1. 第一列“商品ID”这一列进行填充，从1开始增

2. 如果变体的标题跟主商品不一致，请打印一条错误日志，并且忽略这一条数据

1. 第一列“商品ID”这一列进行填充，从1开始增
2. 如果变体的标题跟主商品不一致，请打印一条错误日志，并且忽略这一条数据
tangwang
1 parent 50170c5a
Showing 1 changed file with 32 additions and 3 deletions Show diff stats
scripts/amazon_xlsx_to_shoplazza_xlsx.py
@@ -458,16 +458,45 @@ def main():
     # 先按 SPU 构造每个组的行，方便做“按最大行数拆分但不拆组”
     group_rows_list = []  # List[List[dict]]
     spu_count = 0
+    next_product_id = 1  # 用于填充商品ID，全局自增
+
     for spu_id, variants in groups.items():
         if not variants:
             continue
+
+        # 过滤掉标题与主商品不一致的变体
+        main_title = variants[0].get("商品标题") or ""
+        filtered = []
+        for v in variants:
+            title = v.get("商品标题") or ""
+            if main_title and title and title != main_title:
+                print(
+                    f"SKIP variant due to title mismatch: SPU={spu_id}, ASIN={v.get('ASIN')}, "
+                    f"main_title='{main_title}', variant_title='{title}'",
+                    flush=True,
+                )
+                continue
+            filtered.append(v)
+
+        if not filtered:
+            # 整个SPU都被过滤掉
+            continue
+
         spu_count += 1
         if args.max_products is not None and spu_count > int(args.max_products):
             break
-        if len(variants) == 1:
-            group_rows_list.append([build_s_row(variants[0])])
+
+        if len(filtered) == 1:
+            rows = [build_s_row(filtered[0])]
         else:
-            group_rows_list.append(build_m_p_rows(variants))
+            rows = build_m_p_rows(filtered)
+
+        # 填充商品ID（从1开始全局递增）
+        for r in rows:
+            r["商品ID"] = next_product_id
+            next_product_id += 1
+
+        group_rows_list.append(rows)
  
     # 按最大行数拆成多个文件（注意：同一 SPU 不拆分）
     data_start_row = 4  # 与模板/写入工具保持一致