link_oracle 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +6 -14
- data/lib/link_oracle.rb +2 -2
- data/lib/link_oracle/Utils/image_url_formatter.rb +30 -0
- data/lib/link_oracle/link_data.rb +5 -4
- data/lib/link_oracle/request.rb +10 -3
- data/lib/link_oracle/version.rb +1 -1
- data/link_preview.gemspec +1 -1
- data/spec/link_oracle/Utils/image_url_formatter_spec.rb +20 -0
- data/spec/link_oracle/request_spec.rb +5 -5
- data/spec/link_preview_spec.rb +0 -1
- metadata +16 -12
checksums.yaml
CHANGED
@@ -1,15 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
metadata.gz: !binary |-
|
9
|
-
MTYyNDAxNjJhMjliOGFiNjQwM2IxM2Y1ZDk4ZmNhMTRjNmRkM2YyOGIzMDFh
|
10
|
-
ZjZkNjE2ODA1Y2E3MGYwYjQzYzdmZmUwMTViMmEyMTk0OGI4N2QxMjllZWZj
|
11
|
-
OTdhOTEyNTcyYjJkYjlkYTg3YmQ5YTZkYmZhN2JjMDNjNmJmYTc=
|
12
|
-
data.tar.gz: !binary |-
|
13
|
-
M2Y5OGM3ZmRmNTBkYmI2ZWQ2NjlhYmVkZjhjZDkzOGRmNzE4NDRjYThhYzA4
|
14
|
-
YmM0MDNlMzYwNzkwY2Q1NDgwY2IxYjI0NDNmNDEwOWE2NDI3NmQzNDE5ZmM2
|
15
|
-
YWRhZmM5YWY2NjVkYzI3ZGZiOWQ1YzUwYWU0MTY3OWRkOTNkNjg=
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 31d4f4ed9576a0db912307886f56ee7c908c2508
|
4
|
+
data.tar.gz: a20c3f61a0b7c02e1d7cd0c3b1e310264cbdb7b9
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2796582749c379e8e86f1b48025f9be30de7da7d615b146e1ec1733ada8ecf1b77d4cc5b463e927dbb6238e8a6171217c5e65c8ad79830d6ecc4556d657119e6
|
7
|
+
data.tar.gz: fbd4ce096e982d9b9bdc9e4b84f5992a7686554836b78ee8140f00a09dfbd71450967291c112752385174d4aa889a39b7ce43ae29ab57e9cda1a79c29c310e6d
|
data/lib/link_oracle.rb
CHANGED
@@ -10,7 +10,7 @@ Dir["#{File.dirname(__FILE__)}/link_oracle/**/*.rb"].each {|f| require f}
|
|
10
10
|
|
11
11
|
class LinkOracle
|
12
12
|
def self.extract_from(url)
|
13
|
-
|
14
|
-
LinkData.new(
|
13
|
+
parsed_url = LinkOracle::Request.new(url).parsed_url
|
14
|
+
LinkData.new(parsed_url)
|
15
15
|
end
|
16
16
|
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
module Utils
|
2
|
+
class ImageUrlFormatter
|
3
|
+
attr_reader :url, :image_url
|
4
|
+
|
5
|
+
def initialize(url, image_url)
|
6
|
+
@url = url
|
7
|
+
@image_url = image_url
|
8
|
+
end
|
9
|
+
|
10
|
+
def perform
|
11
|
+
invalid_url? ? "#{scheme}://#{host}#{image_url}" : image_url
|
12
|
+
end
|
13
|
+
|
14
|
+
def host
|
15
|
+
parsed_url.host
|
16
|
+
end
|
17
|
+
|
18
|
+
def scheme
|
19
|
+
parsed_url.scheme
|
20
|
+
end
|
21
|
+
|
22
|
+
def parsed_url
|
23
|
+
@parsed_url ||= URI.parse(url)
|
24
|
+
end
|
25
|
+
|
26
|
+
def invalid_url?
|
27
|
+
image_url[0] == '/'
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -1,9 +1,10 @@
|
|
1
1
|
class LinkOracle
|
2
2
|
class LinkData
|
3
|
-
attr_reader :parsed_data
|
3
|
+
attr_reader :parsed_data, :url
|
4
4
|
|
5
|
-
def initialize(
|
6
|
-
@parsed_data = parsed_data
|
5
|
+
def initialize(parsed_url)
|
6
|
+
@parsed_data = parsed_url[:parsed_data]
|
7
|
+
@url = parsed_url[:url]
|
7
8
|
end
|
8
9
|
|
9
10
|
#TODO: Need to write tests for these
|
@@ -16,7 +17,7 @@ class LinkOracle
|
|
16
17
|
end
|
17
18
|
|
18
19
|
def image_url
|
19
|
-
og.image_url || meta.image_url || body.image_url
|
20
|
+
Utils::ImageUrlFormatter.new(url, og.image_url || meta.image_url || body.image_url).perform
|
20
21
|
end
|
21
22
|
|
22
23
|
def og
|
data/lib/link_oracle/request.rb
CHANGED
@@ -6,10 +6,17 @@ class LinkOracle
|
|
6
6
|
@url = url
|
7
7
|
end
|
8
8
|
|
9
|
-
def
|
9
|
+
def parsed_url
|
10
10
|
validate_url
|
11
11
|
validate_request
|
12
|
-
|
12
|
+
results
|
13
|
+
end
|
14
|
+
|
15
|
+
def results
|
16
|
+
{
|
17
|
+
parsed_data: parsed_data,
|
18
|
+
url: url
|
19
|
+
}
|
13
20
|
end
|
14
21
|
|
15
22
|
def validate_request
|
@@ -38,7 +45,7 @@ class LinkOracle
|
|
38
45
|
}[response.code] || BadThingsHappened
|
39
46
|
end
|
40
47
|
|
41
|
-
def
|
48
|
+
def parsed_data
|
42
49
|
::Nokogiri::HTML.parse(response.body)
|
43
50
|
rescue
|
44
51
|
raise ParsingError
|
data/lib/link_oracle/version.rb
CHANGED
data/link_preview.gemspec
CHANGED
@@ -7,7 +7,7 @@ require 'link_oracle/version'
|
|
7
7
|
Gem::Specification.new do |spec|
|
8
8
|
spec.name = "link_oracle"
|
9
9
|
spec.version = LinkOracle::VERSION
|
10
|
-
spec.authors = ["Ian Cooper", 'Fito von Zastrow', 'Kane Baccigalupi']
|
10
|
+
spec.authors = ["Ian Cooper", 'Fito von Zastrow', 'Kane Baccigalupi', 'Sowjanya Mudunuri']
|
11
11
|
spec.email = ["developers@socialchorus.com"]
|
12
12
|
spec.description = %q{Scrapes pages for open graph, meta, and lastly, body preview data}
|
13
13
|
spec.summary = %q{Scrapes pages for open graph, meta, and lastly, body preview data}
|
@@ -0,0 +1,20 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe Utils::ImageUrlFormatter do
|
4
|
+
let(:url) { "http://berkin.com/whatever/else/is/here" }
|
5
|
+
let(:image_url) { "/some/stupid/path" }
|
6
|
+
let(:formatted_url) { Utils::ImageUrlFormatter.new(url, image_url).perform }
|
7
|
+
|
8
|
+
context 'scheme is http' do
|
9
|
+
it 'should return the image as a full url using the host as domain' do
|
10
|
+
formatted_url.should == 'http://berkin.com/some/stupid/path'
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
context 'scheme is https' do
|
15
|
+
let(:url) { "https://berkin.com/whatever/else/is/here" }
|
16
|
+
it 'should return the image as a full url using the host as domain' do
|
17
|
+
formatted_url.should == 'https://berkin.com/some/stupid/path'
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -42,7 +42,7 @@ describe LinkOracle::Request do
|
|
42
42
|
|
43
43
|
it 'should raise PageNotFound' do
|
44
44
|
expect {
|
45
|
-
requester.
|
45
|
+
requester.parsed_url
|
46
46
|
}.to raise_error(LinkOracle::PageNotFound)
|
47
47
|
end
|
48
48
|
end
|
@@ -52,7 +52,7 @@ describe LinkOracle::Request do
|
|
52
52
|
|
53
53
|
it 'should raise PermissionDenied' do
|
54
54
|
expect {
|
55
|
-
requester.
|
55
|
+
requester.parsed_url
|
56
56
|
}.to raise_error(LinkOracle::PermissionDenied)
|
57
57
|
end
|
58
58
|
end
|
@@ -62,7 +62,7 @@ describe LinkOracle::Request do
|
|
62
62
|
|
63
63
|
it 'should raise BadThingsHappened' do
|
64
64
|
expect {
|
65
|
-
requester.
|
65
|
+
requester.parsed_url
|
66
66
|
}.to raise_error(LinkOracle::BadThingsHappened)
|
67
67
|
end
|
68
68
|
end
|
@@ -72,7 +72,7 @@ describe LinkOracle::Request do
|
|
72
72
|
|
73
73
|
it 'should raise InvalidUrl' do
|
74
74
|
expect {
|
75
|
-
requester.
|
75
|
+
requester.parsed_url
|
76
76
|
}.to raise_error(LinkOracle::InvalidUrl)
|
77
77
|
end
|
78
78
|
end
|
@@ -84,7 +84,7 @@ describe LinkOracle::Request do
|
|
84
84
|
|
85
85
|
it 'should raise ParsingError' do
|
86
86
|
expect {
|
87
|
-
requester.
|
87
|
+
requester.parsed_url
|
88
88
|
}.to raise_error(LinkOracle::ParsingError)
|
89
89
|
end
|
90
90
|
end
|
data/spec/link_preview_spec.rb
CHANGED
metadata
CHANGED
@@ -1,43 +1,44 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: link_oracle
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ian Cooper
|
8
8
|
- Fito von Zastrow
|
9
9
|
- Kane Baccigalupi
|
10
|
+
- Sowjanya Mudunuri
|
10
11
|
autorequire:
|
11
12
|
bindir: bin
|
12
13
|
cert_chain: []
|
13
|
-
date: 2013-
|
14
|
+
date: 2013-09-09 00:00:00.000000000 Z
|
14
15
|
dependencies:
|
15
16
|
- !ruby/object:Gem::Dependency
|
16
17
|
name: nokogiri
|
17
18
|
requirement: !ruby/object:Gem::Requirement
|
18
19
|
requirements:
|
19
|
-
- -
|
20
|
+
- - '>='
|
20
21
|
- !ruby/object:Gem::Version
|
21
22
|
version: '0'
|
22
23
|
type: :runtime
|
23
24
|
prerelease: false
|
24
25
|
version_requirements: !ruby/object:Gem::Requirement
|
25
26
|
requirements:
|
26
|
-
- -
|
27
|
+
- - '>='
|
27
28
|
- !ruby/object:Gem::Version
|
28
29
|
version: '0'
|
29
30
|
- !ruby/object:Gem::Dependency
|
30
31
|
name: rest-client
|
31
32
|
requirement: !ruby/object:Gem::Requirement
|
32
33
|
requirements:
|
33
|
-
- -
|
34
|
+
- - '>='
|
34
35
|
- !ruby/object:Gem::Version
|
35
36
|
version: '0'
|
36
37
|
type: :runtime
|
37
38
|
prerelease: false
|
38
39
|
version_requirements: !ruby/object:Gem::Requirement
|
39
40
|
requirements:
|
40
|
-
- -
|
41
|
+
- - '>='
|
41
42
|
- !ruby/object:Gem::Version
|
42
43
|
version: '0'
|
43
44
|
- !ruby/object:Gem::Dependency
|
@@ -58,28 +59,28 @@ dependencies:
|
|
58
59
|
name: rake
|
59
60
|
requirement: !ruby/object:Gem::Requirement
|
60
61
|
requirements:
|
61
|
-
- -
|
62
|
+
- - '>='
|
62
63
|
- !ruby/object:Gem::Version
|
63
64
|
version: '0'
|
64
65
|
type: :development
|
65
66
|
prerelease: false
|
66
67
|
version_requirements: !ruby/object:Gem::Requirement
|
67
68
|
requirements:
|
68
|
-
- -
|
69
|
+
- - '>='
|
69
70
|
- !ruby/object:Gem::Version
|
70
71
|
version: '0'
|
71
72
|
- !ruby/object:Gem::Dependency
|
72
73
|
name: rspec
|
73
74
|
requirement: !ruby/object:Gem::Requirement
|
74
75
|
requirements:
|
75
|
-
- -
|
76
|
+
- - '>='
|
76
77
|
- !ruby/object:Gem::Version
|
77
78
|
version: '0'
|
78
79
|
type: :development
|
79
80
|
prerelease: false
|
80
81
|
version_requirements: !ruby/object:Gem::Requirement
|
81
82
|
requirements:
|
82
|
-
- -
|
83
|
+
- - '>='
|
83
84
|
- !ruby/object:Gem::Version
|
84
85
|
version: '0'
|
85
86
|
description: Scrapes pages for open graph, meta, and lastly, body preview data
|
@@ -95,6 +96,7 @@ files:
|
|
95
96
|
- README.md
|
96
97
|
- Rakefile
|
97
98
|
- lib/link_oracle.rb
|
99
|
+
- lib/link_oracle/Utils/image_url_formatter.rb
|
98
100
|
- lib/link_oracle/extractor/base.rb
|
99
101
|
- lib/link_oracle/extractor/body.rb
|
100
102
|
- lib/link_oracle/extractor/meta.rb
|
@@ -104,6 +106,7 @@ files:
|
|
104
106
|
- lib/link_oracle/request.rb
|
105
107
|
- lib/link_oracle/version.rb
|
106
108
|
- link_preview.gemspec
|
109
|
+
- spec/link_oracle/Utils/image_url_formatter_spec.rb
|
107
110
|
- spec/link_oracle/extractor/body_spec.rb
|
108
111
|
- spec/link_oracle/extractor/meta_spec.rb
|
109
112
|
- spec/link_oracle/extractor/og_spec.rb
|
@@ -120,12 +123,12 @@ require_paths:
|
|
120
123
|
- lib
|
121
124
|
required_ruby_version: !ruby/object:Gem::Requirement
|
122
125
|
requirements:
|
123
|
-
- -
|
126
|
+
- - '>='
|
124
127
|
- !ruby/object:Gem::Version
|
125
128
|
version: '0'
|
126
129
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
127
130
|
requirements:
|
128
|
-
- -
|
131
|
+
- - '>='
|
129
132
|
- !ruby/object:Gem::Version
|
130
133
|
version: '0'
|
131
134
|
requirements: []
|
@@ -135,6 +138,7 @@ signing_key:
|
|
135
138
|
specification_version: 4
|
136
139
|
summary: Scrapes pages for open graph, meta, and lastly, body preview data
|
137
140
|
test_files:
|
141
|
+
- spec/link_oracle/Utils/image_url_formatter_spec.rb
|
138
142
|
- spec/link_oracle/extractor/body_spec.rb
|
139
143
|
- spec/link_oracle/extractor/meta_spec.rb
|
140
144
|
- spec/link_oracle/extractor/og_spec.rb
|