googscrape 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: c2a3e5e68a8d4368ec2a4f507bef8a20119f2298118a1562ac4f610f3b02c3ab
+  data.tar.gz: 829e29903853c24f6d2e6277d576bdf85df9557a5291470a4b69bb6462aeff46
+SHA512:
+  metadata.gz: 4537cf48b5c8710b32f238a50e20a8c6886ef79fe15f8d611fa9230929a9ee15b05ca6ae485692813eba6755ef4a623d43226af48909ba97dacc5c920360c2a0
+  data.tar.gz: 86a5c66ac1c7e7aa7c8f6e692a4ec542569e0dde25ecf125bea9af485c8ff72f996db459b1120f63e32cf014aedae58ce771b36ca98d5f0c3ad5ea6046994ccd

data/lib/google_image_scrape.rb

@@ -0,0 +1,39 @@
+require 'nokogiri'
+require 'json'
+
+class GoogleImageScrape
+  class << self
+    def scrape_images(source_file)
+
+      html_content = File.read(source_file)
+      doc = Nokogiri::HTML(html_content)
+
+      artworks = []
+
+      doc.css('[class^="klitem"]').each do |artwork|
+        name_element = artwork['aria-label']
+        name = name_element.strip if name_element
+        
+        extensions_element = artwork.at_css('[class^="ellip"]')
+        extensions = extensions_element.text.strip.split(',') if extensions_element
+
+        link = artwork['href']
+        image_element = artwork.at_css('[class^="rISBZc"]')
+        image = image_element['src']
+
+        artworks << {
+          name: name,
+          extensions: extensions,
+          link: "https://www.google.com" + link.to_s,
+          image: image
+        }
+      end
+      
+      output = { artworks: artworks }
+      output_file_path = './results.json'
+      File.write(output_file_path, JSON.pretty_generate(output))
+
+      puts "Results saved to file: #{output_file_path}."
+    end
+  end
+end

metadata

@@ -0,0 +1,85 @@
+--- !ruby/object:Gem::Specification
+name: googscrape
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- MK
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2024-08-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: google image marquee scraper.
+email: ''
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/google_image_scrape.rb
+homepage: https://rubygems.org/gems/google_image_scrape
+licenses:
+- GPL-2.0
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.15
+signing_key:
+specification_version: 4
+summary: scrape google image marquees.
+test_files: []