spa数据查询

coop.py

@@ -11,7 +11,7 @@ from DrissionPage import ChromiumPage
 from DrissionPage.errors import ElementNotFoundError
 from lxml import etree
 
-from helper import helper, file, excel
+from helper import helper, excel, file
 
 page = ChromiumPage()
 page.set.load_mode.eager()
@@ -49,69 +49,73 @@ def export_list_read_data():
     return pd.read_excel(file_name, engine='xlrd')
 
 
-def export_item_read_data(invoice_id):
+def get_report_table_html(invoice_id):
+    page.get(f"https://vendorcentral.amazon.com/hz/vendor/members/coop?searchText={invoice_id}")
+
     try:
-        page.get(f"https://vendorcentral.amazon.com/hz/vendor/members/coop?searchText={invoice_id}")
         # 点击选项卡
         page.ele("#a-autoid-2-announce").click()
         # 下载报表
         page.ele(f"#invoiceDownloads-{invoice_id}_2").click()
-        time.sleep(2)
-
+        time.sleep(1)
         # 获取报表表单内容
         report_table_html = page.ele("#backup-report-table").html
-        tree = etree.HTML(report_table_html)
-        # 提取所有链接
-        links = tree.xpath('//table[@id="backup-report-table"]//a/@href')
-        for link in links:
-            # 解析链接中的查询参数
-            parsed_url = urlparse(link)
-            query_params = parse_qs(parsed_url.query)
-            # 提取 filename 参数
-            filename = query_params.get('fileName', ['未找到文件名'])[0]
-
-            report_file_dir = f"coop\\{invoice_id}"
-            report_file_tmp_dir = f"{report_file_dir}\\{filename}\\"
-
-            full_url = "https://vendorcentral.amazon.com" + link
-            page.download(full_url, report_file_tmp_dir, show_msg=False)
-
-            report_file = report_file_tmp_dir + "BackupReport.xls"
-            file.wait_for_downloads(report_file)
-
-            try:
-                df = pd.read_excel(report_file)
-                # 获取表头
-                headers = df.columns.tolist()
-                # 要检查的列名
-                column_names_to_check = ["Rebate In Agreement Currency", "Vendor Funding In Agreement Currency"]
-                # 判断头文件是否满足读取条件,不满足删除文件夹
-                header_is_normal = any(column in headers for column in column_names_to_check)
-                if not header_is_normal:
-                    shutil.rmtree(report_file_tmp_dir)
-                    continue
-
-                df = df[df['Asin'].notna()]
-                return df
-            except ValueError:
-                # 递归删除文件夹
-                shutil.rmtree(report_file_tmp_dir)
-
+        return report_table_html
     except ElementNotFoundError:
-        print("导出按钮不存在刷新网页")
         page.refresh()
-        export_item_read_data(invoice_id)
+
+def export_item_read_data(invoice_id):
+    file_name = f"coop\\{invoice_id}.xlsx"
+    if os.path.isfile(file_name):
+        df = pd.read_excel(file_name)
+        return df
+
+    # 获取报表表单内容
+    report_table_html = get_report_table_html(invoice_id)
+    tree = etree.HTML(report_table_html)
+    # 提取所有链接
+    links = tree.xpath('//table[@id="backup-report-table"]//a/@href')
+    for link in links:
+        # 解析链接中的查询参数
+        parsed_url = urlparse(link)
+        query_params = parse_qs(parsed_url.query)
+        # 提取 filename 参数
+        filename = query_params.get('fileName', ['未找到文件名'])[0]
+        report_file_tmp_dir = f"coop\\{invoice_id}\\{filename}\\"
+        page.download("https://vendorcentral.amazon.com" + link, report_file_tmp_dir, show_msg=True)
+
+        report_file = report_file_tmp_dir + "BackupReport.xls"
+        file.wait_for_downloads(report_file)
+
+        try:
+            df = pd.read_excel(report_file)
+            # 获取表头
+            headers = df.columns.tolist()
+            # 要检查的列名
+            column_names_to_check = ["Rebate In Agreement Currency", "Vendor Funding In Agreement Currency"]
+            # 判断头文件是否满足读取条件,不满足删除文件夹
+            header_is_normal = any(column in headers for column in column_names_to_check)
+            if not header_is_normal:
+                continue
+
+            data = df[df['Asin'].notna()]
+            excel.save_xls(data, file_name)
+            shutil.rmtree(f"coop\\{invoice_id}")
+            return pd.read_excel(file_name)
+        except ValueError:
+            pass
 
 
 def main():
     relation_data = asin_sku_relations()  # 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[:189]
     print(f"共计:{len(coop_list)},条数据")
 
     i = 0
 
     new_coop_data = []
+    sheet_data = {}
     for _, coop in coop_list.iterrows():
         i += 1
         invoice_id = coop.get("Invoice ID")  # 获取发票 ID
@@ -120,6 +124,10 @@ def main():
         item_coop_data = []
         # 根据发票 ID 获取 item 列表
         item_list = export_item_read_data(invoice_id)
+        if item_list is None:
+            print(f"{invoice_id} 暂无报告信息")
+            continue
+
         for _, item in item_list.iterrows():
             asin = item.get("Asin")
 
@@ -131,7 +139,6 @@ def main():
 
             # 如果未匹配到 SKU，记录空值
             if not relation:
-                print(f"未匹配到 SKU:{asin}")
                 item['Asin'] = asin
                 item['ERP SKU'] = ""
                 item['Group Name'] = ""
@@ -155,12 +162,27 @@ def main():
 
             # 保存已处理的 item 数据到 Excel 文件中
         if item_coop_data:
-            excel.save_xls(item_coop_data, 'SPA查询.xlsx', invoice_id)
+            sheet_data[invoice_id] = item_coop_data
 
     # 保存最终的合作数据
     if new_coop_data:
         excel.save_xls(new_coop_data, 'SPA查询.xlsx')
 
+    max_sheet_data = {}
+
+    if sheet_data:
+        # 循环遍历 sheet_data 字典
+        for key, value in sheet_data.items():
+            if len(value) > 10000:
+                max_sheet_data[key] = value
+                continue
+
+            excel.save_xls(value, 'SPA查询.xlsx', key)
+
+    if max_sheet_data:
+        for key, value in max_sheet_data.items():
+            excel.save_xls(value, 'SPA查询.xlsx', key)
+
     page.close()  # 关闭页面
 
 

helper/file.py

@@ -14,7 +14,7 @@ def wait_for_downloads(file_name, timeout=60):
         files = os.path.isfile(file_name)
         if files:
             return True
-        time.sleep(1)
+        time.sleep(0.5)
     return False