payment 优化

src/payment.py

@@ -5,6 +5,7 @@ import os
 import re
 import urllib.parse
 import warnings
+from datetime import datetime
 
 from decimal import Decimal
 import pandas as pd
@@ -81,7 +82,19 @@ def export_list_read_data():
     return merged_df
 
 
-def invoice_details(invoice_number):
+def invoice_details(invoice_number,last_two,last_three):
+    if len(invoice_number) > 8:
+        # 检查后两位是否在测试列表中
+        if last_two in ["MA", "PC"]:
+            invoice_number = invoice_number[:-2]  # 去掉后两位
+        if last_three in ["PCR"]:
+            invoice_number = invoice_number[:-3]  # 去掉最后三位
+        if last_three in ["+SC", "SC-"]:
+            invoice_number = invoice_number[:-3]  # 去掉最后三位
+            invoice_number = invoice_number + 'SCR'
+        if last_two == "SC":
+            invoice_number = invoice_number + 'R'
+
     params = {
         "invoiceNumber": invoice_number,
         "payeeCode": payeeCode,
@@ -93,17 +106,11 @@ def invoice_details(invoice_number):
     page_get(full_url)
 
 
-def export_details_read_data(invoice_number):
-    # # 读取详情内容
-    file_name = f"payment\\{invoice_number}.csv"
-    if os.path.isfile(file_name):
-        return pd.read_csv(file_name)
-
+def export_details_read_data(file_name):
     count = 0
     while True:
         try:
-            invoice_details(invoice_number)
-            page.ele("#line-items-export-to-spreadsheet-announce", timeout=3).click.to_download(rename=file_name)
+            page.ele("#line-items-export-to-spreadsheet-announce").click.to_download(rename=file_name)
             file.wait_for_downloads(file_name)
             excel.remove_last_comma(file_name)
             break
@@ -128,6 +135,8 @@ def get_po_code(index, po_id) -> dict:
         "po_id": po_id
     }
 
+    po_id = po_id[:8]
+
     cache_key = "payment"
     payment_cache = rdb.get_client().hget(cache_key, po_id)
     if payment_cache:
@@ -196,16 +205,9 @@ def price_extract_data(html_content):
     return data_list
 
 
-def click_get_price_data(invoice_number):
-    cache_key = "price_data"
-    cache_value = rdb.get_client().hget(cache_key, invoice_number)
-    if cache_value:
-        return json.loads(cache_value)
-
+def click_get_price_data():
     while True:
         try:
-            # 进入详情页
-            invoice_details(invoice_number)
             # 点击争议价tab
             page.ele("#pd").click()
             log.debug("等待争议数据加载,5秒后获取表单数据")
@@ -213,7 +215,6 @@ def click_get_price_data(invoice_number):
             table_html = page.ele("#priceDiscrepancyWithDMSGridForm", timeout=5).html
             # 抓取表单数据
             price_data = price_extract_data(table_html)
-            rdb.get_client().hset(cache_key, invoice_number, json.dumps(price_data))
             return price_data
         except ElementNotFoundError:
             log.warning("未获取到表数据")
@@ -259,6 +260,7 @@ def handle_data(detail_datum, vendor, deduction_points):
 
     # 复制原始行数据，避免直接修改
     record = detail_datum.copy()
+    record.update({"Amount": amount})
     record["IsFinished"] = is_finished
     record["DeductionPoints"] = f"{deduction_points}%"  # 拼接百分号
     record["Code"] = vendor
@@ -266,11 +268,17 @@ def handle_data(detail_datum, vendor, deduction_points):
 
     return record
 
-
 def main():
     list_data = export_list_read_data()
     # list_data = list_data[25:]
-    excel.save_xls(list_data, "回款数据.xlsx", "Remittance payments")
+
+    # 获取当前日期和时间并格式化
+    current_datetime = datetime.now().strftime('%Y-%m-%d_%H-%M')  # 格式化为 'YYYY-MM-DD_HH-MM-SS'
+    # 原文件名
+    file_name = "回款数据.xlsx"
+    # 拼接新的文件名
+    new_file_name = f"{current_datetime}_{file_name}"
+    excel.save_xls(list_data, new_file_name, "Remittance payments")
     log.info(f"共计：{len(list_data)} 订单")
 
     all_normal_pay_data = []
@@ -278,43 +286,50 @@ def main():
     i = 0
     for _, data in list_data.iterrows():
         i += 1
-        origin_invoice_number = data.get("Invoice Number")
+        invoice_number = data.get("Invoice Number")
         invoice_amount = data.get("Invoice Amount")
 
-        invoice_number = origin_invoice_number
         # 获取当前订单的Payee和优惠比例
-        vendor_payment_terms = get_po_code(i, invoice_number[:8])
-        vendor_payment_terms['invoice_number'] = origin_invoice_number
+        vendor_payment_terms = get_po_code(i, invoice_number)
         log.info(vendor_payment_terms)
 
         vendor = vendor_payment_terms['vendor']
         deduction_points = int(vendor_payment_terms['payment_terms'])
 
+        # 处理单号主要为了进入详情页
         last_two = invoice_number[-2:]  # 取后两位
         last_three = invoice_number[-3:]  # 取后三位
-        if len(invoice_number) > 8:
-            # 检查后两位是否在测试列表中
-            if last_two in ["MA", "PC"]:
-                invoice_number = invoice_number[:-2]  # 去掉后两位
-            if last_three in ["PCR", "+SC", "SC-"]:
-                invoice_number = invoice_number[:-3]  # 去掉最后三位
-            if last_two == "SC":
-                invoice_number = invoice_number + 'R'
 
         # 判断是否为争议订单
         if last_three == "PCR" or last_two == "PC":
-            # 获取争议数据
-            all_price_data = click_get_price_data(invoice_number)
+            cache_key = "price_data"
+            price_data = rdb.get_client().hget(cache_key, invoice_number)
+            if price_data is None:
+                # 进入详情页
+                invoice_details(invoice_number, last_two, last_three)
+                # 获取争议数据
+                price_data = click_get_price_data()
+                # 缓存数据
+                rdb.get_client().hset(cache_key, invoice_number, json.dumps(price_data))
+            else:
+                price_data = json.loads(price_data)
+
             # 争议回款
-            handle_after_price_data = handle_price_data(all_price_data, invoice_amount)
-            price_data = handle_data(handle_after_price_data, vendor, deduction_points)
-            all_price_pay_data.append(pd.DataFrame(price_data, index=[0]))
+            handle_after_price_data = handle_price_data(price_data, invoice_amount)
+            format_price_data = handle_data(handle_after_price_data, vendor, deduction_points)
+            all_price_pay_data.append(pd.DataFrame(format_price_data, index=[0]))
         else:
-            # 下载excel文件并读取数据
-            detail_data = export_details_read_data(invoice_number)
-            if detail_data is None:
-                log.error("数据存在问题,请手动处理")
-                continue
+            file_name = f"payment\\{invoice_number}.csv"
+            if os.path.isfile(file_name):
+                detail_data = pd.read_csv(file_name)
+            else:
+                # 进入详情页
+                invoice_details(invoice_number, last_two, last_three)
+                # 下载excel文件并读取数据
+                detail_data = export_details_read_data(file_name)
+                if detail_data is None:
+                    log.error("数据存在问题,请手动处理")
+                    continue
 
             # 初始化列表存储新字段数据
             normal_pay_data = []
@@ -329,11 +344,11 @@ def main():
     if all_normal_pay_data:
         # 将所有数据合并为一个 DataFrame
         normal_pay_summary = pd.concat(all_normal_pay_data, ignore_index=True)
-        excel.save_xls(normal_pay_summary, "回款数据.xlsx", "正常回款导出明细")
+        excel.save_xls(normal_pay_summary, new_file_name, "正常回款导出明细")
 
     if all_price_pay_data:
         price_pay_summary = pd.concat(all_price_pay_data, ignore_index=True)
-        excel.save_xls(price_pay_summary, "回款数据.xlsx", "Price导出明细")
+        excel.save_xls(price_pay_summary, new_file_name, "Price导出明细")
 
 
 if __name__ == '__main__':