Merge branch 'challenge'

.github/workflows/ci.yml

@@ -0,0 +1,25 @@
+name: CI
+on:
+  # https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request
+  # opened, synchronize, reopened by default
+  pull_request:
+  push: 
+    branches: 
+      - master # only on push to master branch
+jobs:
+  tests:
+    name: Tests
+    runs-on: ubuntu-latest
+    steps:
+      # https://github.com/marketplace/actions/checkout
+      - uses: actions/checkout@v4 # download the repository
+      # https://github.com/marketplace/actions/setup-ruby-jruby-and-truffleruby
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: .ruby-version # read from file
+          bundler-cache: true # automatically run bundle install and cache the result
+
+      - name: Run Tests
+        env:
+          RAILS_ENV: test
+        run: bundle exec rspec ./specs

.ruby-version

@@ -0,0 +1 @@
+ruby-3.2.4

CHALLENGE.md

@@ -0,0 +1,28 @@
+# Extract Van Gogh Paintings Code Challenge
+
+Goal is to extract a list of Van Gogh paintings from the attached Google search results page.
+
+![Van Gogh paintings](https://github.com/serpapi/code-challenge/blob/master/files/van-gogh-paintings.png?raw=true "Van Gogh paintings")
+
+## Instructions
+
+This is already fully supported on SerpApi. ([relevant test], [html file], [sample json], and [expected array].)
+Try to come up with your own solution and your own test.
+Extract the painting `name`, `extensions` array (date), and Google `link` in an array.
+
+Fork this repository and make a PR when ready.
+
+Programming language wise, Ruby (with RSpec tests) is strongly suggested but feel free to use whatever you feel like.
+
+Parse directly the HTML result page ([html file]) in this repository. No extra HTTP requests should be needed for anything.
+
+[relevant test]: https://github.com/serpapi/test-knowledge-graph-desktop/blob/master/spec/knowledge_graph_claude_monet_paintings_spec.rb
+[sample json]: https://raw.githubusercontent.com/serpapi/code-challenge/master/files/van-gogh-paintings.json
+[html file]: https://raw.githubusercontent.com/serpapi/code-challenge/master/files/van-gogh-paintings.html
+[expected array]: https://raw.githubusercontent.com/serpapi/code-challenge/master/files/expected-array.json
+
+Add also to your array the painting thumbnails present in the result page file (not the ones where extra requests are needed). 
+
+Test against 2 other similar result pages to make sure it works against different layouts. (Pages that contain the same kind of carrousel. Don't necessarily have to be paintings.)
+
+The suggested time for this challenge is 4 hours. But, you can take your time and work more on it if you want.

Gemfile

@@ -0,0 +1,19 @@
+source "https://rubygems.org"
+
+ruby "3.2.4"
+
+# for parsing html documents to nodes tree
+# see nokogiri_based_knowledge_graph.rb
+gem 'nokogiri'
+gem 'nokolexbor'
+
+group :development do
+  # https://github.com/SamSaffron/memory_profiler
+  # see benchmarks/memory.rb
+  gem 'memory_profiler'
+  gem 'debug'
+end
+
+group :test do
+  gem 'rspec'
+end

Gemfile.lock

@@ -0,0 +1,70 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    debug (1.9.2)
+      irb (~> 1.10)
+      reline (>= 0.3.8)
+    diff-lcs (1.5.1)
+    io-console (0.7.2)
+    irb (1.13.2)
+      rdoc (>= 4.0.0)
+      reline (>= 0.4.2)
+    memory_profiler (1.0.2)
+    nokogiri (1.16.6-aarch64-linux)
+      racc (~> 1.4)
+    nokogiri (1.16.6-arm-linux)
+      racc (~> 1.4)
+    nokogiri (1.16.6-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.16.6-x86-linux)
+      racc (~> 1.4)
+    nokogiri (1.16.6-x86_64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.16.6-x86_64-linux)
+      racc (~> 1.4)
+    nokolexbor (0.5.4)
+    nokolexbor (0.5.4-arm64-darwin)
+    nokolexbor (0.5.4-x86_64-darwin)
+    nokolexbor (0.5.4-x86_64-linux)
+    psych (5.1.2)
+      stringio
+    racc (1.8.0)
+    rdoc (6.7.0)
+      psych (>= 4.0.0)
+    reline (0.5.9)
+      io-console (~> 0.5)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.0)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.1)
+    stringio (3.1.1)
+
+PLATFORMS
+  aarch64-linux
+  arm-linux
+  arm64-darwin
+  x86-linux
+  x86_64-darwin
+  x86_64-linux
+
+DEPENDENCIES
+  debug
+  memory_profiler
+  nokogiri
+  nokolexbor
+  rspec
+
+RUBY VERSION
+   ruby 3.2.4p170
+
+BUNDLED WITH
+   2.5.10