semantic-crawler 0.7.0 → 0.7.1
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 +7 -0
- data/.travis.yml +1 -1
- data/README.rdoc +18 -2
- data/lib/semantic_crawler/version.rb +1 -1
- metadata +32 -62
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 49b5cafbf48c8f151bd88c43a80e3f3fe869622f
|
|
4
|
+
data.tar.gz: 2ddfd25e7e4f6597dbf16b454c921ea63a1d6102
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 0b649f857dfb84e3528aab98c80ed8f85d1184c2613002397e9c8f10289bdf52f2d9daf42ef8803293068e4d7dd8122c6711a10907cab66d6a57ea29867673ce
|
|
7
|
+
data.tar.gz: 5d72005f6b1b359ed61415d0517c05fd85bd8674bdb76d439056f43a3b9945ec621b408a63101bdb95e69b9337cf01779b89047061c2033a04b175eb8162292b
|
data/.travis.yml
CHANGED
data/README.rdoc
CHANGED
|
@@ -14,6 +14,7 @@ to bypass complex NLP (natural language processing).
|
|
|
14
14
|
* {LinkedGeoData - LGD}[http://linkedgeodata.org]
|
|
15
15
|
* {GDACS}[http://gdacs.org]
|
|
16
16
|
* {Freebase}[http://freebase.com]
|
|
17
|
+
* Microdata on Websites, e.g. annotated with {schema.org}[http://schema.org/] vocabulary
|
|
17
18
|
|
|
18
19
|
=== TODO
|
|
19
20
|
|
|
@@ -51,6 +52,21 @@ library include or execute the following line:
|
|
|
51
52
|
|
|
52
53
|
>> require "semantic_crawler"
|
|
53
54
|
|
|
55
|
+
=== Microdata from Website
|
|
56
|
+
|
|
57
|
+
Extract in an easy way microdata, e.g. with schema.org vocabulary, from websites.
|
|
58
|
+
|
|
59
|
+
>>> microdata = SemanticCrawler::Websites::MicroData.new("https://www.alex-oberhauser.com")
|
|
60
|
+
>>> org = microdata.to_s['http://schema.org/Organization'][1]
|
|
61
|
+
>>> puts org['name']
|
|
62
|
+
"Sigimera Ltd."
|
|
63
|
+
>>> puts org['url']
|
|
64
|
+
"http://www.sigimera.com"
|
|
65
|
+
>>> puts org['employee']['http://schema.org/Person'].first['name']
|
|
66
|
+
"Alex Oberhauser"
|
|
67
|
+
>>> puts org['employee']['http://schema.org/Person'].first['jobTitle']
|
|
68
|
+
"Co-Founder & CEO"
|
|
69
|
+
|
|
54
70
|
=== GeoNames
|
|
55
71
|
|
|
56
72
|
The GeoNames module is able to return a Factbook::Country and Fao::Country
|
|
@@ -134,8 +150,8 @@ Freebase.com country information:
|
|
|
134
150
|
|
|
135
151
|
== Tested with
|
|
136
152
|
|
|
137
|
-
* Ruby 1.8.7-p358 and Rails 3.2
|
|
138
153
|
* Ruby 1.9.3-p125 and Rails 3.2
|
|
154
|
+
* Ruby 2.0.0-p0 and Rails 3.2
|
|
139
155
|
|
|
140
156
|
|
|
141
157
|
== Additional Links
|
|
@@ -150,7 +166,7 @@ Freebase.com country information:
|
|
|
150
166
|
|
|
151
167
|
== License
|
|
152
168
|
|
|
153
|
-
(c) 2012 by Alex Oberhauser for {Sigimera}[http://www.sigimera.
|
|
169
|
+
(c) 2012 - 2013 by Alex Oberhauser for {Sigimera Ltd.}[http://www.sigimera.com],
|
|
154
170
|
published under MIT license.
|
|
155
171
|
|
|
156
172
|
== Warranty
|
metadata
CHANGED
|
@@ -1,8 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: semantic-crawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.7.
|
|
5
|
-
prerelease:
|
|
4
|
+
version: 0.7.1
|
|
6
5
|
platform: ruby
|
|
7
6
|
authors:
|
|
8
7
|
- Alex Oberhauser
|
|
@@ -14,119 +13,104 @@ dependencies:
|
|
|
14
13
|
- !ruby/object:Gem::Dependency
|
|
15
14
|
name: httparty
|
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
|
17
|
-
none: false
|
|
18
16
|
requirements:
|
|
19
|
-
- -
|
|
17
|
+
- - '>='
|
|
20
18
|
- !ruby/object:Gem::Version
|
|
21
19
|
version: '0'
|
|
22
20
|
type: :runtime
|
|
23
21
|
prerelease: false
|
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
|
25
|
-
none: false
|
|
26
23
|
requirements:
|
|
27
|
-
- -
|
|
24
|
+
- - '>='
|
|
28
25
|
- !ruby/object:Gem::Version
|
|
29
26
|
version: '0'
|
|
30
27
|
- !ruby/object:Gem::Dependency
|
|
31
28
|
name: json
|
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
|
33
|
-
none: false
|
|
34
30
|
requirements:
|
|
35
|
-
- -
|
|
31
|
+
- - '>='
|
|
36
32
|
- !ruby/object:Gem::Version
|
|
37
33
|
version: '0'
|
|
38
34
|
type: :runtime
|
|
39
35
|
prerelease: false
|
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
|
41
|
-
none: false
|
|
42
37
|
requirements:
|
|
43
|
-
- -
|
|
38
|
+
- - '>='
|
|
44
39
|
- !ruby/object:Gem::Version
|
|
45
40
|
version: '0'
|
|
46
41
|
- !ruby/object:Gem::Dependency
|
|
47
42
|
name: nokogiri
|
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
|
49
|
-
none: false
|
|
50
44
|
requirements:
|
|
51
|
-
- -
|
|
45
|
+
- - '>='
|
|
52
46
|
- !ruby/object:Gem::Version
|
|
53
47
|
version: '0'
|
|
54
48
|
type: :runtime
|
|
55
49
|
prerelease: false
|
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
|
57
|
-
none: false
|
|
58
51
|
requirements:
|
|
59
|
-
- -
|
|
52
|
+
- - '>='
|
|
60
53
|
- !ruby/object:Gem::Version
|
|
61
54
|
version: '0'
|
|
62
55
|
- !ruby/object:Gem::Dependency
|
|
63
56
|
name: geonames
|
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
|
65
|
-
none: false
|
|
66
58
|
requirements:
|
|
67
|
-
- -
|
|
59
|
+
- - '>='
|
|
68
60
|
- !ruby/object:Gem::Version
|
|
69
61
|
version: '0'
|
|
70
62
|
type: :runtime
|
|
71
63
|
prerelease: false
|
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
|
73
|
-
none: false
|
|
74
65
|
requirements:
|
|
75
|
-
- -
|
|
66
|
+
- - '>='
|
|
76
67
|
- !ruby/object:Gem::Version
|
|
77
68
|
version: '0'
|
|
78
69
|
- !ruby/object:Gem::Dependency
|
|
79
70
|
name: microdata
|
|
80
71
|
requirement: !ruby/object:Gem::Requirement
|
|
81
|
-
none: false
|
|
82
72
|
requirements:
|
|
83
|
-
- -
|
|
73
|
+
- - '>='
|
|
84
74
|
- !ruby/object:Gem::Version
|
|
85
75
|
version: '0'
|
|
86
76
|
type: :runtime
|
|
87
77
|
prerelease: false
|
|
88
78
|
version_requirements: !ruby/object:Gem::Requirement
|
|
89
|
-
none: false
|
|
90
79
|
requirements:
|
|
91
|
-
- -
|
|
80
|
+
- - '>='
|
|
92
81
|
- !ruby/object:Gem::Version
|
|
93
82
|
version: '0'
|
|
94
83
|
- !ruby/object:Gem::Dependency
|
|
95
84
|
name: yard
|
|
96
85
|
requirement: !ruby/object:Gem::Requirement
|
|
97
|
-
none: false
|
|
98
86
|
requirements:
|
|
99
|
-
- -
|
|
87
|
+
- - '>='
|
|
100
88
|
- !ruby/object:Gem::Version
|
|
101
89
|
version: '0'
|
|
102
90
|
type: :development
|
|
103
91
|
prerelease: false
|
|
104
92
|
version_requirements: !ruby/object:Gem::Requirement
|
|
105
|
-
none: false
|
|
106
93
|
requirements:
|
|
107
|
-
- -
|
|
94
|
+
- - '>='
|
|
108
95
|
- !ruby/object:Gem::Version
|
|
109
96
|
version: '0'
|
|
110
97
|
- !ruby/object:Gem::Dependency
|
|
111
98
|
name: grit
|
|
112
99
|
requirement: !ruby/object:Gem::Requirement
|
|
113
|
-
none: false
|
|
114
100
|
requirements:
|
|
115
|
-
- -
|
|
101
|
+
- - '>='
|
|
116
102
|
- !ruby/object:Gem::Version
|
|
117
103
|
version: '0'
|
|
118
104
|
type: :development
|
|
119
105
|
prerelease: false
|
|
120
106
|
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
-
none: false
|
|
122
107
|
requirements:
|
|
123
|
-
- -
|
|
108
|
+
- - '>='
|
|
124
109
|
- !ruby/object:Gem::Version
|
|
125
110
|
version: '0'
|
|
126
111
|
- !ruby/object:Gem::Dependency
|
|
127
112
|
name: rails
|
|
128
113
|
requirement: !ruby/object:Gem::Requirement
|
|
129
|
-
none: false
|
|
130
114
|
requirements:
|
|
131
115
|
- - ~>
|
|
132
116
|
- !ruby/object:Gem::Version
|
|
@@ -134,7 +118,6 @@ dependencies:
|
|
|
134
118
|
type: :development
|
|
135
119
|
prerelease: false
|
|
136
120
|
version_requirements: !ruby/object:Gem::Requirement
|
|
137
|
-
none: false
|
|
138
121
|
requirements:
|
|
139
122
|
- - ~>
|
|
140
123
|
- !ruby/object:Gem::Version
|
|
@@ -142,97 +125,85 @@ dependencies:
|
|
|
142
125
|
- !ruby/object:Gem::Dependency
|
|
143
126
|
name: sqlite3
|
|
144
127
|
requirement: !ruby/object:Gem::Requirement
|
|
145
|
-
none: false
|
|
146
128
|
requirements:
|
|
147
|
-
- -
|
|
129
|
+
- - '>='
|
|
148
130
|
- !ruby/object:Gem::Version
|
|
149
131
|
version: '0'
|
|
150
132
|
type: :development
|
|
151
133
|
prerelease: false
|
|
152
134
|
version_requirements: !ruby/object:Gem::Requirement
|
|
153
|
-
none: false
|
|
154
135
|
requirements:
|
|
155
|
-
- -
|
|
136
|
+
- - '>='
|
|
156
137
|
- !ruby/object:Gem::Version
|
|
157
138
|
version: '0'
|
|
158
139
|
- !ruby/object:Gem::Dependency
|
|
159
140
|
name: rspec
|
|
160
141
|
requirement: !ruby/object:Gem::Requirement
|
|
161
|
-
none: false
|
|
162
142
|
requirements:
|
|
163
|
-
- -
|
|
143
|
+
- - '>='
|
|
164
144
|
- !ruby/object:Gem::Version
|
|
165
145
|
version: '0'
|
|
166
146
|
type: :development
|
|
167
147
|
prerelease: false
|
|
168
148
|
version_requirements: !ruby/object:Gem::Requirement
|
|
169
|
-
none: false
|
|
170
149
|
requirements:
|
|
171
|
-
- -
|
|
150
|
+
- - '>='
|
|
172
151
|
- !ruby/object:Gem::Version
|
|
173
152
|
version: '0'
|
|
174
153
|
- !ruby/object:Gem::Dependency
|
|
175
154
|
name: simplecov
|
|
176
155
|
requirement: !ruby/object:Gem::Requirement
|
|
177
|
-
none: false
|
|
178
156
|
requirements:
|
|
179
|
-
- -
|
|
157
|
+
- - '>='
|
|
180
158
|
- !ruby/object:Gem::Version
|
|
181
159
|
version: '0'
|
|
182
160
|
type: :development
|
|
183
161
|
prerelease: false
|
|
184
162
|
version_requirements: !ruby/object:Gem::Requirement
|
|
185
|
-
none: false
|
|
186
163
|
requirements:
|
|
187
|
-
- -
|
|
164
|
+
- - '>='
|
|
188
165
|
- !ruby/object:Gem::Version
|
|
189
166
|
version: '0'
|
|
190
167
|
- !ruby/object:Gem::Dependency
|
|
191
168
|
name: simplecov-rcov
|
|
192
169
|
requirement: !ruby/object:Gem::Requirement
|
|
193
|
-
none: false
|
|
194
170
|
requirements:
|
|
195
|
-
- -
|
|
171
|
+
- - '>='
|
|
196
172
|
- !ruby/object:Gem::Version
|
|
197
173
|
version: '0'
|
|
198
174
|
type: :development
|
|
199
175
|
prerelease: false
|
|
200
176
|
version_requirements: !ruby/object:Gem::Requirement
|
|
201
|
-
none: false
|
|
202
177
|
requirements:
|
|
203
|
-
- -
|
|
178
|
+
- - '>='
|
|
204
179
|
- !ruby/object:Gem::Version
|
|
205
180
|
version: '0'
|
|
206
181
|
- !ruby/object:Gem::Dependency
|
|
207
182
|
name: pry
|
|
208
183
|
requirement: !ruby/object:Gem::Requirement
|
|
209
|
-
none: false
|
|
210
184
|
requirements:
|
|
211
|
-
- -
|
|
185
|
+
- - '>='
|
|
212
186
|
- !ruby/object:Gem::Version
|
|
213
187
|
version: '0'
|
|
214
188
|
type: :development
|
|
215
189
|
prerelease: false
|
|
216
190
|
version_requirements: !ruby/object:Gem::Requirement
|
|
217
|
-
none: false
|
|
218
191
|
requirements:
|
|
219
|
-
- -
|
|
192
|
+
- - '>='
|
|
220
193
|
- !ruby/object:Gem::Version
|
|
221
194
|
version: '0'
|
|
222
195
|
- !ruby/object:Gem::Dependency
|
|
223
196
|
name: awesome_print
|
|
224
197
|
requirement: !ruby/object:Gem::Requirement
|
|
225
|
-
none: false
|
|
226
198
|
requirements:
|
|
227
|
-
- -
|
|
199
|
+
- - '>='
|
|
228
200
|
- !ruby/object:Gem::Version
|
|
229
201
|
version: '0'
|
|
230
202
|
type: :development
|
|
231
203
|
prerelease: false
|
|
232
204
|
version_requirements: !ruby/object:Gem::Requirement
|
|
233
|
-
none: false
|
|
234
205
|
requirements:
|
|
235
|
-
- -
|
|
206
|
+
- - '>='
|
|
236
207
|
- !ruby/object:Gem::Version
|
|
237
208
|
version: '0'
|
|
238
209
|
description: SemanticCrawler is a ruby library that encapsulates data gathering from
|
|
@@ -333,27 +304,26 @@ files:
|
|
|
333
304
|
homepage: https://github.com/obale/semantic_crawler
|
|
334
305
|
licenses:
|
|
335
306
|
- MIT
|
|
307
|
+
metadata: {}
|
|
336
308
|
post_install_message:
|
|
337
309
|
rdoc_options: []
|
|
338
310
|
require_paths:
|
|
339
311
|
- lib
|
|
340
312
|
required_ruby_version: !ruby/object:Gem::Requirement
|
|
341
|
-
none: false
|
|
342
313
|
requirements:
|
|
343
|
-
- -
|
|
314
|
+
- - '>='
|
|
344
315
|
- !ruby/object:Gem::Version
|
|
345
316
|
version: '0'
|
|
346
317
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
347
|
-
none: false
|
|
348
318
|
requirements:
|
|
349
|
-
- -
|
|
319
|
+
- - '>='
|
|
350
320
|
- !ruby/object:Gem::Version
|
|
351
321
|
version: '0'
|
|
352
322
|
requirements: []
|
|
353
323
|
rubyforge_project:
|
|
354
|
-
rubygems_version:
|
|
324
|
+
rubygems_version: 2.0.0
|
|
355
325
|
signing_key:
|
|
356
|
-
specification_version:
|
|
326
|
+
specification_version: 4
|
|
357
327
|
summary: SemanticCrawler is a ruby library that encapsulates data gathering from different
|
|
358
328
|
sources, e.g. microdata from websites.
|
|
359
329
|
test_files:
|