payment 优化

requirements.txt

@@ -4,4 +4,5 @@ xlrd==2.0.1
 pandas==2.0.3
 openpyxl==3.1.5
 pyinstaller==6.11.0
-requests==2.32.3
\ No newline at end of file
+requests==2.32.3
+redis==5.0.8
\ No newline at end of file

src/payment.py

 # coding: utf-8
 # 回款明细
+import json
 import os
 import re
 import urllib.parse
 import warnings
 
+from decimal import Decimal
 import pandas as pd
 from DrissionPage import ChromiumPage
 from DrissionPage.errors import ElementNotFoundError
 from lxml import etree
-from pandas.errors import ParserError
 
-from helper import helper, excel, file, domain, logger
+from helper import helper, excel, file, domain, logger, redisx
 
 country = None
 payeeCode = None
 
 log = logger.ConsoleLog()
+rdb = redisx.RedisClient()
 
 page = ChromiumPage()
 page.set.load_mode.normal()
@@ -79,7 +81,7 @@ def export_list_read_data():
     return merged_df
 
 
-def export_details_read_data(origin_invoice_number, invoice_number):
+def invoice_details(invoice_number):
     params = {
         "invoiceNumber": invoice_number,
         "payeeCode": payeeCode,
@@ -90,6 +92,8 @@ def export_details_read_data(origin_invoice_number, invoice_number):
     full_url = f"hz/vendor/members/inv-mgmt/invoice-details?" + query_string
     page_get(full_url)
 
+
+def export_details_read_data(origin_invoice_number,invoice_number):
     # # 读取详情内容
     file_name = f"payment\\{origin_invoice_number}.csv"
     if os.path.isfile(file_name):
@@ -98,6 +102,7 @@ def export_details_read_data(origin_invoice_number, invoice_number):
     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)
             file.wait_for_downloads(file_name)
             excel.remove_last_comma(file_name)
@@ -123,6 +128,14 @@ def get_po_code(index, po_id) -> dict:
         "po_id": po_id
     }
 
+    cache_key = "payment"
+    payment_cache = rdb.get_client().hget(cache_key, po_id)
+    if payment_cache:
+        cache_value = json.loads(payment_cache)
+        result["vendor"] = cache_value['vendor']
+        result["payment_terms"] = cache_value['payment_terms']
+        return result
+
     page_get(f"po/vendor/members/po-mgmt/order?poId={po_id}")
 
     po_table = page.ele("#po-header", timeout=5).html
@@ -131,7 +144,6 @@ def get_po_code(index, po_id) -> dict:
 
     # 获取 Vendor 内容
     result["vendor"] = get_content(tree, 2, 2)
-
     # 正则表达式查找数字和%之间的内容
     match = re.search(r'Payment Terms.*?(\d+%)', po_table)
     if match:
@@ -139,6 +151,10 @@ def get_po_code(index, po_id) -> dict:
     else:
         result["payment_terms"] = 0
 
+    cache_value = result.copy()
+    del cache_value['index']
+    rdb.get_client().hset(cache_key, po_id, json.dumps(cache_value))
+
     return result
 
 
@@ -180,49 +196,48 @@ def price_extract_data(html_content):
     return data_list
 
 
-def click_get_price_data():
-    try:
-        # 获取 Amounts 表格html
-        page_html = page.ele(".a-box-inner", timeout=3).html
-        # 使用 lxml 解析 HTML
-        tree = etree.HTML(page_html)
-        # 提取第二个 class="a-column a-span4" 下的第三个 class="a-row invoice-property-field-row" 下的 span 的值
-        price_variance_amount = tree.xpath(
-            '(//div[@class="a-column a-span4"])[2]//div[@class="a-row invoice-property-field-row"][3]//div[@class="a-column a-span6 a-span-last"]/span/text()')
-        # 检查内容是否有效
-        if price_variance_amount and price_variance_amount[0].strip() != "-":
-            while True:
-                try:
-                    page.ele("#pd", timeout=5).click()
-                    log.debug("等待争议数据加载,5秒后获取表单数据")
-                    page.wait(5)
-                    table_html = page.ele("#priceDiscrepancyWithDMSGridForm", timeout=5).html
-                    price_data = price_extract_data(table_html)
-                    return price_data
-                except ElementNotFoundError:
-                    log.warning("未获取到表数据")
-                    break
-
-        return []
-    except ElementNotFoundError:
-        page.refresh()
-        click_get_price_data()
-
-
-def handle_price_data(price_data, detail_data):
+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)
+
+    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")
+            page.wait(5)
+            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")
+            break
+
+def handle_price_data(price_data_list, invoice_amount):
     result = {}
+    invoice_amount = float(f"{invoice_amount:.2f}")
+
     """处理争议数据"""
-    for price in price_data:
-        if price['ASIN'] == detail_data.get('ASIN'):
-            result = detail_data.to_dict()
-            result['Quantity received'] = price['QUANTITY']
-            if price['RESOLUTION_DECISION'] == "Approved":
+    for data_list in price_data_list:
+        # 计算差异金额单价
+        unit_cost_float = Decimal(data_list['INVOICE_COST']) - Decimal(data_list['INITIAL_RESEARCH_COST'])
+        unit_cost = unit_cost_float * int(data_list['QUANTITY'])
+        amount = float(f"{unit_cost:.2f}")
+        if amount == invoice_amount:
+            result = data_list
+            result['Quantity received'] = data_list['QUANTITY']
+            result['UnitCost'] = unit_cost_float
+            result['Amount'] = f"${amount:.2f}"
+            if data_list['RESOLUTION_DECISION'] == "Approved":
                 result['Shortage quantity'] = 0
-                result['Amount'] = price['RESOLUTION_COST']
             else:
                 result['Shortage quantity'] = 1
-                amount = (float(price['INVOICE_COST']) - float(price['INITIAL_RESEARCH_COST'])) * int(price['QUANTITY'])
-                result['Amount'] = f"${amount:.2f}"
             break
 
     return result
@@ -264,6 +279,9 @@ def main():
     for _, data in list_data.iterrows():
         i += 1
         origin_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
@@ -274,47 +292,39 @@ def main():
         vendor = vendor_payment_terms['vendor']
         deduction_points = int(vendor_payment_terms['payment_terms'])
 
+        last_two = invoice_number[-2:]  # 取后两位
+        last_three = invoice_number[-3:]  # 取后三位
         if len(invoice_number) > 8:
-            last_two = invoice_number[-2:]  # 取后两位
-            last_three = invoice_number[-3:]  # 取后三位
             # 检查后两位是否在测试列表中
             if last_two in ["PC", "MA", "SC"]:
                 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
 
-        # 下载excel文件并读取数据
-        detail_data = export_details_read_data(origin_invoice_number, invoice_number)
-        if detail_data is None:
-            log.error("数据存在问题,请手动处理")
-            continue
-
-        # 获取争议数据
-        all_price_data = click_get_price_data()
-
-        # 初始化列表存储新字段数据
-        normal_pay_data = []
-        price_pay_data = []
-
-        for index, detail_datum in detail_data.iterrows():
-            # 正常回款数据
-            success_data = handle_data(detail_datum, vendor, deduction_points)
-            # 将处理后的记录添加到临时列表
-            normal_pay_data.append(success_data)
-
-            if all_price_data:
-                # 争议回款
-                handle_after_price_data = handle_price_data(all_price_data, detail_datum)
-                if handle_after_price_data:
-                    price_data = handle_data(handle_after_price_data, vendor, deduction_points)
-                    # 将处理后的记录添加到临时列表
-                    price_pay_data.append(price_data)
-
-        # 添加到汇总列表
-        all_normal_pay_data.append(pd.DataFrame(normal_pay_data))
-
-        if len(price_pay_data) > 0:
-            all_price_pay_data.append(pd.DataFrame(price_pay_data))
+        # 判断是否为争议订单
+        if last_three == "PCR":
+            # 获取争议数据
+            all_price_data = click_get_price_data(invoice_number)
+            # 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]))
+        else:
+            # 下载excel文件并读取数据
+            detail_data = export_details_read_data(origin_invoice_number,invoice_number)
+            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 = []
+            for index, detail_datum in detail_data.iterrows():
+                # 正常回款数据
+                success_data = handle_data(detail_datum, vendor, deduction_points)
+                # 将处理后的记录添加到临时列表
+                normal_pay_data.append(success_data)
+            # 添加到汇总列表
+            all_normal_pay_data.append(pd.DataFrame(normal_pay_data))
 
     if all_normal_pay_data:
         # 将所有数据合并为一个 DataFrame
@@ -325,6 +335,7 @@ def main():
         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")
 
+
 if __name__ == '__main__':
     try:
         country = helper.get_input_with_default("国家(目前支持[DE,FR,JP,CA,UK,US])", "US")