images_from_link 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +9 -0
- data/LICENSE.txt +21 -0
- data/README.md +39 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/images_from_link.gemspec +39 -0
- data/lib/HandlerLink.rb +70 -0
- data/lib/ImagesLink.rb +67 -0
- data/lib/images_from_link/version.rb +3 -0
- data/lib/images_from_link.rb +11 -0
- metadata +127 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: d7a96ebdb6430e22f1f2566655793a7579b5e1c4
|
4
|
+
data.tar.gz: c80e576e30626c7d2967589c9a51817cf93c5bc5
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 4120466fde93136b6a0859c87b78e06e1ad25a3c9dcac1ab70b62c166221c8f29816d64fd61a31228bb68e1d9934cf0042eece7a941678f670c073ac8a5805c7
|
7
|
+
data.tar.gz: a2c0e307c68209d197c54ab46b0b66136235ed42898c7dd7ae63c1a461728709b5f45b594b3bfc9d78a128daa870a95faa18f2a6baa8998a70fc99cb4d5e3e8b
|
data/.gitignore
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at exwarvlad@gmail.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 zerocool
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
# ImagesFromLink
|
2
|
+
|
3
|
+
Extracts images by link.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'images_from_link'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install images_from_link
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
```
|
24
|
+
require 'images_from_link'
|
25
|
+
|
26
|
+
ImagesFromLink.get_images('https://www.google.com')
|
27
|
+
|
28
|
+
=>
|
29
|
+
[
|
30
|
+
"https://www.google.com/textinputassistant/tia.png",
|
31
|
+
"https://www.google.com/images/nav_logo229.png",
|
32
|
+
"https://www.google.com/images/branding/googlelogo/1x/googlelogo_white_background_color_272x92dp.png"
|
33
|
+
]
|
34
|
+
```
|
35
|
+
|
36
|
+
## License
|
37
|
+
|
38
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
39
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "images_from_link"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'images_from_link/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "images_from_link"
|
8
|
+
spec.version = ImagesFromLink::VERSION
|
9
|
+
spec.authors = ["zerocool"]
|
10
|
+
spec.email = ["exwarvlad@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = "Get images from link"
|
13
|
+
spec.description = "Get images from link"
|
14
|
+
spec.homepage = "https://github.com/exwarvlad/images_from_link"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
# if spec.respond_to?(:metadata)
|
20
|
+
# spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
|
21
|
+
# else
|
22
|
+
# raise "RubyGems 2.0 or newer is required to protect against " \
|
23
|
+
# "public gem pushes."
|
24
|
+
# end
|
25
|
+
|
26
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
27
|
+
f.match(%r{^(spec|spec|features)/})
|
28
|
+
end
|
29
|
+
spec.bindir = "exe"
|
30
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
31
|
+
spec.require_paths = ["lib"]
|
32
|
+
|
33
|
+
spec.add_development_dependency "bundler", "~> 1.14"
|
34
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
35
|
+
spec.add_development_dependency "rspec", "~> 3.5"
|
36
|
+
|
37
|
+
spec.add_dependency "httparty"
|
38
|
+
spec.add_dependency "nokogiri", "~> 1.7.0"
|
39
|
+
end
|
data/lib/HandlerLink.rb
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
class HandlerLink
|
2
|
+
FORMAT_IMG = ["jpg", "jpeg", "png", "gif"]
|
3
|
+
|
4
|
+
# получает урл - отдает домен
|
5
|
+
def get_host_link(link)
|
6
|
+
uri = URI.parse(link)
|
7
|
+
"#{uri.scheme}://" + uri.host
|
8
|
+
end
|
9
|
+
|
10
|
+
def handler_links(arra_links, link)
|
11
|
+
arra_links.each do |url|
|
12
|
+
if url.include?("(/")
|
13
|
+
uri = get_host_link(link)
|
14
|
+
|
15
|
+
position = url.index("(")
|
16
|
+
url[position] += uri.to_s
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
# добавляет scheme, если это href
|
22
|
+
def handler_prefix_link(host_link, link)
|
23
|
+
abort 'в качестве аргументов передайте строки' unless host_link.is_a?(String) || link.is_a?(String)
|
24
|
+
|
25
|
+
if link[0] == '/' && link[1] != '/'
|
26
|
+
host_link + link
|
27
|
+
elsif link[0..1] == '//'
|
28
|
+
uri = URI.parse(host_link)
|
29
|
+
"#{uri.scheme}:#{link}"
|
30
|
+
else
|
31
|
+
link
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
def remove_unless_symbols(arra_images_links)
|
36
|
+
arra_images_links.each do |image_url|
|
37
|
+
if (image_url[0..3] != "http" || image_url[0..3] != "www.") && image_url.include?("(")
|
38
|
+
position = image_url.index("(")
|
39
|
+
image_url.reverse!
|
40
|
+
position.times { image_url.chop! }
|
41
|
+
image_url.reverse!
|
42
|
+
image_url.delete!("(,;'')")
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
def remove_global_unless_symbols(arra_images_links)
|
48
|
+
arra_images_links.each { |link| link.delete!("(,;'')") }
|
49
|
+
end
|
50
|
+
|
51
|
+
def remove_unless_link(arra_link)
|
52
|
+
|
53
|
+
arra_link.each_with_index do |link, index|
|
54
|
+
arra_link[index] = "" if link[0..3] != "http"
|
55
|
+
|
56
|
+
index_ending = nil
|
57
|
+
|
58
|
+
FORMAT_IMG.each do |i|
|
59
|
+
index_ending = i if link.include?(i)
|
60
|
+
end
|
61
|
+
|
62
|
+
unless index_ending == nil
|
63
|
+
position = link.index(index_ending)
|
64
|
+
arra_link[index] = "" if (link[position + index_ending.size] =~ /[a-z]/)
|
65
|
+
end
|
66
|
+
|
67
|
+
end
|
68
|
+
arra_link.delete("")
|
69
|
+
end
|
70
|
+
end
|
data/lib/ImagesLink.rb
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
require 'httparty'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'uri'
|
4
|
+
require_relative 'HandlerLink'
|
5
|
+
|
6
|
+
class ImagesLink
|
7
|
+
|
8
|
+
def initialize(link)
|
9
|
+
@link = link
|
10
|
+
|
11
|
+
begin
|
12
|
+
@response = HTTParty.get(@link)
|
13
|
+
rescue Errno::ECONNREFUSED => e
|
14
|
+
puts "Неправильный урл"
|
15
|
+
abort e.message
|
16
|
+
end
|
17
|
+
|
18
|
+
@doc = Nokogiri::HTML(@response.body)
|
19
|
+
@doc.search('//noscript').each { |node| node.remove } # убираю мешающие ноды
|
20
|
+
@arra_links = [] # сдесь будут храниться все урлы картинок
|
21
|
+
@handler_link = HandlerLink.new # обработчик урлов
|
22
|
+
@link_host_name = @handler_link.get_host_link(@link) # беру имя домена
|
23
|
+
end
|
24
|
+
|
25
|
+
# возвращает, все найденные, урлы картинок
|
26
|
+
def get_images_from_url
|
27
|
+
@arra_links = (get_url_with_attr_img_link + get_url_with_other_attr).uniq
|
28
|
+
@handler_link.remove_global_unless_symbols(@arra_links)
|
29
|
+
@arra_links
|
30
|
+
end
|
31
|
+
|
32
|
+
def get_url_with_attr_img_link
|
33
|
+
img_arra = []
|
34
|
+
# пробегаю по тегам img (meta og:images...), хватаю урл и закидываю в @arra_links
|
35
|
+
@doc.xpath('//img').each do |img|
|
36
|
+
if img['src'] != nil
|
37
|
+
arra = [img['src'].to_s]
|
38
|
+
src = @handler_link.remove_unless_symbols(arra)
|
39
|
+
got_link = @handler_link.handler_prefix_link(@link_host_name, src.to_s.delete!("[\"]"))
|
40
|
+
|
41
|
+
img_arra << got_link
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
@doc.xpath('//link').each do |link|
|
46
|
+
if link['href'] != nil && link['type'] != nil
|
47
|
+
if link['type'].include?("image")
|
48
|
+
got_link = @handler_link.handler_prefix_link(@link_host_name, link['href'])
|
49
|
+
img_arra << got_link
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
@arra_links.uniq!
|
55
|
+
@handler_link.remove_unless_link(@arra_links)
|
56
|
+
img_arra
|
57
|
+
end
|
58
|
+
|
59
|
+
def get_url_with_other_attr
|
60
|
+
# нахожу все урлы с jpg, png, gif... и закидываю в @arra_links
|
61
|
+
@images_links = URI.extract(@doc.to_s.encode("UTF-16be", :invalid => :replace, :replace => "?").encode('UTF-8')).select { |l| l[/\.(?:gif|png|jpe?g)\b/] }
|
62
|
+
@handler_link.handler_links(@images_links, @link) # обрабатываю урлы
|
63
|
+
@handler_link.remove_unless_symbols(@images_links)
|
64
|
+
@handler_link.remove_unless_link(@images_links)
|
65
|
+
@images_links
|
66
|
+
end
|
67
|
+
end
|
@@ -0,0 +1,11 @@
|
|
1
|
+
require "images_from_link/version"
|
2
|
+
require 'HandlerLink'
|
3
|
+
require 'ImagesLink'
|
4
|
+
|
5
|
+
module ImagesFromLink
|
6
|
+
# выводит каритнки по переданному урлу
|
7
|
+
def self.get_images(link)
|
8
|
+
images_link = ImagesLink.new(link)
|
9
|
+
images_link.get_images_from_url
|
10
|
+
end
|
11
|
+
end
|
metadata
ADDED
@@ -0,0 +1,127 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: images_from_link
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- zerocool
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-03-18 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.14'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.14'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.5'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.5'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: httparty
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: nokogiri
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 1.7.0
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 1.7.0
|
83
|
+
description: Get images from link
|
84
|
+
email:
|
85
|
+
- exwarvlad@gmail.com
|
86
|
+
executables: []
|
87
|
+
extensions: []
|
88
|
+
extra_rdoc_files: []
|
89
|
+
files:
|
90
|
+
- ".gitignore"
|
91
|
+
- CODE_OF_CONDUCT.md
|
92
|
+
- Gemfile
|
93
|
+
- LICENSE.txt
|
94
|
+
- README.md
|
95
|
+
- Rakefile
|
96
|
+
- bin/console
|
97
|
+
- bin/setup
|
98
|
+
- images_from_link.gemspec
|
99
|
+
- lib/HandlerLink.rb
|
100
|
+
- lib/ImagesLink.rb
|
101
|
+
- lib/images_from_link.rb
|
102
|
+
- lib/images_from_link/version.rb
|
103
|
+
homepage: https://github.com/exwarvlad/images_from_link
|
104
|
+
licenses:
|
105
|
+
- MIT
|
106
|
+
metadata: {}
|
107
|
+
post_install_message:
|
108
|
+
rdoc_options: []
|
109
|
+
require_paths:
|
110
|
+
- lib
|
111
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
112
|
+
requirements:
|
113
|
+
- - ">="
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '0'
|
116
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
117
|
+
requirements:
|
118
|
+
- - ">="
|
119
|
+
- !ruby/object:Gem::Version
|
120
|
+
version: '0'
|
121
|
+
requirements: []
|
122
|
+
rubyforge_project:
|
123
|
+
rubygems_version: 2.6.8
|
124
|
+
signing_key:
|
125
|
+
specification_version: 4
|
126
|
+
summary: Get images from link
|
127
|
+
test_files: []
|