Fix total review count detection - sum star ratings

Previous detection was matching wrong elements (partial counts).
Now sums "X stars, Y reviews" aria-labels for accurate total.

Fallback methods:
1. Sum star rating counts (most accurate)
2. Reviews tab text like "Reviews (247)"
3. Span with "X reviews" text

Tested: Soho Club 247/247 correctly detected

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

modules/scraper_clean.py

@@ -293,26 +293,44 @@ def scrape_reviews(driver, url: str, max_reviews: int = 5000, timeout_no_new: in
 
     print("✅ Found scroll container")
 
-    # Extract total review count from page
+    # Extract total review count from page (look in specific places)
     total_reviews = None
     try:
-        page_text = driver.page_source
+        total_reviews = driver.execute_script("""
-        # Look for "XX reviews" pattern
+            // Method 1: Sum up star rating counts (most accurate)
-        patterns = [
+            // Look for aria-labels like "5 stars, 171 reviews"
-            r'(\d{1,3}(?:,\d{3})*)\s+reviews?',
+            var total = 0;
-            r'(\d+\.?\d*K)\s+reviews?',
+            var starLabels = document.querySelectorAll('[aria-label*="stars,"][aria-label*="review"]');
-            r'(\d{1,3}(?:,\d{3})*)\s+reseñas?',
+            if (starLabels.length >= 5) {
-        ]
+                for (var i = 0; i < starLabels.length; i++) {
-        for pattern in patterns:
+                    var match = starLabels[i].getAttribute('aria-label').match(/(\\d+)\\s*review/i);
-            matches = re.findall(pattern, page_text, re.IGNORECASE)
+                    if (match) total += parseInt(match[1]);
-            if matches:
+                }
-                count_str = matches[0]
+                if (total > 0) return total;
-                if 'K' in count_str.upper():
+            }
-                    total_reviews = int(float(count_str.upper().replace('K', '')) * 1000)
+
-                else:
+            // Method 2: Look in reviews tab text (e.g., "Reviews (247)")
-                    total_reviews = int(count_str.replace(',', ''))
+            var tabs = document.querySelectorAll('button[role="tab"]');
+            for (var i = 0; i < tabs.length; i++) {
+                var text = tabs[i].textContent || '';
+                if (/review|reseña/i.test(text)) {
+                    var match = text.match(/\\(([\\d,\\.]+)\\)/);
+                    if (match) return parseInt(match[1].replace(/[,\\.]/g, ''));
+                }
+            }
+
+            // Method 3: Look for "X reviews" near rating
+            var spans = document.querySelectorAll('span');
+            for (var i = 0; i < spans.length; i++) {
+                var text = spans[i].textContent || '';
+                var match = text.match(/^([\\d,\\.]+)\\s*reviews?$/i);
+                if (match) return parseInt(match[1].replace(/[,\\.]/g, ''));
+            }
+
+            return null;
+        """)
+        if total_reviews:
             print(f"📊 Total reviews on page: {total_reviews}")
-                break
     except:
         pass