# site_zto.py import os import re import yaml from datetime import datetime import pandas as pd def _wait_and_get_frame(page, text_indicator, timeout_ms=20000): """动态雷达探测器:全域扫描所有视窗""" start_time = datetime.now() while (datetime.now() - start_time).total_seconds() * 1000 < timeout_ms: # 1. 探测最外层 try: if page.get_by_text(text_indicator).count() > 0: return page except: pass # 2. 穿透扫描所有活跃的子 iframe for frame in page.frames: try: if frame.get_by_text(text_indicator).count() > 0: return frame except: pass page.wait_for_timeout(300) raise TimeoutError(f"爆栈超时:全域未死守到包含 [{text_indicator}] 的弹窗视窗。") def _ensure_menu_expanded(page, level1_name, level2_name=None): """MiniUI 智能菜单展开器""" print(f">> 正在智能路由菜单...") if level2_name: if not page.locator( "li.shrink span.menu-name", has_text=level2_name ).is_visible(): page.locator( "a.treeview-title span.menu-name", has_text=level1_name ).click() page.wait_for_timeout(500) else: if not page.locator( "a.treeview-title span.menu-name", has_text=level1_name ).is_visible(): page.locator( "a.treeview-title span.menu-name", has_text=level1_name ).click() page.wait_for_timeout(500) def zto_smart_menu_click(page, menu_path): """中通智能菜单导航器""" print(f">> 正在导航: {' -> '.join(menu_path)}") for i in range(len(menu_path)): current_menu = menu_path[i] if i < len(menu_path) - 1: next_menu = menu_path[i + 1] next_locator = page.locator("span.menu-name", has_text=next_menu).first if not next_locator.is_visible(): page.locator("span.menu-name", has_text=current_menu).first.click() page.wait_for_timeout(800) else: page.locator("span.menu-name", has_text=current_menu).first.click() page.wait_for_timeout(1000) def zto_expected_download(page): """中通:应到货物数据下载""" print("\n▶ 开始执行【中通 - 应到货物数据下载】任务...") download_dir = os.path.join(os.getcwd(), "downloads") if not os.path.exists(download_dir): os.makedirs(download_dir) export_times = [] try: # 1. 智能导航 zto_smart_menu_click(page, ["运营管理", "进站管理", "进站交接单查询"]) ewb_frame = page.frame_locator('iframe[src*="inEwbsListNoSearch"]') print(">> 正在探针检测表格统计面板 (#inEwbCount)...") ewb_frame.locator("#inEwbCount").wait_for(state="attached", timeout=15000) # 读取 YAML 配置设定天数 query_days = 1 try: if os.path.exists("config.yaml"): with open("config.yaml", "r", encoding="utf-8") as f: config = yaml.safe_load(f) or {} query_days = int(config.get("zto", {}).get("query_days", 1)) except Exception as e: print(f" ⚠️ 读取 config.yaml 失败,默认查询 1 天: {e}") print(f">> 正在设定查询时间范围为近【{query_days}】天...") ewb_frame.locator("#beginDate").click() page.wait_for_timeout(500) today_cell = ewb_frame.locator("td div.day.real-today").first today_cell.wait_for(state="visible") today_time_str = today_cell.get_attribute("time") if today_time_str: today_time = int(today_time_str) start_time = today_time - (query_days - 1) * 86400000 start_cell = ewb_frame.locator(f"td div.day[time='{start_time}']").first if start_cell.is_visible(): start_cell.click() page.wait_for_timeout(300) today_cell.click() else: print(" ⚠️ 设定的天数过大,不在当前日历视窗内,自动降级为查询当天。") today_cell.click() page.wait_for_timeout(300) today_cell.click() else: today_cell.click() page.wait_for_timeout(300) today_cell.click() page.wait_for_timeout(500) # 3. 触发查询与深度状态机判定 print(">> 正在点击【查询】按钮并等待数据响应...") ewb_frame.locator("#searchbtn").click() page.wait_for_timeout(1000) loading_mask = ewb_frame.locator(".mini-mask-loading", has_text="加载中") if loading_mask.is_visible(): print(" ⏳ 检测到数据加载遮罩层,等待系统渲染...") loading_mask.wait_for(state="hidden", timeout=30000) page.wait_for_timeout(1000) empty_flag = ewb_frame.locator("span", has_text="没有搜索到符合条件的数据记录") if empty_flag.is_visible(): print(" ⚠️ 当前查询范围内【没有搜索到符合条件的数据记录】,终止导出。") return ticket_count_str = ewb_frame.locator("#inEwbCount").inner_text().strip() print(f" ✅ 数据渲染完毕!当前进站实际票数为: [{ticket_count_str}]") # 4. 提取主表记录并循环双击 main_rows = ewb_frame.locator("#datagrid1 .mini-grid-rows-view .mini-grid-row") count = main_rows.count() print(f">> 共发现 {count} 个交接单需要导出。") for i in range(count): print(f" ⏳ 正在处理第 {i+1}/{count} 个交接单...") row = ewb_frame.locator( "#datagrid1 .mini-grid-rows-view .mini-grid-row" ).nth(i) # 正则表达式清洗交接单号 raw_text = row.locator("td").nth(3).inner_text() match = re.search(r"\d{18}", raw_text) handover_no = match.group(0) if match else raw_text.strip() print(f" -> 锁定提取单号:{handover_no}") row.dblclick() ewb_frame.locator("#datagrid2").get_by_text("运单号").wait_for( state="visible" ) ewb_frame.locator( "#datagrid2 .mini-grid-row", has_text=handover_no ).first.wait_for(state="visible") # 5. 执行导出流程 ewb_frame.locator("#exportExcel").click() page.locator(".mini-panel-title", has_text="导出选择列").wait_for( state="visible" ) export_frame = page.frame_locator('iframe[src*="download"]') export_frame.locator(".mini-button-text", has_text=">>").click() page.wait_for_timeout(300) export_frame.locator(".mini-button-text", has_text="确定").click() print(" >> [雷达扫描] 正在跨域动态追踪【温馨提示】所在的隐身视窗...") ctx_alert = _wait_and_get_frame(page, "温馨提示") ctx_alert.locator( ".mini-messagebox-buttons .mini-button-text", has_text="确定" ).click() print(" ✅ 【温馨提示】已成功通过父级过滤并确认!") print(" >> 正在等待服务器建立后台离线任务...") try: ctx_tips = _wait_and_get_frame( page, "生成离线导出任务成功", timeout_ms=10000 ) ctx_tips.locator(".mini-tips-success").wait_for( state="hidden", timeout=15000 ) print(" ✅ 成功提示框已平滑隐藏。") except Exception as e: print(" ✅ 成功提示框及其容器已自动销毁 (触发 Detached 拦截)。") export_times.append(datetime.now()) # 同域无缝 Tab 切换回交接单信息 print(" >> 切换回【交接单信息】标签页...") ewb_frame.locator("#ewbsListNo").click() page.wait_for_timeout(1000) if count > 0: print("✅ 所有交接单的导出任务已成功提交!") else: print("⚠️ 未发现任何数据,直接跳转至下载环节。") # 6. 前往【导出任务管理】 print("\n>> 正在前往【导出任务管理】界面...") zto_smart_menu_click(page, ["系统配置", "导出任务管理"]) taskdone_frame = page.frame_locator('iframe[src*="taskdone"]') taskdone_frame.locator("#taskdoneDatagrid").get_by_text("任务标题").wait_for( state="visible" ) page.wait_for_timeout(2000) # 7. 轮询任务状态 print(">> 列表中已渲染,开始匹配并检查后端处理状态...") while True: task_rows = taskdone_frame.locator( "#taskdoneDatagrid .mini-grid-rows-view .mini-grid-row" ) row_count = task_rows.count() pending_tasks = 0 current_ready_timestamps = [] for i in range(row_count): tds = task_rows.nth(i).locator("td") if tds.count() < 10: continue title_str = tds.nth(3).inner_text().strip() submit_time_str = tds.nth(4).inner_text().strip() status_str = tds.nth(6).inner_text().strip() if title_str == "进站交接单查询-运单信息": try: row_time = datetime.strptime( submit_time_str, "%Y-%m-%d %H:%M:%S" ) matched = any( abs((row_time - et).total_seconds()) <= 120 for et in export_times ) if matched: if status_str != "成功执行": pending_tasks += 1 if submit_time_str not in current_ready_timestamps: print( f" ⏳ 任务 [{submit_time_str}] 状态为【{status_str}】,数据生成中..." ) else: if submit_time_str not in current_ready_timestamps: current_ready_timestamps.append(submit_time_str) except Exception as e: print(f" ⚠️ 解析时间时出错: {e}") if pending_tasks > 0: print( f">> 共有 {pending_tasks} 个匹配任务还在处理中,等待 5 秒后刷新..." ) page.wait_for_timeout(5000) page.locator("li.leaf span.menu-name", has_text="导出任务管理").click() page.wait_for_timeout(2000) else: target_task_timestamps = current_ready_timestamps if len(target_task_timestamps) > 0: print(">> ✅ 所有目标任务已就绪!开始并行下载...") break # 8. 下载逻辑 downloaded_files = [] for time_str in target_task_timestamps: try: target_row = taskdone_frame.locator( "#taskdoneDatagrid .mini-grid-rows-view .mini-grid-row" ).filter( has=taskdone_frame.locator( f"td:nth-child(5):has-text('{time_str}')" ) ) print(f" 🎯 触发下载 -> 任务 [{time_str}] ...") # 闭环 Checkbox 勾选逻辑 checkbox = target_row.locator(".mini-grid-checkbox") if checkbox.is_visible(): checkbox.click() print(" -> 已勾选当前记录的 Checkbox") page.wait_for_timeout(500) with page.expect_download() as download_info: target_row.locator("td").nth(10).locator(".ui-btn-download").click() download = download_info.value save_path = os.path.join(download_dir, download.suggested_filename) download.save_as(save_path) downloaded_files.append(save_path) print(f" ⬇️ 文件已落盘: downloads/{download.suggested_filename}") if checkbox.is_visible(): checkbox.click() print(" -> 已取消勾选,清理现场进入下一条") page.wait_for_timeout(500) except Exception as e: print(f" ❌ 下载任务 [{time_str}] 失败: {e}") # 9. 合并数据 if downloaded_files: print("\n>> 🧪 正在开始执行扁平数据高能合并流程...") all_data_frames = [] for file_path in downloaded_files: try: # ==================================================================== # 🛡️ 核心修复:强制以字符串类型 (str) 读取所有列,彻底防止长单号变科学计数法或丢失精度 # ==================================================================== df = pd.read_excel(file_path, dtype=str) if not df.empty: all_data_frames.append(df) except Exception as e: pass if all_data_frames: combined_df = pd.concat(all_data_frames, ignore_index=True) final_output_path = os.path.join(download_dir, "中通-应到货物数据.xlsx") combined_df.to_excel(final_output_path, index=False) print(f"====================================================") print(f" 🎉 恭喜!合并成功!最终输出路径: {final_output_path}") print(f"====================================================") for file_path in downloaded_files: os.remove(file_path) print("✅ 临时数据清理完毕。") print("\n🎉 【中通 - 应到货物数据下载】全流程测试完毕!") except Exception as e: print(f"\n❌ 任务执行过程中发生异常: {e}") def zto_actual_download(page): """中通:实到货物数据下载""" print("\n▶ 开始执行【中通 - 实到货物数据下载】任务...") print("🚧 逻辑开发中 (pass)...") pass