiveScraper::Request)
18
+ @body = obj.body
19
+ @content_type = obj.content_type
20
+ @headers = obj.headers
21
+ @code = obj.code.to_i
22
+ else
23
+ # this is probably not used
24
+ @body = obj.to_s
25
+ @headers = {}
26
+ @content_type = nil
27
+ @code = nil
28
+ end
29
+
30
+ super({})
31
+
32
+ # now set its values
33
+ [:body, :headers, :content_type, :code].each do |a|
34
+ self[a] = self.send(a)
35
+ end
36
+ end
37
+
38
+ # def [](k)
39
+ # @values[k.to_sym]
40
+ # end
41
+
42
+ # def [](k,v)
43
+ # send(:"#{k}=", v)
44
+ # end
45
+
46
+ end
47
+ end
@@ -0,0 +1,98 @@
1
+ require 'addressable/uri'
2
+ module ActiveScraper
3
+ class Request < ActiveRecord::Base
4
+ has_many :responses, :dependent => :destroy
5
+ validates_uniqueness_of :path, scope: [:host, :query, :scheme]
6
+
7
+
8
+ scope :with_url, ->(u){
9
+ params = Request.build_validating_params(u)
10
+ where(params)
11
+ }
12
+
13
+
14
+ def obfuscated?
15
+ is_obfuscated == true
16
+ end
17
+
18
+ def uri
19
+ Addressable::URI.new(
20
+ self.attributes.symbolize_keys.slice(:scheme, :host, :path, :query)
21
+ )
22
+ end
23
+
24
+ def self.build_validating_params(uri, opts={})
25
+ h = build_request_params(uri, opts)
26
+
27
+ h.slice(:scheme, :host, :path, :query)
28
+ end
29
+
30
+ # Returns a Hash with symbolized keys
31
+ def self.build_request_params(uri, opts={})
32
+ u = Addressable::URI.parse(uri)
33
+ hsh = {scheme: u.normalized_scheme, host: u.normalized_host, path: u.normalized_path, query: u.normalized_query, extname: u.extname}
34
+
35
+ if ob_keys = opts.delete(:obfuscate_query)
36
+ Array(ob_keys).each do |key|
37
+ a = Array(key)
38
+
39
+ key_to_omit = Regexp.escape(a[0].to_s)
40
+ char_num = a[1] || 0
41
+
42
+ if val_to_omit = hsh[:query].match(/(?<=#{key_to_omit}=)(.*?)(?=&|$)/)
43
+ val = val_to_omit[1]
44
+ hsh[:query].sub!( val, "__OMIT__#{val[-char_num, char_num]}")
45
+ end
46
+ end
47
+
48
+ hsh[:is_obfuscated] = true
49
+ else
50
+ hsh[:is_obfuscated] = false
51
+ end
52
+
53
+ return hsh
54
+ end
55
+
56
+ def self.build_from_uri(uri, opts={})
57
+ request_params = build_request_params(uri, opts)
58
+ request_obj = Request.new(request_params)
59
+
60
+ return request_obj
61
+ end
62
+
63
+ def self.find_or_build_from_uri(uri, opts={})
64
+ self.with_url(uri).first || self.build_from_uri(uri, opts)
65
+ end
66
+
67
+
68
+ def self.create_from_uri(uri, opts={})
69
+ req = build_from_uri(uri, opts)
70
+ req.save
71
+
72
+ return req
73
+ end
74
+
75
+
76
+ def self.create_and_fetch_response(uri, opts={}, fetcher = nil)
77
+ request = find_or_build_from_uri(uri, opts)
78
+ fetcher = fetcher || Fetcher.new
79
+
80
+ if request.id.nil?
81
+ # this request is new
82
+ # so skip to the fresh
83
+ resp = fetcher.fetch request, fresh: true
84
+ else
85
+ # will check the cache and the fresh
86
+ resp = fetcher.fetch request
87
+ end
88
+
89
+ # build the response
90
+ response = request.responses.build(resp)
91
+ # theoretically, response will be saved too
92
+ request.save
93
+
94
+ return request
95
+ end
96
+
97
+ end
98
+ end
@@ -0,0 +1,26 @@
1
+ module ActiveScraper
2
+ class Response < ActiveRecord::Base
3
+ serialize :headers, Hash
4
+ belongs_to :request
5
+ before_save :set_checksum
6
+
7
+
8
+
9
+ private
10
+ def set_checksum
11
+ self.checksum = body.hash
12
+
13
+ true
14
+ end
15
+
16
+ ############## class methods
17
+ def self.build_from_response_object(resp)
18
+ response = self.new
19
+ [:body, :headers, :content_type, :code].each do |att|
20
+ response.send :write_attribute, att, resp.send(att)
21
+ end
22
+
23
+ return response
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,14 @@
1
+ <!DOCTYPE html>
2
+ <html>
3
+ <head>
4
+ <title>ActiveScraper</title>
5
+ <%= stylesheet_link_tag "active_scraper/application", media: "all" %>
6
+ <%= javascript_include_tag "active_scraper/application" %>
7
+ <%= csrf_meta_tags %>
8
+ </head>
9
+ <body>
10
+
11
+ <%= yield %>
12
+
13
+ </body>
14
+ </html>
data/config/routes.rb ADDED
@@ -0,0 +1,2 @@
1
+ ActiveScraper::Engine.routes.draw do
2
+ end
@@ -0,0 +1,16 @@
1
+ class CreateActiveScraperRequests < ActiveRecord::Migration
2
+ def change
3
+ create_table :active_scraper_requests do |t|
4
+ t.string :host
5
+ t.text :query
6
+ t.string :path
7
+ t.string :meta_tag
8
+ t.boolean :is_obfuscated
9
+
10
+ t.timestamps
11
+ end
12
+
13
+ add_index :active_scraper_requests, [:host, :path]
14
+
15
+ end
16
+ end
@@ -0,0 +1,17 @@
1
+ class CreateActiveScraperResponses < ActiveRecord::Migration
2
+ def change
3
+ create_table :active_scraper_responses do |t|
4
+ t.text :body, :limit => 4294967295
5
+ t.integer :code
6
+ t.text :headers
7
+ t.string :content_type
8
+ t.integer :checksum
9
+ t.integer :active_scraper_request_id
10
+
11
+ t.timestamps
12
+ end
13
+
14
+ add_index :active_scraper_responses, [:active_scraper_request_id, :created_at], name: 'index_request_id_and_created_at'
15
+ add_index :active_scraper_responses, [:active_scraper_request_id, :checksum], name: 'index_request_id_and_checksum'
16
+ end
17
+ end
@@ -0,0 +1,10 @@
1
+ module ActiveScraper
2
+ class Engine < ::Rails::Engine
3
+ isolate_namespace ActiveScraper
4
+ config.generators do |g|
5
+ g.test_framework :rspec, :fixture => false
6
+ g.assets false
7
+ g.helper false
8
+ end
9
+ end
10
+ end
@@ -0,0 +1,65 @@
1
+ require 'httparty'
2
+
3
+ module ActiveScraper
4
+ class Fetcher
5
+
6
+ def fetch(u, opts={})
7
+ url = convert_uri_object(u)
8
+ force_fresh = opts.delete :fresh
9
+
10
+ if force_fresh != true && (record = fetch_from_cache(url, opts))
11
+ resp_obj = record
12
+ else
13
+ resp_obj = fetch_fresh(url, opts)
14
+ end
15
+
16
+ build_response_object(resp_obj)
17
+ end
18
+
19
+
20
+ def fetch_fresh(url, opts={})
21
+ opts = opts.stringify_keys
22
+
23
+ url = url.to_s
24
+ verb = opts.fetch('verb'){ 'get' }
25
+
26
+ resp = HTTParty.send(verb, url)
27
+ end
28
+
29
+
30
+ # returns:
31
+ # single ScrapeCache if a valid ActiveScraper::Request exists
32
+ #
33
+ def fetch_from_cache(uri, opts={})
34
+
35
+ end
36
+
37
+ # true or false if ActiveScraper::Request with these parameters exist
38
+ def has_cache?(uri, opts={})
39
+
40
+ end
41
+
42
+
43
+ # u can either be a Request object, a String, or Addressable::URI
44
+ # returns an Addressable::URI
45
+ def convert_uri_object(u)
46
+ if u.is_a?(ActiveScraper::Request)
47
+ x = u.uri
48
+ else
49
+ x = Addressable::URI.parse(u)
50
+ end
51
+
52
+ return x
53
+ end
54
+
55
+ def build_response_object(obj)
56
+ self.class.build_response_object(obj)
57
+ end
58
+
59
+ # returns an OpenStruct that Response can use
60
+ def self.build_response_object(obj)
61
+ return AgnosticResponseObject.new(obj)
62
+ end
63
+
64
+ end
65
+ end
@@ -0,0 +1,3 @@
1
+ module ActiveScraper
2
+ VERSION = "0.0.1"
3
+ end
@@ -0,0 +1,5 @@
1
+ require "active_scraper/engine"
2
+ require "active_scraper/fetcher"
3
+
4
+ module ActiveScraper
5
+ end
@@ -0,0 +1,4 @@
1
+ # desc "Explaining what the task does"
2
+ # task :active_scraper do
3
+ # # Task goes here
4
+ # end
metadata ADDED
@@ -0,0 +1,243 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: active_scraper
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Dan Nguyen
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-01-03 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: rails
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ~>
18
+ - !ruby/object:Gem::Version
19
+ version: 4.1.0.beta1
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ~>
25
+ - !ruby/object:Gem::Version
26
+ version: 4.1.0.beta1
27
+ - !ruby/object:Gem::Dependency
28
+ name: httparty
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ! '>='
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ! '>='
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: nokogiri
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ! '>='
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ! '>='
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: addressable
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: minitest
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: database_cleaner
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - '='
88
+ - !ruby/object:Gem::Version
89
+ version: 1.0.1
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - '='
95
+ - !ruby/object:Gem::Version
96
+ version: 1.0.1
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: webmock
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: pry
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: pry-rails
141
+ requirement: !ruby/object:Gem::Requirement
142
+ requirements:
143
+ - - ! '>='
144
+ - !ruby/object:Gem::Version
145
+ version: '0'
146
+ type: :development
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: vcr
155
+ requirement: !ruby/object:Gem::Requirement
156
+ requirements:
157
+ - - ! '>='
158
+ - !ruby/object:Gem::Version
159
+ version: '0'
160
+ type: :development
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: rspec
169
+ requirement: !ruby/object:Gem::Requirement
170
+ requirements:
171
+ - - ! '>='
172
+ - !ruby/object:Gem::Version
173
+ version: '0'
174
+ type: :development
175
+ prerelease: false
176
+ version_requirements: !ruby/object:Gem::Requirement
177
+ requirements:
178
+ - - ! '>='
179
+ - !ruby/object:Gem::Version
180
+ version: '0'
181
+ - !ruby/object:Gem::Dependency
182
+ name: rspec-rails
183
+ requirement: !ruby/object:Gem::Requirement
184
+ requirements:
185
+ - - ! '>='
186
+ - !ruby/object:Gem::Version
187
+ version: '0'
188
+ type: :development
189
+ prerelease: false
190
+ version_requirements: !ruby/object:Gem::Requirement
191
+ requirements:
192
+ - - ! '>='
193
+ - !ruby/object:Gem::Version
194
+ version: '0'
195
+ description: A Rails Engine using ActiveRecord to cache results of HTTP scrapes
196
+ email:
197
+ - dansonguyen@gmail.com
198
+ executables: []
199
+ extensions: []
200
+ extra_rdoc_files: []
201
+ files:
202
+ - app/assets/stylesheets/active_scraper/application.css
203
+ - app/controllers/active_scraper/application_controller.rb
204
+ - app/helpers/active_scraper/application_helper.rb
205
+ - app/models/active_scraper/agnostic_response_object.rb
206
+ - app/models/active_scraper/request.rb
207
+ - app/models/active_scraper/response.rb
208
+ - app/views/layouts/active_scraper/application.html.erb
209
+ - config/routes.rb
210
+ - db/migrate/20131229024155_create_active_scraper_requests.rb
211
+ - db/migrate/20131229033843_create_active_scraper_responses.rb
212
+ - lib/active_scraper/engine.rb
213
+ - lib/active_scraper/fetcher.rb
214
+ - lib/active_scraper/version.rb
215
+ - lib/active_scraper.rb
216
+ - lib/tasks/active_scraper_tasks.rake
217
+ - MIT-LICENSE
218
+ - Rakefile
219
+ homepage: http://github.com/dannguyen/active_scraper
220
+ licenses:
221
+ - MIT
222
+ metadata: {}
223
+ post_install_message:
224
+ rdoc_options: []
225
+ require_paths:
226
+ - lib
227
+ required_ruby_version: !ruby/object:Gem::Requirement
228
+ requirements:
229
+ - - ! '>='
230
+ - !ruby/object:Gem::Version
231
+ version: '0'
232
+ required_rubygems_version: !ruby/object:Gem::Requirement
233
+ requirements:
234
+ - - ! '>='
235
+ - !ruby/object:Gem::Version
236
+ version: '0'
237
+ requirements: []
238
+ rubyforge_project:
239
+ rubygems_version: 2.1.11
240
+ signing_key:
241
+ specification_version: 4
242
+ summary: A Rails Engine using ActiveRecord to cache results of HTTP scrapes
243
+ test_files: []