Refactor download and file merging logic to use ExcelConverter for improved data handling

main.py

@@ -7,6 +7,8 @@ import re
 import os
 import pandas as pd
 from time import sleep
+from utils.excel_converter import ExcelConverter
+
 
 def read_order_ids(file_path):
     """读取订单号文件"""
@@ -15,11 +17,13 @@ def read_order_ids(file_path):
         order_ids = [line.strip() for line in f if line.strip()]
     return order_ids
 
+
 def group_order_ids(order_ids, group_size=100):
     """将订单号分组"""
     for i in range(0, len(order_ids), group_size):
         yield order_ids[i:i + group_size]
 
+
 def download_batch(inner_frame, order_ids, batch_index, page1, debug_mode=False, debug_batch=None):
     """下载一批订单号的数据"""
     # 清空文本框
@@ -32,7 +36,7 @@ def download_batch(inner_frame, order_ids, batch_index, page1, debug_mode=False,
     # 点击查询
     inner_frame.locator(".search-component-searchBtn").click()
     print(f"第 {batch_index + 1} 批查询完成，等待加载结果...")
-    #sleep(3)
+
     # 等待加载完成
     loading_locator = inner_frame.locator("div").filter(has_text="加载中").nth(1)
     try:
@@ -80,19 +84,23 @@ def download_batch(inner_frame, order_ids, batch_index, page1, debug_mode=False,
 
     return download_path
 
-def merge_excel_files(file_paths, output_path):
-    """合并多个 Excel 文件"""
+
+def convert_and_merge_files(file_paths, output_path):
+    """使用 ExcelConverter 转换并合并所有文件"""
+    converter = ExcelConverter(verbose=False)  # 不打印详细日志
     all_dataframes = []
 
-    for file_path in file_paths:
-        df = pd.read_excel(file_path)
+    for i, file_path in enumerate(file_paths, 1):
+        print(f"转换第 {i} 个文件: {file_path}")
+        df = converter.convert(file_path, output_file=None)  # 只转换，不保存
         all_dataframes.append(df)
-        print(f"已读取: {file_path}, 共 {len(df)} 行")
+        print(f"  提取到 {len(df)} 条记录")
 
     if all_dataframes:
+        print(f"\n合并 {len(all_dataframes)} 个文件的数据...")
         merged_df = pd.concat(all_dataframes, ignore_index=True)
         merged_df.to_excel(output_path, index=False)
-        print(f"合并完成: {output_path}, 总共 {len(merged_df)} 行")
+        print(f"合并完成: {output_path}, 总共 {len(merged_df)} 条记录")
 
         # 删除临时文件
         for file_path in file_paths:
@@ -102,6 +110,7 @@ def merge_excel_files(file_paths, output_path):
         return output_path
     return None
 
+
 def main():
     with sync_playwright() as playwright:
         # 调用登录模块
@@ -132,7 +141,7 @@ def main():
         inner_frame.locator(".search-name-wrapper > .iconfont").click()
         inner_frame.get_by_text("订单号查询").click()
         inner_frame.get_by_role("tab", name="全部").click()
-        
+
         # 填充并验证，如果失败则重试
         max_retries = 3
         expected_value = "5000"
@@ -162,20 +171,16 @@ def main():
         downloaded_files = []
         for batch_index, order_ids_batch in enumerate(group_order_ids(order_ids, 100)):
             print(f"\n=== 开始处理第 {batch_index + 1} 批，共 {len(order_ids_batch)} 个订单号 ===")
-            downloaded_file = download_batch(inner_frame, order_ids_batch, batch_index, page1, debug_mode=False, debug_batch=1)
+            downloaded_file = download_batch(inner_frame, order_ids_batch, batch_index, page1, debug_mode=False, debug_batch=None)
             downloaded_files.append(downloaded_file)
 
-        # 合并文件
-        if len(downloaded_files) > 1:
-            print(f"\n=== 开始合并 {len(downloaded_files)} 个文件 ===")
+        # 转换并合并文件
+        if downloaded_files:
+            print(f"\n=== 开始转换并合并 {len(downloaded_files)} 个文件 ===")
             final_output = "D:/python/playwrite/data/离散备料计划维护_合并.xlsx"
-            merge_excel_files(downloaded_files, final_output)
+            convert_and_merge_files(downloaded_files, final_output)
         else:
-            print("\n只下载了一个文件，无需合并")
-            final_output = downloaded_files[0]
-            # 重命名为最终文件名
-            os.rename(final_output, "D:/python/playwrite/data/离散备料计划维护_合并.xlsx")
-            final_output = "D:/python/playwrite/data/离散备料计划维护_合并.xlsx"
+            print("\n没有下载到任何文件")
 
         print(f"\n=== 全部完成 ===")
         print(f"最终文件: {final_output}")
@@ -186,5 +191,6 @@ def main():
         context.close()
         browser.close()
 
+
 if __name__ == "__main__":
     main()