link_thumbnailer 1.1.2 → 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -13
- data/.travis.yml +1 -1
- data/CHANGELOG.md +117 -104
- data/Gemfile +1 -1
- data/{LICENSE → LICENSE.txt} +21 -21
- data/README.md +153 -184
- data/lib/generators/link_thumbnailer/install_generator.rb +0 -4
- data/lib/generators/templates/initializer.rb +63 -41
- data/lib/link_thumbnailer/configuration.rb +52 -10
- data/lib/link_thumbnailer/exceptions.rb +6 -0
- data/lib/link_thumbnailer/grader.rb +37 -0
- data/lib/link_thumbnailer/graders/base.rb +32 -0
- data/lib/link_thumbnailer/graders/html_attribute.rb +49 -0
- data/lib/link_thumbnailer/graders/length.rb +19 -0
- data/lib/link_thumbnailer/graders/link_density.rb +21 -0
- data/lib/link_thumbnailer/graders/position.rb +11 -0
- data/lib/link_thumbnailer/image_comparator.rb +24 -0
- data/lib/link_thumbnailer/image_comparators/base.rb +17 -0
- data/lib/link_thumbnailer/image_comparators/size.rb +11 -0
- data/lib/link_thumbnailer/image_parser.rb +18 -0
- data/lib/link_thumbnailer/image_parsers/size.rb +15 -0
- data/lib/link_thumbnailer/image_parsers/type.rb +15 -0
- data/lib/link_thumbnailer/image_validator.rb +30 -0
- data/lib/link_thumbnailer/model.rb +16 -0
- data/lib/link_thumbnailer/models/description.rb +34 -0
- data/lib/link_thumbnailer/models/image.rb +54 -0
- data/lib/link_thumbnailer/models/title.rb +20 -0
- data/lib/link_thumbnailer/models/website.rb +39 -0
- data/lib/link_thumbnailer/page.rb +40 -0
- data/lib/link_thumbnailer/parser.rb +13 -0
- data/lib/link_thumbnailer/processor.rb +94 -0
- data/lib/link_thumbnailer/railtie.rb +9 -9
- data/lib/link_thumbnailer/scraper.rb +64 -0
- data/lib/link_thumbnailer/scrapers/base.rb +63 -0
- data/lib/link_thumbnailer/scrapers/default/base.rb +10 -0
- data/lib/link_thumbnailer/scrapers/default/description.rb +47 -0
- data/lib/link_thumbnailer/scrapers/default/images.rb +64 -0
- data/lib/link_thumbnailer/scrapers/default/title.rb +25 -0
- data/lib/link_thumbnailer/scrapers/opengraph/base.rb +43 -0
- data/lib/link_thumbnailer/scrapers/opengraph/description.rb +10 -0
- data/lib/link_thumbnailer/scrapers/opengraph/image.rb +30 -0
- data/lib/link_thumbnailer/scrapers/opengraph/images.rb +16 -0
- data/lib/link_thumbnailer/scrapers/opengraph/title.rb +10 -0
- data/lib/link_thumbnailer/version.rb +3 -3
- data/lib/link_thumbnailer.rb +36 -119
- data/link_thumbnailer.gemspec +26 -28
- data/spec/configuration_spec.rb +51 -0
- data/spec/examples/empty_og_image_example.html +9 -0
- data/spec/fixture_spec.rb +88 -0
- data/spec/fixtures/bar.png +2907 -0
- data/spec/fixtures/default_from_body.html +12 -0
- data/spec/fixtures/default_from_meta.html +11 -0
- data/spec/{examples → fixtures}/example.html +53 -53
- data/spec/fixtures/foo.png +0 -0
- data/spec/fixtures/og_not_valid_example.html +12 -0
- data/spec/fixtures/og_valid_example.html +12 -0
- data/spec/fixtures/og_valid_multi_image_example.html +13 -0
- data/spec/grader_spec.rb +24 -0
- data/spec/graders/base_spec.rb +12 -0
- data/spec/graders/html_attribute_spec.rb +48 -0
- data/spec/graders/length_spec.rb +81 -0
- data/spec/graders/link_density_spec.rb +22 -0
- data/spec/image_comparators/size_spec.rb +39 -0
- data/spec/image_parsers/size_spec.rb +34 -0
- data/spec/image_parsers/type_spec.rb +34 -0
- data/spec/image_validator_spec.rb +35 -0
- data/spec/model_spec.rb +17 -0
- data/spec/models/description_spec.rb +64 -0
- data/spec/models/image_spec.rb +71 -0
- data/spec/models/title_spec.rb +24 -0
- data/spec/models/website_spec.rb +49 -0
- data/spec/page_spec.rb +26 -0
- data/spec/processor_spec.rb +349 -0
- data/spec/scraper_spec.rb +95 -0
- data/spec/scrapers/base_spec.rb +67 -0
- data/spec/scrapers/opengraph/base_spec.rb +94 -0
- data/spec/spec_helper.rb +15 -13
- metadata +126 -120
- data/app/controllers/link_thumbnailer/application_controller.rb +0 -4
- data/app/controllers/link_thumbnailer/previews_controller.rb +0 -11
- data/lib/link_thumbnailer/doc.rb +0 -65
- data/lib/link_thumbnailer/doc_parser.rb +0 -15
- data/lib/link_thumbnailer/engine.rb +0 -4
- data/lib/link_thumbnailer/fetcher.rb +0 -34
- data/lib/link_thumbnailer/img_comparator.rb +0 -17
- data/lib/link_thumbnailer/img_parser.rb +0 -41
- data/lib/link_thumbnailer/img_url_filter.rb +0 -13
- data/lib/link_thumbnailer/object.rb +0 -41
- data/lib/link_thumbnailer/opengraph.rb +0 -20
- data/lib/link_thumbnailer/rails/routes/mapper.rb +0 -30
- data/lib/link_thumbnailer/rails/routes/mapping.rb +0 -33
- data/lib/link_thumbnailer/rails/routes.rb +0 -47
- data/lib/link_thumbnailer/web_image.rb +0 -19
- data/spec/doc_parser_spec.rb +0 -25
- data/spec/doc_spec.rb +0 -23
- data/spec/examples/empty_example.html +0 -11
- data/spec/examples/og_example.html +0 -12
- data/spec/fetcher_spec.rb +0 -97
- data/spec/img_comparator_spec.rb +0 -16
- data/spec/img_url_filter_spec.rb +0 -31
- data/spec/link_thumbnailer_spec.rb +0 -205
- data/spec/object_spec.rb +0 -130
- data/spec/opengraph_spec.rb +0 -7
- data/spec/web_image_spec.rb +0 -57
@@ -0,0 +1,67 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkThumbnailer::Scrapers::Base do
|
4
|
+
|
5
|
+
let(:document) { double('document') }
|
6
|
+
let(:instance) { described_class.new(document) }
|
7
|
+
|
8
|
+
describe '#call' do
|
9
|
+
|
10
|
+
let(:website) { LinkThumbnailer::Models::Website.new }
|
11
|
+
let(:attr) { :title }
|
12
|
+
let(:value) { 'foo' }
|
13
|
+
let(:action) { instance.call(website, attr) }
|
14
|
+
|
15
|
+
before do
|
16
|
+
instance.stub(:value).and_return(value)
|
17
|
+
end
|
18
|
+
|
19
|
+
it { expect { action }.to change { website.title }.from(nil).to(value) }
|
20
|
+
|
21
|
+
end
|
22
|
+
|
23
|
+
describe '#model_class' do
|
24
|
+
|
25
|
+
let(:action) { instance.send(:model_class) }
|
26
|
+
|
27
|
+
before do
|
28
|
+
instance.stub(:attribute_name).and_return(attr)
|
29
|
+
end
|
30
|
+
|
31
|
+
context 'when internal class exists' do
|
32
|
+
|
33
|
+
let(:attr) { :title }
|
34
|
+
|
35
|
+
it { expect(action).to eq(::LinkThumbnailer::Models::Title) }
|
36
|
+
|
37
|
+
end
|
38
|
+
|
39
|
+
context 'when internal class does not exists' do
|
40
|
+
|
41
|
+
let(:attr) { :foo }
|
42
|
+
|
43
|
+
it { expect { action }.to raise_exception }
|
44
|
+
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
|
49
|
+
describe '#modelize' do
|
50
|
+
|
51
|
+
let(:node) { double('node') }
|
52
|
+
let(:text) { 'foo' }
|
53
|
+
let(:model_class) { double('model_class') }
|
54
|
+
let(:action) { instance.send(:modelize, node, text) }
|
55
|
+
|
56
|
+
before do
|
57
|
+
instance.stub(:model_class).and_return(model_class)
|
58
|
+
end
|
59
|
+
|
60
|
+
it 'instantiates a new model' do
|
61
|
+
expect(model_class).to receive(:new).with(node, text)
|
62
|
+
action
|
63
|
+
end
|
64
|
+
|
65
|
+
end
|
66
|
+
|
67
|
+
end
|
@@ -0,0 +1,94 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkThumbnailer::Scrapers::Opengraph::Base do
|
4
|
+
|
5
|
+
let(:node) { double('node') }
|
6
|
+
let(:document) { double('document') }
|
7
|
+
let(:instance) { described_class.new(document) }
|
8
|
+
|
9
|
+
describe '#applicable?' do
|
10
|
+
|
11
|
+
let(:meta) { [node, node] }
|
12
|
+
let(:action) { instance.applicable? }
|
13
|
+
|
14
|
+
before do
|
15
|
+
instance.stub(:meta).and_return(meta)
|
16
|
+
end
|
17
|
+
|
18
|
+
context 'when all node is an opengraph' do
|
19
|
+
|
20
|
+
before do
|
21
|
+
instance.stub(:opengraph_node?).and_return(true, true)
|
22
|
+
end
|
23
|
+
|
24
|
+
it { expect(action).to be_true }
|
25
|
+
|
26
|
+
end
|
27
|
+
|
28
|
+
context 'when any node is an opengraph' do
|
29
|
+
|
30
|
+
before do
|
31
|
+
instance.stub(:opengraph_node?).and_return(true, false)
|
32
|
+
end
|
33
|
+
|
34
|
+
it { expect(action).to be_true }
|
35
|
+
|
36
|
+
end
|
37
|
+
|
38
|
+
context 'when no node is an opengraph' do
|
39
|
+
|
40
|
+
before do
|
41
|
+
instance.stub(:opengraph_node?).and_return(false, false)
|
42
|
+
end
|
43
|
+
|
44
|
+
it { expect(action).to be_false }
|
45
|
+
|
46
|
+
end
|
47
|
+
|
48
|
+
end
|
49
|
+
|
50
|
+
describe '#opengraph_node?' do
|
51
|
+
|
52
|
+
let(:action) { instance.send(:opengraph_node?, node) }
|
53
|
+
|
54
|
+
before do
|
55
|
+
node.stub(:attribute).with('name').and_return(attribute_from_name)
|
56
|
+
end
|
57
|
+
|
58
|
+
context 'with attribute from name valid' do
|
59
|
+
|
60
|
+
let(:attribute_from_name) { 'og:foo' }
|
61
|
+
|
62
|
+
it { expect(action).to be_true }
|
63
|
+
|
64
|
+
end
|
65
|
+
|
66
|
+
context 'with attribute from name not valid' do
|
67
|
+
|
68
|
+
let(:attribute_from_name) { 'foo' }
|
69
|
+
|
70
|
+
before do
|
71
|
+
node.stub(:attribute).with('property').and_return(attribute_from_property)
|
72
|
+
end
|
73
|
+
|
74
|
+
context 'and attribute from property valid' do
|
75
|
+
|
76
|
+
let(:attribute_from_property) { 'og:bar' }
|
77
|
+
|
78
|
+
it { expect(action).to be_true }
|
79
|
+
|
80
|
+
end
|
81
|
+
|
82
|
+
context 'and attribute from property not valid' do
|
83
|
+
|
84
|
+
let(:attribute_from_property) { 'bar' }
|
85
|
+
|
86
|
+
it { expect(action).to be_false }
|
87
|
+
|
88
|
+
end
|
89
|
+
|
90
|
+
end
|
91
|
+
|
92
|
+
end
|
93
|
+
|
94
|
+
end
|
data/spec/spec_helper.rb
CHANGED
@@ -1,13 +1,15 @@
|
|
1
|
-
require 'simplecov'
|
2
|
-
require 'coveralls'
|
3
|
-
Coveralls.wear!
|
4
|
-
|
5
|
-
require 'link_thumbnailer'
|
6
|
-
require 'rspec'
|
7
|
-
require 'webmock/rspec'
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
1
|
+
require 'simplecov'
|
2
|
+
require 'coveralls'
|
3
|
+
Coveralls.wear!
|
4
|
+
|
5
|
+
require 'link_thumbnailer'
|
6
|
+
require 'rspec'
|
7
|
+
require 'webmock/rspec'
|
8
|
+
|
9
|
+
SimpleCov.formatter = Coveralls::SimpleCov::Formatter
|
10
|
+
|
11
|
+
RSpec.configure do |config|
|
12
|
+
config.expect_with :rspec do |c|
|
13
|
+
c.syntax = :expect
|
14
|
+
end
|
15
|
+
end
|
metadata
CHANGED
@@ -1,153 +1,105 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: link_thumbnailer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 2.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Pierre-Louis Gottfrois
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-
|
11
|
+
date: 2014-05-20 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name:
|
14
|
+
name: activesupport
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - '>='
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '0
|
19
|
+
version: '3.0'
|
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
|
-
version: '0
|
26
|
+
version: '3.0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
28
|
+
name: json
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - '>='
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: 1.
|
34
|
-
- -
|
33
|
+
version: 1.7.7
|
34
|
+
- - ~>
|
35
35
|
- !ruby/object:Gem::Version
|
36
36
|
version: '1.7'
|
37
37
|
type: :runtime
|
38
38
|
prerelease: false
|
39
39
|
version_requirements: !ruby/object:Gem::Requirement
|
40
40
|
requirements:
|
41
|
-
- -
|
41
|
+
- - '>='
|
42
42
|
- !ruby/object:Gem::Version
|
43
|
-
version: 1.
|
44
|
-
- -
|
43
|
+
version: 1.7.7
|
44
|
+
- - ~>
|
45
45
|
- !ruby/object:Gem::Version
|
46
46
|
version: '1.7'
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
|
-
name:
|
48
|
+
name: rake
|
49
49
|
requirement: !ruby/object:Gem::Requirement
|
50
50
|
requirements:
|
51
|
-
- -
|
51
|
+
- - '>='
|
52
52
|
- !ruby/object:Gem::Version
|
53
|
-
version:
|
53
|
+
version: '0.9'
|
54
54
|
type: :runtime
|
55
55
|
prerelease: false
|
56
56
|
version_requirements: !ruby/object:Gem::Requirement
|
57
57
|
requirements:
|
58
|
-
- -
|
58
|
+
- - '>='
|
59
59
|
- !ruby/object:Gem::Version
|
60
|
-
version:
|
60
|
+
version: '0.9'
|
61
61
|
- !ruby/object:Gem::Dependency
|
62
|
-
name:
|
62
|
+
name: nokogiri
|
63
63
|
requirement: !ruby/object:Gem::Requirement
|
64
64
|
requirements:
|
65
65
|
- - ~>
|
66
66
|
- !ruby/object:Gem::Version
|
67
|
-
version: '
|
67
|
+
version: '1.6'
|
68
68
|
type: :runtime
|
69
69
|
prerelease: false
|
70
70
|
version_requirements: !ruby/object:Gem::Requirement
|
71
71
|
requirements:
|
72
72
|
- - ~>
|
73
73
|
- !ruby/object:Gem::Version
|
74
|
-
version: '
|
74
|
+
version: '1.6'
|
75
75
|
- !ruby/object:Gem::Dependency
|
76
|
-
name:
|
76
|
+
name: net-http-persistent
|
77
77
|
requirement: !ruby/object:Gem::Requirement
|
78
78
|
requirements:
|
79
79
|
- - ~>
|
80
80
|
- !ruby/object:Gem::Version
|
81
|
-
version:
|
82
|
-
type: :runtime
|
83
|
-
prerelease: false
|
84
|
-
version_requirements: !ruby/object:Gem::Requirement
|
85
|
-
requirements:
|
86
|
-
- - ~>
|
87
|
-
- !ruby/object:Gem::Version
|
88
|
-
version: 1.5.5
|
89
|
-
- !ruby/object:Gem::Dependency
|
90
|
-
name: json
|
91
|
-
requirement: !ruby/object:Gem::Requirement
|
92
|
-
requirements:
|
93
|
-
- - ! '>='
|
94
|
-
- !ruby/object:Gem::Version
|
95
|
-
version: 1.7.6
|
96
|
-
- - <
|
97
|
-
- !ruby/object:Gem::Version
|
98
|
-
version: '1.9'
|
81
|
+
version: '2.9'
|
99
82
|
type: :runtime
|
100
83
|
prerelease: false
|
101
84
|
version_requirements: !ruby/object:Gem::Requirement
|
102
|
-
requirements:
|
103
|
-
- - ! '>='
|
104
|
-
- !ruby/object:Gem::Version
|
105
|
-
version: 1.7.6
|
106
|
-
- - <
|
107
|
-
- !ruby/object:Gem::Version
|
108
|
-
version: '1.9'
|
109
|
-
- !ruby/object:Gem::Dependency
|
110
|
-
name: bundler
|
111
|
-
requirement: !ruby/object:Gem::Requirement
|
112
85
|
requirements:
|
113
86
|
- - ~>
|
114
87
|
- !ruby/object:Gem::Version
|
115
|
-
version: '
|
116
|
-
type: :development
|
117
|
-
prerelease: false
|
118
|
-
version_requirements: !ruby/object:Gem::Requirement
|
119
|
-
requirements:
|
120
|
-
- - ~>
|
121
|
-
- !ruby/object:Gem::Version
|
122
|
-
version: '1.3'
|
88
|
+
version: '2.9'
|
123
89
|
- !ruby/object:Gem::Dependency
|
124
|
-
name:
|
125
|
-
requirement: !ruby/object:Gem::Requirement
|
126
|
-
requirements:
|
127
|
-
- - ~>
|
128
|
-
- !ruby/object:Gem::Version
|
129
|
-
version: '2.14'
|
130
|
-
type: :development
|
131
|
-
prerelease: false
|
132
|
-
version_requirements: !ruby/object:Gem::Requirement
|
133
|
-
requirements:
|
134
|
-
- - ~>
|
135
|
-
- !ruby/object:Gem::Version
|
136
|
-
version: '2.14'
|
137
|
-
- !ruby/object:Gem::Dependency
|
138
|
-
name: pry
|
90
|
+
name: fastimage
|
139
91
|
requirement: !ruby/object:Gem::Requirement
|
140
92
|
requirements:
|
141
93
|
- - ~>
|
142
94
|
- !ruby/object:Gem::Version
|
143
|
-
version: '
|
144
|
-
type: :
|
95
|
+
version: '1.5'
|
96
|
+
type: :runtime
|
145
97
|
prerelease: false
|
146
98
|
version_requirements: !ruby/object:Gem::Requirement
|
147
99
|
requirements:
|
148
100
|
- - ~>
|
149
101
|
- !ruby/object:Gem::Version
|
150
|
-
version: '
|
102
|
+
version: '1.5'
|
151
103
|
description: Ruby gem generating thumbnail images from a given URL.
|
152
104
|
email:
|
153
105
|
- pierrelouis.gottfrois@gmail.com
|
@@ -160,44 +112,80 @@ files:
|
|
160
112
|
- .travis.yml
|
161
113
|
- CHANGELOG.md
|
162
114
|
- Gemfile
|
163
|
-
- LICENSE
|
115
|
+
- LICENSE.txt
|
164
116
|
- README.md
|
165
117
|
- Rakefile
|
166
|
-
- app/controllers/link_thumbnailer/application_controller.rb
|
167
|
-
- app/controllers/link_thumbnailer/previews_controller.rb
|
168
118
|
- lib/generators/link_thumbnailer/install_generator.rb
|
169
119
|
- lib/generators/templates/initializer.rb
|
170
120
|
- lib/link_thumbnailer.rb
|
171
121
|
- lib/link_thumbnailer/configuration.rb
|
172
|
-
- lib/link_thumbnailer/
|
173
|
-
- lib/link_thumbnailer/
|
174
|
-
- lib/link_thumbnailer/
|
175
|
-
- lib/link_thumbnailer/
|
176
|
-
- lib/link_thumbnailer/
|
177
|
-
- lib/link_thumbnailer/
|
178
|
-
- lib/link_thumbnailer/
|
179
|
-
- lib/link_thumbnailer/
|
180
|
-
- lib/link_thumbnailer/
|
181
|
-
- lib/link_thumbnailer/
|
182
|
-
- lib/link_thumbnailer/
|
183
|
-
- lib/link_thumbnailer/
|
122
|
+
- lib/link_thumbnailer/exceptions.rb
|
123
|
+
- lib/link_thumbnailer/grader.rb
|
124
|
+
- lib/link_thumbnailer/graders/base.rb
|
125
|
+
- lib/link_thumbnailer/graders/html_attribute.rb
|
126
|
+
- lib/link_thumbnailer/graders/length.rb
|
127
|
+
- lib/link_thumbnailer/graders/link_density.rb
|
128
|
+
- lib/link_thumbnailer/graders/position.rb
|
129
|
+
- lib/link_thumbnailer/image_comparator.rb
|
130
|
+
- lib/link_thumbnailer/image_comparators/base.rb
|
131
|
+
- lib/link_thumbnailer/image_comparators/size.rb
|
132
|
+
- lib/link_thumbnailer/image_parser.rb
|
133
|
+
- lib/link_thumbnailer/image_parsers/size.rb
|
134
|
+
- lib/link_thumbnailer/image_parsers/type.rb
|
135
|
+
- lib/link_thumbnailer/image_validator.rb
|
136
|
+
- lib/link_thumbnailer/model.rb
|
137
|
+
- lib/link_thumbnailer/models/description.rb
|
138
|
+
- lib/link_thumbnailer/models/image.rb
|
139
|
+
- lib/link_thumbnailer/models/title.rb
|
140
|
+
- lib/link_thumbnailer/models/website.rb
|
141
|
+
- lib/link_thumbnailer/page.rb
|
142
|
+
- lib/link_thumbnailer/parser.rb
|
143
|
+
- lib/link_thumbnailer/processor.rb
|
184
144
|
- lib/link_thumbnailer/railtie.rb
|
145
|
+
- lib/link_thumbnailer/scraper.rb
|
146
|
+
- lib/link_thumbnailer/scrapers/base.rb
|
147
|
+
- lib/link_thumbnailer/scrapers/default/base.rb
|
148
|
+
- lib/link_thumbnailer/scrapers/default/description.rb
|
149
|
+
- lib/link_thumbnailer/scrapers/default/images.rb
|
150
|
+
- lib/link_thumbnailer/scrapers/default/title.rb
|
151
|
+
- lib/link_thumbnailer/scrapers/opengraph/base.rb
|
152
|
+
- lib/link_thumbnailer/scrapers/opengraph/description.rb
|
153
|
+
- lib/link_thumbnailer/scrapers/opengraph/image.rb
|
154
|
+
- lib/link_thumbnailer/scrapers/opengraph/images.rb
|
155
|
+
- lib/link_thumbnailer/scrapers/opengraph/title.rb
|
185
156
|
- lib/link_thumbnailer/version.rb
|
186
|
-
- lib/link_thumbnailer/web_image.rb
|
187
157
|
- link_thumbnailer.gemspec
|
188
|
-
- spec/
|
189
|
-
- spec/
|
190
|
-
- spec/
|
191
|
-
- spec/
|
192
|
-
- spec/
|
193
|
-
- spec/
|
194
|
-
- spec/
|
195
|
-
- spec/
|
196
|
-
- spec/
|
197
|
-
- spec/
|
198
|
-
- spec/
|
158
|
+
- spec/configuration_spec.rb
|
159
|
+
- spec/examples/empty_og_image_example.html
|
160
|
+
- spec/fixture_spec.rb
|
161
|
+
- spec/fixtures/bar.png
|
162
|
+
- spec/fixtures/default_from_body.html
|
163
|
+
- spec/fixtures/default_from_meta.html
|
164
|
+
- spec/fixtures/example.html
|
165
|
+
- spec/fixtures/foo.png
|
166
|
+
- spec/fixtures/og_not_valid_example.html
|
167
|
+
- spec/fixtures/og_valid_example.html
|
168
|
+
- spec/fixtures/og_valid_multi_image_example.html
|
169
|
+
- spec/grader_spec.rb
|
170
|
+
- spec/graders/base_spec.rb
|
171
|
+
- spec/graders/html_attribute_spec.rb
|
172
|
+
- spec/graders/length_spec.rb
|
173
|
+
- spec/graders/link_density_spec.rb
|
174
|
+
- spec/image_comparators/size_spec.rb
|
175
|
+
- spec/image_parsers/size_spec.rb
|
176
|
+
- spec/image_parsers/type_spec.rb
|
177
|
+
- spec/image_validator_spec.rb
|
178
|
+
- spec/model_spec.rb
|
179
|
+
- spec/models/description_spec.rb
|
180
|
+
- spec/models/image_spec.rb
|
181
|
+
- spec/models/title_spec.rb
|
182
|
+
- spec/models/website_spec.rb
|
183
|
+
- spec/page_spec.rb
|
184
|
+
- spec/processor_spec.rb
|
185
|
+
- spec/scraper_spec.rb
|
186
|
+
- spec/scrapers/base_spec.rb
|
187
|
+
- spec/scrapers/opengraph/base_spec.rb
|
199
188
|
- spec/spec_helper.rb
|
200
|
-
- spec/web_image_spec.rb
|
201
189
|
homepage: https://github.com/gottfrois/link_thumbnailer
|
202
190
|
licenses: []
|
203
191
|
metadata: {}
|
@@ -207,32 +195,50 @@ require_paths:
|
|
207
195
|
- lib
|
208
196
|
required_ruby_version: !ruby/object:Gem::Requirement
|
209
197
|
requirements:
|
210
|
-
- -
|
198
|
+
- - '>='
|
211
199
|
- !ruby/object:Gem::Version
|
212
200
|
version: '0'
|
213
201
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
214
202
|
requirements:
|
215
|
-
- -
|
203
|
+
- - '>='
|
216
204
|
- !ruby/object:Gem::Version
|
217
205
|
version: '0'
|
218
206
|
requirements: []
|
219
207
|
rubyforge_project:
|
220
|
-
rubygems_version: 2.
|
208
|
+
rubygems_version: 2.2.2
|
221
209
|
signing_key:
|
222
210
|
specification_version: 4
|
223
211
|
summary: Ruby gem ranking images from a given URL returning an object containing images
|
224
212
|
and website informations.
|
225
213
|
test_files:
|
226
|
-
- spec/
|
227
|
-
- spec/
|
228
|
-
- spec/
|
229
|
-
- spec/
|
230
|
-
- spec/
|
231
|
-
- spec/
|
232
|
-
- spec/
|
233
|
-
- spec/
|
234
|
-
- spec/
|
235
|
-
- spec/
|
236
|
-
- spec/
|
214
|
+
- spec/configuration_spec.rb
|
215
|
+
- spec/examples/empty_og_image_example.html
|
216
|
+
- spec/fixture_spec.rb
|
217
|
+
- spec/fixtures/bar.png
|
218
|
+
- spec/fixtures/default_from_body.html
|
219
|
+
- spec/fixtures/default_from_meta.html
|
220
|
+
- spec/fixtures/example.html
|
221
|
+
- spec/fixtures/foo.png
|
222
|
+
- spec/fixtures/og_not_valid_example.html
|
223
|
+
- spec/fixtures/og_valid_example.html
|
224
|
+
- spec/fixtures/og_valid_multi_image_example.html
|
225
|
+
- spec/grader_spec.rb
|
226
|
+
- spec/graders/base_spec.rb
|
227
|
+
- spec/graders/html_attribute_spec.rb
|
228
|
+
- spec/graders/length_spec.rb
|
229
|
+
- spec/graders/link_density_spec.rb
|
230
|
+
- spec/image_comparators/size_spec.rb
|
231
|
+
- spec/image_parsers/size_spec.rb
|
232
|
+
- spec/image_parsers/type_spec.rb
|
233
|
+
- spec/image_validator_spec.rb
|
234
|
+
- spec/model_spec.rb
|
235
|
+
- spec/models/description_spec.rb
|
236
|
+
- spec/models/image_spec.rb
|
237
|
+
- spec/models/title_spec.rb
|
238
|
+
- spec/models/website_spec.rb
|
239
|
+
- spec/page_spec.rb
|
240
|
+
- spec/processor_spec.rb
|
241
|
+
- spec/scraper_spec.rb
|
242
|
+
- spec/scrapers/base_spec.rb
|
243
|
+
- spec/scrapers/opengraph/base_spec.rb
|
237
244
|
- spec/spec_helper.rb
|
238
|
-
- spec/web_image_spec.rb
|
data/lib/link_thumbnailer/doc.rb
DELETED
@@ -1,65 +0,0 @@
|
|
1
|
-
require 'uri'
|
2
|
-
|
3
|
-
module LinkThumbnailer
|
4
|
-
|
5
|
-
module Doc
|
6
|
-
|
7
|
-
def doc_base_href
|
8
|
-
base = at('//head/base')
|
9
|
-
base['href'] if base
|
10
|
-
end
|
11
|
-
|
12
|
-
def img_srcs
|
13
|
-
search('//img').map { |i| i['src'] }.compact
|
14
|
-
end
|
15
|
-
|
16
|
-
def img_abs_urls(base_url = nil)
|
17
|
-
result = []
|
18
|
-
|
19
|
-
img_srcs.each do |i|
|
20
|
-
begin
|
21
|
-
u = URI(i)
|
22
|
-
rescue URI::InvalidURIError
|
23
|
-
next
|
24
|
-
end
|
25
|
-
|
26
|
-
result << if u.is_a?(URI::HTTP)
|
27
|
-
u
|
28
|
-
else
|
29
|
-
URI.join(base_url || doc_base_href || source_url, i)
|
30
|
-
end
|
31
|
-
end
|
32
|
-
|
33
|
-
result
|
34
|
-
end
|
35
|
-
|
36
|
-
def title
|
37
|
-
css('title').text.strip
|
38
|
-
end
|
39
|
-
|
40
|
-
def description
|
41
|
-
if element = xpath("//meta[translate(@name,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz') = 'description' and @content]").first
|
42
|
-
return element.attributes['content'].value.strip
|
43
|
-
end
|
44
|
-
|
45
|
-
css('body p').each do |node|
|
46
|
-
if !node.has_attribute?('style') && node.first_element_child.nil?
|
47
|
-
return node.text.strip
|
48
|
-
end
|
49
|
-
end
|
50
|
-
|
51
|
-
nil
|
52
|
-
end
|
53
|
-
|
54
|
-
def canonical_url
|
55
|
-
if element = xpath("//link[translate(@rel, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz') = 'canonical' and @href]").first
|
56
|
-
return element.attributes['href'].value.strip
|
57
|
-
end
|
58
|
-
nil
|
59
|
-
end
|
60
|
-
|
61
|
-
attr_accessor :source_url
|
62
|
-
|
63
|
-
end
|
64
|
-
|
65
|
-
end
|
@@ -1,34 +0,0 @@
|
|
1
|
-
require 'net/http/persistent'
|
2
|
-
|
3
|
-
module LinkThumbnailer
|
4
|
-
|
5
|
-
class Fetcher
|
6
|
-
|
7
|
-
attr_accessor :url
|
8
|
-
|
9
|
-
def fetch(url, redirect_count = 0)
|
10
|
-
if redirect_count > LinkThumbnailer.configuration.redirect_limit
|
11
|
-
raise ArgumentError, "too many redirects (#{redirect_count})"
|
12
|
-
end
|
13
|
-
|
14
|
-
self.url = url.is_a?(URI) ? url : URI(url)
|
15
|
-
|
16
|
-
if self.url.is_a?(URI::HTTP)
|
17
|
-
http = Net::HTTP::Persistent.new('linkthumbnailer')
|
18
|
-
http.headers['User-Agent'] = LinkThumbnailer.configuration.user_agent
|
19
|
-
http.verify_mode = OpenSSL::SSL::VERIFY_NONE unless LinkThumbnailer.configuration.verify_ssl
|
20
|
-
http.open_timeout = LinkThumbnailer.configuration.http_timeout
|
21
|
-
resp = http.request(self.url)
|
22
|
-
case resp
|
23
|
-
when Net::HTTPSuccess then resp.body
|
24
|
-
when Net::HTTPRedirection
|
25
|
-
location = resp['location'].start_with?('http') ? resp['location'] : "#{self.url.scheme}://#{self.url.host}#{resp['location']}"
|
26
|
-
fetch(location, redirect_count + 1)
|
27
|
-
else resp.error!
|
28
|
-
end
|
29
|
-
end
|
30
|
-
end
|
31
|
-
|
32
|
-
end
|
33
|
-
|
34
|
-
end
|