From 3180ccacb8fde494d1d38fca324d3dacc4e1c1a9 Mon Sep 17 00:00:00 2001 From: Misaka_Company Date: Thu, 5 Feb 2026 15:17:18 +0800 Subject: [PATCH] feat: enhance progress reporting granularity in data extraction workflow - Break down query phase into 3 detailed steps (read file, query database, complete) - Split download batch process into 7 granular steps per batch (clear, fill, search, wait, select, configure, download) - Divide conversion phase into 2 steps per file plus 3 final steps (merge, cleanup) - Add 'action' parameter to all progress reports for better categorization - Improve user feedback with more detailed status messages and completion indicators Co-Authored-By: Claude Sonnet 4.5 --- utils/离散备料计划维护数据提取.py | 275 +++++++++++++++++++++--------- 1 file changed, 193 insertions(+), 82 deletions(-) diff --git a/utils/离散备料计划维护数据提取.py b/utils/离散备料计划维护数据提取.py index a5ca9c0..331115b 100644 --- a/utils/离散备料计划维护数据提取.py +++ b/utils/离散备料计划维护数据提取.py @@ -84,10 +84,29 @@ class DiscreteMaterialPlanExtractor: Returns: 生产订单号列表 """ + if report_progress: + self._report_progress( + "query", + 1, + 3, + "正在读取总排号文件...", + action="read_file", + ) + # 读取总排号 production_ids = read_production_ids(production_id_file) self._print(f"从文件读取到 {len(production_ids)} 个总排号") + if report_progress: + self._report_progress( + "query", + 2, + 3, + f"正在查询数据库（{len(production_ids)} 个总排号）...", + action="query_database", + production_id_count=len(production_ids), + ) + # 查询数据库获取生产订单号 order_ids = query_production_order_numbers(production_ids) self._print(f"查询到 {len(order_ids)} 个生产订单号") @@ -95,10 +114,11 @@ class DiscreteMaterialPlanExtractor: if report_progress: self._report_progress( "query", - 1, - 1, - f"查询到 {len(order_ids)} 个生产订单号", - count=len(order_ids), + 3, + 3, + f"查询完成：获取到 {len(order_ids)} 个生产订单号", + action="query_complete", + order_id_count=len(order_ids), ) return order_ids @@ -123,18 +143,51 @@ class DiscreteMaterialPlanExtractor: import re import time - # 清空文本框 + # 步骤1：清空文本框 + self._report_progress( + "download", + batch_index * 7 + 1, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 准备输入订单号", + batch_index=batch_index + 1, + action="clear_textbox", + ) textbox = inner_frame.get_by_role("textbox", name="来源生产订单号") textbox.fill("") - # 填充订单号 + # 步骤2：填充订单号 + self._report_progress( + "download", + batch_index * 7 + 2, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 输入 {len(order_ids)} 个订单号", + batch_index=batch_index + 1, + action="fill_order_ids", + order_count=len(order_ids), + ) textbox.fill(",".join(order_ids)) - # 点击查询 + # 步骤3：点击查询 + self._report_progress( + "download", + batch_index * 7 + 3, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 提交查询请求", + batch_index=batch_index + 1, + action="click_search", + ) inner_frame.locator(".search-component-searchBtn").click() self._print(f"第 {batch_index + 1} 批查询完成，等待加载结果...") - # 等待加载完成 + # 步骤4：等待加载完成 + self._report_progress( + "download", + batch_index * 7 + 4, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 等待数据加载...", + batch_index=batch_index + 1, + action="wait_loading", + ) loading_locator = inner_frame.locator("div").filter(has_text="加载中").nth(1) try: loading_locator.wait_for(state="visible", timeout=3000) @@ -149,9 +202,27 @@ class DiscreteMaterialPlanExtractor: self._print(f"=== 调试暂停：第 {batch_index + 1} 批 ===") page1.pause() - # 选择所有数据 + # 步骤5：选择所有数据 + self._report_progress( + "download", + batch_index * 7 + 5, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 选择所有数据行", + batch_index=batch_index + 1, + action="select_all_rows", + ) inner_frame.get_by_role("row", name="序号").get_by_label("").click() + # 步骤6：配置并触发导出 + self._report_progress( + "download", + batch_index * 7 + 6, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 配置导出参数", + batch_index=batch_index + 1, + action="configure_export", + ) + # 点击输出 inner_frame.get_by_role("button", name="更多").hover() inner_frame.get_by_text("输出", exact=True).click() @@ -164,7 +235,15 @@ class DiscreteMaterialPlanExtractor: ) input_box.fill("300000") - # 下载文件 + # 步骤7：下载文件 + self._report_progress( + "download", + batch_index * 7 + 7, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批 - 正在下载文件...", + batch_index=batch_index + 1, + action="downloading_file", + ) download_path = f"D:/python/playwrite/data/temp_batch_{batch_index + 1}.xlsx" with page1.expect_download() as download_info: inner_frame.get_by_role("button", name="确定(Y)").click() @@ -173,21 +252,17 @@ class DiscreteMaterialPlanExtractor: download.save_as(download_path) self._print(f"第 {batch_index + 1} 批下载完成: {download_path}") - # 报告进度 + # 报告批次完成 self._report_progress( "download", - batch_index + 1, - total_batches, - f"第 {batch_index + 1}/{total_batches} 批下载完成", + (batch_index + 1) * 7, + total_batches * 7, + f"第 {batch_index + 1}/{total_batches} 批下载完成 ✓", batch_index=batch_index + 1, + action="batch_complete", + file_path=download_path, ) - # 关闭输出对话框（如果有的话） - # try: - # inner_frame.get_by_role("button", name="取消").click() - # except: - # pass - # 等待页面恢复，准备下一次查询 time.sleep(1) @@ -204,37 +279,77 @@ class DiscreteMaterialPlanExtractor: self._print(f"输出目录: {output_dir}") self._print(f"输出文件名: {output_filename}") - # 确保输出文件的父目录存在 + # 步骤1：检查并创建输出目录 + self._report_progress( + "convert", + 1, + len(file_paths) * 2 + 3, + "准备转换：检查输出目录", + action="check_directory", + ) + if output_dir and not os.path.exists(output_dir): self._print(f"创建输出目录: {output_dir}") os.makedirs(output_dir) all_dataframes = [] + # 步骤2-N：转换每个文件 for i, file_path in enumerate(file_paths, 1): self._print(f"转换第 {i} 个文件: {file_path}") - # 报告进度 + # 报告开始转换 self._report_progress( "convert", - i, - len(file_paths), - f"转换第 {i}/{len(file_paths)} 个文件", + 1 + (i - 1) * 2 + 1, + len(file_paths) * 2 + 3, + f"正在转换文件 {i}/{len(file_paths)}", file_index=i, file_path=file_path, + action="converting_file", ) df = self.converter.convert(file_path, output_file=None) # 只转换，不保存 all_dataframes.append(df) self._print(f" 提取到 {len(df)} 条记录") + + # 报告转换完成 + self._report_progress( + "convert", + 1 + (i - 1) * 2 + 2, + len(file_paths) * 2 + 3, + f"文件 {i}/{len(file_paths)} 转换完成（{len(df)} 条记录）", + file_index=i, + record_count=len(df), + action="file_converted", + ) if all_dataframes: + # 步骤N+1：合并数据 + self._report_progress( + "convert", + len(file_paths) * 2 + 2, + len(file_paths) * 2 + 3, + f"正在合并 {len(all_dataframes)} 个文件的数据...", + action="merging_data", + file_count=len(all_dataframes), + ) + self._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) self._print(f"合并完成: {output_path}, 总共 {len(merged_df)} 条记录") - # 删除临时文件 + # 步骤N+2：删除临时文件 + self._report_progress( + "convert", + len(file_paths) * 2 + 3, + len(file_paths) * 2 + 3, + f"清理临时文件...", + action="cleanup", + total_records=len(merged_df), + ) + for file_path in file_paths: os.remove(file_path) self._print(f"已删除临时文件: {file_path}") @@ -243,21 +358,23 @@ class DiscreteMaterialPlanExtractor: return None def setup_query_interface(self, inner_frame): - """设置查询界面""" + """设置查询界面（不报告进度，由 extract 统一报告）""" import re - # 点击图标按钮打开查询界面 + # 打开查询界面 inner_frame.locator(".search-name-wrapper > .iconfont").click() inner_frame.get_by_text("订单号查询").click() + + # 选择"全部"标签 inner_frame.get_by_role("tab", name="全部").click() - # 填充并验证，如果失败则重试 + # 填充并验证 max_retries = 3 expected_value = "5000" for attempt in range(max_retries): inner_frame.locator("#rc_select_0").fill(expected_value) inner_frame.locator("#rc_select_0").press("Enter") - # 检查填充是否成功 + actual_value = inner_frame.locator("#rc_select_0").input_value() if actual_value == expected_value: self._print(f"文本框填充成功: {expected_value}") @@ -280,28 +397,21 @@ class DiscreteMaterialPlanExtractor: debug_batch=None, progress_callback=None, ): - """ - 执行完整的数据提取流程 - - Args: - production_id_file: ProductionID.txt 文件路径 - data_dir: 数据保存目录 - output_file: 最终输出文件路径 - debug_mode: 是否启用调试模式 - debug_batch: 调试批次号 - progress_callback: 进度回调函数（覆盖初始化时的回调） - - Returns: - 输出文件路径 - """ - # 保存原始回调 + """执行完整的数据提取流程""" original_callback = self.progress_callback - # 使用传入的回调或初始化时的回调 self.progress_callback = progress_callback or self.progress_callback try: with sync_playwright() as playwright: - # 调用登录模块 + # 步骤1：启动浏览器并登录 + self._report_progress( + "login", + 1, + 3, # 保持 3 步 + "启动浏览器并登录...", + action="launch_browser", + ) + browser, context, page, main_frame = login( playwright=playwright, username=self.username, @@ -310,41 +420,48 @@ class DiscreteMaterialPlanExtractor: ignore_https_errors=True, ) - # 登录完成 - self._report_progress("login", 1, 1, "登录成功") + # 步骤2：打开功能页面 + self._report_progress( + "login", + 2, + 3, # 保持 3 步 + "登录成功，打开功能页面...", + action="open_function_page", + ) self._print("=" * 80) self._print("开始执行离散备料计划维护数据提取") self._print("=" * 80) - # 登录成功后可以进行后续操作 - # 点击打开"功能菜单" main_frame.locator("i").first.click() - # 点击打开"离散备料计划维护" with page.expect_popup() as page1_info: main_frame.get_by_title( "离散备料计划维护", exact=True ).first.click() page1 = page1_info.value - # 获取 nested iframe main_frame = page1.locator("#forwardFrame").content_frame inner_frame_locator = main_frame.locator("#mainiframe") inner_frame_locator.wait_for(state="visible", timeout=15000) inner_frame = inner_frame_locator.content_frame - # 设置查询界面 + # 步骤3：设置查询界面 + self._report_progress( + "login", + 3, + 3, # 保持 3 步 + "配置查询界面...", + action="setup_query_interface", + ) self.setup_query_interface(inner_frame) - # 读取总排号并查询生产订单号 + # 后续代码保持不变... order_ids = self.get_production_order_numbers( production_id_file, report_progress=True ) - # 按批次下载 downloaded_files = [] - # 计算总批次数 total_batches = sum( 1 for _ in self.group_order_ids(order_ids, self.batch_size) ) @@ -356,16 +473,6 @@ class DiscreteMaterialPlanExtractor: f"\n=== 开始处理第 {batch_index + 1} 批，共 {len(order_ids_batch)} 个订单号 ===" ) - # 报告开始下载批次 - self._report_progress( - "download", - batch_index, - total_batches, - f"正在下载第 {batch_index + 1}/{total_batches} 批...", - batch_index=batch_index + 1, - batch_size=len(order_ids_batch), - ) - downloaded_file = self.download_batch( inner_frame, order_ids_batch, @@ -377,20 +484,25 @@ class DiscreteMaterialPlanExtractor: ) downloaded_files.append(downloaded_file) - # 执行账号注销 self._print("\n开始执行账号注销...") - self._report_progress("logout", 1, 1, "正在注销账号...") + self._report_progress( + "logout", + 1, + 2, + "正在注销账号...", + action="logout_start", + ) logout(main_frame, verbose=self.verbose) + + self._report_progress( + "logout", + 2, + 2, + "注销完成 ✓", + action="logout_complete", + ) - # 转换并合并文件 if downloaded_files: - self._report_progress( - "convert", - 0, - len(downloaded_files), - f"开始转换并合并 {len(downloaded_files)} 个文件", - file_count=len(downloaded_files), - ) self._print( f"\n=== 开始转换并合并 {len(downloaded_files)} 个文件 ===" ) @@ -401,19 +513,18 @@ class DiscreteMaterialPlanExtractor: self._print(f"\n=== 全部完成 ===") self._print(f"最终文件: {output_file}") - # 报告完成 self._report_progress( - "complete", 1, 1, "提取完成", output_file=output_file + "complete", 1, 1, "数据提取完成 ✓", + output_file=output_file, + action="all_complete", ) - # 关闭浏览器 context.close() browser.close() return output_file finally: - # 恢复原始回调 self.progress_callback = original_callback @@ -435,4 +546,4 @@ def main(): if __name__ == "__main__": - main() + main() \ No newline at end of file