InboundVerify/main_task.py

import os
import re
import glob
from datetime import datetime
import pandas as pd
from playwright.sync_api import sync_playwright


def task_expected_goods_download(page):
    """模块一：应到货物数据下载"""
    print("\n▶ 开始执行【应到货物数据下载】任务...")

    # 初始化并创建下载目录
    download_dir = os.path.join(os.getcwd(), "downloads")
    if not os.path.exists(download_dir):
        os.makedirs(download_dir)
        print(f">> 已创建专属下载文件夹: {download_dir}")

    export_times = []
    target_task_timestamps = []

    try:
        # 1. 导航与页面加载判断
        print(">> 正在进入【车辆点到】界面...")
        page.locator("span.ant-pro-menu-item-title:has-text('派件管理')").click()
        page.locator("div.ant-pro-menu-item:has-text('车辆点到')").click()

        page.get_by_role("button", name="点到").wait_for(state="visible")
        page.get_by_role("button", name="打印交接单").wait_for(state="visible")
        page.get_by_role("button", name="强卸").wait_for(state="visible")
        print("✅ 车辆点到界面加载完毕")

        # 2. 筛选条件：1天、状态=已发 -> 已到、查询
        print(">> 正在设置筛选条件: 选择【1天】...")
        page.get_by_role("radio", name="1天").check()

        print(">> 正在展开【状态】下拉菜单...")
        # 匹配包含 已发 或 已到 的下拉选项
        page.locator(
            ".ant-select-selection-item", has_text=re.compile(r"已发|已到")
        ).click()

        print(">> 正在选择状态为【已到】...")
        page.locator(".ant-select-item-option", has_text="已到").click()

        print(">> 正在点击【查询】按钮...")
        page.get_by_role("button", name="search 查询").click()
        page.wait_for_timeout(2000)

        # 3. 获取所有【运单列表】按钮并循环处理
        waybill_btns = page.get_by_role("button", name="运单列表")
        count = waybill_btns.count()
        print(f">> 共发现 {count} 个班次需要导出。")

        for i in range(count):
            print(f"   ⏳ 正在处理第 {i+1}/{count} 个班次...")

            waybill_btns.nth(i).click()
            page.locator("label[title='运单查询']").wait_for(state="visible")

            # 4. 执行导出流程
            page.get_by_role("button", name="export 导出").click()

            page.locator(
                "span.ant-transfer-list-header-title:has-text('待选导出列')"
            ).wait_for(state="visible")
            page.locator(".ant-transfer-list").first.locator(
                ".ant-transfer-list-header label"
            ).click()
            page.get_by_label("导出").get_by_role("button", name="right").click()
            page.get_by_role("button", name="export 导出数据").click()

            export_times.append(datetime.now())

            page.locator("text=任务添加成功!").wait_for(state="visible")
            page.get_by_role("button", name="知道了").click()

            page.get_by_role("tab", name="车辆点到").click()
            page.wait_for_timeout(500)

        if count > 0:
            print("✅ 所有班次的导出任务已成功提交！")
        else:
            print("⚠️ 未发现任何运单列表，直接跳转至下载环节。")

        # 6. 前往数据导出页面去下载
        print(">> 正在前往【数据导出】界面...")
        page.locator("a[href='/dataExport']").click()
        page.get_by_role("columnheader", name="任务标题").wait_for(state="visible")
        page.wait_for_timeout(2000)
        page.get_by_role("button", name="search 查询").click()
        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:
            rows = page.locator(".ant-table-tbody > tr.ant-table-row")
            row_count = rows.count()
            pending_tasks = 0
            current_ready_timestamps = []

            for i in range(row_count):
                tds = rows.nth(i).locator("td")
                if tds.count() < 9:
                    continue

                submit_time_str = tds.nth(2).inner_text().strip()
                title_str = tds.nth(5).inner_text().strip()
                status_str = tds.nth(6).inner_text().strip()

                if title_str == "发车管理运单列表":
                    try:
                        row_time = datetime.strptime(
                            submit_time_str, "%Y-%m-%d %H:%M:%S"
                        )
                        matched = any(
                            abs((row_time - et).total_seconds()) <= 60
                            for et in export_times
                        )

                        if matched:
                            if status_str != "执行完成":
                                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.get_by_role("button", name="search 查询").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 = page.locator(".ant-table-tbody > tr.ant-table-row").filter(
                    has=page.locator(f"td:nth-child(3):has-text('{time_str}')")
                )
                print(f"   🎯 触发下载 -> 任务 [{time_str}] ...")

                with page.expect_download() as download_info:
                    target_row.locator("td").nth(8).locator(
                        "button", has_text=re.compile(r"下\s*载")
                    ).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}")
            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:
                    df = pd.read_excel(file_path)
                    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, "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🎉 【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 task_actual_goods_download(page):
    """模块二：实到货物数据下载"""
    print("\n▶ 开始执行【实到货物数据下载】任务...")

    # 初始化并创建下载目录
    download_dir = os.path.join(os.getcwd(), "downloads")
    if not os.path.exists(download_dir):
        os.makedirs(download_dir)

    export_times = []
    target_task_timestamps = []

    try:
        # 1. 导航与页面加载
        print(">> 正在进入【卸车扫描记录】界面...")
        page.locator("span.ant-pro-menu-item-title:has-text('派件管理')").click()
        page.locator("div.ant-pro-menu-item:has-text('卸车扫描记录')").click()

        page.get_by_role("radio", name="1天").wait_for(state="visible")
        # page.locator("button:has-text('查询')").wait_for(state="visible")
        print("✅ 卸车扫描记录界面加载完毕")

        # 2. 筛选条件：1天、查询
        print(">> 正在设置筛选条件: 选择【1天】...")
        page.get_by_role("radio", name="1天").check()
        # page.pause()
        print(">> 正在点击【查询】按钮...")
        page.get_by_role("button", name="search 查询").click()
        page.wait_for_timeout(2000)

        # 3. 直接发起全局导出
        print(">> 正在发起导出请求...")
        page.get_by_role("button", name="export 导出").click()

        page.locator(
            "span.ant-transfer-list-header-title:has-text('待选导出列')"
        ).wait_for(state="visible")
        page.locator(".ant-transfer-list").first.locator(
            ".ant-transfer-list-header label"
        ).click()
        page.get_by_label("导出").get_by_role("button", name="right").click()
        page.get_by_role("button", name="export 导出数据").click()

        export_times.append(datetime.now())

        page.locator("text=任务添加成功!").wait_for(state="visible")
        page.get_by_role("button", name="知道了").click()
        print("✅ 卸车扫描记录导出任务已成功提交！")

        # 4. 前往数据导出页面去下载
        print(">> 正在前往【数据导出】界面...")
        page.locator("a[href='/dataExport']").click()
        # page.pause()
        page.get_by_role("columnheader", name="任务标题").wait_for(state="visible")
        page.wait_for_timeout(2000)
        page.get_by_role("button", name="search 查询").click()
        page.wait_for_timeout(2000)
        # 5. 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:
            rows = page.locator(".ant-table-tbody > tr.ant-table-row")
            row_count = rows.count()
            pending_tasks = 0
            current_ready_timestamps = []

            for i in range(row_count):
                tds = rows.nth(i).locator("td")
                if tds.count() < 9:
                    continue

                submit_time_str = tds.nth(2).inner_text().strip()
                title_str = tds.nth(5).inner_text().strip()
                status_str = tds.nth(6).inner_text().strip()

                if title_str.startswith("卸车扫描记录"):
                    try:
                        row_time = datetime.strptime(
                            submit_time_str, "%Y-%m-%d %H:%M:%S"
                        )
                        matched = any(
                            abs((row_time - et).total_seconds()) <= 60
                            for et in export_times
                        )

                        if matched:
                            if status_str != "执行完成":
                                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.get_by_role("button", name="search 查询").click()
                page.wait_for_timeout(2000)
            else:
                target_task_timestamps = current_ready_timestamps
                if len(target_task_timestamps) > 0:
                    print(">> ✅ 目标任务已就绪！开始下载...")
                break

        # 6. 下载逻辑
        downloaded_files = []
        for time_str in target_task_timestamps:
            try:
                target_row = page.locator(".ant-table-tbody > tr.ant-table-row").filter(
                    has=page.locator(f"td:nth-child(3):has-text('{time_str}')")
                )
                print(f"   🎯 触发下载 -> 任务 [{time_str}] ...")

                with page.expect_download() as download_info:
                    target_row.locator("td").nth(8).locator(
                        "button", has_text=re.compile(r"下\s*载")
                    ).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}")
            except Exception as e:
                print(f"   ❌ 下载任务 [{time_str}] 失败: {e}")

        # 7. 合并数据
        if downloaded_files:
            print("\n>> 🧪 正在开始执行数据归档整理...")
            all_data_frames = []
            for file_path in downloaded_files:
                try:
                    df = pd.read_excel(file_path)
                    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, "实到货物数据.xlsx")
                combined_df.to_excel(final_output_path, index=False)
                print(f"====================================================")
                print(f"   🎉 恭喜！处理成功！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🎉 【实到货物数据下载】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 task_process_undelivered_data():
    """模块三：对下载的应到与实到数据进行高级清洗与比对，抽取出应到未到的异常运单"""
    print("\n▶ 开始执行【应到未到数据处理】任务...")

    download_dir = os.path.join(os.getcwd(), "downloads")
    expected_path = os.path.join(download_dir, "应到货物数据.xlsx")
    actual_path = os.path.join(download_dir, "实到货物数据.xlsx")
    output_path = os.path.join(download_dir, "应到未到货物数据.xlsx")

    # 基础校验：确保源文件全部存在
    if not os.path.exists(expected_path):
        print(f"❌ 错误：找不到【应到货物数据】主文档：{expected_path}")
        print("💡 请先执行菜单选项 [1] 进行提取下载。")
        return

    if not os.path.exists(actual_path):
        print(f"❌ 错误：找不到【实到货物数据】主文档：{actual_path}")
        print("💡 请先执行菜单选项 [2] 进行提取下载。")
        return

    try:
        print(">> 正在载入本地 Excel 文档...")
        df_expected = pd.read_excel(expected_path)
        df_actual = pd.read_excel(actual_path)

        # 字段安全检查
        if "运单号" not in df_expected.columns:
            print(
                "❌ 核心资产校验失败：应到货物数据中缺失【运单号】字段，请检查系统导出配置。"
            )
            return
        if "运单号" not in df_actual.columns:
            print(
                "❌ 核心资产校验失败：实到货物数据中缺失【运单号】字段，请检查系统导出配置。"
            )
            return

        print(">> 正在启动多维数据集比对引擎...")
        # 核心比对清洗逻辑：在应到中剔除已经实到的运单号 (Left Anti-Join 机制)
        df_undelivered = df_expected[~df_expected["运单号"].isin(df_actual["运单号"])]

        # 按需求抽取指定的输出列：班次号、交接单号、运单号
        target_columns = ["班次号", "交接单号", "运单号"]
        # 确保列名完全匹配
        available_columns = [
            col for col in target_columns if col in df_undelivered.columns
        ]

        df_output = df_undelivered[available_columns]

        print(f">> 筛选完毕！共捕获到异常【应到未到】货物数据: {len(df_output)} 条。")

        # 输出最终汇总报告
        df_output.to_excel(output_path, index=False)
        print(f"====================================================")
        print(f"   🎉 异常比对流完成！独立数据已安全输出。")
        print(f"   📁 成果归档成果路径: {output_path}")
        print(f"====================================================")

    except Exception as e:
        print(f"❌ 数据处理引擎在执行连接和输出时发生致命异常: {e}")


def run_daemon_automation():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=False)
        context = browser.new_context()
        page = context.new_page()

        target_url = "https://sxne.sxjdfreight.com"
        print(f"正在打开登录页面: {target_url}")
        page.goto(target_url)

        print("====================================================")
        print("【等待人工介入】请手动完成登录。")
        print("====================================================")

        try:
            page.wait_for_selector('h1:has-text("盟商门户网")', timeout=120000)
            print("🎉 登录成功！系统已接管浏览器。")
            page.wait_for_timeout(1000)

            # 跳过初始一些弹窗干扰
            page.locator("a").nth(4).click()
            page.wait_for_timeout(1000)
            page.get_by_role("button", name="Close").click()
            page.wait_for_timeout(1000)
            page.get_by_role("button", name="不再询问").click()
            page.wait_for_timeout(1000)

            while True:
                print("\n==============================")
                print("      物流数据自动提取系统      ")
                print("==============================")
                print("1. 执行【应到货物数据下载】")
                print("2. 执行【实到货物数据下载】")
                print("3. 执行【应到未到数据处理】 (★新)")
                print("4. 退出程序")
                print("==============================")

                choice = input("请输入任务编号并回车: ")

                if choice == "1":
                    task_expected_goods_download(page)
                elif choice == "2":
                    task_actual_goods_download(page)
                elif choice == "3":
                    task_process_undelivered_data()
                elif choice == "4":
                    print("\n准备退出程序...")
                    break
                else:
                    print("\n⚠️ 无效输入，请重新选一下。")

        except Exception as e:
            print(f"❌ 运行发生致命错误: {e}")

        finally:
            browser.close()
            print("浏览器已安全关闭。")


if __name__ == "__main__":
    run_daemon_automation()