link_thumbnailer 3.3.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +19 -0
- data/.rspec +2 -0
- data/.ruby-version +1 -0
- data/.travis.yml +5 -0
- data/CHANGELOG.md +334 -0
- data/Gemfile +12 -0
- data/LICENSE.txt +22 -0
- data/README.md +210 -0
- data/Rakefile +9 -0
- data/lib/generators/link_thumbnailer/install_generator.rb +17 -0
- data/lib/generators/templates/initializer.rb +89 -0
- data/lib/link_thumbnailer.rb +38 -0
- data/lib/link_thumbnailer/configuration.rb +72 -0
- data/lib/link_thumbnailer/exceptions.rb +11 -0
- data/lib/link_thumbnailer/grader.rb +43 -0
- data/lib/link_thumbnailer/graders/base.rb +39 -0
- data/lib/link_thumbnailer/graders/html_attribute.rb +48 -0
- data/lib/link_thumbnailer/graders/length.rb +37 -0
- data/lib/link_thumbnailer/graders/link_density.rb +20 -0
- data/lib/link_thumbnailer/graders/position.rb +13 -0
- data/lib/link_thumbnailer/image_comparator.rb +26 -0
- data/lib/link_thumbnailer/image_comparators/base.rb +19 -0
- data/lib/link_thumbnailer/image_comparators/size.rb +13 -0
- data/lib/link_thumbnailer/image_parser.rb +62 -0
- data/lib/link_thumbnailer/image_validator.rb +32 -0
- data/lib/link_thumbnailer/model.rb +20 -0
- data/lib/link_thumbnailer/models/description.rb +37 -0
- data/lib/link_thumbnailer/models/favicon.rb +27 -0
- data/lib/link_thumbnailer/models/image.rb +56 -0
- data/lib/link_thumbnailer/models/title.rb +22 -0
- data/lib/link_thumbnailer/models/video.rb +44 -0
- data/lib/link_thumbnailer/models/website.rb +54 -0
- data/lib/link_thumbnailer/page.rb +43 -0
- data/lib/link_thumbnailer/parser.rb +15 -0
- data/lib/link_thumbnailer/processor.rb +128 -0
- data/lib/link_thumbnailer/railtie.rb +6 -0
- data/lib/link_thumbnailer/response.rb +39 -0
- data/lib/link_thumbnailer/scraper.rb +62 -0
- data/lib/link_thumbnailer/scrapers/base.rb +69 -0
- data/lib/link_thumbnailer/scrapers/default/base.rb +12 -0
- data/lib/link_thumbnailer/scrapers/default/description.rb +49 -0
- data/lib/link_thumbnailer/scrapers/default/favicon.rb +38 -0
- data/lib/link_thumbnailer/scrapers/default/images.rb +78 -0
- data/lib/link_thumbnailer/scrapers/default/title.rb +27 -0
- data/lib/link_thumbnailer/scrapers/default/videos.rb +18 -0
- data/lib/link_thumbnailer/scrapers/opengraph/base.rb +45 -0
- data/lib/link_thumbnailer/scrapers/opengraph/description.rb +12 -0
- data/lib/link_thumbnailer/scrapers/opengraph/favicon.rb +17 -0
- data/lib/link_thumbnailer/scrapers/opengraph/image.rb +107 -0
- data/lib/link_thumbnailer/scrapers/opengraph/images.rb +18 -0
- data/lib/link_thumbnailer/scrapers/opengraph/title.rb +12 -0
- data/lib/link_thumbnailer/scrapers/opengraph/video.rb +115 -0
- data/lib/link_thumbnailer/scrapers/opengraph/videos.rb +18 -0
- data/lib/link_thumbnailer/uri.rb +20 -0
- data/lib/link_thumbnailer/version.rb +5 -0
- data/lib/link_thumbnailer/video_parser.rb +47 -0
- data/link_thumbnailer.gemspec +29 -0
- data/spec/configuration_spec.rb +61 -0
- data/spec/fixture_spec.rb +114 -0
- data/spec/fixtures/bar.png +2907 -0
- data/spec/fixtures/default_from_body.html +13 -0
- data/spec/fixtures/default_from_meta.html +12 -0
- data/spec/fixtures/foo.png +0 -0
- data/spec/fixtures/google_shift_jis.html +6 -0
- data/spec/fixtures/google_utf8.html +6 -0
- data/spec/fixtures/og_not_valid_example.html +12 -0
- data/spec/fixtures/og_valid_example.html +18 -0
- data/spec/fixtures/og_valid_multi_image_example.html +13 -0
- data/spec/fixtures/og_valid_multi_video_example.html +13 -0
- data/spec/grader_spec.rb +27 -0
- data/spec/graders/base_spec.rb +14 -0
- data/spec/graders/html_attribute_spec.rb +50 -0
- data/spec/graders/length_spec.rb +93 -0
- data/spec/graders/link_density_spec.rb +52 -0
- data/spec/graders/position_spec.rb +49 -0
- data/spec/image_comparators/size_spec.rb +58 -0
- data/spec/image_validator_spec.rb +37 -0
- data/spec/model_spec.rb +27 -0
- data/spec/models/description_spec.rb +66 -0
- data/spec/models/favicon_spec.rb +12 -0
- data/spec/models/image_spec.rb +95 -0
- data/spec/models/title_spec.rb +26 -0
- data/spec/models/video_spec.rb +49 -0
- data/spec/models/website_spec.rb +51 -0
- data/spec/page_spec.rb +28 -0
- data/spec/processor_spec.rb +410 -0
- data/spec/response_spec.rb +62 -0
- data/spec/scraper_spec.rb +70 -0
- data/spec/scrapers/base_spec.rb +69 -0
- data/spec/scrapers/opengraph/base_spec.rb +96 -0
- data/spec/spec_helper.rb +11 -0
- data/spec/uri_spec.rb +44 -0
- data/spec/video_parser_spec.rb +148 -0
- metadata +271 -0
@@ -0,0 +1,26 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/image_comparators/base'
|
4
|
+
require 'link_thumbnailer/image_comparators/size'
|
5
|
+
|
6
|
+
module LinkThumbnailer
|
7
|
+
class ImageComparator
|
8
|
+
|
9
|
+
attr_reader :image
|
10
|
+
|
11
|
+
def initialize(image)
|
12
|
+
@image = image
|
13
|
+
end
|
14
|
+
|
15
|
+
def call(other)
|
16
|
+
size_comparator.call(other)
|
17
|
+
end
|
18
|
+
|
19
|
+
private
|
20
|
+
|
21
|
+
def size_comparator
|
22
|
+
::LinkThumbnailer::ImageComparators::Size.new(image)
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module LinkThumbnailer
|
4
|
+
module ImageComparators
|
5
|
+
class Base
|
6
|
+
|
7
|
+
attr_reader :image
|
8
|
+
|
9
|
+
def initialize(image)
|
10
|
+
@image = image
|
11
|
+
end
|
12
|
+
|
13
|
+
def call
|
14
|
+
fail NotImplementedError
|
15
|
+
end
|
16
|
+
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'image_info'
|
4
|
+
|
5
|
+
module LinkThumbnailer
|
6
|
+
class ImageParser
|
7
|
+
|
8
|
+
attr_reader :images
|
9
|
+
|
10
|
+
def initialize(urls)
|
11
|
+
@images = perform? ? image_info(urls) : default_images(urls)
|
12
|
+
end
|
13
|
+
|
14
|
+
def size
|
15
|
+
images.first.size
|
16
|
+
end
|
17
|
+
|
18
|
+
def type
|
19
|
+
images.first.type
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
def default_images(urls)
|
25
|
+
Array(urls).compact.map(&method(:build_default_image))
|
26
|
+
end
|
27
|
+
|
28
|
+
def build_default_image(uri)
|
29
|
+
NullImage.new(uri)
|
30
|
+
end
|
31
|
+
|
32
|
+
def perform?
|
33
|
+
::LinkThumbnailer.page.config.image_stats
|
34
|
+
end
|
35
|
+
|
36
|
+
def max_concurrency
|
37
|
+
::LinkThumbnailer.page.config.max_concurrency
|
38
|
+
end
|
39
|
+
|
40
|
+
def image_info(urls)
|
41
|
+
::ImageInfo.from(urls, max_concurrency: max_concurrency)
|
42
|
+
rescue
|
43
|
+
default_images(urls)
|
44
|
+
end
|
45
|
+
|
46
|
+
class NullImage
|
47
|
+
attr_reader :uri
|
48
|
+
|
49
|
+
def initialize(uri)
|
50
|
+
@uri = uri
|
51
|
+
end
|
52
|
+
|
53
|
+
def size
|
54
|
+
[0, 0]
|
55
|
+
end
|
56
|
+
|
57
|
+
def type
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
end
|
62
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'delegate'
|
4
|
+
|
5
|
+
module LinkThumbnailer
|
6
|
+
class ImageValidator < ::SimpleDelegator
|
7
|
+
|
8
|
+
attr_reader :config, :image
|
9
|
+
|
10
|
+
def initialize(image)
|
11
|
+
@config = ::LinkThumbnailer.page.config
|
12
|
+
@image = image
|
13
|
+
|
14
|
+
super(config)
|
15
|
+
end
|
16
|
+
|
17
|
+
def call
|
18
|
+
blacklist_urls.each do |url|
|
19
|
+
return false if image.src && image.src.to_s[url]
|
20
|
+
end
|
21
|
+
|
22
|
+
true
|
23
|
+
end
|
24
|
+
|
25
|
+
private
|
26
|
+
|
27
|
+
def blacklist_urls
|
28
|
+
config.blacklist_urls
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module LinkThumbnailer
|
4
|
+
class Model
|
5
|
+
|
6
|
+
def to_json(*args)
|
7
|
+
as_json.to_json(*args)
|
8
|
+
end
|
9
|
+
|
10
|
+
private
|
11
|
+
|
12
|
+
def sanitize(str)
|
13
|
+
return unless str
|
14
|
+
|
15
|
+
str = str.dup
|
16
|
+
str.encode!("UTF-16", "UTF-8", invalid: :replace, undef: :replace, replace: "")
|
17
|
+
str.encode!("UTF-8", "UTF-16").strip.gsub(/[\r\n\f]+/, "\n")
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/model'
|
4
|
+
require 'link_thumbnailer/grader'
|
5
|
+
|
6
|
+
module LinkThumbnailer
|
7
|
+
module Models
|
8
|
+
class Description < ::LinkThumbnailer::Model
|
9
|
+
|
10
|
+
attr_reader :node, :text, :position, :candidates_number
|
11
|
+
attr_accessor :probability
|
12
|
+
|
13
|
+
def initialize(node, text, position = 1, candidates_number = 1)
|
14
|
+
@node = node
|
15
|
+
@text = sanitize(text)
|
16
|
+
@position = position
|
17
|
+
@candidates_number = candidates_number
|
18
|
+
@probability = compute_probability
|
19
|
+
end
|
20
|
+
|
21
|
+
def to_s
|
22
|
+
text
|
23
|
+
end
|
24
|
+
|
25
|
+
def <=>(other)
|
26
|
+
probability <=> other.probability
|
27
|
+
end
|
28
|
+
|
29
|
+
private
|
30
|
+
|
31
|
+
def compute_probability
|
32
|
+
::LinkThumbnailer::Grader.new(self).call
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/model'
|
4
|
+
|
5
|
+
module LinkThumbnailer
|
6
|
+
module Models
|
7
|
+
class Favicon < ::LinkThumbnailer::Model
|
8
|
+
|
9
|
+
attr_reader :uri
|
10
|
+
|
11
|
+
def initialize(uri)
|
12
|
+
@uri = uri
|
13
|
+
end
|
14
|
+
|
15
|
+
def to_s
|
16
|
+
uri.to_s
|
17
|
+
end
|
18
|
+
|
19
|
+
def as_json(*)
|
20
|
+
{
|
21
|
+
src: to_s
|
22
|
+
}
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/model'
|
4
|
+
require 'link_thumbnailer/image_parser'
|
5
|
+
require 'link_thumbnailer/image_comparator'
|
6
|
+
require 'link_thumbnailer/image_validator'
|
7
|
+
|
8
|
+
module LinkThumbnailer
|
9
|
+
module Models
|
10
|
+
class Image < ::LinkThumbnailer::Model
|
11
|
+
|
12
|
+
attr_reader :src, :type, :size
|
13
|
+
|
14
|
+
def initialize(src, size = nil, type = nil)
|
15
|
+
@src = src
|
16
|
+
@size = size || parser.size
|
17
|
+
@type = type || parser.type
|
18
|
+
end
|
19
|
+
|
20
|
+
def to_s
|
21
|
+
src.to_s
|
22
|
+
end
|
23
|
+
|
24
|
+
def <=>(other)
|
25
|
+
comparator.call(other)
|
26
|
+
end
|
27
|
+
|
28
|
+
def valid?
|
29
|
+
validator.call
|
30
|
+
end
|
31
|
+
|
32
|
+
def as_json(*)
|
33
|
+
{
|
34
|
+
src: src.to_s,
|
35
|
+
size: size,
|
36
|
+
type: type
|
37
|
+
}
|
38
|
+
end
|
39
|
+
|
40
|
+
private
|
41
|
+
|
42
|
+
def parser
|
43
|
+
@parser ||= ::LinkThumbnailer::ImageParser.new(src)
|
44
|
+
end
|
45
|
+
|
46
|
+
def validator
|
47
|
+
::LinkThumbnailer::ImageValidator.new(self)
|
48
|
+
end
|
49
|
+
|
50
|
+
def comparator
|
51
|
+
::LinkThumbnailer::ImageComparator.new(self)
|
52
|
+
end
|
53
|
+
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/model'
|
4
|
+
|
5
|
+
module LinkThumbnailer
|
6
|
+
module Models
|
7
|
+
class Title < ::LinkThumbnailer::Model
|
8
|
+
|
9
|
+
attr_reader :node, :text
|
10
|
+
|
11
|
+
def initialize(node, text = nil)
|
12
|
+
@node = node
|
13
|
+
@text = sanitize(text || node.text)
|
14
|
+
end
|
15
|
+
|
16
|
+
def to_s
|
17
|
+
text
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/model'
|
4
|
+
require 'link_thumbnailer/video_parser'
|
5
|
+
|
6
|
+
module LinkThumbnailer
|
7
|
+
module Models
|
8
|
+
class Video < ::LinkThumbnailer::Model
|
9
|
+
|
10
|
+
attr_reader :src, :size, :duration, :provider, :id, :embed_code
|
11
|
+
|
12
|
+
def initialize(src, size = nil)
|
13
|
+
@src = src
|
14
|
+
@id = parser.id
|
15
|
+
@size = size || parser.size
|
16
|
+
@duration = parser.duration
|
17
|
+
@provider = parser.provider
|
18
|
+
@embed_code = parser.embed_code
|
19
|
+
end
|
20
|
+
|
21
|
+
def to_s
|
22
|
+
src.to_s
|
23
|
+
end
|
24
|
+
|
25
|
+
def as_json(*)
|
26
|
+
{
|
27
|
+
id: id,
|
28
|
+
src: src.to_s,
|
29
|
+
size: size,
|
30
|
+
duration: duration,
|
31
|
+
provider: provider,
|
32
|
+
embed_code: embed_code
|
33
|
+
}
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
def parser
|
39
|
+
@parser ||= ::LinkThumbnailer::VideoParser.new(self)
|
40
|
+
end
|
41
|
+
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/model'
|
4
|
+
|
5
|
+
module LinkThumbnailer
|
6
|
+
module Models
|
7
|
+
class Website < ::LinkThumbnailer::Model
|
8
|
+
|
9
|
+
attr_accessor :url, :title, :description, :images, :videos, :favicon
|
10
|
+
|
11
|
+
def initialize
|
12
|
+
@images = []
|
13
|
+
@videos = []
|
14
|
+
end
|
15
|
+
|
16
|
+
def video=(video)
|
17
|
+
self.videos = video
|
18
|
+
end
|
19
|
+
|
20
|
+
def videos=(videos)
|
21
|
+
Array(videos).each do |video|
|
22
|
+
@videos << video
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
def image=(image)
|
27
|
+
self.images = image
|
28
|
+
end
|
29
|
+
|
30
|
+
def images=(images)
|
31
|
+
Array(images).each do |image|
|
32
|
+
next unless image.valid?
|
33
|
+
@images << image
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
def images
|
38
|
+
@images.sort!
|
39
|
+
end
|
40
|
+
|
41
|
+
def as_json(*)
|
42
|
+
{
|
43
|
+
url: url.to_s,
|
44
|
+
favicon: favicon,
|
45
|
+
title: title,
|
46
|
+
description: description,
|
47
|
+
images: images.map(&:as_json),
|
48
|
+
videos: videos.map(&:as_json)
|
49
|
+
}
|
50
|
+
end
|
51
|
+
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'link_thumbnailer/response'
|
4
|
+
require 'link_thumbnailer/processor'
|
5
|
+
require 'link_thumbnailer/scraper'
|
6
|
+
|
7
|
+
module LinkThumbnailer
|
8
|
+
class Page
|
9
|
+
|
10
|
+
attr_reader :url, :options, :source
|
11
|
+
|
12
|
+
def initialize(url, options = {})
|
13
|
+
@url = url
|
14
|
+
@options = options
|
15
|
+
|
16
|
+
set_options
|
17
|
+
end
|
18
|
+
|
19
|
+
def generate
|
20
|
+
@source = processor.call(url)
|
21
|
+
scraper.call
|
22
|
+
end
|
23
|
+
|
24
|
+
def config
|
25
|
+
@config ||= ::LinkThumbnailer.config.dup
|
26
|
+
end
|
27
|
+
|
28
|
+
private
|
29
|
+
|
30
|
+
def set_options
|
31
|
+
options.each { |k, v| config.send("#{k}=", v) }
|
32
|
+
end
|
33
|
+
|
34
|
+
def processor
|
35
|
+
@processor ||= ::LinkThumbnailer::Processor.new
|
36
|
+
end
|
37
|
+
|
38
|
+
def scraper
|
39
|
+
@scraper ||= ::LinkThumbnailer::Scraper.new(source, processor.url)
|
40
|
+
end
|
41
|
+
|
42
|
+
end
|
43
|
+
end
|