kabutops 0.0.1 → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/LICENSE +8 -191
- data/README.md +24 -3
- data/lib/kabutops.rb +5 -0
- data/lib/kabutops/adapters/base.rb +17 -0
- data/lib/kabutops/adapters/callback.rb +1 -1
- data/lib/kabutops/adapters/database_adapter.rb +11 -2
- data/lib/kabutops/adapters/elastic_search.rb +13 -9
- data/lib/kabutops/adapters/mysql.rb +7 -3
- data/lib/kabutops/crawler.rb +12 -28
- data/lib/kabutops/crawler_extensions/debugging.rb +45 -0
- data/lib/kabutops/crawler_extensions/elastic_search.rb +1 -0
- data/lib/kabutops/crawler_extensions/mysql.rb +21 -0
- data/lib/kabutops/crawler_extensions/pstore_storage.rb +24 -9
- data/lib/kabutops/parameterable.rb +33 -0
- data/lib/kabutops/recipe.rb +5 -3
- data/lib/kabutops/recipe_item.rb +2 -0
- data/lib/kabutops/version.rb +1 -1
- metadata +67 -22
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3558c828ca14af27797b234bab95569992e00f1e
|
4
|
+
data.tar.gz: 317fec36ba533f78861203c4142e4a7c7d3add84
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8bf4d1916494080e06c5cda2a830f78857851c1d07228aa271b2c106896b712a54a2ef5747b881cd828d506a03a1f2d8e4db672864f888585cc3780640d317a1
|
7
|
+
data.tar.gz: efbef6ae896963703a2c39963b55cf57b6729d58ed1b9749d2052a5821e0366420c65b16f0a1256ef267453e2bc57732530b89a777e5ecc9669885b232cb9b9e
|
data/LICENSE
CHANGED
@@ -1,191 +1,8 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
"License" shall mean the terms and conditions for use, reproduction, and
|
10
|
-
distribution as defined by Sections 1 through 9 of this document.
|
11
|
-
|
12
|
-
"Licensor" shall mean the copyright owner or entity authorized by the copyright
|
13
|
-
owner that is granting the License.
|
14
|
-
|
15
|
-
"Legal Entity" shall mean the union of the acting entity and all other entities
|
16
|
-
that control, are controlled by, or are under common control with that entity.
|
17
|
-
For the purposes of this definition, "control" means (i) the power, direct or
|
18
|
-
indirect, to cause the direction or management of such entity, whether by
|
19
|
-
contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
20
|
-
outstanding shares, or (iii) beneficial ownership of such entity.
|
21
|
-
|
22
|
-
"You" (or "Your") shall mean an individual or Legal Entity exercising
|
23
|
-
permissions granted by this License.
|
24
|
-
|
25
|
-
"Source" form shall mean the preferred form for making modifications, including
|
26
|
-
but not limited to software source code, documentation source, and configuration
|
27
|
-
files.
|
28
|
-
|
29
|
-
"Object" form shall mean any form resulting from mechanical transformation or
|
30
|
-
translation of a Source form, including but not limited to compiled object code,
|
31
|
-
generated documentation, and conversions to other media types.
|
32
|
-
|
33
|
-
"Work" shall mean the work of authorship, whether in Source or Object form, made
|
34
|
-
available under the License, as indicated by a copyright notice that is included
|
35
|
-
in or attached to the work (an example is provided in the Appendix below).
|
36
|
-
|
37
|
-
"Derivative Works" shall mean any work, whether in Source or Object form, that
|
38
|
-
is based on (or derived from) the Work and for which the editorial revisions,
|
39
|
-
annotations, elaborations, or other modifications represent, as a whole, an
|
40
|
-
original work of authorship. For the purposes of this License, Derivative Works
|
41
|
-
shall not include works that remain separable from, or merely link (or bind by
|
42
|
-
name) to the interfaces of, the Work and Derivative Works thereof.
|
43
|
-
|
44
|
-
"Contribution" shall mean any work of authorship, including the original version
|
45
|
-
of the Work and any modifications or additions to that Work or Derivative Works
|
46
|
-
thereof, that is intentionally submitted to Licensor for inclusion in the Work
|
47
|
-
by the copyright owner or by an individual or Legal Entity authorized to submit
|
48
|
-
on behalf of the copyright owner. For the purposes of this definition,
|
49
|
-
"submitted" means any form of electronic, verbal, or written communication sent
|
50
|
-
to the Licensor or its representatives, including but not limited to
|
51
|
-
communication on electronic mailing lists, source code control systems, and
|
52
|
-
issue tracking systems that are managed by, or on behalf of, the Licensor for
|
53
|
-
the purpose of discussing and improving the Work, but excluding communication
|
54
|
-
that is conspicuously marked or otherwise designated in writing by the copyright
|
55
|
-
owner as "Not a Contribution."
|
56
|
-
|
57
|
-
"Contributor" shall mean Licensor and any individual or Legal Entity on behalf
|
58
|
-
of whom a Contribution has been received by Licensor and subsequently
|
59
|
-
incorporated within the Work.
|
60
|
-
|
61
|
-
2. Grant of Copyright License.
|
62
|
-
|
63
|
-
Subject to the terms and conditions of this License, each Contributor hereby
|
64
|
-
grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
|
65
|
-
irrevocable copyright license to reproduce, prepare Derivative Works of,
|
66
|
-
publicly display, publicly perform, sublicense, and distribute the Work and such
|
67
|
-
Derivative Works in Source or Object form.
|
68
|
-
|
69
|
-
3. Grant of Patent License.
|
70
|
-
|
71
|
-
Subject to the terms and conditions of this License, each Contributor hereby
|
72
|
-
grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
|
73
|
-
irrevocable (except as stated in this section) patent license to make, have
|
74
|
-
made, use, offer to sell, sell, import, and otherwise transfer the Work, where
|
75
|
-
such license applies only to those patent claims licensable by such Contributor
|
76
|
-
that are necessarily infringed by their Contribution(s) alone or by combination
|
77
|
-
of their Contribution(s) with the Work to which such Contribution(s) was
|
78
|
-
submitted. If You institute patent litigation against any entity (including a
|
79
|
-
cross-claim or counterclaim in a lawsuit) alleging that the Work or a
|
80
|
-
Contribution incorporated within the Work constitutes direct or contributory
|
81
|
-
patent infringement, then any patent licenses granted to You under this License
|
82
|
-
for that Work shall terminate as of the date such litigation is filed.
|
83
|
-
|
84
|
-
4. Redistribution.
|
85
|
-
|
86
|
-
You may reproduce and distribute copies of the Work or Derivative Works thereof
|
87
|
-
in any medium, with or without modifications, and in Source or Object form,
|
88
|
-
provided that You meet the following conditions:
|
89
|
-
|
90
|
-
You must give any other recipients of the Work or Derivative Works a copy of
|
91
|
-
this License; and
|
92
|
-
You must cause any modified files to carry prominent notices stating that You
|
93
|
-
changed the files; and
|
94
|
-
You must retain, in the Source form of any Derivative Works that You distribute,
|
95
|
-
all copyright, patent, trademark, and attribution notices from the Source form
|
96
|
-
of the Work, excluding those notices that do not pertain to any part of the
|
97
|
-
Derivative Works; and
|
98
|
-
If the Work includes a "NOTICE" text file as part of its distribution, then any
|
99
|
-
Derivative Works that You distribute must include a readable copy of the
|
100
|
-
attribution notices contained within such NOTICE file, excluding those notices
|
101
|
-
that do not pertain to any part of the Derivative Works, in at least one of the
|
102
|
-
following places: within a NOTICE text file distributed as part of the
|
103
|
-
Derivative Works; within the Source form or documentation, if provided along
|
104
|
-
with the Derivative Works; or, within a display generated by the Derivative
|
105
|
-
Works, if and wherever such third-party notices normally appear. The contents of
|
106
|
-
the NOTICE file are for informational purposes only and do not modify the
|
107
|
-
License. You may add Your own attribution notices within Derivative Works that
|
108
|
-
You distribute, alongside or as an addendum to the NOTICE text from the Work,
|
109
|
-
provided that such additional attribution notices cannot be construed as
|
110
|
-
modifying the License.
|
111
|
-
You may add Your own copyright statement to Your modifications and may provide
|
112
|
-
additional or different license terms and conditions for use, reproduction, or
|
113
|
-
distribution of Your modifications, or for any such Derivative Works as a whole,
|
114
|
-
provided Your use, reproduction, and distribution of the Work otherwise complies
|
115
|
-
with the conditions stated in this License.
|
116
|
-
|
117
|
-
5. Submission of Contributions.
|
118
|
-
|
119
|
-
Unless You explicitly state otherwise, any Contribution intentionally submitted
|
120
|
-
for inclusion in the Work by You to the Licensor shall be under the terms and
|
121
|
-
conditions of this License, without any additional terms or conditions.
|
122
|
-
Notwithstanding the above, nothing herein shall supersede or modify the terms of
|
123
|
-
any separate license agreement you may have executed with Licensor regarding
|
124
|
-
such Contributions.
|
125
|
-
|
126
|
-
6. Trademarks.
|
127
|
-
|
128
|
-
This License does not grant permission to use the trade names, trademarks,
|
129
|
-
service marks, or product names of the Licensor, except as required for
|
130
|
-
reasonable and customary use in describing the origin of the Work and
|
131
|
-
reproducing the content of the NOTICE file.
|
132
|
-
|
133
|
-
7. Disclaimer of Warranty.
|
134
|
-
|
135
|
-
Unless required by applicable law or agreed to in writing, Licensor provides the
|
136
|
-
Work (and each Contributor provides its Contributions) on an "AS IS" BASIS,
|
137
|
-
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied,
|
138
|
-
including, without limitation, any warranties or conditions of TITLE,
|
139
|
-
NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are
|
140
|
-
solely responsible for determining the appropriateness of using or
|
141
|
-
redistributing the Work and assume any risks associated with Your exercise of
|
142
|
-
permissions under this License.
|
143
|
-
|
144
|
-
8. Limitation of Liability.
|
145
|
-
|
146
|
-
In no event and under no legal theory, whether in tort (including negligence),
|
147
|
-
contract, or otherwise, unless required by applicable law (such as deliberate
|
148
|
-
and grossly negligent acts) or agreed to in writing, shall any Contributor be
|
149
|
-
liable to You for damages, including any direct, indirect, special, incidental,
|
150
|
-
or consequential damages of any character arising as a result of this License or
|
151
|
-
out of the use or inability to use the Work (including but not limited to
|
152
|
-
damages for loss of goodwill, work stoppage, computer failure or malfunction, or
|
153
|
-
any and all other commercial damages or losses), even if such Contributor has
|
154
|
-
been advised of the possibility of such damages.
|
155
|
-
|
156
|
-
9. Accepting Warranty or Additional Liability.
|
157
|
-
|
158
|
-
While redistributing the Work or Derivative Works thereof, You may choose to
|
159
|
-
offer, and charge a fee for, acceptance of support, warranty, indemnity, or
|
160
|
-
other liability obligations and/or rights consistent with this License. However,
|
161
|
-
in accepting such obligations, You may act only on Your own behalf and on Your
|
162
|
-
sole responsibility, not on behalf of any other Contributor, and only if You
|
163
|
-
agree to indemnify, defend, and hold each Contributor harmless for any liability
|
164
|
-
incurred by, or claims asserted against, such Contributor by reason of your
|
165
|
-
accepting any such warranty or additional liability.
|
166
|
-
|
167
|
-
END OF TERMS AND CONDITIONS
|
168
|
-
|
169
|
-
APPENDIX: How to apply the Apache License to your work
|
170
|
-
|
171
|
-
To apply the Apache License to your work, attach the following boilerplate
|
172
|
-
notice, with the fields enclosed by brackets "[]" replaced with your own
|
173
|
-
identifying information. (Don't include the brackets!) The text should be
|
174
|
-
enclosed in the appropriate comment syntax for the file format. We also
|
175
|
-
recommend that a file or class name and description of purpose be included on
|
176
|
-
the same "printed page" as the copyright notice for easier identification within
|
177
|
-
third-party archives.
|
178
|
-
|
179
|
-
Copyright [yyyy] [name of copyright owner]
|
180
|
-
|
181
|
-
Licensed under the Apache License, Version 2.0 (the "License");
|
182
|
-
you may not use this file except in compliance with the License.
|
183
|
-
You may obtain a copy of the License at
|
184
|
-
|
185
|
-
http://www.apache.org/licenses/LICENSE-2.0
|
186
|
-
|
187
|
-
Unless required by applicable law or agreed to in writing, software
|
188
|
-
distributed under the License is distributed on an "AS IS" BASIS,
|
189
|
-
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
190
|
-
See the License for the specific language governing permissions and
|
191
|
-
limitations under the License.
|
1
|
+
/*
|
2
|
+
* ----------------------------------------------------------------------------
|
3
|
+
* "THE BEER-WARE LICENSE" (Revision 42):
|
4
|
+
* As long as you retain this notice you can do whatever you want with this
|
5
|
+
* stuff. If we meet some day, and you think this stuff is worth it, you can
|
6
|
+
* buy me a beer in return. Rene Klacan
|
7
|
+
* ----------------------------------------------------------------------------
|
8
|
+
*/
|
data/README.md
CHANGED
@@ -13,7 +13,7 @@ gem install kabutops
|
|
13
13
|
Or you can put it in your Gemfile
|
14
14
|
|
15
15
|
```ruby
|
16
|
-
gem 'kabutops'
|
16
|
+
gem 'kabutops', '~> 0.0.2'
|
17
17
|
```
|
18
18
|
|
19
19
|
Basic example
|
@@ -33,18 +33,19 @@ class FruitCrawler < Kabutops::Crawler
|
|
33
33
|
url: "https://www.example.com/fruits/#{id}",
|
34
34
|
}
|
35
35
|
}.shuffle
|
36
|
+
|
36
37
|
proxy '127.0.0.1', 81818
|
37
38
|
cache true
|
38
39
|
|
39
40
|
elasticsearch do
|
40
41
|
index :books
|
41
|
-
|
42
|
+
type :book
|
42
43
|
|
43
44
|
data do
|
44
45
|
id :var, :id
|
45
46
|
url :var, :url
|
46
47
|
some_attr :css, 'h1.bookTitle'
|
47
|
-
grape :lambda, ->(page) {
|
48
|
+
grape :lambda, ->(resource, page) {
|
48
49
|
page.css('h3.fruit').split(',').first
|
49
50
|
}
|
50
51
|
|
@@ -85,3 +86,23 @@ One document will look something like this
|
|
85
86
|
}
|
86
87
|
}
|
87
88
|
```
|
89
|
+
|
90
|
+
Debugging
|
91
|
+
---------
|
92
|
+
|
93
|
+
As we all know, crawler can't be written on the first time.
|
94
|
+
|
95
|
+
Therefore there are methods for debugging
|
96
|
+
|
97
|
+
```ruby
|
98
|
+
FruitCrawler.debug_first # will take first from collection
|
99
|
+
FruitCrawler.debug_first 7 # will take first 7 resources
|
100
|
+
FruitCrawler.debug_random # will take random one
|
101
|
+
FruitCrawler.debug_random 3 # will take 3 random resources
|
102
|
+
FruitCrawler.debug_last # will take last from collection
|
103
|
+
FruitCrawler.debug_last 5 # will take last 5 resources
|
104
|
+
FruitCrawler.debug_resource { id: '123', url: '...' }
|
105
|
+
```
|
106
|
+
|
107
|
+
These methods will print out what would be otherwise saved to the
|
108
|
+
database but for this time there is no save to the database.
|
data/lib/kabutops.rb
CHANGED
@@ -1,12 +1,16 @@
|
|
1
|
+
require 'hashie'
|
1
2
|
require 'sidekiq'
|
2
3
|
require 'cachy'
|
3
4
|
require 'moneta'
|
4
5
|
require 'pstore'
|
6
|
+
require 'elasticsearch'
|
5
7
|
|
6
8
|
Cachy.cache_store = Moneta.new(:File, dir: 'cache') # temporary
|
7
9
|
|
10
|
+
require 'kabutops/parameterable'
|
8
11
|
require 'kabutops/recipe'
|
9
12
|
require 'kabutops/recipe_item'
|
13
|
+
require 'kabutops/adapters/base'
|
10
14
|
require 'kabutops/adapters/callback'
|
11
15
|
require 'kabutops/adapters/database_adapter'
|
12
16
|
require 'kabutops/adapters/elastic_search'
|
@@ -15,4 +19,5 @@ require 'kabutops/crawler_extensions/callback'
|
|
15
19
|
require 'kabutops/crawler_extensions/elastic_search'
|
16
20
|
require 'kabutops/crawler_extensions/mysql'
|
17
21
|
require 'kabutops/crawler_extensions/pstore_storage'
|
22
|
+
require 'kabutops/crawler_extensions/debugging'
|
18
23
|
require 'kabutops/crawler'
|
@@ -1,6 +1,8 @@
|
|
1
1
|
module Kabutops
|
2
|
+
|
2
3
|
module Adapters
|
3
|
-
|
4
|
+
|
5
|
+
class DatabaseAdapter < Base
|
4
6
|
def data &block
|
5
7
|
@recipe = Recipe.new
|
6
8
|
@recipe.instance_eval &block
|
@@ -8,7 +10,12 @@ module Kabutops
|
|
8
10
|
|
9
11
|
def process resource, page
|
10
12
|
result = @recipe.process(resource, page)
|
11
|
-
|
13
|
+
if debug
|
14
|
+
puts "#{self.class.to_s} outputs:"
|
15
|
+
p result.to_hash
|
16
|
+
else
|
17
|
+
store(result)
|
18
|
+
end
|
12
19
|
end
|
13
20
|
|
14
21
|
def store result
|
@@ -19,5 +26,7 @@ module Kabutops
|
|
19
26
|
raise NotImplementedError
|
20
27
|
end
|
21
28
|
end
|
29
|
+
|
22
30
|
end
|
31
|
+
|
23
32
|
end
|
@@ -1,23 +1,27 @@
|
|
1
1
|
module Kabutops
|
2
|
+
|
2
3
|
module Adapters
|
4
|
+
|
3
5
|
class ElasticSearch < DatabaseAdapter
|
4
|
-
|
5
|
-
@index = value
|
6
|
-
end
|
6
|
+
include Parameterable
|
7
7
|
|
8
|
-
|
9
|
-
@document = value
|
10
|
-
end
|
8
|
+
params :host, :port, :index, :type
|
11
9
|
|
12
10
|
def store result
|
13
|
-
|
14
|
-
|
15
|
-
|
11
|
+
@@client ||= Elasticsearch::Client.new
|
12
|
+
@@client.index(
|
13
|
+
index: @params[:index] || 'default',
|
14
|
+
type: @params[:type] || 'default',
|
15
|
+
id: result[:id],
|
16
|
+
body: result.to_hash,
|
17
|
+
)
|
16
18
|
end
|
17
19
|
|
18
20
|
def nested?
|
19
21
|
true
|
20
22
|
end
|
21
23
|
end
|
24
|
+
|
22
25
|
end
|
26
|
+
|
23
27
|
end
|
@@ -1,13 +1,17 @@
|
|
1
1
|
module Kabutops
|
2
|
+
|
2
3
|
module Adapters
|
4
|
+
|
3
5
|
class MySQL < DatabaseAdapter
|
4
|
-
|
5
|
-
|
6
|
-
|
6
|
+
include Parameterable
|
7
|
+
|
8
|
+
params :host, :port, :database, :user, :password, :table
|
7
9
|
|
8
10
|
def nested?
|
9
11
|
false
|
10
12
|
end
|
11
13
|
end
|
14
|
+
|
12
15
|
end
|
16
|
+
|
13
17
|
end
|
data/lib/kabutops/crawler.rb
CHANGED
@@ -1,40 +1,23 @@
|
|
1
1
|
module Kabutops
|
2
|
+
|
2
3
|
class Crawler
|
3
|
-
include CrawlerExtensions::
|
4
|
+
include CrawlerExtensions::Debugging
|
5
|
+
include CrawlerExtensions::PStoreStorage
|
4
6
|
include CrawlerExtensions::Callback
|
7
|
+
include CrawlerExtensions::ElasticSearch
|
5
8
|
|
6
9
|
class << self
|
7
|
-
include
|
8
|
-
|
9
|
-
attr_reader :params
|
10
|
-
|
11
|
-
[
|
12
|
-
:collection,
|
13
|
-
:workers,
|
14
|
-
:proxy,
|
15
|
-
:cache
|
16
|
-
].each do |name|
|
17
|
-
define_method name do |*args|
|
18
|
-
@params ||= {}
|
19
|
-
if args.size == 1
|
20
|
-
@params[name] = args[0]
|
21
|
-
else
|
22
|
-
@params[name] = args
|
23
|
-
end
|
24
|
-
end
|
25
|
-
end
|
10
|
+
include Parameterable
|
26
11
|
|
27
|
-
|
28
|
-
@params
|
29
|
-
end
|
12
|
+
params :collection, :proxy, :cache
|
30
13
|
|
31
14
|
def adapters
|
32
15
|
@adapters
|
33
16
|
end
|
34
17
|
|
35
18
|
def crawl! collection=nil
|
36
|
-
if storage
|
37
|
-
@collection = collection ||
|
19
|
+
if storage[:status] == :none
|
20
|
+
@collection = collection || params[:collection] || []
|
38
21
|
@collection.each do |resource|
|
39
22
|
raise "url must be specified" if resource[:id].nil?
|
40
23
|
perform_async(resource)
|
@@ -48,9 +31,9 @@ module Kabutops
|
|
48
31
|
end
|
49
32
|
|
50
33
|
def perform resource
|
51
|
-
resource =
|
34
|
+
resource = Hashie::Mash.new(resource)
|
52
35
|
|
53
|
-
content = Cachy.cache_if(self.class.params
|
36
|
+
content = Cachy.cache_if(self.class.params.cache, resource[:url]) do
|
54
37
|
agent = Mechanize.new
|
55
38
|
#agent.set_proxy(*self.class.params[:proxy])
|
56
39
|
agent.get(resource[:url]).body
|
@@ -64,7 +47,8 @@ module Kabutops
|
|
64
47
|
end
|
65
48
|
|
66
49
|
def << resource
|
67
|
-
self.class.perform_async(resource)
|
50
|
+
self.class.perform_async(resource.to_hash)
|
68
51
|
end
|
69
52
|
end
|
53
|
+
|
70
54
|
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
module Kabutops
|
2
|
+
|
3
|
+
module CrawlerExtensions
|
4
|
+
|
5
|
+
module Debugging
|
6
|
+
|
7
|
+
def self.included base
|
8
|
+
base.extend(ClassMethods)
|
9
|
+
end
|
10
|
+
|
11
|
+
module ClassMethods
|
12
|
+
|
13
|
+
def debug_first count=1
|
14
|
+
params[:collection].take(count).map{ |r| debug_resource(r) }
|
15
|
+
end
|
16
|
+
|
17
|
+
def debug_random count=1
|
18
|
+
params[:collection].sample(count).map{ |r| debug_resource(r) }
|
19
|
+
end
|
20
|
+
|
21
|
+
def debug_last count=1
|
22
|
+
params[:collection][(0 - count)..-1].map{ |r| debug_resource(r) }
|
23
|
+
end
|
24
|
+
|
25
|
+
def debug_resource resource
|
26
|
+
enable_debug
|
27
|
+
self.new.perform(resource)
|
28
|
+
end
|
29
|
+
|
30
|
+
def enable_debug
|
31
|
+
@debug = true
|
32
|
+
adapters.each { |a| a.enable_debug }
|
33
|
+
end
|
34
|
+
|
35
|
+
def debug
|
36
|
+
@debug == true
|
37
|
+
end
|
38
|
+
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
@@ -3,21 +3,36 @@ module Kabutops
|
|
3
3
|
module CrawlerExtensions
|
4
4
|
|
5
5
|
module PStoreStorage
|
6
|
+
class Storage
|
7
|
+
def initialize path
|
8
|
+
@storage ||= PStore.new(path)
|
9
|
+
end
|
10
|
+
|
11
|
+
def [] key
|
12
|
+
@storage.transaction { @storage[key.to_sym] }
|
13
|
+
end
|
14
|
+
|
15
|
+
def []= key, value
|
16
|
+
@storage.transaction do
|
17
|
+
@storage[key.to_sym] = value
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
6
21
|
|
7
|
-
def
|
8
|
-
|
22
|
+
def self.included base
|
23
|
+
base.extend(ClassMethods)
|
9
24
|
end
|
10
25
|
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
@storage
|
26
|
+
module ClassMethods
|
27
|
+
|
28
|
+
def storage
|
29
|
+
@storage ||= Storage.new(".kabutopus.config.pstore")
|
15
30
|
end
|
31
|
+
|
16
32
|
end
|
17
33
|
|
18
|
-
def storage
|
19
|
-
|
20
|
-
@storage.transaction { @storage[key.to_sym] }
|
34
|
+
def storage
|
35
|
+
self.class.storage
|
21
36
|
end
|
22
37
|
|
23
38
|
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
module Kabutops
|
2
|
+
|
3
|
+
module Parameterable
|
4
|
+
|
5
|
+
def self.included base
|
6
|
+
base.extend(ClassMethods)
|
7
|
+
base.class_eval do
|
8
|
+
attr_reader :params
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
module ClassMethods
|
13
|
+
|
14
|
+
def params *list
|
15
|
+
return @params if list.empty?
|
16
|
+
|
17
|
+
list.each do |name|
|
18
|
+
define_method name do |*args|
|
19
|
+
@params ||= Hashie::Mash.new
|
20
|
+
if args.size == 1
|
21
|
+
@params[name] = args[0]
|
22
|
+
else
|
23
|
+
@params[name] = args
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
32
|
+
|
33
|
+
end
|
data/lib/kabutops/recipe.rb
CHANGED
@@ -1,7 +1,8 @@
|
|
1
1
|
module Kabutops
|
2
|
+
|
2
3
|
class Recipe
|
3
4
|
def initialize
|
4
|
-
@items =
|
5
|
+
@items = Hashie::Mash.new
|
5
6
|
@nested = false
|
6
7
|
end
|
7
8
|
|
@@ -18,7 +19,7 @@ module Kabutops
|
|
18
19
|
end
|
19
20
|
|
20
21
|
def process resource, page
|
21
|
-
result =
|
22
|
+
result = Hashie::Mash.new
|
22
23
|
|
23
24
|
@items.each do |name, item|
|
24
25
|
result[name] = case item.type
|
@@ -31,7 +32,7 @@ module Kabutops
|
|
31
32
|
when :xpath
|
32
33
|
page.xpath(item.value).text
|
33
34
|
when :lambda
|
34
|
-
item.value.call(page)
|
35
|
+
item.value.call(resource, page)
|
35
36
|
when :proc
|
36
37
|
page.instance_eval &item.value
|
37
38
|
else
|
@@ -46,4 +47,5 @@ module Kabutops
|
|
46
47
|
@nested
|
47
48
|
end
|
48
49
|
end
|
50
|
+
|
49
51
|
end
|
data/lib/kabutops/recipe_item.rb
CHANGED
data/lib/kabutops/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: kabutops
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Rene Klacan
|
@@ -14,93 +14,138 @@ dependencies:
|
|
14
14
|
name: mechanize
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '0'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- -
|
24
|
+
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: cachy
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: '0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- -
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: moneta
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- -
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
47
|
version: '0'
|
48
48
|
type: :runtime
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- -
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: sidekiq
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- -
|
59
|
+
- - ">="
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: '0'
|
62
62
|
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- -
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: elasticsearch
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
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: hashie
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
67
95
|
- !ruby/object:Gem::Version
|
68
96
|
version: '0'
|
69
97
|
- !ruby/object:Gem::Dependency
|
70
98
|
name: rspec
|
71
99
|
requirement: !ruby/object:Gem::Requirement
|
72
100
|
requirements:
|
73
|
-
- - ~>
|
101
|
+
- - "~>"
|
74
102
|
- !ruby/object:Gem::Version
|
75
103
|
version: 3.0.0
|
76
104
|
type: :development
|
77
105
|
prerelease: false
|
78
106
|
version_requirements: !ruby/object:Gem::Requirement
|
79
107
|
requirements:
|
80
|
-
- - ~>
|
108
|
+
- - "~>"
|
81
109
|
- !ruby/object:Gem::Version
|
82
110
|
version: 3.0.0
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rspec-mocks
|
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'
|
83
125
|
description: ''
|
84
126
|
email: rene@klacan.sk
|
85
127
|
executables: []
|
86
128
|
extensions: []
|
87
129
|
extra_rdoc_files: []
|
88
130
|
files:
|
131
|
+
- LICENSE
|
132
|
+
- README.md
|
89
133
|
- lib/kabutops.rb
|
90
|
-
- lib/kabutops/adapters/
|
134
|
+
- lib/kabutops/adapters/base.rb
|
91
135
|
- lib/kabutops/adapters/callback.rb
|
92
|
-
- lib/kabutops/adapters/
|
136
|
+
- lib/kabutops/adapters/database_adapter.rb
|
93
137
|
- lib/kabutops/adapters/elastic_search.rb
|
94
|
-
- lib/kabutops/
|
138
|
+
- lib/kabutops/adapters/mysql.rb
|
139
|
+
- lib/kabutops/crawler.rb
|
95
140
|
- lib/kabutops/crawler_extensions/callback.rb
|
96
|
-
- lib/kabutops/crawler_extensions/
|
141
|
+
- lib/kabutops/crawler_extensions/debugging.rb
|
97
142
|
- lib/kabutops/crawler_extensions/elastic_search.rb
|
143
|
+
- lib/kabutops/crawler_extensions/mysql.rb
|
144
|
+
- lib/kabutops/crawler_extensions/pstore_storage.rb
|
145
|
+
- lib/kabutops/parameterable.rb
|
98
146
|
- lib/kabutops/recipe.rb
|
99
|
-
- lib/kabutops/version.rb
|
100
147
|
- lib/kabutops/recipe_item.rb
|
101
|
-
- lib/kabutops/
|
102
|
-
- LICENSE
|
103
|
-
- README.md
|
148
|
+
- lib/kabutops/version.rb
|
104
149
|
homepage: https://github.com/reneklacan/kabutops
|
105
150
|
licenses:
|
106
151
|
- Beerware
|
@@ -111,17 +156,17 @@ require_paths:
|
|
111
156
|
- lib
|
112
157
|
required_ruby_version: !ruby/object:Gem::Requirement
|
113
158
|
requirements:
|
114
|
-
- - ~>
|
159
|
+
- - "~>"
|
115
160
|
- !ruby/object:Gem::Version
|
116
161
|
version: '1.9'
|
117
162
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
118
163
|
requirements:
|
119
|
-
- -
|
164
|
+
- - ">="
|
120
165
|
- !ruby/object:Gem::Version
|
121
166
|
version: '0'
|
122
167
|
requirements: []
|
123
168
|
rubyforge_project:
|
124
|
-
rubygems_version: 2.
|
169
|
+
rubygems_version: 2.2.2
|
125
170
|
signing_key:
|
126
171
|
specification_version: 4
|
127
172
|
summary: ''
|