spa查询

src/spa_search.py

@@ -64,10 +64,9 @@ def get_report_table_html(invoice_id):
 
 
 def get_report_agreement_text(invoice_id):
-    # 关闭下载报表窗口
-    page.ele("#return-to-invoice-overview").click()
     # 点击选项卡
     page.ele("#a-autoid-2-announce").click()
+    page.wait(1)
     # 下载报表
     page.ele(f"#invoiceDownloads-{invoice_id}_3").click()
     page.wait(5)
@@ -104,10 +103,11 @@ def get_report_agreement_text(invoice_id):
 
     return data_list
 
+
 def export_item_read_data(invoice_id):
     file_name = f"spa\\{invoice_id}.xlsx"
     if os.path.isfile(file_name):
-        df = pd.read_excel(file_name)
+        df = pd.read_excel(file_name, sheet_name=None)
         return df
 
     # 获取报表表单内容
@@ -116,8 +116,9 @@ def export_item_read_data(invoice_id):
     # 提取所有链接
     links = tree.xpath('//table[@id="backup-report-table"]//a/@href')
     if len(links) == 0:
+        page.refresh()
         data_list = get_report_agreement_text(invoice_id)
-        return pd.DataFrame(data_list)
+        return {"Sheet1": pd.DataFrame(data_list)}
 
     for link in links:
         # 解析链接中的查询参数
@@ -130,7 +131,9 @@ def export_item_read_data(invoice_id):
         page.download(host + link, report_file_tmp_dir, show_msg=True)
 
         report_file = report_file_tmp_dir + "BackupReport.xls"
-        file.wait_for_downloads(report_file, 120)
+        is_down = file.wait_for_downloads(report_file, 60)
+        if is_down is False:
+            raise FileNotFoundError(f"{report_file},文件不存在")
 
         try:
             df = pd.read_excel(report_file)
@@ -160,6 +163,7 @@ def main():
     # 获取数据
     relation_data = api.sku_relations(country)  # 获取 ASIN 与 SKU 的对应关系数据
     coop_list = export_list_read_data()  # 获取合作数据列表
+    # coop_list = coop_list[140:]
     log.info(f"共计: {len(coop_list)} 条数据")
 
     # 获取当前日期和时间并格式化
@@ -180,27 +184,28 @@ def main():
             continue
 
         # 获取当前发票的 item 列表
-        item_list = export_item_read_data(invoice_id)
-        if item_list is None:
+        item_dict = export_item_read_data(invoice_id)
+        if item_dict is None:
             log.warning(f"{invoice_id} 暂无报告信息")
             continue
 
-        # 如果是字典，遍历其值
-        if isinstance(item_list, dict):
-            for i, value in enumerate(item_list.values(), start=1):
+        if len(item_dict) > 1:
+            for i, value in enumerate(item_dict.values(), start=1):
                 invoice_id_num = f"{invoice_id}-{i}"
                 processed_items = process_large_items(value, relation_data)
                 if processed_items:
                     large_sheet_data[invoice_id_num] = processed_items
-        # 如果是列表且长度 >= 10
-        elif len(item_list) >= 10:
-            processed_items = process_large_items(item_list, relation_data)
-            if processed_items:
-                large_sheet_data[invoice_id] = processed_items
         else:
-            # 如果是较小的列表
-            processed_items = process_small_items(item_list, coop, relation_data)
-            sheet_data.extend(processed_items)
+            item_list = item_dict['Sheet1']
+            # 如果是列表且长度 >= 10 则新增sheet
+            if len(item_list) >= 10:
+                processed_items = process_large_items(item_list, relation_data)
+                if processed_items:
+                    large_sheet_data[invoice_id] = processed_items
+            else:
+                # 如果是较小的列表
+                processed_items = process_small_items(item_list, coop, relation_data)
+                sheet_data.extend(processed_items)
 
         # 保存数据到 Excel 文件
     save_excel(sheet_data, large_sheet_data, new_file_name)