处理

coop.py

@@ -50,9 +50,9 @@ def export_list_read_data():
 
 
 def get_report_table_html(invoice_id):
-    page.get(f"https://vendorcentral.amazon.com/hz/vendor/members/coop?searchText={invoice_id}")
-
+    while True:
         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
@@ -60,10 +60,14 @@ def get_report_table_html(invoice_id):
             time.sleep(1)
             # 获取报表表单内容
             report_table_html = page.ele("#backup-report-table").html
+            if report_table_html is None or report_table_html == "":
+                print("表单内容为空,刷新网页")
+                page.refresh()
+                continue
             return report_table_html
         except ElementNotFoundError:
+            print("元素未找到,刷新网页")
             page.refresh()
-        get_report_table_html(invoice_id)
 
 def export_item_read_data(invoice_id):
     file_name = f"coop\\{invoice_id}.xlsx"
@@ -110,7 +114,7 @@ def export_item_read_data(invoice_id):
 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[:10]
+    coop_list = coop_list[:10]
     print(f"共计:{len(coop_list)},条数据")
 
     i = 0
@@ -180,7 +184,7 @@ def main():
     if sheet_data:
         # 循环遍历 sheet_data 字典
         for key, value in sheet_data.items():
-            if len(value) > 10000:
+            if len(value) > 5000:
                 max_sheet_data[key] = value
                 continue
 

invoices.py

@@ -29,18 +29,22 @@ warnings.filterwarnings("ignore", category=UserWarning, module="openpyxl")
 
 def export_list_read_data():
     file_name = 'Payments.xlsx'
-    if not os.path.isfile(file_name):
+    if os.path.isfile(file_name):
+        df = pd.read_excel(file_name)
+        return df
+
     page.get(f"https://vendorcentral.amazon.com/hz/vendor/members/remittance/home", timeout=3)
     page.ele("#remittance-home-select-all", timeout=2).click()
     page.ele("#remittance-home-export-link", timeout=2).click.to_download()
     file.wait_for_downloads(file_name)
 
-    df = pd.read_excel(file_name, skiprows=22)
+    df = pd.read_excel(file_name, skiprows=21)
     # 定义正则表达式模式，匹配包含 'Price' 或 'PCR' 或 'XXXXXXXX/XXXX/' 的描述
     pattern = r'Price Claim|PCR|Missed Adjustment|Shortage Claim|^[A-Z0-9]{8}/[A-Z0-9]{4}/'
     # 过滤符合条件的行
-    return df[df['Description'].str.contains(pattern, na=False, regex=True)]
-
+    data = df[df['Description'].str.contains(pattern, na=False, regex=True)]
+    excel.save_xls(data,"Payments.xlsx","Remittance payments")
+    return df
 
 def export_details_read_data(invoice_number):
     # 读取详情内容
@@ -55,7 +59,7 @@ def export_details_read_data(invoice_number):
         # 将字典转换为 URL 查询参数
         query_string = urllib.parse.urlencode(params)
         page.get(
-            f"https://vendorcentral.amazon.com/hz/vendor/members/inv-mgmt/invoice-details" + query_string)
+            f"https://vendorcentral.amazon.com/hz/vendor/members/inv-mgmt/invoice-details?" + query_string)
 
         if not os.path.isfile(file_name):
             page.ele("#line-items-export-to-spreadsheet-announce", timeout=5).click.to_download(rename=file_name)
@@ -212,7 +216,6 @@ def handle_data(detail_datum, vendor, deduction_points):
 
 def main():
     list_data = export_list_read_data()
-    excel.save_xls(list_data, "回款数据.xlsx", "Remittance payments")
     # list_data = list_data[62:]
     print(f"共计：{len(list_data)} 订单")
     all_normal_pay_data = []