Implement parseUnits() HTML parsing with cheerio

- Extract apartment unit data from section.spaces__tab-unit container
- Parse all data-spaces-* attributes from article elements
- Deduplicate units by unit_code with warning logging
- Handle missing container gracefully (returns empty array)
- Add comprehensive test suite with HTML fixture (22 tests)

services/scraperService.js

@@ -6,6 +6,7 @@
  */
 
 const axios = require('axios');
+const cheerio = require('cheerio');
 const config = require('../config/scraper');
 
 /**
@@ -106,8 +107,100 @@ async function fetchPage(url, logger) {
   throw lastError;
 }
 
+/**
+ * Parse unit data from HTML using cheerio
+ * @param {string} html - HTML content
+ * @param {Object} logger - Logger instance
+ * @returns {Array<Object>} Array of raw unit objects (string values, no type conversion)
+ */
+function parseUnits(html, logger) {
+  const $ = cheerio.load(html);
+  const units = [];
+
+  // Find the main container
+  const container = $('section.spaces__tab-unit');
+
+  if (container.length === 0) {
+    logger.error('Container section.spaces__tab-unit not found - possible structure change', {});
+    return [];
+  }
+
+  // Extract each article element
+  container.find('article').each((index, article) => {
+    const $article = $(article);
+
+    const unit = {
+      // Core identifiers
+      id: $article.attr('data-spaces-id'),
+      unit_code: $article.attr('data-spaces-unit'),
+      unit_id: $article.attr('data-spaces-unit-id'),
+
+      // Physical attributes
+      floor: $article.attr('data-spaces-unit-floor'),
+      area: $article.attr('data-spaces-sort-area'),
+      bed_count: $article.attr('data-spaces-sort-bed'),
+      bath_count: $article.attr('data-spaces-sort-bath'),
+
+      // Pricing
+      price: $article.attr('data-spaces-sort-price'),
+
+      // Availability
+      available: $article.attr('data-spaces-available'),
+      unavailable: $article.attr('data-spaces-unavailable'),
+      soonest: $article.attr('data-spaces-soonest'),
+      date_available: $article.attr('data-spaces-sort-date'),
+
+      // Plan information
+      plan_id: $article.attr('data-spaces-plan-id'),
+      plan_name: $article.attr('data-spaces-sort-plan-name'),
+
+      // Property information
+      obj_type: $article.attr('data-spaces-obj'),
+      community: $article.attr('data-spaces-community'),
+      asset: $article.attr('data-spaces-asset'),
+
+      // URLs
+      href: $article.attr('data-spaces-href'),
+      inventory_href: $article.attr('data-spaces-inventory-href'),
+
+      // Specials
+      specials_content: $article.attr('data-spaces-specials-content')
+    };
+
+    // Extract image URL from nested element if present
+    const imgElement = $article.find('img').first();
+    if (imgElement.length > 0) {
+      unit.image_url = imgElement.attr('src') || imgElement.attr('data-src');
+    }
+
+    units.push(unit);
+  });
+
+  logger.info('Units parsed', { count: units.length });
+
+  // Deduplicate by unit_code (in case of duplicate articles)
+  const seen = new Set();
+  const deduplicated = units.filter(unit => {
+    if (!unit.unit_code || seen.has(unit.unit_code)) {
+      return false;
+    }
+    seen.add(unit.unit_code);
+    return true;
+  });
+
+  if (deduplicated.length < units.length) {
+    logger.warn('Duplicate units removed', {
+      original: units.length,
+      deduplicated: deduplicated.length
+    });
+  }
+
+  return deduplicated;
+}
+
 module.exports = {
   fetchPage,
+  parseUnits,
   // Export for testing
   isRetryableError,
   sleep