google_image_scraper 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 +13 -0
- data/.rspec +3 -0
- data/.rubocop.yml +10 -0
- data/Gemfile +14 -0
- data/LICENSE.txt +21 -0
- data/README.md +38 -0
- data/Rakefile +12 -0
- data/bin/console +15 -0
- data/bin/setup +8 -0
- data/exe/google_image_scraper +7 -0
- data/google_image_scraper.gemspec +32 -0
- data/lib/google_image_scraper.rb +13 -0
- data/lib/google_image_scraper/file_saver.rb +43 -0
- data/lib/google_image_scraper/scraper.rb +62 -0
- data/lib/google_image_scraper/version.rb +5 -0
- metadata +75 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 896f50afed6a74a3456062ed7110ffa03c51f53cba692e9662e6e5e0586a7644
|
4
|
+
data.tar.gz: ce7ae263ab5eb217d354f92fad2f61702b94fde058d4c914498edd402808782b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2b07827bb2a238ac55dc43578371c4c16e52755c5f46230c92fd6ee5466412f45e82b62c628b00a71d1d992759017a7128873ea1cdb43cb115831fde907a4b84
|
7
|
+
data.tar.gz: 54b982e88b162bc77cf0439943cbd73093968c8c5e753bf4c45987eac9731e91ec7b787961e2400c8cac8981cbd99b6d5968dabf09c713557c892936adb23893
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.rubocop.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2021 Yudai Tanaka
|
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 +1,38 @@
|
|
1
|
+
# GoogleImageScraper
|
2
|
+
|
3
|
+
A command line tool for downloadng image from Google Image Search.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
```
|
7
|
+
$ gem install google_image_scraper
|
8
|
+
```
|
9
|
+
|
10
|
+
## Usage
|
11
|
+
Execute `google_image_scaper` with `search_word`.
|
12
|
+
If you want to limit the amount of downloaded images, specify an integer as `max_number`.
|
13
|
+
|
14
|
+
```
|
15
|
+
$ google_image_scraper search_word [max_number]
|
16
|
+
```
|
17
|
+
|
18
|
+
After execution of this command, downloaded images will be saved at a directory named current date with YYYYMMDDHHMM format(e.g. 202001011023).
|
19
|
+
|
20
|
+
e.g.
|
21
|
+
```
|
22
|
+
$ google_image_scraper cat
|
23
|
+
$ google_image_scraper cat 10
|
24
|
+
```
|
25
|
+
|
26
|
+
## Development
|
27
|
+
|
28
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
29
|
+
|
30
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
31
|
+
|
32
|
+
## Contributing
|
33
|
+
|
34
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/ytnk531/google_image_scraper.
|
35
|
+
|
36
|
+
## License
|
37
|
+
|
38
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require "bundler/setup"
|
5
|
+
require "google_image_scraper"
|
6
|
+
|
7
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
8
|
+
# with your gem easier. You can also use a different console, if you like.
|
9
|
+
|
10
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
11
|
+
# require "pry"
|
12
|
+
# Pry.start
|
13
|
+
|
14
|
+
require "irb"
|
15
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'lib/google_image_scraper/version'
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = 'google_image_scraper'
|
7
|
+
spec.version = GoogleImageScraper::VERSION
|
8
|
+
spec.authors = ['Yudai Tanaka']
|
9
|
+
spec.email = ['ytnk531@gmail.com']
|
10
|
+
|
11
|
+
spec.summary = 'An image downloader using Google image search.'
|
12
|
+
spec.description = 'An image downloader using Google image search. This is unofficial gem.'
|
13
|
+
spec.homepage = 'https://github.com/ytnk531/google_image_scraper'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
spec.required_ruby_version = Gem::Requirement.new('>= 2.7.0')
|
16
|
+
|
17
|
+
# spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
|
18
|
+
spec.metadata['homepage_uri'] = spec.homepage
|
19
|
+
spec.metadata['source_code_uri'] = 'https://github.com/ytnk531/google_image_scraper'
|
20
|
+
# spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
|
21
|
+
|
22
|
+
# Specify which files should be added to the gem when it is released.
|
23
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
24
|
+
spec.files = Dir.chdir(File.expand_path(__dir__)) do
|
25
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features)/}) }
|
26
|
+
end
|
27
|
+
spec.bindir = 'exe'
|
28
|
+
spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
|
29
|
+
spec.require_paths = ['lib']
|
30
|
+
|
31
|
+
spec.add_dependency 'selenium-webdriver', '~> 3.0'
|
32
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'google_image_scraper/version'
|
4
|
+
require_relative 'google_image_scraper/file_saver'
|
5
|
+
require_relative 'google_image_scraper/scraper'
|
6
|
+
require 'logger'
|
7
|
+
|
8
|
+
# Google image scraper
|
9
|
+
module GoogleImageScraper
|
10
|
+
Logger = ::Logger.new($stdout)
|
11
|
+
|
12
|
+
class Error < StandardError; end
|
13
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
require 'base64'
|
2
|
+
require 'digest'
|
3
|
+
|
4
|
+
# File saving and convert.
|
5
|
+
module GoogleImageScraper
|
6
|
+
class FileSaver
|
7
|
+
def save(src)
|
8
|
+
binary, extname = if src.start_with?('data:')
|
9
|
+
to_file_from_base64(src)
|
10
|
+
else
|
11
|
+
to_file_from_url(src)
|
12
|
+
end
|
13
|
+
fname = "#{Digest::MD5.hexdigest(src)[0...10]}.#{extname}"
|
14
|
+
|
15
|
+
File.write(File.join(dir.path, fname), binary)
|
16
|
+
end
|
17
|
+
|
18
|
+
private
|
19
|
+
|
20
|
+
def dir
|
21
|
+
return @dir if @dir
|
22
|
+
|
23
|
+
dirname = Time.new.strftime('%Y%m%d%H%M')
|
24
|
+
Dir.mkdir(dirname) unless Dir.exist? dirname
|
25
|
+
@dir = Dir.open(dirname)
|
26
|
+
end
|
27
|
+
|
28
|
+
def to_file_from_base64(src)
|
29
|
+
data_prefix, base64 = src.split(',')
|
30
|
+
[Base64.decode64(base64), "data.#{data_extname(data_prefix)}"]
|
31
|
+
end
|
32
|
+
|
33
|
+
def to_file_from_url(url)
|
34
|
+
meta = URI.open(url)
|
35
|
+
[meta.read, meta.content_type.split('/').last]
|
36
|
+
end
|
37
|
+
|
38
|
+
def data_extname(data_prefix)
|
39
|
+
%r{data:image/(?<extname>.+);base64} =~ data_prefix
|
40
|
+
extname
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'selenium-webdriver'
|
3
|
+
|
4
|
+
module GoogleImageScraper
|
5
|
+
class Scraper
|
6
|
+
LARGE_PICTURE_XPATH = '/html/body/div[2]/c-wiz/div[3]' \
|
7
|
+
'/div[2]/div[3]/div/div/div[3]/div[2]/c-wiz/div[1]/div[1]/div/div[2]/a/img'.freeze
|
8
|
+
SEARCH_PAGE_URL_FORMAT = 'https://www.google.com/search?q=%s&source=lnms&tbm=isch'.freeze
|
9
|
+
|
10
|
+
def initialize
|
11
|
+
@driver = setup_driver
|
12
|
+
@file_saver = FileSaver.new
|
13
|
+
@wait = Selenium::WebDriver::Wait.new(timeout: 10)
|
14
|
+
end
|
15
|
+
|
16
|
+
def scrape(keyword, limit = nil)
|
17
|
+
@driver.get search_page_url(keyword)
|
18
|
+
img_end = limit&.-(1) || -1
|
19
|
+
start = 0
|
20
|
+
|
21
|
+
loop do
|
22
|
+
# After 2nd time of this execution, html_elements are increased than previous execution.
|
23
|
+
# This is because search page uses continuous loading triggered by scroll point.
|
24
|
+
elements = @driver.find_elements(css: '.mJxzWe img')
|
25
|
+
break if start == elements.size
|
26
|
+
|
27
|
+
download_images elements[start..img_end]
|
28
|
+
|
29
|
+
start = elements.size
|
30
|
+
elements.last.click unless limit
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
def search_page_url(keyword)
|
37
|
+
format(SEARCH_PAGE_URL_FORMAT, URI.encode_www_form_component(keyword))
|
38
|
+
end
|
39
|
+
|
40
|
+
def download_images(html_elements)
|
41
|
+
html_elements.each do |element|
|
42
|
+
# Show image in left side and then wait for large image will be displayed.
|
43
|
+
element.click
|
44
|
+
|
45
|
+
sleep 0.4
|
46
|
+
large_picture_element = @wait.until do
|
47
|
+
@driver.find_element(:xpath, LARGE_PICTURE_XPATH)
|
48
|
+
end
|
49
|
+
src = large_picture_element.attribute('src')
|
50
|
+
@file_saver.save(src)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def setup_driver
|
55
|
+
caps = Selenium::WebDriver::Remote::Capabilities.chrome(
|
56
|
+
'chromeOptions' => { args: %w[--headless --disable-gpu window-size=1280x8000] }
|
57
|
+
)
|
58
|
+
# caps = Selenium::WebDriver::Remote::Capabilities.chrome
|
59
|
+
Selenium::WebDriver.for :chrome, desired_capabilities: caps
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
metadata
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: google_image_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Yudai Tanaka
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2021-01-02 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: selenium-webdriver
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '3.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '3.0'
|
27
|
+
description: An image downloader using Google image search. This is unofficial gem.
|
28
|
+
email:
|
29
|
+
- ytnk531@gmail.com
|
30
|
+
executables:
|
31
|
+
- google_image_scraper
|
32
|
+
extensions: []
|
33
|
+
extra_rdoc_files: []
|
34
|
+
files:
|
35
|
+
- ".gitignore"
|
36
|
+
- ".rspec"
|
37
|
+
- ".rubocop.yml"
|
38
|
+
- Gemfile
|
39
|
+
- LICENSE.txt
|
40
|
+
- README.md
|
41
|
+
- Rakefile
|
42
|
+
- bin/console
|
43
|
+
- bin/setup
|
44
|
+
- exe/google_image_scraper
|
45
|
+
- google_image_scraper.gemspec
|
46
|
+
- lib/google_image_scraper.rb
|
47
|
+
- lib/google_image_scraper/file_saver.rb
|
48
|
+
- lib/google_image_scraper/scraper.rb
|
49
|
+
- lib/google_image_scraper/version.rb
|
50
|
+
homepage: https://github.com/ytnk531/google_image_scraper
|
51
|
+
licenses:
|
52
|
+
- MIT
|
53
|
+
metadata:
|
54
|
+
homepage_uri: https://github.com/ytnk531/google_image_scraper
|
55
|
+
source_code_uri: https://github.com/ytnk531/google_image_scraper
|
56
|
+
post_install_message:
|
57
|
+
rdoc_options: []
|
58
|
+
require_paths:
|
59
|
+
- lib
|
60
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
61
|
+
requirements:
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: 2.7.0
|
65
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - ">="
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
requirements: []
|
71
|
+
rubygems_version: 3.2.3
|
72
|
+
signing_key:
|
73
|
+
specification_version: 4
|
74
|
+
summary: An image downloader using Google image search.
|
75
|
+
test_files: []
|