meta_information 1.0.1 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +11 -6
- data/lib/meta_information.rb +55 -52
- data/lib/meta_information/version.rb +1 -1
- data/spec/lib/meta_information_spec.rb +108 -42
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f65e782ac7eaa37bbdf77b9b44ae5424ed3172b2
|
4
|
+
data.tar.gz: a51c2c644b512bebdc08d7bf268f2e7fefd22f18
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7a8e67c5268d725856ea3e2c001b022892b0d2b2ca557b175a94e95920b7e0833b9d28c967b19b2e91318378973c1644fdb5153c35536471baa69e3ae6f42b26
|
7
|
+
data.tar.gz: 2057cf51280e5d455370a188b7a98bb6652d0c9452d67ea75095ec3f17fdbe198a35c2fb18c88cb9ae388bdcad4f9e3fd5bea2b5c67663898cd8552f362a3dad
|
data/README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1
1
|
# MetaInformation
|
2
|
+
[![Gem Version](https://badge.fury.io/rb/meta_information.svg)](https://badge.fury.io/rb/meta_information)
|
3
|
+
|
2
4
|
Simple gem for parsing meta information from websites. It scan all meta-tags by name or property attributes.
|
3
5
|
## Instalation
|
4
6
|
Add this line to your application's Gemfile:
|
@@ -21,15 +23,18 @@ pp meta
|
|
21
23
|
# :all_meta=>
|
22
24
|
# [{:type=>"name",
|
23
25
|
# :name=>"viewport",
|
26
|
+
# :property=>nil,
|
24
27
|
# :content=>"width=device-width, initial-scale=1.0"},
|
25
|
-
# {:type=>"name", :name=>"description", :content=>"some description"},
|
26
|
-
# {:type=>"name", :name=>"title", :content=>"i am title"},
|
27
|
-
# {:type=>"name", :name=>"og:title", :content=>"some content"},
|
28
|
-
# {:type=>"name", :name=>"og:description", :content=>"some description"},
|
28
|
+
# {:type=>"name", :name=>"description", :property=>nil, :content=>"some description"},
|
29
|
+
# {:type=>"name", :name=>"title", :property=>nil, :content=>"i am title"},
|
30
|
+
# {:type=>"name", :name=>"og:title", :property=>nil, :content=>"some content"},
|
31
|
+
# {:type=>"name", :name=>"og:description", :property=>nil, :content=>"some description"},
|
29
32
|
# {:type=>"name",
|
30
33
|
# :name=>"og:image",
|
31
|
-
# :
|
34
|
+
# :property=>nil,
|
35
|
+
# :content=> "https://www.awesome_site.com/assets/awesome_picture.jpg"}]},
|
36
|
+
# {:type=>"property", :name=>nil, :property=>"fb:app_id", :content=>"1234567890"},
|
32
37
|
###
|
33
38
|
```
|
34
39
|
## License
|
35
|
-
MIT License.
|
40
|
+
MIT License.
|
data/lib/meta_information.rb
CHANGED
@@ -7,68 +7,71 @@ require 'open-uri'
|
|
7
7
|
# for usage
|
8
8
|
# MetaInformation.get_meta('https://some_site.com/some_page')
|
9
9
|
module MetaInformation
|
10
|
-
|
11
|
-
def get_meta(input_url)
|
12
|
-
return not_valid_url_error unless valid_url?(input_url)
|
10
|
+
extend self
|
13
11
|
|
14
|
-
|
15
|
-
|
12
|
+
def get_meta(input_url)
|
13
|
+
return not_valid_url_error unless valid_url?(input_url)
|
16
14
|
|
17
|
-
|
18
|
-
|
19
|
-
end
|
15
|
+
document = create_document(input_url)
|
16
|
+
return nokogiri_error if document == false
|
20
17
|
|
21
|
-
|
18
|
+
meta_hash = create_meta_array(document)
|
19
|
+
success_hash.merge(all_meta: meta_hash)
|
20
|
+
end
|
22
21
|
|
23
|
-
|
24
|
-
array = []
|
25
|
-
document.css('meta').each do |node|
|
26
|
-
if !node['name'].nil?
|
27
|
-
array.push(
|
28
|
-
type: 'name',
|
29
|
-
name: node['name'],
|
30
|
-
content: node['content']
|
31
|
-
)
|
32
|
-
elsif !node['property'].nil?
|
33
|
-
array.push(
|
34
|
-
type: 'property',
|
35
|
-
property: node['property'],
|
36
|
-
content: node['content']
|
37
|
-
)
|
38
|
-
end
|
39
|
-
end
|
40
|
-
array
|
41
|
-
end
|
22
|
+
private
|
42
23
|
|
43
|
-
|
44
|
-
|
24
|
+
def create_meta_array(document)
|
25
|
+
array = []
|
26
|
+
document.css('meta').each do |node|
|
27
|
+
array.push(
|
28
|
+
type: node_type(node),
|
29
|
+
name: node['name'],
|
30
|
+
property: node['property'],
|
31
|
+
content: node['content']
|
32
|
+
)
|
45
33
|
end
|
34
|
+
array
|
35
|
+
end
|
46
36
|
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
37
|
+
def node_type(node)
|
38
|
+
if !node['name'].nil?
|
39
|
+
'name'
|
40
|
+
elsif !node['property'].nil?
|
41
|
+
'property'
|
42
|
+
else
|
43
|
+
''
|
51
44
|
end
|
45
|
+
end
|
52
46
|
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
error: 'url is not valid'
|
57
|
-
}
|
58
|
-
end
|
47
|
+
def valid_url?(uri)
|
48
|
+
!(uri =~ URI.regexp).nil?
|
49
|
+
end
|
59
50
|
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
end
|
51
|
+
def create_document(input_url)
|
52
|
+
Nokogiri::HTML(open(input_url))
|
53
|
+
rescue
|
54
|
+
false
|
55
|
+
end
|
66
56
|
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
57
|
+
def not_valid_url_error
|
58
|
+
{
|
59
|
+
success: false,
|
60
|
+
error: 'url is not valid'
|
61
|
+
}
|
62
|
+
end
|
63
|
+
|
64
|
+
def nokogiri_error
|
65
|
+
{
|
66
|
+
success: false,
|
67
|
+
error: 'error with parsing a document'
|
68
|
+
}
|
69
|
+
end
|
70
|
+
|
71
|
+
def success_hash
|
72
|
+
{
|
73
|
+
succes: 'true',
|
74
|
+
error: ''
|
75
|
+
}
|
73
76
|
end
|
74
77
|
end
|
@@ -1,38 +1,68 @@
|
|
1
1
|
require './lib/meta_information'
|
2
|
+
require './spec/shared_stuff.rb'
|
3
|
+
require './spec/config.rb'
|
2
4
|
|
3
5
|
RSpec.describe 'MetaInformation' do
|
4
|
-
|
6
|
+
include_context 'shared stuff'
|
7
|
+
|
8
|
+
describe 'get_meta' do
|
9
|
+
it 'should return not_valid_url_error' do
|
10
|
+
allow(MetaInformation).to receive(:valid_url?).and_return(false)
|
11
|
+
result = MetaInformation.get_meta('http://some_url.com')
|
12
|
+
expect(result).to(
|
13
|
+
eq(
|
14
|
+
success: false,
|
15
|
+
error: 'url is not valid'
|
16
|
+
)
|
17
|
+
)
|
18
|
+
end
|
19
|
+
|
20
|
+
describe 'with mock for valid_url?' do
|
21
|
+
before do
|
22
|
+
allow(MetaInformation).to receive(:valid_url?).and_return(true)
|
23
|
+
end
|
24
|
+
it 'should return nokogiri_error' do
|
25
|
+
allow(MetaInformation).to receive(:create_document).and_return(false)
|
26
|
+
|
27
|
+
result = MetaInformation.get_meta('http://some_url.com')
|
28
|
+
expect(result).to(
|
29
|
+
eq(
|
30
|
+
success: false,
|
31
|
+
error: 'error with parsing a document'
|
32
|
+
)
|
33
|
+
)
|
34
|
+
end
|
35
|
+
|
36
|
+
it 'should return success_hash' do
|
37
|
+
allow(MetaInformation).to(
|
38
|
+
receive(:create_document).and_return(
|
39
|
+
Nokogiri::HTML(default_html)
|
40
|
+
)
|
41
|
+
)
|
42
|
+
|
43
|
+
result = MetaInformation.get_meta('http://some_url.com')
|
44
|
+
expect(result).to(
|
45
|
+
eq(
|
46
|
+
succes: 'true',
|
47
|
+
error: '',
|
48
|
+
all_meta: default_html_meta_array
|
49
|
+
)
|
50
|
+
)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
5
55
|
describe 'create_meta_array' do
|
6
56
|
describe 'we have meta' do
|
7
57
|
it 'must create array' do
|
8
|
-
document = Nokogiri::HTML(
|
9
|
-
|
10
|
-
|
11
|
-
<meta name="title" content="some title" />
|
12
|
-
<meta property="author" content="Bob" />
|
13
|
-
<meta property="og:title" content="og_title" />
|
14
|
-
<meta property="twitter:image" content="http://some_host.com/some_path" />
|
15
|
-
<meta property="og:locale" content="ru_RU" />
|
16
|
-
<meta property="al:ios:app_store_id" content="12345678900" />
|
17
|
-
<body>
|
18
|
-
<h1>Mr. Belvedere Fan Club</h1>
|
19
|
-
</body>
|
20
|
-
</html>
|
21
|
-
')
|
22
|
-
expect(MetaInformation.send(:create_meta_array, document)).to eq([
|
23
|
-
{ type: 'name', name: 'description', content: '' },
|
24
|
-
{ type: 'name', name: 'title', content: 'some title' },
|
25
|
-
{ type: 'property', property: 'author', content: 'Bob' },
|
26
|
-
{ type: 'property', property: 'og:title', content: 'og_title' },
|
27
|
-
{ type: 'property', property: 'twitter:image', content: 'http://some_host.com/some_path' },
|
28
|
-
{ type: 'property', property: 'og:locale', content: 'ru_RU' },
|
29
|
-
{ type: 'property', property: 'al:ios:app_store_id', content: '12345678900' }
|
30
|
-
])
|
58
|
+
document = Nokogiri::HTML(default_html)
|
59
|
+
result = MetaInformation.send(:create_meta_array, document)
|
60
|
+
expect(result).to eq(default_html_meta_array)
|
31
61
|
end
|
32
62
|
end
|
33
|
-
|
34
|
-
describe 'without meta' do
|
35
|
-
it '
|
63
|
+
|
64
|
+
describe 'without meta has empty array' do
|
65
|
+
it 'if have not mate' do
|
36
66
|
first_document = Nokogiri::HTML('
|
37
67
|
<html>
|
38
68
|
<body>
|
@@ -40,31 +70,45 @@ RSpec.describe 'MetaInformation' do
|
|
40
70
|
</body>
|
41
71
|
</html>
|
42
72
|
')
|
43
|
-
second_document = Nokogiri::HTML('')
|
44
73
|
expect(MetaInformation.send(:create_meta_array, first_document)).to eq([])
|
74
|
+
end
|
75
|
+
|
76
|
+
it 'if html is empty' do
|
77
|
+
second_document = Nokogiri::HTML('')
|
45
78
|
expect(MetaInformation.send(:create_meta_array, second_document)).to eq([])
|
46
79
|
end
|
47
80
|
end
|
48
81
|
end
|
49
82
|
|
50
83
|
describe 'valid_url?' do
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
expect(MetaInformation.send(:valid_url?, 'wwwsome_site.ru')).to be_truthy
|
56
|
-
expect(MetaInformation.send(:valid_url?, 'https://somesite.com/some_page')).to be_truthy
|
57
|
-
expect(MetaInformation.send(:valid_url?, 'https://somesite.com/some_page/page')).to be_truthy
|
58
|
-
expect(MetaInformation.send(:valid_url?, 'https://somesite.com.uk/some_page')).to be_truthy
|
84
|
+
def self.validate_valid_url(url)
|
85
|
+
it "#{url} must be valid" do
|
86
|
+
expect(MetaInformation.send(:valid_url?, url)).to be_truthy
|
87
|
+
end
|
59
88
|
end
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
89
|
+
|
90
|
+
validate_valid_url('http://www.somesite.com')
|
91
|
+
validate_valid_url('https://www.somesite.com')
|
92
|
+
validate_valid_url('https://somesite.com')
|
93
|
+
validate_valid_url('http://www.siteforadmin.ru')
|
94
|
+
validate_valid_url('https://somesite.com/some_page')
|
95
|
+
validate_valid_url('https://somesite.com/some_page/page')
|
96
|
+
validate_valid_url('http://somesite.com/some_page/2012/12/page/another_page')
|
97
|
+
validate_valid_url('http://somesite.com/2012/12/page-page-page')
|
98
|
+
validate_valid_url('https://somesite.com.uk/some_page')
|
99
|
+
validate_valid_url('https://meduza.io/short/2017/03/25/v-londone-proshel-mnogotysyachnyy-marsh-protiv-brekzita-fotografiya')
|
100
|
+
|
101
|
+
def self.validate_invalid_url(url)
|
102
|
+
it "#{url} must be invalid" do
|
103
|
+
expect(MetaInformation.send(:valid_url?, url)).to be_falsey
|
104
|
+
end
|
65
105
|
end
|
106
|
+
|
107
|
+
validate_invalid_url('some_site')
|
108
|
+
validate_invalid_url('http\\:wwwsome_site.ru')
|
109
|
+
validate_invalid_url('com.some_site')
|
66
110
|
end
|
67
|
-
|
111
|
+
|
68
112
|
describe 'private hash equal' do
|
69
113
|
it 'not_valid_url_error hash' do
|
70
114
|
expect(MetaInformation.send(:not_valid_url_error)).to eq({
|
@@ -87,4 +131,26 @@ RSpec.describe 'MetaInformation' do
|
|
87
131
|
})
|
88
132
|
end
|
89
133
|
end
|
134
|
+
|
135
|
+
describe 'node_type' do
|
136
|
+
it 'must return name' do
|
137
|
+
document = Nokogiri::HTML('<meta name="description" content="" />')
|
138
|
+
node = document.css('meta').first
|
139
|
+
expect(MetaInformation.send(:node_type, node)).to eq('name')
|
140
|
+
end
|
141
|
+
|
142
|
+
it 'must return property' do
|
143
|
+
document = Nokogiri::HTML(
|
144
|
+
'<meta property="og:title" content="og_title" />'
|
145
|
+
)
|
146
|
+
node = document.css('meta').first
|
147
|
+
expect(MetaInformation.send(:node_type, node)).to eq('property')
|
148
|
+
end
|
149
|
+
|
150
|
+
it 'must return empty string' do
|
151
|
+
document = Nokogiri::HTML('<meta content="og_title" />')
|
152
|
+
node = document.css('meta').first
|
153
|
+
expect(MetaInformation.send(:node_type, node)).to eq('')
|
154
|
+
end
|
155
|
+
end
|
90
156
|
end
|