google_image_scraper 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 896f50afed6a74a3456062ed7110ffa03c51f53cba692e9662e6e5e0586a7644
+  data.tar.gz: ce7ae263ab5eb217d354f92fad2f61702b94fde058d4c914498edd402808782b
+SHA512:
+  metadata.gz: 2b07827bb2a238ac55dc43578371c4c16e52755c5f46230c92fd6ee5466412f45e82b62c628b00a71d1d992759017a7128873ea1cdb43cb115831fde907a4b84
+  data.tar.gz: 54b982e88b162bc77cf0439943cbd73093968c8c5e753bf4c45987eac9731e91ec7b787961e2400c8cac8981cbd99b6d5968dabf09c713557c892936adb23893

data/.gitignore

@@ -0,0 +1,13 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/20*
+/Gemfile.lock
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,10 @@
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Layout/LineLength:
+  Max: 120

data/Gemfile

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in google_image_scraper.gemspec
+gemspec
+
+gem 'rake', '~> 13.0'
+
+gem 'rspec', '~> 3.0'
+
+gem 'rubocop', '~> 0.80'
+
+gem 'byebug'

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2021 Yudai Tanaka
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,38 @@
+# GoogleImageScraper
+
+A command line tool for downloadng image from Google Image Search.
+
+## Installation
+```
+$ gem install google_image_scraper
+```
+
+## Usage
+Execute `google_image_scaper` with `search_word`.
+If you want to limit the amount of downloaded images, specify an integer as `max_number`.
+
+```
+$ google_image_scraper search_word [max_number]
+```
+
+After execution of this command, downloaded images will be saved at a directory named current date with YYYYMMDDHHMM format(e.g. 202001011023).
+
+e.g.
+```
+$ google_image_scraper cat
+$ google_image_scraper cat 10
+```
+
+## Development
+
+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.
+
+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).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/ytnk531/google_image_scraper.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+require "rubocop/rake_task"
+
+RuboCop::RakeTask.new
+
+task default: %i[spec rubocop]

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require "bundler/setup"
+require "google_image_scraper"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/exe/google_image_scraper

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require 'google_image_scraper'
+
+keyword = ARGV[0]
+limit = ARGV[1]&.to_i || nil
+GoogleImageScraper::Scraper.new.scrape(keyword, limit)

data/google_image_scraper.gemspec

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+require_relative 'lib/google_image_scraper/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'google_image_scraper'
+  spec.version       = GoogleImageScraper::VERSION
+  spec.authors       = ['Yudai Tanaka']
+  spec.email         = ['ytnk531@gmail.com']
+
+  spec.summary       = 'An image downloader using Google image search.'
+  spec.description   = 'An image downloader using Google image search. This is unofficial gem.'
+  spec.homepage      = 'https://github.com/ytnk531/google_image_scraper'
+  spec.license       = 'MIT'
+  spec.required_ruby_version = Gem::Requirement.new('>= 2.7.0')
+
+  # spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['source_code_uri'] = 'https://github.com/ytnk531/google_image_scraper'
+  # spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features)/}) }
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'selenium-webdriver', '~> 3.0'
+end

data/lib/google_image_scraper.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require_relative 'google_image_scraper/version'
+require_relative 'google_image_scraper/file_saver'
+require_relative 'google_image_scraper/scraper'
+require 'logger'
+
+# Google image scraper
+module GoogleImageScraper
+  Logger = ::Logger.new($stdout)
+
+  class Error < StandardError; end
+end

data/lib/google_image_scraper/file_saver.rb

@@ -0,0 +1,43 @@
+require 'base64'
+require 'digest'
+
+# File saving and convert.
+module GoogleImageScraper
+  class FileSaver
+    def save(src)
+      binary, extname = if src.start_with?('data:')
+                          to_file_from_base64(src)
+                        else
+                          to_file_from_url(src)
+                        end
+      fname = "#{Digest::MD5.hexdigest(src)[0...10]}.#{extname}"
+
+      File.write(File.join(dir.path, fname), binary)
+    end
+
+    private
+
+    def dir
+      return @dir if @dir
+
+      dirname = Time.new.strftime('%Y%m%d%H%M')
+      Dir.mkdir(dirname) unless Dir.exist? dirname
+      @dir = Dir.open(dirname)
+    end
+
+    def to_file_from_base64(src)
+      data_prefix, base64 = src.split(',')
+      [Base64.decode64(base64), "data.#{data_extname(data_prefix)}"]
+    end
+
+    def to_file_from_url(url)
+      meta = URI.open(url)
+      [meta.read, meta.content_type.split('/').last]
+    end
+
+    def data_extname(data_prefix)
+      %r{data:image/(?<extname>.+);base64} =~ data_prefix
+      extname
+    end
+  end
+end

data/lib/google_image_scraper/scraper.rb

@@ -0,0 +1,62 @@
+require 'open-uri'
+require 'selenium-webdriver'
+
+module GoogleImageScraper
+  class Scraper
+    LARGE_PICTURE_XPATH = '/html/body/div[2]/c-wiz/div[3]' \
+            '/div[2]/div[3]/div/div/div[3]/div[2]/c-wiz/div[1]/div[1]/div/div[2]/a/img'.freeze
+    SEARCH_PAGE_URL_FORMAT = 'https://www.google.com/search?q=%s&source=lnms&tbm=isch'.freeze
+
+    def initialize
+      @driver = setup_driver
+      @file_saver = FileSaver.new
+      @wait = Selenium::WebDriver::Wait.new(timeout: 10)
+    end
+
+    def scrape(keyword, limit = nil)
+      @driver.get search_page_url(keyword)
+      img_end = limit&.-(1) || -1
+      start = 0
+
+      loop do
+        # After 2nd time of this execution, html_elements are increased than previous execution.
+        # This is because search page uses continuous loading triggered by scroll point.
+        elements = @driver.find_elements(css: '.mJxzWe img')
+        break if start == elements.size
+
+        download_images elements[start..img_end]
+
+        start = elements.size
+        elements.last.click unless limit
+      end
+    end
+
+    private
+
+    def search_page_url(keyword)
+      format(SEARCH_PAGE_URL_FORMAT, URI.encode_www_form_component(keyword))
+    end
+
+    def download_images(html_elements)
+      html_elements.each do |element|
+        # Show image in left side and then wait for large image will be displayed.
+        element.click
+
+        sleep 0.4
+        large_picture_element = @wait.until do
+          @driver.find_element(:xpath, LARGE_PICTURE_XPATH)
+        end
+        src = large_picture_element.attribute('src')
+        @file_saver.save(src)
+      end
+    end
+
+    def setup_driver
+      caps = Selenium::WebDriver::Remote::Capabilities.chrome(
+        'chromeOptions' => { args: %w[--headless --disable-gpu window-size=1280x8000] }
+      )
+      # caps = Selenium::WebDriver::Remote::Capabilities.chrome
+      Selenium::WebDriver.for :chrome, desired_capabilities: caps
+    end
+  end
+end

data/lib/google_image_scraper/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module GoogleImageScraper
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,75 @@
+--- !ruby/object:Gem::Specification
+name: google_image_scraper
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Yudai Tanaka
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2021-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: selenium-webdriver
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: An image downloader using Google image search. This is unofficial gem.
+email:
+- ytnk531@gmail.com
+executables:
+- google_image_scraper
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- exe/google_image_scraper
+- google_image_scraper.gemspec
+- lib/google_image_scraper.rb
+- lib/google_image_scraper/file_saver.rb
+- lib/google_image_scraper/scraper.rb
+- lib/google_image_scraper/version.rb
+homepage: https://github.com/ytnk531/google_image_scraper
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/ytnk531/google_image_scraper
+  source_code_uri: https://github.com/ytnk531/google_image_scraper
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.3
+signing_key: 
+specification_version: 4
+summary: An image downloader using Google image search.
+test_files: []