spa数据查询

coop.py

 # coding: utf-8
 # 回款明细
+import math
 import os
+import shutil
+import time
+from urllib.parse import urlparse, parse_qs
 
 import pandas as pd
 from DrissionPage import ChromiumPage
-from DrissionPage.errors import PageDisconnectedError, ElementNotFoundError
+from DrissionPage.errors import ElementNotFoundError
+from lxml import etree
 
-from helper import helper
+from helper import helper, file, excel
 
 page = ChromiumPage()
 page.set.load_mode.eager()
@@ -20,6 +25,16 @@ helper.make_dir(download_path)
 page.set.download_path(download_path)
 
 
+def asin_sku_relations():
+    relations_dict = {}
+    df = pd.read_excel('relations.xlsx')
+    for index, row in df.iterrows():
+        row_dict = row.to_dict()
+        relations_dict[row_dict['ASIN']] = {"SKU": row_dict['SKU'], "NAME": row_dict['NAME']}
+
+    return relations_dict
+
+
 def export_list_read_data():
     file_name = "ContraCogsInvoices.xls"
     if not os.path.isfile(file_name):
@@ -36,15 +51,52 @@ def export_list_read_data():
 
 def export_item_read_data(invoice_id):
     try:
-        file_name = f"coop\\{invoice_id}.csv"
-        if not os.path.isfile(file_name):
-            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
-            file_name = f"coop\\{invoice_id}.csv"
-            page.ele(f"#invoiceDownloads-{invoice_id}_1").click.to_download(rename=file_name).wait()
-            return pd.read_csv(file_name, engine='python', on_bad_lines='skip')
+        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)
+
+        # 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)
+
     except ElementNotFoundError:
         print("导出按钮不存在刷新网页")
         page.refresh()
@@ -52,19 +104,67 @@ def export_item_read_data(invoice_id):
 
 
 def main():
-    coop_data = export_list_read_data()
-    for _, data in coop_data.iterrows():
-        # 根据回款id搜索下载报表
-        invoice_id = data.get("Invoice ID")
-        print(invoice_id)
-        export_item_read_data(invoice_id)
+    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
+
+    print(f"共计:{len(coop_list)},条数据")
+
+    i = 0
+
+    new_coop_data = []
+    for _, coop in coop_list.iterrows():
+        if i == 20: break
+
+        i += 1
+        invoice_id = coop.get("Invoice ID")  # 获取发票 ID
+        print({"index": i, "invoice_id": invoice_id})
+
+        item_coop_data = []
+        # 根据发票 ID 获取 item 列表
+        item_list = export_item_read_data(invoice_id)
+        for _, item in item_list.iterrows():
+            asin = item.get("Asin")
+
+            # 判断 ASIN 是否为空或无效
+            if not asin or (isinstance(asin, float) and math.isnan(asin)):
+                break
+
+            relation = relation_data.get(asin)
+
+            # 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'] = ""
+                item_coop_data.append(item)
+                continue  # 跳过当前条目，继续下一个
+
+            # 如果 item_list 长度大于 10，使用原有数据
+            if len(item_list) >= 10:
+                new_item = item.copy()
+                new_item['Asin'] = asin
+                new_item['ERP SKU'] = relation.get("SKU")
+                new_item['Group Name'] = relation.get("NAME")
+                item_coop_data.append(new_item)
+            else:
+                # 否则新建一个条目
+                new_item = coop.copy()
+                new_item['Asin'] = asin
+                new_item['ERP SKU'] = relation.get("SKU")
+                new_item['Group Name'] = relation.get("NAME")
+                new_coop_data.append(new_item)
+
+            # 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)
+
+    # 保存最终的合作数据
+    if new_coop_data:
+        excel.save_xls(new_coop_data, 'SPA查询.xlsx')
+
+    page.close()  # 关闭页面
 
-    page.close()
 
 if __name__ == '__main__':
-    try:
-        main()
-    except KeyboardInterrupt:
-        pass
-    except PageDisconnectedError as e:
-        print("与页面的连接已断开")
+    main()

invoices.py

@@ -55,7 +55,7 @@ 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)