Merge dev: Node.js scraper migration + CI fix (#32)

Co-authored-by: Stephen Minakian <stephenminakian@gmail.com>
Co-committed-by: Stephen Minakian <stephenminakian@gmail.com>

config/scraper.js

@@ -0,0 +1,41 @@
+/**
+ * Scraper Configuration Module
+ *
+ * Contains all constants and settings for the apartment price scraper.
+ * All values can be overridden via environment variables for deployment flexibility.
+ *
+ * See py_migration/phase-3/3.2-TECHNICAL-DESIGN.md Section 5.3 for full documentation.
+ */
+
+module.exports = {
+  // Target URL for apartment listings
+  TARGET_URL: 'https://countryclubtowersandgardens.com/property/country-club-towers/apartments/?spaces_tab=unit',
+
+  // Scheduling configuration
+  SCRAPER_SCHEDULE: process.env.SCRAPER_SCHEDULE || '0 6 * * *',
+  SCRAPER_TIMEZONE: process.env.SCRAPER_TIMEZONE || 'UTC',
+  SCRAPER_ENABLED: process.env.SCRAPER_ENABLED !== 'false',
+
+  // HTTP settings
+  SCRAPER_TIMEOUT: parseInt(process.env.SCRAPER_TIMEOUT, 10) || 30000,
+  USER_AGENT: 'Mozilla/5.0 (compatible; ApartmentScraper/1.0)',
+
+  // Retry configuration for HTTP requests
+  RETRY_CONFIG: {
+    maxRetries: 3,
+    baseDelay: 1000, // 1 second, exponential backoff: 1s, 2s, 4s
+    timeout: parseInt(process.env.SCRAPER_TIMEOUT, 10) || 30000
+  },
+
+  // Graceful shutdown timeout (how long to wait for running job before force-stopping)
+  SHUTDOWN_TIMEOUT: parseInt(process.env.SCRAPER_SHUTDOWN_TIMEOUT, 10) || 30000,
+
+  // MongoDB collection names - defaults to validation collections for scraper validation;
+  // switch to production collections via env vars (SCRAPER_UNITS_COLLECTION, SCRAPER_PRICES_COLLECTION) when ready
+  COLLECTIONS: {
+    UNITS: process.env.SCRAPER_UNITS_COLLECTION || 'units_scraper',
+    PRICES: process.env.SCRAPER_PRICES_COLLECTION || 'unit_prices_scraper',
+    DAILY_SUMMARIES: process.env.SCRAPER_SUMMARIES_COLLECTION || 'daily_summaries',
+    SCRAPER_RUNS: process.env.SCRAPER_RUNS_COLLECTION || 'scraper_runs'
+  }
+};