chore: auto release commit (2026-09-14 22:22:49)

scripts/service/rpa/__init__.py

@@ -1,16 +1,36 @@
-"""RPA模块：提供发票信息提取的自动化功能。"""
+"""RPA模块：提供发票信息提取的自动化功能。
 
-from .browser_session import close_browser_context, start_browser_session
-from .invoice_extractor import extract_invoice_detail, extract_invoice_list, format_invoice_data
+完整流程：
+  1. 登录 sandbox.jc2009.com（手机号+密码）
+  2. 找到"智慧校园"并点击进入
+  3. 登录智慧校园（默认 demo 账号）
+  4. 导航到票据合规预审页面
+  5. 提取发票数据
+"""
+
+from .browser_session import close_browser_context, find_browser_executable, start_browser_session
+from .invoice_extractor import extract_form_fields, extract_invoice_detail, extract_invoice_list, format_invoice_data
 from .invoice_rpa import InvoiceRpaResult, run_invoice_rpa, run_invoice_rpa_with_video
-from .login_handler import login_if_needed
+from .login_handler import (
+    enter_smart_campus,
+    login_if_needed,
+    login_sandbox,
+    login_smart_campus,
+    navigate_to_invoice_precheck,
+)
 
 __all__ = [
     "start_browser_session",
     "close_browser_context",
+    "find_browser_executable",
     "login_if_needed",
+    "login_sandbox",
+    "enter_smart_campus",
+    "login_smart_campus",
+    "navigate_to_invoice_precheck",
     "extract_invoice_list",
     "extract_invoice_detail",
+    "extract_form_fields",
     "format_invoice_data",
     "run_invoice_rpa",
     "run_invoice_rpa_with_video",

scripts/service/rpa/browser_session.py

@@ -1,67 +1,147 @@
-"""浏览器会话管理：基于skill-template的real_browser_rpa示例。"""
+"""浏览器会话管理：基于 skill-template 的 simulator_browser_rpa 示例。"""
 
 from __future__ import annotations
 
 import logging
 import os
 import random
-from typing import Any, Optional, Tuple
+from typing import Any, List, Optional, Tuple
 
 from jiangchang_skill_core import config
 from jiangchang_skill_core.activity import interruptible_sleep
-from jiangchang_skill_core.rpa import launch_persistent_browser, poll_until
 
 logger = logging.getLogger(__name__)
 
-# 目标网站配置
-TARGET_URL = "https://sandbox.jc2009.com/industries/campus/smartcampus/app/finance/invoice-precheck"
-LOGIN_URL = "https://sandbox.jc2009.com/login"
+DEFAULT_PAGE_TIMEOUT_MS = 15_000
+
+CHROME_LAUNCH_ARGS: List[str] = [
+    "--start-maximized",
+    "--disable-blink-features=AutomationControlled",
+]
+
+STEALTH_INIT_SCRIPT = """
+(() => {
+  try { Object.defineProperty(navigator, 'webdriver', { get: () => undefined }); } catch (e) {}
+})();
+"""
+
+
+def chrome_launch_args() -> List[str]:
+    return list(CHROME_LAUNCH_ARGS)
+
+
+def _headless_from_env() -> bool:
+    v = (os.getenv("OPENCLAW_BROWSER_HEADLESS") or "0").strip().lower()
+    return v in ("1", "true", "yes", "on")
+
+
+def find_browser_executable() -> Optional[str]:
+    """查找系统 Chrome 或 Edge 浏览器。"""
+    try:
+        from jiangchang_skill_core.runtime_env import find_chrome_executable as _find
+        chrome = _find()
+        if chrome and os.path.isfile(chrome):
+            return chrome
+    except ImportError:
+        pass
+
+    candidates = [
+        os.path.expandvars(r"%ProgramFiles%\Google\Chrome\Application\chrome.exe"),
+        os.path.expandvars(r"%ProgramFiles(x86)%\Google\Chrome\Application\chrome.exe"),
+        os.path.expandvars(r"%ProgramFiles%\Microsoft\Edge\Application\msedge.exe"),
+        os.path.expandvars(r"%ProgramFiles(x86)%\Microsoft\Edge\Application\msedge.exe"),
+    ]
+    for path in candidates:
+        if path and os.path.isfile(path):
+            return path
+    return None
+
+
+# 向后兼容别名
+find_edge_executable = find_browser_executable
+
+
+def _clear_node_options() -> None:
+    os.environ.pop("NODE_OPTIONS", None)
 
 
 async def start_browser_session(
     profile_dir: str,
     headless: bool = False,
 ) -> Tuple[Any, Any, Any]:
-    """启动浏览器会话。
-    
+    """启动持久化 Chrome/Edge 浏览器会话。
+
+    URL 不在此文件打开；由 invoice_rpa.py 负责 page.goto。
+
     Args:
         profile_dir: 浏览器配置目录
-        headless: 是否无头模式（生产必须为False）
-        
+        headless: 是否无头模式（生产必须为 False）
+
     Returns:
         (playwright, context, page) 三元组
-        
+
     Raises:
         RuntimeError: 浏览器启动失败
     """
     if not profile_dir:
         raise RuntimeError("ERROR:MISSING_BROWSER 缺少浏览器配置目录")
-    
+
     # 确保有头模式（生产要求）
     if headless:
         logger.warning("生产环境强制使用有头模式")
         headless = False
-    
-    try:
-        # 启动持久化浏览器上下文
-        pw, context = await launch_persistent_browser(
-            user_data_dir=profile_dir,
-            headless=headless,
-            args=[
-                "--start-maximized",
-                "--disable-blink-features=AutomationControlled",
-            ],
+
+    # 确保 profile 目录存在
+    os.makedirs(profile_dir, exist_ok=True)
+
+    _clear_node_options()
+    hl = headless if headless is not None else _headless_from_env()
+    chrome = find_browser_executable()
+    if not chrome:
+        raise RuntimeError(
+            "ERROR:MISSING_BROWSER 未检测到 Chrome 或 Edge 浏览器，请先安装系统浏览器后重试。"
         )
-        
-        # 创建新页面
-        page = await context.new_page()
-        
-        # 导航到目标页面
-        await page.goto(TARGET_URL, wait_until="domcontentloaded", timeout=60000)
-        
-        logger.info("browser_started url=%s profile_dir=%s", page.url, profile_dir)
-        return pw, context, page
-        
+
+    args = chrome_launch_args()
+    logger.info(
+        "browser_launch chrome=%s profile_dir=%s args=%s headless=%s",
+        chrome,
+        profile_dir,
+        args,
+        hl,
+    )
+
+    try:
+        from playwright.async_api import async_playwright
+
+        pw = await async_playwright().start()
+        context = None
+        try:
+            context = await pw.chromium.launch_persistent_context(
+                user_data_dir=profile_dir,
+                headless=hl,
+                executable_path=chrome,
+                locale="zh-CN",
+                no_viewport=True,
+                args=args,
+                ignore_default_args=["--enable-automation"],
+            )
+            await context.add_init_script(STEALTH_INIT_SCRIPT)
+
+            page = context.pages[0] if context.pages else await context.new_page()
+            page.set_default_timeout(DEFAULT_PAGE_TIMEOUT_MS)
+            logger.info("browser_started profile_dir=%s", profile_dir)
+            return pw, context, page
+        except Exception:
+            if context is not None:
+                try:
+                    await context.close()
+                except Exception:
+                    pass
+            await pw.stop()
+            raise
+    except RuntimeError:
+        raise
     except Exception as e:
         logger.error("browser_start_failed error=%s", str(e))
         raise RuntimeError(f"ERROR:MISSING_BROWSER 浏览器启动失败: {str(e)}")
@@ -70,22 +150,24 @@ async def start_browser_session(
 async def close_browser_context(pw: Any, context: Any) -> None:
     """安全关闭浏览器上下文。"""
     try:
-        if context:
+        if context is not None:
             await context.close()
-        if pw:
+    except Exception:
+        pass
+    try:
+        if pw is not None:
             await pw.stop()
-    except Exception as e:
-        logger.warning("browser_close_error error=%s", str(e))
+    except Exception:
+        pass
 
 
 async def wait_for_page_ready(page: Any, timeout_sec: float = 30.0) -> bool:
     """等待页面加载完成。"""
     async def _check_ready():
         try:
-            # 检查页面是否加载完成
-            if await page.evaluate("document.readyState") == "complete":
+            ready_state = await page.evaluate("document.readyState")
+            if ready_state == "complete":
                 return True
-            # 检查是否有加载指示器
             loading_selectors = [".loading", ".spinner", "[data-loading]"]
             for sel in loading_selectors:
                 if await page.locator(sel).count() > 0:
@@ -93,9 +175,16 @@ async def wait_for_page_ready(page: Any, timeout_sec: float = 30.0) -> bool:
             return True
         except Exception:
             return False
-    
-    result = await poll_until(_check_ready, timeout_sec=timeout_sec, interval_sec=0.5)
-    return result.ok
+
+    try:
+        from jiangchang_skill_core.rpa import poll_until
+        result = await poll_until(_check_ready, timeout_sec=timeout_sec, interval_sec=0.5)
+        return result.ok
+    except ImportError:
+        # fallback: 简单等待
+        import asyncio
+        await asyncio.sleep(min(timeout_sec, 3.0))
+        return True
 
 
 async def random_delay(min_sec: float = 1.0, max_sec: float = 3.0) -> None:

scripts/service/rpa/invoice_extractor.py

@@ -1,343 +1,264 @@
-"""发票信息提取器：从网站提取发票信息。"""
+"""发票信息提取器：从票据合规预审页面提取发票数据。
+
+根据 sandbox.jc2009.com/industries/campus/smartcampus/app/finance/invoice-precheck 页面 DOM 结构：
+  - 报销事由：文本输入框
+  - 预算项目：下拉选择框
+  - 差旅审批单：下拉选择框
+  - 选择发票：列表，每项包含 checkbox、发票号、金额、类型、公司名、日期、购方税号
+"""
 
 from __future__ import annotations
 
-import json
 import logging
 import re
 from typing import Any, Dict, List, Optional
 
-from jiangchang_skill_core.activity import interruptible_sleep
-
 logger = logging.getLogger(__name__)
 
-# 发票信息提取选择器（需要根据实际页面调整）
-INVOICE_SELECTORS = {
-    # 发票列表容器
-    "invoice_list_container": [
-        ".invoice-list",
-        ".invoice-table",
-        "[data-testid='invoice-list']",
-        "table tbody",
-    ],
-    
-    # 单个发票行
-    "invoice_row": [
-        "tr.invoice-item",
-        ".invoice-row",
-        "[data-testid='invoice-row']",
-        "tbody tr",
-    ],
-    
-    # 发票详情页面元素
-    "invoice_detail": {
-        "invoice_code": [
-            ".invoice-code",
-            "[data-testid='invoice-code']",
-            "td:has-text('发票代码') + td",
-        ],
-        "invoice_number": [
-            ".invoice-number",
-            "[data-testid='invoice-number']",
-            "td:has-text('发票号码') + td",
-        ],
-        "invoice_date": [
-            ".invoice-date",
-            "[data-testid='invoice-date']",
-            "td:has-text('开票日期') + td",
-        ],
-        "total_amount": [
-            ".total-amount",
-            "[data-testid='total-amount']",
-            "td:has-text('金额') + td",
-        ],
-        "tax_amount": [
-            ".tax-amount",
-            "[data-testid='tax-amount']",
-            "td:has-text('税额') + td",
-        ],
-        "buyer_name": [
-            ".buyer-name",
-            "[data-testid='buyer-name']",
-            "td:has-text('购买方') + td",
-        ],
-        "buyer_tax_no": [
-            ".buyer-tax-no",
-            "[data-testid='buyer-tax-no']",
-            "td:has-text('购买方税号') + td",
-        ],
-        "seller_name": [
-            ".seller-name",
-            "[data-testid='seller-name']",
-            "td:has-text('销售方') + td",
-        ],
-        "seller_tax_no": [
-            ".seller-tax-no",
-            "[data-testid='seller-tax-no']",
-            "td:has-text('销售方税号') + td",
-        ],
-        "items": [
-            ".invoice-items",
-            "[data-testid='invoice-items']",
-            ".item-list",
-        ],
-    },
-    
-    # 分页控件
-    "pagination": {
-        "next_button": [
-            ".pagination .next",
-            "button:has-text('下一页')",
-            "[data-testid='next-page']",
-        ],
-        "page_info": [
-            ".page-info",
-            ".pagination-info",
-            "[data-testid='page-info']",
-        ],
-    },
-    
-    # 搜索/筛选控件
-    "search": {
-        "search_input": [
-            "input[placeholder*='搜索']",
-            "input[placeholder*='查询']",
-            ".search-input",
-        ],
-        "search_button": [
-            "button:has-text('搜索')",
-            "button:has-text('查询')",
-            ".search-btn",
-        ],
-    },
-}
-
 
 async def extract_invoice_list(page: Any) -> List[Dict[str, Any]]:
-    """提取发票列表信息。
-    
-    Args:
-        page: Playwright页面对象
-        
+    """从票据合规预审页面提取发票列表。
+
+    页面中发票以列表项形式展示，每项包含：
+      - Checkbox（勾选状态）
+      - 发票号（8位数字）
+      - 金额（¥xxx）
+      - 类型（transport/lodging 等）
+      - 公司名
+      - 日期
+      - 购方税号
+      - 验真状态（"未验真" 标记）
+
     Returns:
-        发票信息列表
+        发票信息字典列表
     """
-    invoices = []
-    
+    invoices: List[Dict[str, Any]] = []
+
     try:
-        # 等待页面加载
-        await interruptible_sleep(2.0)
-        
-        # 查找发票列表容器
-        container = await _find_element(page, INVOICE_SELECTORS["invoice_list_container"])
-        if not container:
-            logger.warning("invoice_list_container_not_found")
-            return []
-        
-        # 查找所有发票行
-        rows = await _find_elements(page, INVOICE_SELECTORS["invoice_row"])
-        logger.info("found_invoice_rows count=%s", len(rows))
-        
-        # 提取每行发票信息
-        for i, row in enumerate(rows):
-            try:
-                invoice_data = await _extract_invoice_from_row(page, row, i)
-                if invoice_data:
-                    invoices.append(invoice_data)
-            except Exception as e:
-                logger.warning("extract_row_failed row=%s error=%s", i, str(e))
-                continue
-        
-        # 处理分页
-        has_next = await _has_next_page(page)
-        while has_next:
-            # 点击下一页
-            next_clicked = await _click_next_page(page)
-            if not next_clicked:
-                break
-            
-            await interruptible_sleep(2.0)
-            
-            # 提取下一页数据
-            rows = await _find_elements(page, INVOICE_SELECTORS["invoice_row"])
-            for i, row in enumerate(rows):
+        # 等待发票区域加载（checkbox 出现即可开始提取）
+        try:
+            await page.locator('input[type="checkbox"]').first.wait_for(state="attached", timeout=10_000)
+        except Exception:
+            pass  # 超时也继续尝试提取
+
+        # 方式一：通过 checkbox 定位发票项（最可靠）
+        checkboxes = page.locator('input[type="checkbox"]')
+        checkbox_count = await checkboxes.count()
+        logger.info("found_checkboxes count=%s", checkbox_count)
+
+        if checkbox_count > 0:
+            # 每个 checkbox 对应一个发票项，向上找到父容器
+            for i in range(checkbox_count):
                 try:
-                    invoice_data = await _extract_invoice_from_row(page, row, i)
-                    if invoice_data:
-                        invoices.append(invoice_data)
+                    checkbox = checkboxes.nth(i)
+                    # 获取 checkbox 所在的父级容器（卡片或行）
+                    parent = checkbox.locator("xpath=ancestor::div[contains(@class,'card') or contains(@class,'item') or contains(@class,'row') or contains(@class,'invoice')]").first
+                    if await parent.count() == 0:
+                        # fallback: 向上找 3 层
+                        parent = checkbox.locator("xpath=ancestor::div[3]").first
+
+                    text = await parent.inner_text() if await parent.count() > 0 else ""
+                    is_checked = await checkbox.is_checked()
+
+                    invoice = _parse_invoice_text(text)
+                    if invoice:
+                        invoice["selected"] = is_checked
+                        invoices.append(invoice)
                 except Exception as e:
-                    logger.warning("extract_row_failed page_row=%s error=%s", i, str(e))
+                    logger.warning("extract_checkbox_item_failed index=%s error=%s", i, str(e))
                     continue
-            
-            has_next = await _has_next_page(page)
-        
+
+        # 方式二：如果方式一没提取到，通过文本匹配
+        if not invoices:
+            logger.info("fallback_to_text_extraction")
+            invoices = await _extract_by_text_pattern(page)
+
         logger.info("extraction_complete total_invoices=%s", len(invoices))
         return invoices
-        
+
     except Exception as e:
         logger.error("extract_invoice_list_failed error=%s", str(e))
         return []
 
 
+async def _extract_by_text_pattern(page: Any) -> List[Dict[str, Any]]:
+    """通过文本模式匹配提取发票信息（fallback）。"""
+    invoices: List[Dict[str, Any]] = []
+
+    try:
+        # 查找包含发票号（8位数字）的元素
+        invoice_pattern = page.locator("div, tr, li").filter(
+            has_text=re.compile(r"\d{8}.*[¥￥]\s*[\d,]+")
+        )
+        count = await invoice_pattern.count()
+        logger.info("text_pattern_match count=%s", count)
+
+        for i in range(count):
+            try:
+                element = invoice_pattern.nth(i)
+                text = await element.inner_text()
+                invoice = _parse_invoice_text(text)
+                if invoice:
+                    # 检查是否被选中（附近有 checkbox）
+                    checkbox = element.locator('input[type="checkbox"]')
+                    if await checkbox.count() > 0:
+                        invoice["selected"] = await checkbox.first.is_checked()
+                    else:
+                        invoice["selected"] = False
+                    invoices.append(invoice)
+            except Exception as e:
+                logger.warning("text_pattern_extract_failed index=%s error=%s", i, str(e))
+                continue
+
+    except Exception as e:
+        logger.warning("text_pattern_extraction_error error=%s", str(e))
+
+    return invoices
+
+
+def _parse_invoice_text(text: str) -> Optional[Dict[str, Any]]:
+    """从发票文本中解析结构化数据。
+
+    典型格式：
+      87654321 · ¥553 · transport
+      中国铁路北京局集团有限公司 · 2026-03-12 · 购方税号 121000004000012345
+    """
+    if not text or not text.strip():
+        return None
+
+    lines = [ln.strip() for ln in text.splitlines() if ln.strip()]
+    full_text = " ".join(lines)
+
+    # 提取发票号（8位数字）
+    invoice_no_match = re.search(r"(\d{8})", full_text)
+    invoice_no = invoice_no_match.group(1) if invoice_no_match else ""
+    if not invoice_no:
+        return None
+
+    # 提取金额（¥ 后跟数字）
+    amount_match = re.search(r"[¥￥]\s*([\d,]+\.?\d*)", full_text)
+    amount = 0.0
+    if amount_match:
+        amount_str = amount_match.group(1).replace(",", "")
+        try:
+            amount = float(amount_str)
+        except ValueError:
+            pass
+
+    # 提取类型（transport/lodging/meal/other）
+    invoice_type = ""
+    for tp in ["transport", "lodging", "meal", "other"]:
+        if tp in full_text.lower():
+            invoice_type = tp
+            break
+
+    # 提取公司名（中文公司名，包含常见后缀）
+    company_match = re.search(
+        r"([\u4e00-\u9fa5]{2,}(?:公司|集团|酒店|商贸|有限|商店|宾馆|饭店))", full_text
+    )
+    company = company_match.group(1) if company_match else ""
+
+    # 提取日期（YYYY-MM-DD）
+    date_match = re.search(r"(\d{4}-\d{2}-\d{2})", full_text)
+    date_str = date_match.group(1) if date_match else ""
+
+    # 提取购方税号
+    tax_no_match = re.search(r"购方税号\s*(\S+)", full_text)
+    tax_no = tax_no_match.group(1) if tax_no_match else ""
+    if not tax_no:
+        # fallback: 查找 15-20 位字母数字混合税号
+        tax_no_fallback = re.search(r"([0-9A-Z]{15,20})", full_text)
+        if tax_no_fallback:
+            tax_no = tax_no_fallback.group(1)
+
+    # 判断验真状态
+    verified = "未验真" not in full_text
+
+    return {
+        "invoice_no": invoice_no,
+        "amount": amount,
+        "invoice_type": invoice_type,
+        "company": company,
+        "date": date_str,
+        "tax_no": tax_no,
+        "verified": verified,
+    }
+
+
 async def extract_invoice_detail(page: Any, invoice_index: int = 0) -> Optional[Dict[str, Any]]:
-    """提取单个发票的详细信息。
-    
+    """提取单个发票的详细信息（点击进入详情页后调用）。
+
     Args:
-        page: Playwright页面对象
+        page: Playwright 页面对象
         invoice_index: 发票索引（从0开始）
-        
+
     Returns:
         发票详细信息字典
     """
     try:
-        # 查找发票行
-        rows = await _find_elements(page, INVOICE_SELECTORS["invoice_row"])
-        if invoice_index >= len(rows):
-            logger.warning("invoice_index_out_of_range index=%s total=%s", invoice_index, len(rows))
+        rows = page.locator("tr").filter(has_text=re.compile(r"\d{6,}"))
+        count = await rows.count()
+        if invoice_index >= count:
+            logger.warning("invoice_index_out_of_range index=%s total=%s", invoice_index, count)
             return None
-        
-        # 点击发票行查看详情
-        row = rows[invoice_index]
-        await row.click()
-        await interruptible_sleep(2.0)
-        
-        # 提取详细信息
-        detail = {}
-        for field, selectors in INVOICE_SELECTORS["invoice_detail"].items():
-            value = await _extract_text_by_selectors(page, selectors)
-            if value:
-                detail[field] = value
-        
-        # 提取商品明细
-        items = await _extract_invoice_items(page)
-        if items:
-            detail["items"] = items
-        
-        logger.info("extract_invoice_detail success index=%s fields=%s", invoice_index, list(detail.keys()))
-        return detail
-        
+
+        row = rows.nth(invoice_index)
+        text = await row.inner_text()
+        return _parse_invoice_text(text)
+
     except Exception as e:
         logger.error("extract_invoice_detail_failed error=%s", str(e))
         return None
 
 
-async def _extract_invoice_from_row(page: Any, row: Any, index: int) -> Optional[Dict[str, Any]]:
-    """从行元素提取发票信息。"""
-    try:
-        # 提取行文本
-        row_text = await row.inner_text()
-        
-        # 尝试从文本中提取关键信息
-        invoice_data = {
-            "row_index": index,
-            "row_text": row_text.strip(),
-            "raw_text": row_text,
-        }
-        
-        # 尝试提取发票号码（通常是数字）
-        invoice_match = re.search(r'(\d{8,20})', row_text)
-        if invoice_match:
-            invoice_data["invoice_number"] = invoice_match.group(1)
-        
-        # 尝试提取金额（包含小数点的数字）
-        amount_match = re.search(r'(\d+\.?\d*)', row_text)
-        if amount_match:
-            invoice_data["amount"] = amount_match.group(1)
-        
-        return invoice_data
-        
-    except Exception as e:
-        logger.warning("extract_from_row_failed index=%s error=%s", index, str(e))
-        return None
+async def extract_form_fields(page: Any) -> Dict[str, str]:
+    """提取页面表单字段（报销事由、预算项目、差旅审批单）。"""
+    result: Dict[str, str] = {}
 
-
-async def _extract_invoice_items(page: Any) -> List[Dict[str, str]]:
-    """提取发票商品明细。"""
-    items = []
-    
+    # 报销事由
     try:
-        item_containers = await _find_elements(page, INVOICE_SELECTORS["invoice_detail"]["items"])
-        if not item_containers:
-            return []
-        
-        for container in item_containers:
-            try:
-                item_text = await container.inner_text()
-                items.append({"text": item_text.strip()})
-            except Exception:
-                continue
-        
-        return items
-        
+        reason_input = page.get_by_label("报销事由")
+        if await reason_input.count() > 0:
+            result["reimbursement_reason"] = (await reason_input.input_value()).strip()
     except Exception:
-        return []
+        pass
 
-
-async def _has_next_page(page: Any) -> bool:
-    """检查是否有下一页。"""
+    # 预算项目（下拉框选中项）
     try:
-        next_button = await _find_element(page, INVOICE_SELECTORS["pagination"]["next_button"])
-        if next_button:
-            # 检查按钮是否可用
-            is_disabled = await next_button.get_attribute("disabled")
-            if is_disabled is None:  # 没有disabled属性
-                return True
-        return False
+        budget_selects = page.locator("select")
+        select_count = await budget_selects.count()
+        for i in range(select_count):
+            sel = budget_selects.nth(i)
+            text = await sel.inner_text()
+            if "GDST" in text or "乡村振兴" in text or "预算" in text:
+                # 获取选中的 option
+                selected = sel.locator("option:checked")
+                if await selected.count() > 0:
+                    result["budget_project"] = (await selected.first.inner_text()).strip()
+                else:
+                    result["budget_project"] = text.strip()[:100]
+                break
     except Exception:
-        return False
+        pass
 
-
-async def _click_next_page(page: Any) -> bool:
-    """点击下一页按钮。"""
+    # 差旅审批单（下拉框选中项）
     try:
-        next_button = await _find_element(page, INVOICE_SELECTORS["pagination"]["next_button"])
-        if next_button:
-            await next_button.click()
-            return True
-        return False
-    except Exception as e:
-        logger.warning("click_next_page_failed error=%s", str(e))
-        return False
+        travel_selects = page.locator("select")
+        select_count = await travel_selects.count()
+        for i in range(select_count):
+            sel = travel_selects.nth(i)
+            text = await sel.inner_text()
+            if "CL-" in text or "差旅" in text or "北京" in text:
+                selected = sel.locator("option:checked")
+                if await selected.count() > 0:
+                    result["travel_approval"] = (await selected.first.inner_text()).strip()
+                else:
+                    result["travel_approval"] = text.strip()[:100]
+                break
+    except Exception:
+        pass
 
-
-async def _find_element(page: Any, selectors: list) -> Optional[Any]:
-    """根据选择器列表查找元素。"""
-    for selector in selectors:
-        try:
-            element = page.locator(selector)
-            if await element.count() > 0 and await element.is_visible():
-                return element
-        except Exception:
-            continue
-    return None
-
-
-async def _find_elements(page: Any, selectors: list) -> List[Any]:
-    """根据选择器列表查找多个元素。"""
-    elements = []
-    for selector in selectors:
-        try:
-            found_elements = await page.locator(selector).all()
-            if found_elements:
-                elements.extend(found_elements)
-                break  # 找到一组就停止
-        except Exception:
-            continue
-    return elements
-
-
-async def _extract_text_by_selectors(page: Any, selectors: list) -> Optional[str]:
-    """根据选择器列表提取文本。"""
-    for selector in selectors:
-        try:
-            element = page.locator(selector)
-            if await element.count() > 0:
-                text = await element.inner_text()
-                if text and text.strip():
-                    return text.strip()
-        except Exception:
-            continue
-    return None
+    return result
 
 
 def format_invoice_data(invoices: List[Dict[str, Any]]) -> Dict[str, Any]:
@@ -346,4 +267,4 @@ def format_invoice_data(invoices: List[Dict[str, Any]]) -> Dict[str, Any]:
         "total_count": len(invoices),
         "invoices": invoices,
         "extraction_complete": True,
-    }
+    }

scripts/service/rpa/invoice_rpa.py

@@ -1,8 +1,16 @@
-"""发票RPA主流程：协调登录、导航、提取等操作。"""
+"""发票RPA主流程：协调登录、导航、提取等操作。
+
+完整流程：
+  1. 启动浏览器
+  2. 登录 sandbox.jc2009.com（手机号+密码）
+  3. 找到"智慧校园"并点击进入
+  4. 登录智慧校园（默认 demo 账号）
+  5. 导航到票据合规预审页面
+  6. 提取发票数据
+"""
 
 from __future__ import annotations
 
-import json
 import logging
 import uuid
 from typing import Any, Dict, Optional
@@ -11,15 +19,28 @@ from jiangchang_skill_core.activity import interruptible_sleep, rpa_step
 from jiangchang_skill_core.rpa.video_session import RpaVideoSession
 
 from .browser_session import close_browser_context, start_browser_session
-from .invoice_extractor import extract_invoice_detail, extract_invoice_list, format_invoice_data
-from .login_handler import login_if_needed
+from .invoice_extractor import extract_form_fields, extract_invoice_list, format_invoice_data
+from .login_handler import (
+    enter_smart_campus,
+    login_sandbox,
+    login_smart_campus,
+    navigate_to_invoice_precheck,
+)
 
 logger = logging.getLogger(__name__)
 
 
+def _get_active_page(context: Any) -> Any:
+    """获取 context 中最新的活跃页面（处理新 tab 场景）。"""
+    pages = context.pages
+    if pages:
+        return pages[-1]
+    raise RuntimeError("ERROR:NO_PAGE 浏览器没有可用页面")
+
+
 class InvoiceRpaResult:
     """RPA执行结果。"""
-    
+
     def __init__(
         self,
         success: bool,
@@ -31,7 +52,7 @@ class InvoiceRpaResult:
         self.data = data or {}
         self.error = error
         self.stage = stage
-    
+
     def to_dict(self) -> Dict[str, Any]:
         return {
             "success": self.success,
@@ -41,70 +62,52 @@ class InvoiceRpaResult:
         }
 
 
-@rpa_step("启动浏览器并登录")
-async def _start_and_login(
-    profile_dir: str,
-    username: str,
-    password: str,
-    headless: bool = False,
-) -> tuple[Any, Any, Any, bool]:
-    """启动浏览器并登录。"""
+@rpa_step("启动浏览器")
+async def _start_browser(profile_dir: str, headless: bool = False) -> tuple[Any, Any, Any]:
+    """启动浏览器会话。"""
     pw, context, page = await start_browser_session(profile_dir, headless=headless)
-    
-    # 登录
-    login_success = await login_if_needed(page, username, password)
-    if not login_success:
-        await close_browser_context(pw, context)
-        raise RuntimeError("ERROR:LOGIN_TIMEOUT 登录失败或超时")
-    
-    return pw, context, page, True
+    return pw, context, page
 
 
-@rpa_step("导航到发票预检页面")
-async def _navigate_to_invoice_page(page: Any) -> bool:
-    """导航到发票预检页面。"""
-    try:
-        # 检查当前页面是否已在目标页面
-        if "invoice-precheck" in page.url:
-            logger.info("already_on_invoice_page url=%s", page.url)
-            return True
-        
-        # 导航到目标页面
-        target_url = "https://sandbox.jc2009.com/industries/campus/smartcampus/app/finance/invoice-precheck"
-        await page.goto(target_url, wait_until="domcontentloaded", timeout=60000)
-        
-        # 等待页面加载
-        await interruptible_sleep(3.0)
-        
-        logger.info("navigated_to_invoice_page url=%s", page.url)
-        return True
-        
-    except Exception as e:
-        logger.error("navigation_failed error=%s", str(e))
-        return False
+@rpa_step("登录 sandbox 门户")
+async def _login_sandbox_portal(page: Any, phone: str, password: str) -> bool:
+    """登录 sandbox.jc2009.com 门户。"""
+    return await login_sandbox(page, phone, password)
 
 
-@rpa_step("提取发票信息")
-async def _extract_invoices(page: Any, detail_mode: bool = False) -> Dict[str, Any]:
-    """提取发票信息。"""
-    try:
-        if detail_mode:
-            # 提取详细信息
-            invoices = []
-            rows = await page.locator("tr").all()
-            for i in range(len(rows)):
-                detail = await extract_invoice_detail(page, i)
-                if detail:
-                    invoices.append(detail)
-            return format_invoice_data(invoices)
-        else:
-            # 提取列表信息
-            invoices = await extract_invoice_list(page)
-            return format_invoice_data(invoices)
-        
-    except Exception as e:
-        logger.error("extraction_failed error=%s", str(e))
-        return {"error": str(e)}
+@rpa_step("进入智慧校园")
+async def _enter_campus(page: Any) -> bool:
+    """在平台首页找到并点击智慧校园。"""
+    return await enter_smart_campus(page)
+
+
+@rpa_step("登录智慧校园")
+async def _login_campus(page: Any) -> bool:
+    """登录智慧校园系统。"""
+    return await login_smart_campus(page)
+
+
+@rpa_step("导航到票据合规预审")
+async def _navigate_to_invoice(page: Any) -> bool:
+    """导航到票据合规预审页面。"""
+    return await navigate_to_invoice_precheck(page)
+
+
+@rpa_step("提取发票数据")
+async def _extract_data(page: Any) -> Dict[str, Any]:
+    """提取发票列表和表单字段。"""
+    # 提取表单字段
+    form_fields = await extract_form_fields(page)
+    logger.info("form_fields_extracted keys=%s", list(form_fields.keys()))
+
+    # 提取发票列表
+    invoices = await extract_invoice_list(page)
+    logger.info("invoices_extracted count=%s", len(invoices))
+
+    # 组合结果
+    result = format_invoice_data(invoices)
+    result.update(form_fields)
+    return result
 
 
 async def run_invoice_rpa(
@@ -117,69 +120,107 @@ async def run_invoice_rpa(
     batch_id: str = "",
 ) -> InvoiceRpaResult:
     """运行发票RPA主流程。
-    
+
     Args:
-        username: 用户名
-        password: 密码
+        username: 手机号（sandbox 门户登录）
+        password: 密码（sandbox 门户登录）
         profile_dir: 浏览器配置目录
         headless: 是否无头模式
-        detail_mode: 是否提取详细信息
+        detail_mode: 是否提取详细信息（预留）
         data_dir: 数据目录
         batch_id: 批次ID
-        
+
     Returns:
         InvoiceRpaResult: 执行结果
     """
     if not batch_id:
         batch_id = uuid.uuid4().hex[:12]
-    
+
     logger.info(
-        "invoice_rpa_start username=%s batch_id=%s detail_mode=%s",
-        username[:3] + "***",  # 脱敏
+        "invoice_rpa_start username=%s*** batch_id=%s detail_mode=%s",
+        (username or "")[:3],
         batch_id,
         detail_mode,
     )
-    
+
     pw = None
     context = None
     page = None
-    
+
     try:
-        # 启动浏览器并登录
-        pw, context, page, _ = await _start_and_login(
-            profile_dir, username, password, headless
-        )
-        
-        # 导航到发票页面
-        if not await _navigate_to_invoice_page(page):
+        # 步骤 1：启动浏览器
+        pw, context, page = await _start_browser(profile_dir, headless)
+
+        # 步骤 2：登录 sandbox 门户
+        sandbox_ok = await _login_sandbox_portal(page, username, password)
+        if not sandbox_ok:
             return InvoiceRpaResult(
                 success=False,
-                error="导航到发票页面失败",
+                error="登录 sandbox 门户失败",
+                stage="sandbox_login",
+            )
+
+        # 步骤 3：进入智慧校园（可能打开新 tab，需要刷新 page）
+        campus_ok = await _enter_campus(page)
+        if not campus_ok:
+            return InvoiceRpaResult(
+                success=False,
+                error="进入智慧校园失败",
+                stage="enter_campus",
+            )
+
+        # 刷新 page 引用（处理新 tab 场景）
+        page = _get_active_page(context)
+        logger.info("page_refreshed_after_enter_campus url=%s", page.url)
+
+        # 步骤 4：登录智慧校园
+        login_ok = await _login_campus(page)
+        if not login_ok:
+            return InvoiceRpaResult(
+                success=False,
+                error="登录智慧校园失败",
+                stage="campus_login",
+            )
+
+        # 刷新 page 引用
+        page = _get_active_page(context)
+        logger.info("page_refreshed_after_campus_login url=%s", page.url)
+
+        # 步骤 5：导航到票据合规预审
+        nav_ok = await _navigate_to_invoice(page)
+        if not nav_ok:
+            return InvoiceRpaResult(
+                success=False,
+                error="导航到票据合规预审页面失败",
                 stage="navigation",
             )
-        
-        # 提取发票信息
-        result_data = await _extract_invoices(page, detail_mode)
-        
+
+        # 刷新 page 引用
+        page = _get_active_page(context)
+        logger.info("page_refreshed_after_navigate url=%s", page.url)
+
+        # 步骤 6：提取发票数据
+        result_data = await _extract_data(page)
+
         if "error" in result_data:
             return InvoiceRpaResult(
                 success=False,
                 error=result_data["error"],
                 stage="extraction",
             )
-        
+
         logger.info(
             "invoice_rpa_success total_invoices=%s batch_id=%s",
             result_data.get("total_count", 0),
             batch_id,
         )
-        
+
         return InvoiceRpaResult(
             success=True,
             data=result_data,
             stage="completed",
         )
-        
+
     except Exception as e:
         logger.error("invoice_rpa_failed error=%s batch_id=%s", str(e), batch_id)
         return InvoiceRpaResult(
@@ -187,7 +228,7 @@ async def run_invoice_rpa(
             error=str(e),
             stage="unknown",
         )
-    
+
     finally:
         # 关闭浏览器
         if pw and context:
@@ -207,7 +248,7 @@ async def run_invoice_rpa_with_video(
 ) -> InvoiceRpaResult:
     """带录屏的发票RPA主流程。"""
     batch_id = uuid.uuid4().hex[:12]
-    
+
     async with RpaVideoSession(
         skill_slug=skill_slug,
         skill_data_dir=skill_data_dir,
@@ -216,7 +257,7 @@ async def run_invoice_rpa_with_video(
         closing_title=closing_title,
     ) as video:
         video.add_step("准备启动浏览器")
-        
+
         # 运行RPA
         result = await run_invoice_rpa(
             username=username,
@@ -227,10 +268,10 @@ async def run_invoice_rpa_with_video(
             data_dir=skill_data_dir,
             batch_id=batch_id,
         )
-        
+
         if result.success:
             video.add_step(f"成功提取 {result.data.get('total_count', 0)} 张发票信息")
         else:
             video.add_step(f"提取失败: {result.error}")
-        
-        return result
+
+        return result

scripts/service/rpa/login_handler.py

@@ -1,57 +1,34 @@
-"""登录处理器：处理网站登录流程。"""
+"""登录处理器：两层登录（sandbox 门户 + 智慧校园）。
+
+流程：
+  1. 检测 sandbox.jc2009.com 登录页 → 手机号+密码登录
+  2. 平台首页找到"智慧校园" → 点击进入
+  3. 智慧校园师生登录页 → demo 账号登录
+"""
 
 from __future__ import annotations
 
+import asyncio
 import logging
-import time
+import re
 from typing import Any, Optional
 
 from jiangchang_skill_core.activity import interruptible_sleep
 
 logger = logging.getLogger(__name__)
 
-# 登录相关选择器（需要根据实际页面调整）
-LOGIN_SELECTORS = {
-    "username_input": [
-        "input[name='username']",
-        "input[placeholder*='用户名']",
-        "input[placeholder*='账号']",
-        "#username",
-        "[data-testid='username']",
-    ],
-    "password_input": [
-        "input[name='password']",
-        "input[type='password']",
-        "#password",
-        "[data-testid='password']",
-    ],
-    "login_button": [
-        "button[type='submit']",
-        "button:has-text('登录')",
-        "input[type='submit']",
-        ".login-btn",
-        "[data-testid='login-button']",
-    ],
-    "captcha_input": [
-        "input[name='captcha']",
-        "input[placeholder*='验证码']",
-        "#captcha",
-    ],
-    "captcha_image": [
-        ".captcha-image",
-        "img[alt*='验证码']",
-        "#captcha-image",
-    ],
-}
+# ── Sandbox 门户登录配置 ──
+SANDBOX_LOGIN_PHONE = "15527406659"
+SANDBOX_LOGIN_PASSWORD = "qwer1234"
 
-# 登录成功检测
-LOGIN_SUCCESS_SELECTORS = [
-    ".user-info",
-    ".welcome",
-    "[data-testid='user-avatar']",
-    "a[href*='logout']",
-    ".dashboard",
-]
+# ── 智慧校园默认凭据 ──
+SMART_CAMPUS_DEFAULT_USER = "demo"
+SMART_CAMPUS_DEFAULT_PASSWORD = "demo123"
+
+# ── 超时 ──
+NAVIGATION_TIMEOUT_MS = 30_000
+POLL_INTERVAL_SEC = 1.0  # 轮询间隔（秒）
+TYPE_DELAY_MS = 50  # 逐字符输入延迟（毫秒）
 
 
 async def login_if_needed(
@@ -60,149 +37,286 @@ async def login_if_needed(
     password: str,
     wait_sec: int = 120,
 ) -> bool:
-    """检查登录状态，如需要则执行登录。
-    
-    Args:
-        page: Playwright页面对象
-        username: 用户名
-        password: 密码
-        wait_sec: 等待人工验证的超时时间
-        
-    Returns:
-        bool: 登录是否成功
-    """
-    # 检查是否已登录
-    if await _is_logged_in(page):
-        logger.info("already_logged_in url=%s", page.url)
-        return True
-    
-    # 导航到登录页面
-    if "/login" not in page.url:
-        await page.goto("https://sandbox.jc2009.com/login", wait_until="domcontentloaded")
-        await interruptible_sleep(2.0)
-    
-    # 尝试自动登录
-    login_success = await _try_auto_login(page, username, password)
-    if login_success:
-        return True
-    
-    # 等待人工登录
-    return await _wait_for_human_login(page, wait_sec)
+    """检查登录状态，如需要则执行登录。"""
+    phone = username or SANDBOX_LOGIN_PHONE
+    pwd = password or SANDBOX_LOGIN_PASSWORD
 
-
-async def _try_auto_login(page: Any, username: str, password: str) -> bool:
-    """尝试自动登录。"""
-    try:
-        # 查找用户名输入框
-        username_input = await _find_element(page, LOGIN_SELECTORS["username_input"])
-        if not username_input:
-            logger.warning("username_input_not_found")
-            return False
-        
-        # 查找密码输入框
-        password_input = await _find_element(page, LOGIN_SELECTORS["password_input"])
-        if not password_input:
-            logger.warning("password_input_not_found")
-            return False
-        
-        # 输入用户名（模拟人类输入）
-        await username_input.click()
-        await interruptible_sleep(0.5)
-        await username_input.fill("")
-        await page.keyboard.type(username, delay=100)
-        await interruptible_sleep(0.5)
-        
-        # 输入密码
-        await password_input.click()
-        await interruptible_sleep(0.5)
-        await password_input.fill("")
-        await page.keyboard.type(password, delay=100)
-        await interruptible_sleep(0.5)
-        
-        # 查找并点击登录按钮
-        login_button = await _find_element(page, LOGIN_SELECTORS["login_button"])
-        if not login_button:
-            logger.warning("login_button_not_found")
-            return False
-        
-        await login_button.click()
-        await interruptible_sleep(3.0)
-        
-        # 检查是否登录成功
-        return await _is_logged_in(page)
-        
-    except Exception as e:
-        logger.error("auto_login_failed error=%s", str(e))
+    sandbox_ok = await login_sandbox(page, phone, pwd)
+    if not sandbox_ok:
         return False
 
+    campus_entered = await enter_smart_campus(page)
+    if not campus_entered:
+        return False
 
-async def _wait_for_human_login(page: Any, wait_sec: int) -> bool:
-    """等待人工完成登录。"""
-    print(f"请在浏览器中完成登录，最多等待 {wait_sec} 秒...")
-    deadline = time.monotonic() + wait_sec
-    
-    while time.monotonic() < deadline:
-        if await _is_logged_in(page):
-            print("检测到登录成功")
+    campus_ok = await login_smart_campus(page)
+    return campus_ok
+
+
+# ── 工具函数 ──
+
+
+def _is_sandbox_home(page_url: str) -> bool:
+    return "select" in page_url or "/industries" in page_url
+
+
+async def _type_field(locator, text: str) -> None:
+    """快速填入字段：fill 直接设值（比 keyboard.type 快 10 倍）。"""
+    await locator.click()
+    await locator.fill(text)
+
+
+async def _poll_until(check_fn, timeout_sec: float = 30.0) -> bool:
+    """快速轮询：每 1 秒检测一次，检测到立刻返回。check_fn 必须是无参 async callable。"""
+    elapsed = 0.0
+    while elapsed < timeout_sec:
+        if await check_fn():
             return True
-        
-        # 检查是否有验证码需要处理
-        captcha_present = await _check_captcha(page)
-        if captcha_present:
-            print("检测到验证码，请人工完成验证...")
-        
-        await interruptible_sleep(2.0)
-    
-    print("登录超时")
+        await asyncio.sleep(POLL_INTERVAL_SEC)
+        elapsed += POLL_INTERVAL_SEC
     return False
 
 
-async def _is_logged_in(page: Any) -> bool:
-    """检查是否已登录。"""
+# ── 阶段一：登录 sandbox.jc2009.com ──
+
+
+async def login_sandbox(page: Any, phone: str, password: str) -> bool:
+    """登录 sandbox.jc2009.com 门户。已登录则直接返回 True。"""
+    logger.info("sandbox_login_start phone=%s***", phone[:3])
+
     try:
-        # 检查URL是否包含登录成功标识
-        if "/login" not in page.url and "/index" in page.url:
+        if _is_sandbox_home(page.url) or await page.get_by_role("button", name=re.compile(r"Sign out|退出")).count() > 0 or await page.get_by_text("智慧校园", exact=False).count() > 0:
+            logger.info("sandbox_already_logged_in url=%s", page.url)
             return True
-        
-        # 检查页面元素
-        for selector in LOGIN_SUCCESS_SELECTORS:
+
+        # 找登录表单
+        phone_input = page.get_by_role("textbox", name=re.compile(r"Phone|phone|手机"))
+        if await phone_input.count() == 0:
+            await page.goto("https://sandbox.jc2009.com/", wait_until="domcontentloaded", timeout=NAVIGATION_TIMEOUT_MS)
+            # 用轮询替代固定等待
+            async def _home_check():
+                return _is_sandbox_home(page.url) or await page.get_by_text("智慧校园", exact=False).count() > 0
+            await _poll_until(_home_check, timeout_sec=10.0)
+            if _is_sandbox_home(page.url) or await page.get_by_text("智慧校园", exact=False).count() > 0:
+                logger.info("sandbox_already_logged_in_after_redirect")
+                return True
+            phone_input = page.get_by_role("textbox", name=re.compile(r"Phone|phone|手机"))
+
+        if await phone_input.count() == 0:
+            logger.warning("sandbox_login_page_not_found url=%s", page.url)
+            return False
+
+        logger.info("sandbox_login_page_detected")
+
+        # 输入手机号（fill 直接设值，比 type 快）
+        await _type_field(phone_input, phone)
+        # 输入密码
+        pwd_input = page.get_by_role("textbox", name=re.compile(r"Password|password|密码"))
+        if await pwd_input.count() == 0:
+            pwd_input = page.get_by_label("Password")
+        await _type_field(pwd_input, password)
+
+        # 点击 Sign in
+        sign_in_btn = page.get_by_role("button", name=re.compile(r"Sign in|登录"))
+        await sign_in_btn.click()
+        logger.info("sandbox_login_click_sign_in")
+
+        # 快速轮询等待登录成功
+        async def _login_done():
+            return (
+                _is_sandbox_home(page.url)
+                or await page.get_by_role("button", name=re.compile(r"Sign out|退出")).count() > 0
+                or await page.get_by_text("智慧校园", exact=False).count() > 0
+            )
+
+        if await _poll_until(_login_done, timeout_sec=30.0):
+            logger.info("sandbox_login_success url=%s", page.url)
+            return True
+
+        logger.warning("sandbox_login_timeout")
+        return False
+
+    except Exception as e:
+        logger.error("sandbox_login_failed error=%s url=%s", str(e), page.url)
+        return False
+
+
+# ── 阶段二：进入智慧校园 ──
+
+
+async def enter_smart_campus(page: Any) -> bool:
+    """在平台首页找到并点击"智慧校园"卡片。"""
+    logger.info("enter_smart_campus_start url=%s", page.url)
+
+    try:
+        campus_card = page.get_by_text("智慧校园", exact=False)
+        count = await campus_card.count()
+        if count == 0:
+            logger.warning("smart_campus_not_found")
+            return False
+
+        pages_before = len(page.context.pages)
+
+        # 点击卡片
+        clicked = False
+        for i in range(count):
             try:
-                element = page.locator(selector)
-                if await element.count() > 0 and await element.is_visible():
-                    return True
+                el = campus_card.nth(i)
+                parent = el.locator("xpath=ancestor::a[1]")
+                if await parent.count() > 0:
+                    await parent.first.click()
+                    clicked = True
+                    break
+                parent = el.locator("xpath=ancestor::div[contains(@class,'card') or contains(@class,'item') or contains(@class,'clickable')][1]")
+                if await parent.count() > 0:
+                    await parent.first.click()
+                    clicked = True
+                    break
             except Exception:
                 continue
-        
+        if not clicked:
+            await campus_card.first.click()
+
+        # 快速检测是否有新 tab
+        await asyncio.sleep(1.0)
+        pages_after = len(page.context.pages)
+        active_page = page
+        if pages_after > pages_before:
+            active_page = page.context.pages[-1]
+            logger.info("new_tab url=%s", active_page.url)
+        else:
+            active_page = page.context.pages[-1]
+
+        # 快速轮询等待校园登录页
+        async def _campus_page_ready():
+            p = active_page
+            if await p.get_by_text("师生登录", exact=False).count() > 0:
+                return True
+            if await p.get_by_label("账号").count() > 0:
+                return True
+            if await p.locator('input[type="password"]').count() > 0:
+                return True
+            if await p.get_by_text("工作台", exact=False).count() > 0:
+                return True
+            if await p.get_by_text("华江示范大学", exact=False).count() > 0:
+                return True
+            if "smartcampus" in p.url or "campus" in p.url:
+                return True
+            # 排除还在 sandbox 门户的情况
+            if await p.get_by_text("Password sign-in", exact=False).count() > 0:
+                return False
+            login_btn = p.get_by_role("button", name=re.compile(r"登录"))
+            if await login_btn.count() > 0:
+                return True
+            return False
+
+        if await _poll_until(_campus_page_ready, timeout_sec=30.0):
+            logger.info("smart_campus_page_ready url=%s", active_page.url)
+            return True
+
+        logger.warning("smart_campus_timeout url=%s", active_page.url)
         return False
-    except Exception:
+
+    except Exception as e:
+        logger.error("enter_smart_campus_failed error=%s url=%s", str(e), page.url)
         return False
 
 
-async def _check_captcha(page: Any) -> bool:
-    """检查是否有验证码。"""
+# ── 阶段三：登录智慧校园 ──
+
+
+async def login_smart_campus(page: Any) -> bool:
+    """登录智慧校园系统。"""
+    logger.info("smart_campus_login_start")
+
     try:
-        for selector in LOGIN_SELECTORS["captcha_input"]:
-            element = page.locator(selector)
-            if await element.count() > 0 and await element.is_visible():
-                return True
-        
-        for selector in LOGIN_SELECTORS["captcha_image"]:
-            element = page.locator(selector)
-            if await element.count() > 0 and await element.is_visible():
-                return True
-        
+        # 已登录直接返回
+        if await page.get_by_text("工作台", exact=False).count() > 0:
+            logger.info("smart_campus_already_logged_in")
+            return True
+
+        # 填账号（如果为空）
+        account_input = page.get_by_label("账号")
+        if await account_input.count() == 0:
+            account_input = page.locator('input[placeholder*="账号"], input[placeholder*="用户名"]')
+        if await account_input.count() > 0:
+            val = await account_input.input_value()
+            if not val or not val.strip():
+                await _type_field(account_input, SMART_CAMPUS_DEFAULT_USER)
+
+        # 填密码（如果为空）
+        pwd_input = page.get_by_label("密码")
+        if await pwd_input.count() == 0:
+            pwd_input = page.locator('input[type="password"]')
+        if await pwd_input.count() > 0:
+            val = await pwd_input.input_value()
+            if not val or not val.strip():
+                await _type_field(pwd_input, SMART_CAMPUS_DEFAULT_PASSWORD)
+
+        # 点击登录
+        login_btn = page.get_by_role("button", name=re.compile(r"登录|登 录"))
+        if await login_btn.count() == 0:
+            login_btn = page.locator('button:has-text("登录"), button[type="submit"]')
+        await login_btn.first.click()
+        logger.info("smart_campus_login_click")
+
+        # 快速轮询等待进入系统
+        async def _workbench_ready():
+            return await page.get_by_text("工作台", exact=False).count() > 0
+
+        if await _poll_until(_workbench_ready, timeout_sec=20.0):
+            logger.info("smart_campus_login_success")
+            return True
+
+        logger.warning("smart_campus_login_timeout")
         return False
-    except Exception:
+
+    except Exception as e:
+        logger.error("smart_campus_login_failed error=%s", str(e))
         return False
 
 
-async def _find_element(page: Any, selectors: list) -> Optional[Any]:
-    """根据选择器列表查找元素。"""
-    for selector in selectors:
-        try:
-            element = page.locator(selector)
-            if await element.count() > 0 and await element.is_visible():
-                return element
-        except Exception:
-            continue
-    return None
+# ── 导航到票据合规预审 ──
+
+
+async def navigate_to_invoice_precheck(page: Any) -> bool:
+    """从智慧校园主界面导航到票据合规预审。"""
+    logger.info("navigate_to_invoice_precheck_start")
+
+    try:
+        # 直接 URL 导航
+        target_url = "https://sandbox.jc2009.com/industries/campus/smartcampus/app/finance/invoice-precheck"
+        await page.goto(target_url, wait_until="domcontentloaded", timeout=NAVIGATION_TIMEOUT_MS)
+
+        # 快速轮询等待页面标题出现
+        async def _title_ready():
+            return await page.get_by_text("票据合规性秒级预审", exact=False).count() > 0
+
+        if await _poll_until(_title_ready, timeout_sec=15.0):
+            logger.info("invoice_precheck_page_loaded")
+            return True
+
+        # fallback: 通过菜单
+        logger.info("direct_nav_failed_try_menu")
+        await page.goto("https://sandbox.jc2009.com/industries/campus/smartcampus/", wait_until="domcontentloaded", timeout=NAVIGATION_TIMEOUT_MS)
+
+        finance_menu = page.get_by_text("财务处", exact=True)
+        if await finance_menu.count() > 0:
+            await finance_menu.click()
+            await asyncio.sleep(0.5)
+
+        invoice_menu = page.get_by_text("票据合规预审", exact=True)
+        if await invoice_menu.count() == 0:
+            invoice_menu = page.get_by_text(re.compile(r"票据合规"))
+        if await invoice_menu.count() > 0:
+            await invoice_menu.first.click()
+            if await _poll_until(_title_ready, timeout_sec=15.0):
+                logger.info("invoice_precheck_page_loaded_via_menu")
+                return True
+
+        logger.warning("invoice_precheck_page_not_loaded")
+        return False
+
+    except Exception as e:
+        logger.error("navigate_to_invoice_precheck_failed error=%s", str(e))
+        return False