metainspector 5.2.1 → 5.2.2
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 +4 -4
- data/.travis.yml +1 -1
- data/README.md +2 -2
- data/lib/meta_inspector/request.rb +1 -1
- data/lib/meta_inspector/version.rb +1 -1
- data/meta_inspector.gemspec +1 -1
- data/spec/document_spec.rb +8 -0
- data/spec/fixtures/encoding.response +0 -0
- data/spec/spec_helper.rb +1 -1
- metadata +39 -39
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6cecd7d0c5bc039440b960b63d6f95117370d064
|
4
|
+
data.tar.gz: 9017254d980488f088f362bbb6659369636a13e1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b66b076fc13a4bf18ba416fda0e5814502626f11ea2df0cded4e2249b7224b34369b6af49ea232949bd9512657a4c7ec7715d77449ed8ca41f6c2c6342b1691d
|
7
|
+
data.tar.gz: ed153dc93c8b70c45e28add1315d2472e2933c23a086c0db431740d3e2693f4c5d2061d69eafc5174c0c432391ed0b6c8f89b8689d4d4b430d70e9ecee794456
|
data/.travis.yml
CHANGED
data/README.md
CHANGED
@@ -267,13 +267,13 @@ page = MetaInspector.new('www.google', :connection_timeout => 10, :read_timeout
|
|
267
267
|
```
|
268
268
|
|
269
269
|
If MetaInspector fails to fetch the page after it has exhausted its retries,
|
270
|
-
it will raise `
|
270
|
+
it will raise `MetaInspector::TimeoutError`, which you can rescue in your
|
271
271
|
application code.
|
272
272
|
|
273
273
|
```ruby
|
274
274
|
begin
|
275
275
|
page = MetaInspector.new(url)
|
276
|
-
rescue
|
276
|
+
rescue MetaInspector::TimeoutError
|
277
277
|
enqueue_for_future_fetch_attempt(url)
|
278
278
|
render_simple(url)
|
279
279
|
else
|
data/meta_inspector.gemspec
CHANGED
@@ -5,7 +5,7 @@ Gem::Specification.new do |gem|
|
|
5
5
|
gem.email = ["jaimeiniesta@gmail.com"]
|
6
6
|
gem.description = %q{MetaInspector lets you scrape a web page and get its links, images, texts, meta tags...}
|
7
7
|
gem.summary = %q{MetaInspector is a ruby gem for web scraping purposes, that returns metadata from a given URL}
|
8
|
-
gem.homepage = "
|
8
|
+
gem.homepage = "https://github.com/jaimeiniesta/metainspector"
|
9
9
|
gem.license = "MIT"
|
10
10
|
|
11
11
|
gem.files = `git ls-files`.split("\n")
|
data/spec/document_spec.rb
CHANGED
@@ -137,5 +137,13 @@ describe MetaInspector::Document do
|
|
137
137
|
it 'should encode description according to the charset' do
|
138
138
|
expect(MetaInspector.new('http://example-rtl.com/').description).to eq('أعلن النائب مصطفى بكري انسحابه من ائتلاف دعم مصر بعد اعتراضه على نتيجة الانتخابات الداخلية للائتلاف، وخسارته فيها، وقال إنه سيترشح غدا على منصب الوكيل بالمجلس')
|
139
139
|
end
|
140
|
+
|
141
|
+
it 'should replace NULL characters' do
|
142
|
+
doc = MetaInspector.new('http://example-rtl.com/').parsed
|
143
|
+
|
144
|
+
image_src = doc.css('.some_class').first.attribute('src').value
|
145
|
+
|
146
|
+
expect(image_src).to eq('/path/to/image.jpg')
|
147
|
+
end
|
140
148
|
end
|
141
149
|
end
|
Binary file
|
data/spec/spec_helper.rb
CHANGED
@@ -41,7 +41,7 @@ FakeWeb.register_uri(:get, "http://example.com/10x10", :response => fixture_file
|
|
41
41
|
FakeWeb.register_uri(:get, "http://example.com/100x100", :response => fixture_file("100x100.jpg.response"))
|
42
42
|
FakeWeb.register_uri(:get, "http://www.24-horas.mx/mexico-firma-acuerdo-bilateral-automotriz-con-argentina/", :response => fixture_file("relative_og_image.response"))
|
43
43
|
|
44
|
-
#Used to test canonical URLs in head
|
44
|
+
# Used to test canonical URLs in head
|
45
45
|
FakeWeb.register_uri(:get, "http://example.com/head_links", :response => fixture_file("head_links.response"))
|
46
46
|
FakeWeb.register_uri(:get, "https://example.com/head_links", :response => fixture_file("head_links.response"))
|
47
47
|
FakeWeb.register_uri(:get, "http://example.com/broken_head_links", :response => fixture_file("broken_head_links.response"))
|
metadata
CHANGED
@@ -1,153 +1,153 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: metainspector
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 5.2.
|
4
|
+
version: 5.2.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jaime Iniesta
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-
|
11
|
+
date: 2016-08-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - ~>
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '1.6'
|
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: '1.6'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: faraday
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - ~>
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: '0.9'
|
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: '0.9'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: faraday_middleware
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- -
|
45
|
+
- - ~>
|
46
46
|
- !ruby/object:Gem::Version
|
47
47
|
version: '0.10'
|
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: '0.10'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: faraday-cookie_jar
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- -
|
59
|
+
- - ~>
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: '0.0'
|
62
62
|
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- -
|
66
|
+
- - ~>
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '0.0'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: faraday-http-cache
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- -
|
73
|
+
- - ~>
|
74
74
|
- !ruby/object:Gem::Version
|
75
75
|
version: '1.2'
|
76
76
|
type: :runtime
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- -
|
80
|
+
- - ~>
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: '1.2'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: faraday-encoding
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
|
-
- -
|
87
|
+
- - ~>
|
88
88
|
- !ruby/object:Gem::Version
|
89
89
|
version: 0.0.3
|
90
90
|
type: :runtime
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
|
-
- -
|
94
|
+
- - ~>
|
95
95
|
- !ruby/object:Gem::Version
|
96
96
|
version: 0.0.3
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
98
|
name: addressable
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
|
-
- -
|
101
|
+
- - ~>
|
102
102
|
- !ruby/object:Gem::Version
|
103
103
|
version: '2.4'
|
104
104
|
type: :runtime
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
|
-
- -
|
108
|
+
- - ~>
|
109
109
|
- !ruby/object:Gem::Version
|
110
110
|
version: '2.4'
|
111
111
|
- !ruby/object:Gem::Dependency
|
112
112
|
name: fastimage
|
113
113
|
requirement: !ruby/object:Gem::Requirement
|
114
114
|
requirements:
|
115
|
-
- -
|
115
|
+
- - ~>
|
116
116
|
- !ruby/object:Gem::Version
|
117
117
|
version: '2.0'
|
118
118
|
type: :runtime
|
119
119
|
prerelease: false
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
121
121
|
requirements:
|
122
|
-
- -
|
122
|
+
- - ~>
|
123
123
|
- !ruby/object:Gem::Version
|
124
124
|
version: '2.0'
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
126
|
name: nesty
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
128
128
|
requirements:
|
129
|
-
- -
|
129
|
+
- - ~>
|
130
130
|
- !ruby/object:Gem::Version
|
131
131
|
version: '1.0'
|
132
132
|
type: :runtime
|
133
133
|
prerelease: false
|
134
134
|
version_requirements: !ruby/object:Gem::Requirement
|
135
135
|
requirements:
|
136
|
-
- -
|
136
|
+
- - ~>
|
137
137
|
- !ruby/object:Gem::Version
|
138
138
|
version: '1.0'
|
139
139
|
- !ruby/object:Gem::Dependency
|
140
140
|
name: rspec
|
141
141
|
requirement: !ruby/object:Gem::Requirement
|
142
142
|
requirements:
|
143
|
-
- -
|
143
|
+
- - ~>
|
144
144
|
- !ruby/object:Gem::Version
|
145
145
|
version: '3.0'
|
146
146
|
type: :development
|
147
147
|
prerelease: false
|
148
148
|
version_requirements: !ruby/object:Gem::Requirement
|
149
149
|
requirements:
|
150
|
-
- -
|
150
|
+
- - ~>
|
151
151
|
- !ruby/object:Gem::Version
|
152
152
|
version: '3.0'
|
153
153
|
- !ruby/object:Gem::Dependency
|
@@ -168,70 +168,70 @@ dependencies:
|
|
168
168
|
name: webmock
|
169
169
|
requirement: !ruby/object:Gem::Requirement
|
170
170
|
requirements:
|
171
|
-
- -
|
171
|
+
- - '>='
|
172
172
|
- !ruby/object:Gem::Version
|
173
173
|
version: '0'
|
174
174
|
type: :development
|
175
175
|
prerelease: false
|
176
176
|
version_requirements: !ruby/object:Gem::Requirement
|
177
177
|
requirements:
|
178
|
-
- -
|
178
|
+
- - '>='
|
179
179
|
- !ruby/object:Gem::Version
|
180
180
|
version: '0'
|
181
181
|
- !ruby/object:Gem::Dependency
|
182
182
|
name: awesome_print
|
183
183
|
requirement: !ruby/object:Gem::Requirement
|
184
184
|
requirements:
|
185
|
-
- -
|
185
|
+
- - '>='
|
186
186
|
- !ruby/object:Gem::Version
|
187
187
|
version: '0'
|
188
188
|
type: :development
|
189
189
|
prerelease: false
|
190
190
|
version_requirements: !ruby/object:Gem::Requirement
|
191
191
|
requirements:
|
192
|
-
- -
|
192
|
+
- - '>='
|
193
193
|
- !ruby/object:Gem::Version
|
194
194
|
version: '0'
|
195
195
|
- !ruby/object:Gem::Dependency
|
196
196
|
name: rake
|
197
197
|
requirement: !ruby/object:Gem::Requirement
|
198
198
|
requirements:
|
199
|
-
- -
|
199
|
+
- - ~>
|
200
200
|
- !ruby/object:Gem::Version
|
201
201
|
version: 10.1.0
|
202
202
|
type: :development
|
203
203
|
prerelease: false
|
204
204
|
version_requirements: !ruby/object:Gem::Requirement
|
205
205
|
requirements:
|
206
|
-
- -
|
206
|
+
- - ~>
|
207
207
|
- !ruby/object:Gem::Version
|
208
208
|
version: 10.1.0
|
209
209
|
- !ruby/object:Gem::Dependency
|
210
210
|
name: pry
|
211
211
|
requirement: !ruby/object:Gem::Requirement
|
212
212
|
requirements:
|
213
|
-
- -
|
213
|
+
- - '>='
|
214
214
|
- !ruby/object:Gem::Version
|
215
215
|
version: '0'
|
216
216
|
type: :development
|
217
217
|
prerelease: false
|
218
218
|
version_requirements: !ruby/object:Gem::Requirement
|
219
219
|
requirements:
|
220
|
-
- -
|
220
|
+
- - '>='
|
221
221
|
- !ruby/object:Gem::Version
|
222
222
|
version: '0'
|
223
223
|
- !ruby/object:Gem::Dependency
|
224
224
|
name: rubocop
|
225
225
|
requirement: !ruby/object:Gem::Requirement
|
226
226
|
requirements:
|
227
|
-
- -
|
227
|
+
- - '>='
|
228
228
|
- !ruby/object:Gem::Version
|
229
229
|
version: '0'
|
230
230
|
type: :development
|
231
231
|
prerelease: false
|
232
232
|
version_requirements: !ruby/object:Gem::Requirement
|
233
233
|
requirements:
|
234
|
-
- -
|
234
|
+
- - '>='
|
235
235
|
- !ruby/object:Gem::Version
|
236
236
|
version: '0'
|
237
237
|
description: MetaInspector lets you scrape a web page and get its links, images, texts,
|
@@ -242,10 +242,10 @@ executables: []
|
|
242
242
|
extensions: []
|
243
243
|
extra_rdoc_files: []
|
244
244
|
files:
|
245
|
-
-
|
246
|
-
-
|
247
|
-
-
|
248
|
-
-
|
245
|
+
- .gitignore
|
246
|
+
- .rspec.example
|
247
|
+
- .rubocop.yml.example
|
248
|
+
- .travis.yml
|
249
249
|
- CHANGELOG.md
|
250
250
|
- Gemfile
|
251
251
|
- MIT-LICENSE
|
@@ -334,7 +334,7 @@ files:
|
|
334
334
|
- spec/request_spec.rb
|
335
335
|
- spec/spec_helper.rb
|
336
336
|
- spec/url_spec.rb
|
337
|
-
homepage:
|
337
|
+
homepage: https://github.com/jaimeiniesta/metainspector
|
338
338
|
licenses:
|
339
339
|
- MIT
|
340
340
|
metadata: {}
|
@@ -344,12 +344,12 @@ require_paths:
|
|
344
344
|
- lib
|
345
345
|
required_ruby_version: !ruby/object:Gem::Requirement
|
346
346
|
requirements:
|
347
|
-
- -
|
347
|
+
- - '>='
|
348
348
|
- !ruby/object:Gem::Version
|
349
349
|
version: '0'
|
350
350
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
351
351
|
requirements:
|
352
|
-
- -
|
352
|
+
- - '>='
|
353
353
|
- !ruby/object:Gem::Version
|
354
354
|
version: '0'
|
355
355
|
requirements: []
|