Refactor monolithic script into multi-site module architecture

- Introduce main_router.py as multi-site controller with interactive menu
- Extract 顺心 site logic into site_shunxin.py (expected & actual download)
- Add site_baishi.py stub for upcoming 百世 integration
- Add global 应到未到 data reconciliation via Left Anti-Join on 运单号

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

main_router.py

@@ -0,0 +1,173 @@
+# main_router.py
+
+import os
+import pandas as pd
+from playwright.sync_api import sync_playwright
+
+# 导入抽离出去的各个网点模块
+import site_shunxin
+import site_baishi
+
+# 定义网点及对应的初始登录 URL
+SITES_CONFIG = {
+    "顺心": "https://sxne.sxjdfreight.com",
+    "百世": "https://v5.800best.com",
+}
+
+
+def task_process_undelivered_data():
+    """全局模块：应到未到异常件比对引擎"""
+    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")
+
+    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}")
+        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}")
+        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)
+
+        if "运单号" not in df_expected.columns or "运单号" not in df_actual.columns:
+            print("❌ 核心资产校验失败：数据源中缺失【运单号】字段，请检查导出配置。")
+            return
+
+        print(">> 正在启动多维数据集比对引擎...")
+
+        # Left Anti-Join：在应到中找出不存在于实到里的运单号
+        df_undelivered = df_expected[~df_expected["运单号"].isin(df_actual["运单号"])]
+
+        target_columns = ["班次号", "交接单号", "运单号"]
+        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。")
+
+        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_multi_site_daemon():
+    """多网点自动化主控引擎"""
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=False)
+        # 取消禁用视口大小限制，防止有些系统自适应出问题
+        context = browser.new_context(viewport={"width": 1920, "height": 1080})
+
+        # 用于存储网点名称与 Page 对象的映射字典
+        pages_map = {}
+
+        print("\n====================================================")
+        print("【初始化阶段】正在构建多网点运行环境...")
+        print("====================================================")
+
+        # 遍历配置，依次创建独立的标签页
+        for site_name, url in SITES_CONFIG.items():
+            print(f">> 正在打开【{site_name}】页面: {url}")
+            page = context.new_page()
+            page.goto(url)
+            pages_map[site_name] = page
+            page.wait_for_timeout(1000)
+
+        print("\n====================================================")
+        print("⚠️ 【等待人工介入】")
+        print("请在弹出的浏览器中，依次切换标签页，人工完成所有网点的登录！")
+        print("====================================================")
+
+        # 阻塞程序，等待用户登录完毕
+        input(">> 登录全部完成后，请在此处按下【回车键】正式接管中控台...")
+
+        print("\n====================================================")
+        print("【系统接管】正在执行各网点就绪前初始化动作...")
+        print("====================================================")
+
+        # 处理【顺心】网点的登录后就绪判定与弹窗清理
+        try:
+            sx_page = pages_map["顺心"]
+            sx_page.bring_to_front()
+            print(">> 正在处理【顺心】网点初始状态...")
+
+            # 使用较长超时时间确认登录状态（避免回车按得太早没加载完）
+            sx_page.wait_for_selector('h1:has-text("盟商门户网")', timeout=30000)
+            print("   🎉 登录成功！系统已接管顺心浏览器。")
+            sx_page.wait_for_timeout(1000)
+
+            # 跳过初始一些弹窗干扰
+            sx_page.locator("a").nth(4).click()
+            sx_page.wait_for_timeout(1000)
+            sx_page.get_by_role("button", name="Close").click()
+            sx_page.wait_for_timeout(1000)
+            sx_page.get_by_role("button", name="不再询问").click()
+            sx_page.wait_for_timeout(1000)
+            print("   ✅ 【顺心】弹窗清理完毕，状态就绪！")
+
+        except Exception as e:
+            print(f"   ⚠️ 【顺心】初始化或弹窗清理异常 (如无弹窗可忽略): {e}")
+
+        # 未来如果要加【百世】的弹窗清理，可以直接在这里依葫芦画瓢加上
+        # try:
+        #     bs_page = pages_map["百世"]
+        #     bs_page.bring_to_front()
+        #     ...
+
+        while True:
+            print("\n==============================")
+            print("      物流数据多端提取总枢纽     ")
+            print("==============================")
+            print("1. [顺心] - 执行【应到货物数据下载】")
+            print("2. [顺心] - 执行【实到货物数据下载】")
+            print("3. [百世] - 执行【应到货物数据下载】")
+            print("4. [百世] - 执行【实到货物数据下载】")
+            print("5. [全局] - 执行【应到未到数据清洗比对】")
+            print("0. 退出系统")
+            print("==============================")
+
+            choice = input("请输入任务编号并回车: ")
+
+            try:
+                if choice == "1":
+                    pages_map["顺心"].bring_to_front()  # 切换到对应标签页
+                    site_shunxin.shunxin_expected_download(pages_map["顺心"])
+                elif choice == "2":
+                    pages_map["顺心"].bring_to_front()
+                    site_shunxin.shunxin_actual_download(pages_map["顺心"])
+                elif choice == "3":
+                    pages_map["百世"].bring_to_front()
+                    site_baishi.baishi_expected_download(pages_map["百世"])
+                elif choice == "4":
+                    pages_map["百世"].bring_to_front()
+                    site_baishi.baishi_actual_download(pages_map["百世"])
+                elif choice == "5":
+                    task_process_undelivered_data()
+                elif choice == "0":
+                    print("\n准备退出程序，释放浏览器资源...")
+                    break
+                else:
+                    print("\n⚠️ 无效输入，请重新选一下。")
+            except Exception as e:
+                print(f"❌ 调度执行异常: {e}")
+
+        # 退出循环后关闭浏览器
+        browser.close()
+        print("系统已安全关闭。")
+
+
+if __name__ == "__main__":
+    run_multi_site_daemon()

site_baishi.py

@@ -0,0 +1,15 @@
+# site_baishi.py
+
+
+def baishi_expected_download(page):
+    """百世：应到货物数据下载"""
+    print("\n▶ 开始执行【百世 - 应到货物数据下载】任务...")
+    print("🚧 逻辑开发中 (pass)...")
+    pass
+
+
+def baishi_actual_download(page):
+    """百世：实到货物数据下载"""
+    print("\n▶ 开始执行【百世 - 实到货物数据下载】任务...")
+    print("🚧 逻辑开发中 (pass)...")
+    pass

site_shunxin.py

@@ -0,0 +1,375 @@
+# site_shunxin.py
+
+import os
+import re
+from datetime import datetime
+import pandas as pd
+
+
+def shunxin_expected_download(page):
+    """顺心：应到货物数据下载"""
+    print("\n▶ 开始执行【顺心 - 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...")
+        # 尊重改动：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】...")
+        # 尊重改动：精确定位选项
+        page.locator(".ant-select-item-option", has_text="已到").click()
+
+        print(">> 正在点击【查询】按钮...")
+        # 尊重改动：使用带 search 标识的 exact role 定位
+        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
+            # 尊重改动：精准的 export role 定位
+            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()
+
+            # 尊重改动：限定在"导出"区域内的向右按钮
+            page.get_by_label("导出").get_by_role("button", name="right").click()
+            # 尊重改动：精准的 export 数据按钮
+            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()
+
+        # 尊重改动：使用 columnheader 确保表格表头真正加载完毕
+        page.get_by_role("columnheader", name="任务标题").wait_for(state="visible")
+        page.wait_for_timeout(2000)
+
+        # 尊重改动：进入页面后主动点击一次查询刷新状态
+        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)
+                # 尊重改动：使用更精准的 search 查询按钮定位
+                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🎉 【顺心 - 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 shunxin_actual_download(page):
+    """顺心：实到货物数据下载"""
+    print("\n▶ 开始执行【顺心 - 实到货物数据下载】任务...")
+
+    download_dir = os.path.join(os.getcwd(), "downloads")
+    if not os.path.exists(download_dir):
+        os.makedirs(download_dir)
+
+    export_times = []
+    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")
+        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()
+
+        print(">> 正在点击【查询】按钮...")
+        # 尊重改动：精确到 search 查询
+        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...")
+        # 尊重改动：精确定位
+        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()
+
+        # 尊重改动：定位 right 按钮
+        page.get_by_label("导出").get_by_role("button", name="right").click()
+        # 尊重改动：精准的 export 导出数据按钮
+        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()
+
+        # 尊重改动：使用 columnheader 确保表格加载
+        page.get_by_role("columnheader", name="任务标题").wait_for(state="visible")
+        page.wait_for_timeout(2000)
+
+        # 尊重改动：主动点击查询刷新
+        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)
+                # 尊重改动：精准定位刷新查询
+                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🎉 【顺心 - 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}")