From e0db86252ba510496cf0fa2960f77889bb6b24f4 Mon Sep 17 00:00:00 2001
From: Rene Fichtmueller <renefichtmueller@MacStudio-von-Rene-8.local>
Date: Mon, 6 Apr 2026 01:19:25 +0200
Subject: [PATCH] fix: parsePrice requires currency symbol + uses largest
 number to avoid misreads

Root cause of fake prices (e.g. 1.30 for 800G OSFP):
- parsePrice accepted any bare number without currency symbol
- Could misread stock counts, page numbers, or CSS values as prices
- Also picked the first number, not the main price

Fix:
- Require explicit currency symbol or decimal format (1234.56)
- Use the LARGEST number found in the price string
- Returns price=0 (rejected) when no valid price pattern found
---
 packages/scraper/src/utils/hash.ts | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/packages/scraper/src/utils/hash.ts b/packages/scraper/src/utils/hash.ts
index 44a4d8c..a3d3f8a 100644
--- a/packages/scraper/src/utils/hash.ts
+++ b/packages/scraper/src/utils/hash.ts
@@ -14,16 +14,36 @@ export function contentHash(data: Record<string, unknown>): string {
  * Handles: "$12.50", "12,50 €", "US$12.50", "12.50 USD"
  */
 export function parsePrice(raw: string): { price: number; currency: string } {
-  const cleaned = raw.replace(/[^\d.,]/g, "").replace(",", ".");
-  const price = parseFloat(cleaned);
+  if (!raw) return { price: 0, currency: "USD" };
+
   const currency = raw.includes("€")
     ? "EUR"
     : raw.includes("£")
       ? "GBP"
       : raw.includes("¥")
         ? "CNY"
-        : "USD";
-  return { price: isNaN(price) ? 0 : price, currency };
+        : raw.includes("$") || raw.toLowerCase().includes("usd")
+          ? "USD"
+          : "";
+
+  // Require an explicit currency symbol OR a price pattern like "1,234.56"
+  // This prevents stock counts ("1914"), page numbers, or CSS values from being parsed as prices
+  if (!currency) {
+    // No currency symbol — only accept if the text is clearly a decimal price (e.g. "1234.56")
+    const decimalMatch = raw.match(/^\s*[\d,]+\.\d{2}\s*$/);
+    if (!decimalMatch) return { price: 0, currency: "USD" };
+  }
+
+  // Extract the numeric value: take the last price-like number in the string
+  // (handles cases like "$1,063.02" or "USD 1,063.02" or "1,063.02 USD")
+  const allNumbers = raw.match(/[\d]{1,3}(?:[,.][\d]{3})*(?:[.,]\d{1,2})?|\d+\.\d{1,2}/g);
+  if (!allNumbers || allNumbers.length === 0) return { price: 0, currency: currency || "USD" };
+
+  // Use the LARGEST number found — avoids picking up "2" from "2 in stock" over "1063.02"
+  const prices = allNumbers.map(n => parseFloat(n.replace(/,/g, "")));
+  const price = Math.max(...prices);
+
+  return { price: isNaN(price) ? 0 : price, currency: currency || "USD" };
 }
 
 /**