serpapi · pmonfort · Jul 29, 2025 · Jul 29, 2025
diff --git a/.ruby-version b/.ruby-version
@@ -0,0 +1 @@
+3.3.5
diff --git a/Gemfile b/Gemfile
@@ -0,0 +1,10 @@
+source 'https://rubygems.org'
+
+ruby '3.3.5'
+
+gem 'nokogiri', '~> 1.15'
+gem 'rspec', '~> 3.12'
+
+group :development do
+  gem "debug", ">= 1.0.0"
+end 
diff --git a/Gemfile.lock b/Gemfile.lock
@@ -0,0 +1,77 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    date (3.4.1)
+    debug (1.11.0)
+      irb (~> 1.10)
+      reline (>= 0.3.8)
+    diff-lcs (1.6.2)
+    erb (5.0.2)
+    io-console (0.8.1)
+    irb (1.15.2)
+      pp (>= 0.6.0)
+      rdoc (>= 4.0.0)
+      reline (>= 0.4.2)
+    nokogiri (1.18.9-aarch64-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.18.9-aarch64-linux-musl)
+      racc (~> 1.4)
+    nokogiri (1.18.9-arm-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.18.9-arm-linux-musl)
+      racc (~> 1.4)
+    nokogiri (1.18.9-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.18.9-x86_64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.18.9-x86_64-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.18.9-x86_64-linux-musl)
+      racc (~> 1.4)
+    pp (0.6.2)
+      prettyprint
+    prettyprint (0.2.0)
+    psych (5.2.6)
+      date
+      stringio
+    racc (1.8.1)
+    rdoc (6.14.2)
+      erb
+      psych (>= 4.0.0)
+    reline (0.6.2)
+      io-console (~> 0.5)
+    rspec (3.13.1)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.5)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.5)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.5)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.4)
+    stringio (3.1.7)
+
+PLATFORMS
+  aarch64-linux-gnu
+  aarch64-linux-musl
+  arm-linux-gnu
+  arm-linux-musl
+  arm64-darwin
+  x86_64-darwin
+  x86_64-linux-gnu
+  x86_64-linux-musl
+
+DEPENDENCIES
+  debug (>= 1.0.0)
+  nokogiri (~> 1.15)
+  rspec (~> 3.12)
+
+RUBY VERSION
+   ruby 3.3.5p100
+
+BUNDLED WITH
+   2.7.1
diff --git a/README.md b/README.md
@@ -26,3 +26,20 @@ Add also to your array the painting thumbnails present in the result page file (
 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.
+
+## Solution
+
+Created a GoogleSearchParser service and added specs to validate the expected behavior. Built with Ruby 3.3.5, Nokogiri for HTML parsing and RSpec for testing.
+Included three additional test pages (pablo_picasso, claude_monet, and leonardo_da_vinci) to ensure the parser works across different layouts.
+
+# Setup
+
+```
+bundle install
+```
+
+# Run tests
+
+```
+bundle exec rspec
+```
diff --git a/files/claude_monet/expected_result.json b/files/claude_monet/expected_result.json
diff --git a/files/claude_monet/search_result.html b/files/claude_monet/search_result.html
diff --git a/files/empty_page.html b/files/empty_page.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Empty Page</title>
+  </head>
+  <body>
+    <div class="empty-page">
+      <h1>No Artworks Found</h1>
+      <p>This page contains no artwork information.</p>
+    </div>
+  </body>
+</html> 
diff --git a/files/leonardo_da_vinci/expected_result.json b/files/leonardo_da_vinci/expected_result.json
diff --git a/files/leonardo_da_vinci/search_result.html b/files/leonardo_da_vinci/search_result.html
diff --git a/files/malformed.html b/files/malformed.html
@@ -0,0 +1,34 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Malformed HTML</title>
+  </head>
+  <body>
+    <div class="search-results">
+      <div class="knowledge-panel">
+        <div class="kno-fv">
+          <div class="kno-fv__tab-content" data-attrid="artworks">
+            <div class="kno-fv__tab-panel">
+              <h3>Artworks</h3>
+              <div class="artworks-grid">
+                <div class="artwork-item">
+                  <img src="https://example.com/starry-night.jpg" alt="The Starry Night" class="kno-fv__img">
+                  <div class="artwork-info">
+                    <span class="title">The Starry Night
+                    <span class="year">1889
+                  </div>
+                </div>
+                <div class="artwork-item">
+                  <img src="https://example.com/self-portrait.jpg" alt="Van Gogh self-portrait" class="kno-fv__img">
+                  <div class="artwork-info">
+                    <span class="title">Van Gogh self-portrait</span>
+                    <span class="year">1889</span>
+                  </div>
+              </div>
+            </div>
+          </div>
+        </div>
+      </div>
+    </div>
+  </body>
+</html> 
diff --git a/files/malformed_with_valid_data.html b/files/malformed_with_valid_data.html
@@ -0,0 +1,33 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Malformed HTML</title>
+  </head>
+  <body>
+    <div class="search-results">
+      <div class="knowledge-panel">
+        <div class="kno-fv">
+            <h3>Artworks</h3>
+            <div class="artworks-grid">
+                <a href="/search?sca_esv=c2e426814f4d07e9&amp;gl=us&amp;hl=en&amp;q=Sunflowers&amp;stick=H4sIAAAAAAAAAONgFuLQz9U3MI_PNVLiArFMUszTjcu1lLKTrfTLMotLE3PiE4tKkJiZxSVW5flF2cWLWLmCS_PScvLLU4uKARitY11JAAAA&amp;sa=X&amp;ved=2ahUKEwjK-K-JwLWKAxXcQTABHePpOFoQtq8DegQIMxAX">
+                  <img class="taFZJe" alt="Sunflowers" data-src="https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcS1s9TeQSMp52s4RilDMm5lMGHK26HjE3T6D-88O1l6Xf3pDCvv" src="data:image/gif;base64,R0lGODlhAQABAIAAAP///////yH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==" data-csiid="L_FkZ4qlAtyDwbkP49Pj0QU_13" data-lzy_="1">
+                </a>
+
+              <div class="iELo6" style="display:none;width:0px;top:0px;left:0px" jsdata="JI96Wc;unsupported;BCVKGw">
+                <a href="/search?sca_esv=c2e426814f4d07e9&amp;gl=us&amp;hl=en&amp;q=Wheat+Field+with+Cypresses&amp;stick=H4sIAAAAAAAAAONgFuLQz9U3MI_PNVLiArFMSnJMTeK1lLKTrfTLMotLE3PiE4tKkJiZxSVW5flF2cWLWKXCM1ITSxTcMlNzUhTKM0syFJwrC4pSi4tTiwEkoHZyWQAAAA&amp;sa=X&amp;ved=2ahUKEwjK-K-JwLWKAxXcQTABHePpOFoQtq8DegQIMxAv">
+                  <img class="taFZJe" alt="Wheat Field with Cypresses" data-src="https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ-YYo-yqMf-K5i2GTIoT8OmNzoTdfxd55p4TbIcmtxLbyYvKzO" src="data:image/gif;base64,R0lGODlhAQABAIAAAP///////yH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==" data-csiid="L_FkZ4qlAtyDwbkP49Pj0QU_25" data-lzy_="1">
+                  <div class="KHK6lb">
+                    <div class="pgNMRc">  </div>
+                    <div class="cxzHyb">1889</div>
+                  </div>
+                </a>
+              </div>
+
+              </div>
+            </div>
+          </div>
+        </div>
+      </div>
+    </div>
+  </body>
+</html> 
diff --git a/files/pablo_picasso/expected_result.json b/files/pablo_picasso/expected_result.json