link_oracle 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +7 -0
- data/lib/link_oracle/extractor/base.rb +29 -0
- data/lib/link_oracle/extractor/body.rb +37 -0
- data/lib/link_oracle/extractor/meta.rb +26 -0
- data/lib/link_oracle/extractor/og.rb +21 -0
- data/lib/link_oracle/link_data/data.rb +24 -0
- data/lib/link_oracle/link_data.rb +34 -0
- data/lib/link_oracle/request.rb +53 -0
- data/lib/link_oracle/version.rb +3 -0
- data/lib/link_oracle.rb +11 -0
- data/link_preview.gemspec +28 -0
- data/spec/link_oracle/extractor/body_spec.rb +78 -0
- data/spec/link_oracle/extractor/meta_spec.rb +49 -0
- data/spec/link_oracle/extractor/og_spec.rb +52 -0
- data/spec/link_oracle/request_spec.rb +93 -0
- data/spec/link_preview_spec.rb +63 -0
- data/spec/spec_helper.rb +13 -0
- metadata +143 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
OWViOGJkNzViMDA0NWFjYTE1YmE5MmY1ZjIwYTdhMWEyMTdmMWY4Yw==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
ODFiZjNiYTNmNzQ5NDM3MzE4ZmYyNGE1NDBkZTBmNWFlMTE4NDJlNQ==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
OWY2M2E0MjZhN2IxNjEwNzY5YmQ1ZTBhODFjM2QyNzBjNTJkMjEzODhhN2Q2
|
10
|
+
ZWUyNGY5NTIxOGMzYTllNDdlYmI2Y2NhOTdkZjY3Njk3MjIzNWM5MzMyMzky
|
11
|
+
NzczM2Y5ZmQ5OTU3MGJiOGJiYmFjMzA0ZGU3MGY4NGY4MTkxNTc=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
ZDk2NmM2MDRkYjYxMmE2OGQ5ZjU0NWVkYzdhMGRjMTk2ZDBlNGE1ZWM4Mjhl
|
14
|
+
MTBjMDY2MjE5ODk4ZGRmNTRmNmM2YjczNTRkNzlkOWFjNzM2NjJmMjdiZTAw
|
15
|
+
NTU5ODdlYThmMDczYzkwNWEwOWQ2NDhiN2I3YjIxYThmYWE1MjE=
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Ian Cooper
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# LinkOracle
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'link_oracle'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install link_oracle
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
module Extractor
|
3
|
+
class Base
|
4
|
+
attr_reader :parsed_body, :link_data
|
5
|
+
|
6
|
+
def initialize(parsed_body)
|
7
|
+
@parsed_body = parsed_body
|
8
|
+
@link_data = LinkData::Data.new
|
9
|
+
end
|
10
|
+
|
11
|
+
def type
|
12
|
+
raise "implement me"
|
13
|
+
end
|
14
|
+
|
15
|
+
def perform
|
16
|
+
link_data.assign({
|
17
|
+
titles: title,
|
18
|
+
image_urls: image,
|
19
|
+
descriptions: description
|
20
|
+
})
|
21
|
+
end
|
22
|
+
|
23
|
+
def get_content(selector)
|
24
|
+
found = parsed_body.xpath(selector).first
|
25
|
+
found ? [found[:content]] : []
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
module Extractor
|
3
|
+
class Body
|
4
|
+
attr_reader :parsed_body, :link_data
|
5
|
+
|
6
|
+
def initialize(parsed_body)
|
7
|
+
@parsed_body = parsed_body
|
8
|
+
@link_data = LinkData::Data.new
|
9
|
+
end
|
10
|
+
|
11
|
+
def perform
|
12
|
+
link_data.assign({
|
13
|
+
titles: titles,
|
14
|
+
image_urls: images,
|
15
|
+
descriptions: descriptions
|
16
|
+
})
|
17
|
+
|
18
|
+
end
|
19
|
+
|
20
|
+
def titles
|
21
|
+
@titles ||= parsed_body.xpath(
|
22
|
+
"//h1/text() | //h2/text() | //h3/text()"
|
23
|
+
).first(3).compact.map{ |text| text.content }
|
24
|
+
end
|
25
|
+
|
26
|
+
def images
|
27
|
+
@images ||= parsed_body.xpath(
|
28
|
+
"//img[@src[contains(.,'://') and not(contains(.,'ads.') or contains(.,'ad.') or contains(.,'?'))]]"
|
29
|
+
).first(3).compact.map{ |node| node['src'] }
|
30
|
+
end
|
31
|
+
|
32
|
+
def descriptions
|
33
|
+
@description ||= parsed_body.xpath("//p/text()").first(3).compact.map{ |text| text.content }
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
module Extractor
|
3
|
+
class Meta < Base
|
4
|
+
def type
|
5
|
+
:meta
|
6
|
+
end
|
7
|
+
|
8
|
+
def title
|
9
|
+
found = parsed_body.at_xpath("/html/head/title/text()")
|
10
|
+
found ? [found.content] : []
|
11
|
+
end
|
12
|
+
|
13
|
+
def image
|
14
|
+
get_content("/html/head/meta[contains(@name, 'thumbnail')]")
|
15
|
+
end
|
16
|
+
|
17
|
+
def description
|
18
|
+
get_content("/html/head/meta[translate(
|
19
|
+
@name,
|
20
|
+
'ABCDEFGHIJKLMNOPQRSTUVWXYZ',
|
21
|
+
'abcdefghijklmnopqrstuvwxyz'
|
22
|
+
) = 'description']")
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
module Extractor
|
3
|
+
class OG < Base
|
4
|
+
def type
|
5
|
+
:og
|
6
|
+
end
|
7
|
+
|
8
|
+
def title
|
9
|
+
get_content("/html/head/meta[@property='og:title']")
|
10
|
+
end
|
11
|
+
|
12
|
+
def image
|
13
|
+
get_content("/html/head/meta[@property='og:image']")
|
14
|
+
end
|
15
|
+
|
16
|
+
def description
|
17
|
+
get_content("/html/head/meta[@property='og:description']")
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
class LinkData
|
3
|
+
class Data
|
4
|
+
attr_accessor :titles, :image_urls, :descriptions
|
5
|
+
|
6
|
+
def assign(hash)
|
7
|
+
hash.each {|key, value| self.send("#{key}=", value) }
|
8
|
+
self
|
9
|
+
end
|
10
|
+
|
11
|
+
def image_url
|
12
|
+
image_urls.first
|
13
|
+
end
|
14
|
+
|
15
|
+
def title
|
16
|
+
titles.first
|
17
|
+
end
|
18
|
+
|
19
|
+
def description
|
20
|
+
descriptions.first
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
class LinkData
|
3
|
+
attr_reader :parsed_data
|
4
|
+
|
5
|
+
def initialize(parsed_data)
|
6
|
+
@parsed_data = parsed_data
|
7
|
+
end
|
8
|
+
|
9
|
+
#TODO: Need to write tests for these
|
10
|
+
def title
|
11
|
+
og.title || meta.title || body.title
|
12
|
+
end
|
13
|
+
|
14
|
+
def description
|
15
|
+
og.description || meta.description|| body.description
|
16
|
+
end
|
17
|
+
|
18
|
+
def image_url
|
19
|
+
og.image_url || meta.image_url || body.image_url
|
20
|
+
end
|
21
|
+
|
22
|
+
def og
|
23
|
+
@og ||= Extractor::OG.new(parsed_data).perform
|
24
|
+
end
|
25
|
+
|
26
|
+
def meta
|
27
|
+
@meta ||= Extractor::Meta.new(parsed_data).perform
|
28
|
+
end
|
29
|
+
|
30
|
+
def body
|
31
|
+
@body ||= Extractor::Body.new(parsed_data).perform
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
@@ -0,0 +1,53 @@
|
|
1
|
+
class LinkOracle
|
2
|
+
class Request
|
3
|
+
attr_reader :url
|
4
|
+
|
5
|
+
def initialize(url)
|
6
|
+
@url = url
|
7
|
+
end
|
8
|
+
|
9
|
+
def parsed_data
|
10
|
+
validate_url
|
11
|
+
validate_request
|
12
|
+
parsed_body
|
13
|
+
end
|
14
|
+
|
15
|
+
def validate_request
|
16
|
+
raise error_class if error_class
|
17
|
+
end
|
18
|
+
|
19
|
+
def validate_url
|
20
|
+
!!URI.parse(url)
|
21
|
+
rescue URI::InvalidURIError
|
22
|
+
raise InvalidUrl
|
23
|
+
end
|
24
|
+
|
25
|
+
def response
|
26
|
+
@response ||= request
|
27
|
+
end
|
28
|
+
|
29
|
+
def request
|
30
|
+
::RestClient.get url
|
31
|
+
end
|
32
|
+
|
33
|
+
def error_class
|
34
|
+
return if response.code == 200
|
35
|
+
{
|
36
|
+
404 => PageNotFound,
|
37
|
+
403 => PermissionDenied
|
38
|
+
}[response.code] || BadThingsHappened
|
39
|
+
end
|
40
|
+
|
41
|
+
def parsed_body
|
42
|
+
::Nokogiri::HTML.parse(response.body)
|
43
|
+
rescue
|
44
|
+
raise ParsingError
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
class PageNotFound < StandardError; end
|
49
|
+
class PermissionDenied < StandardError; end
|
50
|
+
class BadThingsHappened < StandardError; end
|
51
|
+
class InvalidUrl < StandardError; end
|
52
|
+
class ParsingError < StandardError; end
|
53
|
+
end
|
data/lib/link_oracle.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'link_oracle/extractor/base'
|
5
|
+
require 'link_oracle/version'
|
6
|
+
|
7
|
+
Gem::Specification.new do |spec|
|
8
|
+
spec.name = "link_oracle"
|
9
|
+
spec.version = LinkOracle::VERSION
|
10
|
+
spec.authors = ["Ian Cooper", 'Fito von Zastrow', 'Kane Baccigalupi']
|
11
|
+
spec.email = ["developers@socialchorus.com"]
|
12
|
+
spec.description = %q{Scrapes pages for open graph, meta, and lastly, body preview data}
|
13
|
+
spec.summary = %q{Scrapes pages for open graph, meta, and lastly, body preview data}
|
14
|
+
spec.homepage = "http://github.com/socialchorus/link_oracle"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files`.split($/)
|
18
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
19
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_dependency 'nokogiri'
|
23
|
+
spec.add_dependency 'rest-client'
|
24
|
+
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
26
|
+
spec.add_development_dependency "rake"
|
27
|
+
spec.add_development_dependency "rspec"
|
28
|
+
end
|
@@ -0,0 +1,78 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkOracle::Extractor::Body do
|
4
|
+
let(:parsed_body) { ::Nokogiri::HTML.parse(body) }
|
5
|
+
let(:link_data) { LinkOracle::Extractor::Body.new(parsed_body).perform }
|
6
|
+
|
7
|
+
let(:body) {
|
8
|
+
<<-HTML
|
9
|
+
<html>
|
10
|
+
<head>
|
11
|
+
<meta property=\"og:title\" content=\"This is a title\">
|
12
|
+
<meta property=\"og:description\" content=\"A description for your face\">
|
13
|
+
<meta property=\"og:image\" content=\"http://imageurl.com\">
|
14
|
+
<meta name=\"Description\" content=\"Here is a description not for facebook\">
|
15
|
+
<meta name=\"KEYWORDS\" content=\"Keywords, Keywords everywhere\">
|
16
|
+
<title>TITLE!</title>
|
17
|
+
<meta itemprop='thumbnailUrl' name='thumbnail' content='http://imageurlfrommeta.com'>
|
18
|
+
</head>
|
19
|
+
<body>
|
20
|
+
<img src='http://ads.berkin.com'>
|
21
|
+
<img src='http://berkin.com'>
|
22
|
+
<img src='/berkin/cherbin.jpg'>
|
23
|
+
<img src='http://cherbin.com'>
|
24
|
+
<img src='http://flerbin.com'>
|
25
|
+
<h1>Berkin</h1>
|
26
|
+
<h2>Derbin</h2>
|
27
|
+
<h3>Cherbin</h3>
|
28
|
+
<p>paragraph 1</p>
|
29
|
+
<p>paragraph 2</p>
|
30
|
+
<p>paragraph 3</p>
|
31
|
+
</body>
|
32
|
+
</html>
|
33
|
+
HTML
|
34
|
+
}
|
35
|
+
|
36
|
+
describe 'perform' do
|
37
|
+
context 'there is no suitable stuff in the body' do
|
38
|
+
let(:body) {
|
39
|
+
"<html>
|
40
|
+
<head>
|
41
|
+
</head>
|
42
|
+
<body>
|
43
|
+
</body>
|
44
|
+
</html>"
|
45
|
+
}
|
46
|
+
|
47
|
+
it 'should fail quietly' do
|
48
|
+
expect { link_data }.to_not raise_error
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
context 'there are body attributes' do
|
53
|
+
it 'should populate link_data titles' do
|
54
|
+
link_data.titles.should == [
|
55
|
+
'Berkin',
|
56
|
+
'Derbin',
|
57
|
+
'Cherbin'
|
58
|
+
]
|
59
|
+
end
|
60
|
+
|
61
|
+
it 'should populate link_data image_urls' do
|
62
|
+
link_data.image_urls.should == [
|
63
|
+
"http://berkin.com",
|
64
|
+
"http://cherbin.com",
|
65
|
+
"http://flerbin.com"
|
66
|
+
]
|
67
|
+
end
|
68
|
+
|
69
|
+
it 'should populate link_data descriptions' do
|
70
|
+
link_data.descriptions.should == [
|
71
|
+
"paragraph 1",
|
72
|
+
"paragraph 2",
|
73
|
+
"paragraph 3"
|
74
|
+
]
|
75
|
+
end
|
76
|
+
end
|
77
|
+
end
|
78
|
+
end
|
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkOracle::Extractor::Meta do
|
4
|
+
let(:parsed_body) { ::Nokogiri::HTML.parse(body) }
|
5
|
+
let(:link_data) { LinkOracle::Extractor::Meta.new(parsed_body).perform }
|
6
|
+
|
7
|
+
let(:body) {
|
8
|
+
"<html>
|
9
|
+
<head>
|
10
|
+
<meta property=\"og:title\" content=\"This is a title\">
|
11
|
+
<meta property=\"og:description\" content=\"A description for your face\">
|
12
|
+
<meta property=\"og:image\" content=\"http://imageurl.com\">
|
13
|
+
<meta name=\"Description\" content=\"Here is a description not for facebook\">
|
14
|
+
<meta name=\"KEYWORDS\" content=\"Keywords, Keywords everywhere\">
|
15
|
+
<title>TITLE!</title>
|
16
|
+
<meta itemprop='thumbnailUrl' name='thumbnail' content='http://imageurlfrommeta.com'>
|
17
|
+
</head>
|
18
|
+
</html>"
|
19
|
+
}
|
20
|
+
|
21
|
+
describe 'perform' do
|
22
|
+
context 'there is no suitable meta data' do
|
23
|
+
let(:body) {
|
24
|
+
"<html>
|
25
|
+
<head>
|
26
|
+
</head>
|
27
|
+
</html>"
|
28
|
+
}
|
29
|
+
|
30
|
+
it 'should fail quietly' do
|
31
|
+
expect { link_data }.to_not raise_error
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
context 'there is meta data' do
|
36
|
+
it 'should populate link_data title' do
|
37
|
+
link_data.title.should == 'TITLE!'
|
38
|
+
end
|
39
|
+
|
40
|
+
it 'should populate link_data image_url' do
|
41
|
+
link_data.image_url.should == "http://imageurlfrommeta.com"
|
42
|
+
end
|
43
|
+
|
44
|
+
it 'should populate link_data description' do
|
45
|
+
link_data.description.should == 'Here is a description not for facebook'
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
@@ -0,0 +1,52 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkOracle::Extractor::OG do
|
4
|
+
let(:parsed_body) { ::Nokogiri::HTML.parse(body) }
|
5
|
+
let(:link_data) { LinkOracle::Extractor::OG.new(parsed_body).perform }
|
6
|
+
|
7
|
+
let(:body) {
|
8
|
+
"<html>
|
9
|
+
<head>
|
10
|
+
<meta property=\"og:title\" content=\"This is a title\">
|
11
|
+
<meta property=\"og:description\" content=\"A description for your face\">
|
12
|
+
<meta property=\"og:image\" content=\"http://imageurl.com\">
|
13
|
+
<meta name=\"Description\" content=\" \tHere is a description not for facebook\t\">
|
14
|
+
<meta name=\"KEYWORDS\" content=\" \tKeywords, Keywords everywhere \t\">
|
15
|
+
<title>TITLE!</title>
|
16
|
+
</head>
|
17
|
+
</html>"
|
18
|
+
}
|
19
|
+
|
20
|
+
describe 'perform' do
|
21
|
+
context 'there is no og_data' do
|
22
|
+
let(:body) {
|
23
|
+
"<html>
|
24
|
+
<head>
|
25
|
+
<meta name=\"Description\" content=\" \tHere is a description not for facebook\t\">
|
26
|
+
<meta name=\"KEYWORDS\" content=\" \tKeywords, Keywords everywhere \t\">
|
27
|
+
<title>TITLE!</title>
|
28
|
+
</head>
|
29
|
+
</html>"
|
30
|
+
}
|
31
|
+
|
32
|
+
it 'should fail quietly' do
|
33
|
+
expect { link_data }.to_not raise_error
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
context 'there is og_data' do
|
38
|
+
|
39
|
+
it 'should populate link_data title' do
|
40
|
+
link_data.title.should == 'This is a title'
|
41
|
+
end
|
42
|
+
|
43
|
+
it 'should populate link_data image_url' do
|
44
|
+
link_data.image_url.should == "http://imageurl.com"
|
45
|
+
end
|
46
|
+
|
47
|
+
it 'should populate link_data description' do
|
48
|
+
link_data.description.should == 'A description for your face'
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
@@ -0,0 +1,93 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkOracle::Request do
|
4
|
+
let(:requester) { LinkOracle::Request.new(url) }
|
5
|
+
let(:url) { 'http://someurl.com' }
|
6
|
+
let(:code) { 200 }
|
7
|
+
let(:response_hash) {
|
8
|
+
{
|
9
|
+
code: code,
|
10
|
+
body: body,
|
11
|
+
headers: {}
|
12
|
+
}
|
13
|
+
}
|
14
|
+
|
15
|
+
let(:body) {
|
16
|
+
"<html>
|
17
|
+
<head>
|
18
|
+
<meta property=\"og:title\" content=\"This is a title\">
|
19
|
+
<meta property=\"og:description\" content=\"A description for your face\">
|
20
|
+
<meta property=\"og:image\" content=\"http://imageurl.com\">
|
21
|
+
<meta name=\"Description\" content=\"Here is a description not for facebook\">
|
22
|
+
<meta name=\"KEYWORDS\" content=\"Keywords, Keywords everywhere\">
|
23
|
+
<title>TITLE!</title>
|
24
|
+
<meta itemprop='thumbnailUrl' name='thumbnail' content='http://imageurlfrommeta.com'>
|
25
|
+
</head>
|
26
|
+
</html>"
|
27
|
+
}
|
28
|
+
|
29
|
+
describe 'perform' do
|
30
|
+
before do
|
31
|
+
RestClient.stub(:get).and_return(
|
32
|
+
double(
|
33
|
+
'response',
|
34
|
+
response_hash
|
35
|
+
)
|
36
|
+
)
|
37
|
+
end
|
38
|
+
|
39
|
+
context 'invalid url' do
|
40
|
+
context 'response code is 404' do
|
41
|
+
let(:code) { 404 }
|
42
|
+
|
43
|
+
it 'should raise PageNotFound' do
|
44
|
+
expect {
|
45
|
+
requester.parsed_data
|
46
|
+
}.to raise_error(LinkOracle::PageNotFound)
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
context 'response code is 403' do
|
51
|
+
let(:code) { 403 }
|
52
|
+
|
53
|
+
it 'should raise PermissionDenied' do
|
54
|
+
expect {
|
55
|
+
requester.parsed_data
|
56
|
+
}.to raise_error(LinkOracle::PermissionDenied)
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
context 'response code is weird' do
|
61
|
+
let(:code) { 42 }
|
62
|
+
|
63
|
+
it 'should raise BadThingsHappened' do
|
64
|
+
expect {
|
65
|
+
requester.parsed_data
|
66
|
+
}.to raise_error(LinkOracle::BadThingsHappened)
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
context 'url is invalid' do
|
71
|
+
let(:url) { nil }
|
72
|
+
|
73
|
+
it 'should raise InvalidUrl' do
|
74
|
+
expect {
|
75
|
+
requester.parsed_data
|
76
|
+
}.to raise_error(LinkOracle::InvalidUrl)
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
context 'parsing goes awry' do
|
81
|
+
before do
|
82
|
+
::Nokogiri::HTML.should_receive(:parse).and_raise(ArgumentError)
|
83
|
+
end
|
84
|
+
|
85
|
+
it 'should raise ParsingError' do
|
86
|
+
expect {
|
87
|
+
requester.parsed_data
|
88
|
+
}.to raise_error(LinkOracle::ParsingError)
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
93
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LinkOracle do
|
4
|
+
let(:link_data) { LinkOracle.extract_from('http://someurl.com') }
|
5
|
+
let(:response) {
|
6
|
+
double(
|
7
|
+
code: 200,
|
8
|
+
body: body,
|
9
|
+
headers: {}
|
10
|
+
)
|
11
|
+
}
|
12
|
+
|
13
|
+
let(:body) {
|
14
|
+
<<-HTML
|
15
|
+
<html>
|
16
|
+
<head>
|
17
|
+
<meta property="og:title" content="This is a title">
|
18
|
+
<meta property="og:description" content="A description for your face">
|
19
|
+
<meta property="og:image" content="http://imageurl.com">
|
20
|
+
<meta name="Description" content="Here is a description not for facebook">
|
21
|
+
<meta name="KEYWORDS" content="Keywords, Keywords everywhere">
|
22
|
+
<title>TITLE!</title>
|
23
|
+
<meta itemprop='thumbnailUrl' name='thumbnail' content='http://imageurlfrommeta.com'>
|
24
|
+
</head>
|
25
|
+
<body>
|
26
|
+
<img src='http://ads.berkin.com'>
|
27
|
+
<img src='http://berkin.com'>
|
28
|
+
<img src='/berkin/cherbin.jpg'>
|
29
|
+
<img src='http://cherbin.com'>
|
30
|
+
<img src='http://flerbin.com'>
|
31
|
+
<h1>Berkin</h1>
|
32
|
+
<h2>Derbin</h2>
|
33
|
+
<h3>Cherbin</h3>
|
34
|
+
<p>paragraph 1</p>
|
35
|
+
<p>paragraph 2</p>
|
36
|
+
<p>paragraph 3</p>
|
37
|
+
</body>
|
38
|
+
</html>
|
39
|
+
HTML
|
40
|
+
}
|
41
|
+
before do
|
42
|
+
RestClient.stub(:get).and_return(response)
|
43
|
+
end
|
44
|
+
|
45
|
+
describe '.extract_from' do
|
46
|
+
it "returns a link data object" do
|
47
|
+
link_data.should be_a(LinkOracle::LinkData)
|
48
|
+
end
|
49
|
+
|
50
|
+
it "defaults to the og title" do
|
51
|
+
link_data.title.should == "This is a title"
|
52
|
+
end
|
53
|
+
|
54
|
+
it 'defaults to the og image' do
|
55
|
+
link_data.image_url.should == 'http://imageurl.com'
|
56
|
+
end
|
57
|
+
|
58
|
+
it "defaults to the og description" do
|
59
|
+
link_data.description.should == 'A description for your face'
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
2
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
3
|
+
|
4
|
+
require 'rspec'
|
5
|
+
# Requires supporting files with custom matchers and macros, etc,
|
6
|
+
# in ./support/ and its subdirectories.
|
7
|
+
Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
|
8
|
+
|
9
|
+
Dir["#{File.dirname(__FILE__)}/../lib/**/*.rb"].each {|f| require f}
|
10
|
+
|
11
|
+
|
12
|
+
RSpec.configure do |config|
|
13
|
+
end
|
metadata
ADDED
@@ -0,0 +1,143 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: link_oracle
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ian Cooper
|
8
|
+
- Fito von Zastrow
|
9
|
+
- Kane Baccigalupi
|
10
|
+
autorequire:
|
11
|
+
bindir: bin
|
12
|
+
cert_chain: []
|
13
|
+
date: 2013-08-26 00:00:00.000000000 Z
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: nokogiri
|
17
|
+
requirement: !ruby/object:Gem::Requirement
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
requirements:
|
26
|
+
- - ! '>='
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
version: '0'
|
29
|
+
- !ruby/object:Gem::Dependency
|
30
|
+
name: rest-client
|
31
|
+
requirement: !ruby/object:Gem::Requirement
|
32
|
+
requirements:
|
33
|
+
- - ! '>='
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: '0'
|
36
|
+
type: :runtime
|
37
|
+
prerelease: false
|
38
|
+
version_requirements: !ruby/object:Gem::Requirement
|
39
|
+
requirements:
|
40
|
+
- - ! '>='
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '0'
|
43
|
+
- !ruby/object:Gem::Dependency
|
44
|
+
name: bundler
|
45
|
+
requirement: !ruby/object:Gem::Requirement
|
46
|
+
requirements:
|
47
|
+
- - ~>
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: '1.3'
|
50
|
+
type: :development
|
51
|
+
prerelease: false
|
52
|
+
version_requirements: !ruby/object:Gem::Requirement
|
53
|
+
requirements:
|
54
|
+
- - ~>
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '1.3'
|
57
|
+
- !ruby/object:Gem::Dependency
|
58
|
+
name: rake
|
59
|
+
requirement: !ruby/object:Gem::Requirement
|
60
|
+
requirements:
|
61
|
+
- - ! '>='
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: '0'
|
64
|
+
type: :development
|
65
|
+
prerelease: false
|
66
|
+
version_requirements: !ruby/object:Gem::Requirement
|
67
|
+
requirements:
|
68
|
+
- - ! '>='
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '0'
|
71
|
+
- !ruby/object:Gem::Dependency
|
72
|
+
name: rspec
|
73
|
+
requirement: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
type: :development
|
79
|
+
prerelease: false
|
80
|
+
version_requirements: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ! '>='
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
description: Scrapes pages for open graph, meta, and lastly, body preview data
|
86
|
+
email:
|
87
|
+
- developers@socialchorus.com
|
88
|
+
executables: []
|
89
|
+
extensions: []
|
90
|
+
extra_rdoc_files: []
|
91
|
+
files:
|
92
|
+
- .gitignore
|
93
|
+
- Gemfile
|
94
|
+
- LICENSE.txt
|
95
|
+
- README.md
|
96
|
+
- Rakefile
|
97
|
+
- lib/link_oracle.rb
|
98
|
+
- lib/link_oracle/extractor/base.rb
|
99
|
+
- lib/link_oracle/extractor/body.rb
|
100
|
+
- lib/link_oracle/extractor/meta.rb
|
101
|
+
- lib/link_oracle/extractor/og.rb
|
102
|
+
- lib/link_oracle/link_data.rb
|
103
|
+
- lib/link_oracle/link_data/data.rb
|
104
|
+
- lib/link_oracle/request.rb
|
105
|
+
- lib/link_oracle/version.rb
|
106
|
+
- link_preview.gemspec
|
107
|
+
- spec/link_oracle/extractor/body_spec.rb
|
108
|
+
- spec/link_oracle/extractor/meta_spec.rb
|
109
|
+
- spec/link_oracle/extractor/og_spec.rb
|
110
|
+
- spec/link_oracle/request_spec.rb
|
111
|
+
- spec/link_preview_spec.rb
|
112
|
+
- spec/spec_helper.rb
|
113
|
+
homepage: http://github.com/socialchorus/link_oracle
|
114
|
+
licenses:
|
115
|
+
- MIT
|
116
|
+
metadata: {}
|
117
|
+
post_install_message:
|
118
|
+
rdoc_options: []
|
119
|
+
require_paths:
|
120
|
+
- lib
|
121
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - ! '>='
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
126
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - ! '>='
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '0'
|
131
|
+
requirements: []
|
132
|
+
rubyforge_project:
|
133
|
+
rubygems_version: 2.0.7
|
134
|
+
signing_key:
|
135
|
+
specification_version: 4
|
136
|
+
summary: Scrapes pages for open graph, meta, and lastly, body preview data
|
137
|
+
test_files:
|
138
|
+
- spec/link_oracle/extractor/body_spec.rb
|
139
|
+
- spec/link_oracle/extractor/meta_spec.rb
|
140
|
+
- spec/link_oracle/extractor/og_spec.rb
|
141
|
+
- spec/link_oracle/request_spec.rb
|
142
|
+
- spec/link_preview_spec.rb
|
143
|
+
- spec/spec_helper.rb
|