差旅报销和普通报销都已经完成

.gitignore

@@ -10,4 +10,5 @@ logs/
 .vscode/
 uploads/
 .env
+images/
 scripts/data/

README.md

@@ -52,19 +52,66 @@
 
 ```mermaid
 flowchart TB
-    PDF[PDF 发票 / 图片] --> Extract[extractor 提取]
-    Extract --> Classify{发票类型分类}
+    PDF[PDF 发票 / 图片] --> Extract[extractor 多模态提取]
+    Extract --> Cache[(.invoice_cache/*.json)]
+
+    Cache --> Classify{发票类型分类}
     Classify -->|差旅发票| Travel[高铁票 / 酒店住宿]
     Classify -->|普通发票| General[普通发票]
-    Travel --> CSV[(invoice_summary.csv)]
-    General --> CSV
-    CSV -->|仅普通发票| Fill[fill_consumable_doc]
+    Classify -->|支付记录| Payment[支付截图]
+    Classify -->|申请单| Application[出差事前申请单]
+
+    Travel --> Matcher[matcher 金额匹配]
+    Payment --> Matcher
+    Matcher --> MatchResult[(match_result.json)]
+
+    Cache --> TravelLLM[LLM 差旅信息提取]
+    MatchResult --> TravelLLM
+    TravelLLM --> TravelInfo[(travel_info.json)]
+
+    Cache --> NormalLLM[LLM 普通发票信息提取]
+    MatchResult --> NormalLLM
+    NormalLLM --> NormalInfo[(normal_info.json)]
+
+    TravelInfo -->|差旅基本信息| Bot_T[bot/travel.py<br/>差旅填报流程]
+    TravelInfo -->|报销明细| Bot_T
+    TravelInfo -->|支付方式| Bot_T
+    TravelInfo -->|补助清单| Bot_T
+    TravelInfo -->|附件清单| Bot_T
+    Bot_T --> Submit_T[差旅报销提交]
+
+    NormalInfo -->|报销说明| Bot_G[bot/normal.py<br/>普通填报流程]
+    NormalInfo -->|发票总数/金额| Bot_G
+    NormalInfo -->|支付方式| Bot_G
+    NormalInfo -->|附件清单| Bot_G
+    Bot_G --> Submit_G[普通报销提交]
+
+    General --> CSV[(invoice_summary.csv)]
+    CSV --> Fill[fill_consumable_doc]
     Fill --> Doc[易耗品、出库单.doc]
-    CSV --> Bot[bot 浏览器自动化]
-    Bot -->|差旅模式| Submit_T[差旅报销填报]
-    Bot -->|普通模式| Submit_G[普通报销填报]
 ```
 
+### 关键中间产物
+
+| 文件 | 生成阶段 | 作用 |
+|------|---------|------|
+| `.invoice_cache/*.json` | extractor 提取 | 单张发票/支付记录/申请单的结构化数据 |
+| `match_result.json` | matcher 匹配 | 支付截图与发票的关联关系（按金额匹配） |
+| `travel_info.json` | LLM 差旅信息提取 | 综合发票缓存 + 匹配结果，生成差旅报销所需的全部结构化数据 |
+| `normal_info.json` | LLM 普通发票信息提取 | 综合普通发票 + 匹配结果，生成普通报销所需的全部结构化数据 |
+| `invoice_summary.csv` | extractor 提取 | 普通发票汇总（用于生成易耗品出库单） |
+
+### bot 模块架构
+
+`bot/` 包负责浏览器自动化填报，仅接收已提取的信息并执行填报操作，不承担信息提取职责：
+
+| 模块 | 职责 |
+|------|------|
+| `bot/base.py` | `BaseBot` 基类：浏览器生命周期、登录、导航、截图 |
+| `bot/travel.py` | 差旅填报流程：基本信息 → 差旅明细 → 支付方式 → 补助清单 → 附件上传 |
+| `bot/normal.py` | 普通填报流程：基本信息 → 总明细 → 支付方式 → 附件上传 |
+| `bot/__init__.py` | 入口函数：`run_bot()` / `run_bot_web()`，负责类型判断和流程路由 |
+
 ## 环境要求
 
 - **Python 3.12+**

src/README.md

@@ -1,5 +1,5 @@
 ---
-last_reviewed: 2026-06-11
+last_reviewed: 2026-06-12
 ---
 
 # src — 主源码目录
@@ -12,41 +12,42 @@ last_reviewed: 2026-06-11
 |-----------|------|
 | `__init__.py` | 包初始化：提供 `get_logger()` 日志工厂（支持终端 + 文件双输出，按日期自动分文件） |
 | `config.py` | 配置加载：从 `config.json` 读取用户凭据和默认值，从环境变量读取服务端配置（SSO 地址、LLM 参数） |
-| `pipeline.py` | 流程编排：串联发票提取 → 分类 → CSV 保存 → 浏览器填报，支持分步执行 |
+| `pipeline.py` | 流程编排：串联发票提取 → 类型判断 → 差旅/普通信息提取 → 浏览器填报，支持分步执行 |
 | `main.py` | CLI 入口：支持 `--step` 分步执行、`-u/-p` 覆盖凭据、`--cache-dir` 指定缓存目录 |
-| `bot.py` | 浏览器自动化：Playwright 驱动的财务系统填报机器人（含差旅/普通两种模式，支持 headless） |
+| `bot/` | 浏览器自动化：Playwright 驱动的财务系统填报机器人（仅负责接收信息并填报） |
 | `doc/` | 文档处理模块：PDF 渲染、LLM 提取、支付匹配、发票分类、出库单生成 |
 | `web/` | Web 界面模块：Flask 应用、SSE 日志、可编辑表格、移动端上传、会话隔离 |
 
 ## 数据流
 
+```mermaid
+graph TD
+    A[CLI/Web 入口] --> B["pipeline.py (编排)"]
+    B --> C["doc/extractor.py (统一提取入口)"]
+    C --> D["doc/pdf.py (PDF 渲染为图片)"]
+    C --> E["doc/llm_extractor.py (多模态 LLM 识别)"]
+    E --> F["发票 invoice_type=train/hotel/general"]
+    E --> G["支付记录 invoice_type=payment"]
+    E --> H["出差事前申请单 invoice_type=application"]
+    C --> I["doc/matcher.py (发票与支付记录按金额匹配)"]
+    I --> J["一对一匹配 发票数 == 刷卡数"]
+    I --> K["一对多匹配 贪心算法 相对容差 3%"]
+    C --> L["doc/invoice.py (CSV/JSON 读写)"]
+    L --> M["payment_records.csv (支付记录级别)"]
+    L --> N["invoice_summary.csv (发票级别)"]
+    L --> O["travel_applications.json (出差申请单)"]
+    B --> R{"判断报销类型"}
+    R -->|差旅| T["doc/llm_extractor.py (差旅信息提取)"]
+    R -->|普通| V["doc/llm_extractor.py (普通发票信息提取)"]
+    T --> W["travel_info.json (差旅信息: 交通/住宿明细、补贴、附件清单)"]
+    V --> X["normal_info.json (普通发票信息: 报销说明、发票总数、总金额、支付方式、附件清单)"]
+    W --> P["bot/ (浏览器填报 - 仅接收信息并填报)"]
+    X --> P
+    P --> Q["差旅模式: travel_info.json → 填报差旅单 → 上传差旅附件"]
+    P --> S["普通模式: 基本信息 → 录入明细 → 支付信息 → 上传附件"]
 ```
-CLI/Web 入口 → pipeline.py (编排)
-                   ↓
-            doc/extractor.py (统一提取入口)
-                   ↓
-            ┌──── doc/pdf.py (PDF 渲染为图片)
-            │
-            ├── doc/llm_extractor.py (多模态 LLM 识别)
-            │       ├── 发票 (invoice_type=train/hotel/general)
-            │       ├── 支付记录 (invoice_type=payment)
-            │       └── 出差事前申请单 (invoice_type=application)
-            │
-            ├── doc/matcher.py (发票与支付记录按金额匹配)
-            │       ├── 一对一匹配 (发票数 == 刷卡数)
-            │       └── 一对多匹配 (贪心算法，相对容差 3%)
-            │
-            └── doc/invoice.py (CSV/JSON 读写)
-                    ├── payment_records.csv (支付记录级别)
-                    ├── invoice_summary.csv (发票级别)
-                    └── travel_applications.json (出差申请单)
-                   ↓
-            doc/fill_consumable_doc.py (普通发票 → Word 出库单)
-                   ↓
-            bot.py (浏览器填报)
-                ├── 差旅模式: 差旅信息提取 → 填报差旅单 → 上传差旅附件
-                └── 普通模式: 基本信息 → 录入明细 → 支付信息 → 上传附件
-```
+
+**数据流变更（2026-06-11）：** 差旅信息提取从 `bot.py` 提升到 `pipeline.py` 编排层。在发票提取和匹配完成后立即判断报销类型，差旅发票调用 LLM 提取 `travel_info.json`，普通发票调用 LLM 提取 `normal_info.json`。Bot 仅负责接收信息并填报，不再承担信息提取职责。
 
 ## 文档处理子模块 (`doc/`)
 
@@ -57,6 +58,7 @@ CLI/Web 入口 → pipeline.py (编排)
 - **JSON 缓存**：提取结果缓存于 `.invoice_cache/`，避免重复处理
 - **金额匹配**：支持一对多匹配，相对容差 3%，未匹配发票单独列为记录
 - **差旅信息提取**：综合发票、支付记录和匹配结果，提取出差事由、地点、时间等
+- **普通发票信息提取**：综合普通发票、支付记录和匹配结果，提取报销说明、发票总数、总金额、支付方式、附件清单
 - **出库单生成**：将 CSV 数据填入 Word 模板（pywin32 COM，仅 Windows）
 
 ## Web 界面子模块 (`web/`)

src/__init__.py

@@ -22,15 +22,26 @@ def get_logger(name: str) -> logging.Logger:
 
     输出格式: 2026-05-24 12:34:56 [INFO ] extractor: 扫描目录: ...
     日志同时输出到终端和 logs/<日期>.log
+
+    只在最顶层的 logger 上添加标准 handler（stream + file），
+    子 logger 通过 propagate 将日志传递给父 logger 统一处理。
+    这样 _SSELogHandler 只需挂在父 logger 上即可捕获所有子日志。
     """
     logger = logging.getLogger(name)
+    logger.setLevel(logging.INFO)
 
-    # 使用专属标记判断是否已初始化标准 handler（stream + file），
-    # 避免被 _SSELogHandler 等外部 handler 干扰
-    if not getattr(logger, "_standard_handlers_initialized", False):
-        logger.setLevel(logging.INFO)
+    # 检查是否有父 logger 已初始化标准 handler
+    # 如果有，子 logger 不重复添加，靠 propagate 传递即可
+    parent_name = name.rsplit(".", 1)[0] if "." in name else None
+    parent_has_handlers = False
+    if parent_name:
+        parent = logging.getLogger(parent_name)
+        parent_has_handlers = getattr(parent, "_standard_handlers_initialized", False)
+
+    if not getattr(logger, "_standard_handlers_initialized", False) and not parent_has_handlers:
         formatter = logging.Formatter(_LOG_FMT, _LOG_DATE_FMT)
 
+        # 只有没有已初始化的父 logger 时，才添加标准 handler
         # 终端输出
         utf8_stream = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
         stream_handler = logging.StreamHandler(utf8_stream)

src/bot.py

@@ -1,649 +0,0 @@
-"""
-浏览器自动化填报
-
-使用 Playwright 操作财务报销系统，自动完成登录、填单、上传附件等操作。
-
-对外接口:
-    run_bot(config, invoices)                           启动浏览器并执行填报流程
-"""
-
-import json
-from pathlib import Path
-from typing import Any
-
-from . import get_logger
-
-log = get_logger("bot")
-
-
-# ------------------------------------------------------------------
-# 日期格式化
-# ------------------------------------------------------------------
-
-
-def _format_date(date_str: str) -> str:
-    """将 '2026/5/13' 或 '2026-5-13' 转为 '2026-05-13'"""
-    if not date_str:
-        return ""
-    parts = date_str.replace("-", "/").split("/")
-    if len(parts) == 3:
-        return f"{parts[0].zfill(4)}-{parts[1].zfill(2)}-{parts[2].zfill(2)}"
-    return date_str
-
-
-def _classify_invoice_batch(
-    invoices: list[dict[str, str]],
-) -> dict[str, list[dict[str, str]]]:
-    """按发票类型分组"""
-    travel: list[dict[str, str]] = []
-    general: list[dict[str, str]] = []
-    application: list[dict[str, str]] = []
-    for inv in invoices:
-        inv_type = inv.get("invoice_type", "general")
-        if inv_type == "application":
-            application.append(inv)
-        elif inv_type in ("train", "hotel"):
-            travel.append(inv)
-        else:
-            general.append(inv)
-    return {"travel": travel, "general": general, "application": application}
-
-
-# ------------------------------------------------------------------
-# 报销机器人
-# ------------------------------------------------------------------
-
-
-class ReimburseBot:
-    """财务报销自动化机器人"""
-
-    def __init__(self, config: dict[str, Any], headless: bool = False, work_dir: Path | None = None):
-        self.config = config
-        self.headless = headless
-        self.work_dir: Path | None = None
-        self.browser: Any = None
-        self.context: Any = None
-        self.page: Any = None
-
-        from playwright.sync_api import sync_playwright
-
-        self._pw_ctx = sync_playwright()
-        self.pw = self._pw_ctx.__enter__()
-
-    def launch(self) -> None:
-        """启动浏览器"""
-        self.browser = self.pw.chromium.launch(headless=self.headless)
-        self.context = self.browser.new_context(viewport={"width": 1360, "height": 768})
-        self.page = self.context.new_page()
-        self.page.set_default_timeout(30000)
-
-    def login_portal(self) -> None:
-        """登录信息门户"""
-        log.info("登录信息门户...")
-
-        self.page.goto(self.config["sso_login_url"], wait_until="domcontentloaded")
-        self._wait_for('text="微信扫码登录"', timeout=5000)
-
-        try:
-            self.page.fill('input[placeholder*="工号"], input[placeholder*="学号"]', self.config["username"])
-            self.page.fill('input[placeholder*="密码"]', self.config["password"])
-        except Exception:
-            log.warning("未找到登录输入框，可能已登录")
-
-        try:
-            checkbox = self.page.query_selector('input[type="checkbox"]')
-            if checkbox and not checkbox.is_checked():
-                checkbox.click()
-        except Exception:
-            pass
-
-        for selector in ['button:has-text("登录")', 'input[value="登录"]', 'text="登录"']:
-            try:
-                self.page.click(selector, timeout=3000)
-                break
-            except Exception:
-                continue
-
-        self._wait_for_portal()
-
-    def _wait_for_portal(self) -> None:
-        """等待跳转到统一信息平台"""
-        for _ in range(30):
-            self.page.wait_for_timeout(1000)
-            url = self.page.url
-            if any(kw in url for kw in ("tyrz.fynu.edu.cn/zs-uip", "tyrz.fynu.edu.cn/oshall", "portal")):
-                self._screenshot("portal_loaded")
-                return
-        log.error("等待门户跳转超时")
-        self._screenshot("portal_timeout")
-        raise TimeoutError("登录超时，未跳转到信息门户")
-
-    def navigate_to_reimburse(self, page_key: str = "reimburse_page") -> None:
-        """从统一信息平台进入报销系统"""
-        log.info("进入报销系统...")
-        self._wait_for('text="快捷入口"', timeout=5000)
-
-        try:
-            self.page.click('text="财务系统"', timeout=5000)
-        except Exception:
-            log.warning("未找到财务系统入口")
-
-        new_tab = None
-        for _ in range(15):
-            self.page.wait_for_timeout(1000)
-            for p in self.context.pages:
-                if "dddl" in p.url or "210.45.32.214" in p.url:
-                    new_tab = p
-                    break
-            if new_tab:
-                break
-
-        if new_tab:
-            self.page = new_tab
-            self._wait_for('text="网络报销"', timeout=5000)
-        else:
-            log.warning(f"未找到单点登录页面，当前 URL: {self.page.url}")
-
-        for p in self.context.pages[:-1]:
-            try:
-                p.close()
-            except Exception:
-                pass
-
-        try:
-            link = self.page.query_selector('a:has(img[src*="wlbx"])')
-            if link:
-                reimburse_url = link.get_attribute("href")
-                self.page.goto(reimburse_url, wait_until="domcontentloaded", timeout=15000)
-        except Exception:
-            pass
-
-        self._wait_for('text="报销录入"', timeout=5000)
-        common_url = self.config["reimburse_url"] + self.config[page_key]
-        self.page.goto(common_url, wait_until="domcontentloaded", timeout=15000)
-        self._wait_for('text="单据状态:"', timeout=5000)
-
-    def create_new_form(self) -> None:
-        """点击「新增」创建新单据"""
-        log.info("创建新单据...")
-        self.page.wait_for_timeout(2000)
-
-        try:
-            self.page.click("#insert", timeout=5000)
-        except Exception:
-            try:
-                self.page.click("text=新增", timeout=3000)
-            except Exception as err:
-                self._screenshot("no_add_button")
-                raise RuntimeError("无法点击新增按钮") from err
-
-        self.page.wait_for_timeout(3000)
-        self._screenshot("after_add_click")
-
-    def fill_travel_info(self, basic_info: dict[str, Any]) -> None:
-        """填写差旅报销基本信息"""
-        log.info("填写差旅报销信息...")
-
-        try:
-            self.page.fill("#CAUSE", basic_info.get("travel_purpose", ""))
-            self.page.fill("#SITE", basic_info.get("travel_location", ""))
-
-            self.page.click("#PROJECTCODE", timeout=10000)
-            self.page.wait_for_timeout(1000)
-            self.page.wait_for_selector("#promodal .fixed-table-body tbody tr", timeout=10000)
-            first_row = self.page.query_selector("#promodal .fixed-table-body tbody tr")
-            if first_row:
-                first_row.click()
-                self.page.wait_for_timeout(1000)
-
-            self.page.fill("#THEKSRQ", _format_date(basic_info.get("start_date", "")))
-            self.page.fill("#THEJSRQ", _format_date(basic_info.get("end_date", "")))
-            self.page.click("#saveAndNext", timeout=5000)
-            self.page.wait_for_timeout(2000)
-            self._screenshot("travel_basic_done")
-        except Exception:
-            log.error("填写基本信息失败")
-            self._screenshot("travel_basic_error")
-
-    def fill_basic_info(self, description: str = "元器件采购报销") -> None:
-        """填写基本信息"""
-        log.info("填写基本信息...")
-
-        try:
-            self.page.fill("#EXPENEXPLAIN", description)
-        except Exception:
-            pass
-
-        try:
-            self.page.click("#PROJECTCODE", timeout=10000)
-            self.page.wait_for_timeout(1000)
-        except Exception:
-            pass
-
-        self._screenshot("step3_project_modal")
-
-        try:
-            self.page.wait_for_selector("#promodal .fixed-table-body tbody tr", timeout=10000)
-            first_row = self.page.query_selector("#promodal .fixed-table-body tbody tr")
-            if first_row:
-                first_row.click()
-                self.page.wait_for_timeout(1000)
-        except Exception:
-            pass
-
-        self._screenshot("step3_project_selected")
-
-        try:
-            self.page.click("#saveAndNext", timeout=5000)
-            self.page.wait_for_timeout(2000)
-        except Exception:
-            pass
-
-        self._screenshot("step3_done")
-
-    def add_travel_items(self, travel_items: dict[str, Any]) -> None:
-        """录入差旅报销明细"""
-        vehicle_map = {
-            "火车": "01",
-            "汽车": "02",
-            "轮船": "03",
-            "自带车": "04",
-            "公务车": "05",
-            "飞机": "06",
-            "租车": "07",
-            "自驾车": "08",
-        }
-        try:
-            traffic_info = travel_items.get("transport_fee") or []
-            for item in traffic_info:
-                self.page.click("#insertDetail", timeout=5000)
-                self._wait_for('text="增加明细"', timeout=5000)
-                self.page.select_option("#cost", "1")
-                self.page.wait_for_timeout(500)
-                vehicle = item.get("vehicle_type", "")
-                if vehicle in vehicle_map:
-                    self.page.select_option("#jtgj", vehicle_map[vehicle])
-
-                self.page.fill("#ksdd", item.get("departure_place", ""))
-                self.page.fill("#jsdd", item.get("arrival_place", ""))
-                self.page.fill(
-                    '#t1 input[name="expenPwTraveldetail.MONEY"]',
-                    str(item.get("amount", "")),
-                )
-                self.page.fill(
-                    '#t1 input[name="expenPwTraveldetail.HOWBILL"]',
-                    str(item.get("bill_count", "")),
-                )
-                self.page.fill(
-                    '#t1 input[name="expenPwTraveldetail.SMARK"]',
-                    str(item.get("remark", "")),
-                )
-                self.page.click("#detailAdd", timeout=3000)
-                self.page.wait_for_timeout(1000)
-
-            hotel_info = travel_items.get("hotel_fee") or []
-            for item in hotel_info:
-                self.page.click("#insertDetail", timeout=5000)
-                self._wait_for('text="增加明细"', timeout=5000)
-                self.page.select_option("#cost", "2")
-                self.page.wait_for_timeout(500)
-                self.page.fill("#ksrq2", _format_date(str(item.get("checkin_date", ""))))
-                self.page.fill("#jsrq2", _format_date(str(item.get("checkout_date", ""))))
-                self.page.fill("#ts2", str(item.get("days", "")))
-                self.page.fill("#rs2", str(item.get("person_count", "")))
-                self.page.fill(
-                    '#t2 input[name="expenPwTraveldetail.FPMONEY"]',
-                    str(item.get("invoice_amount", "")),
-                )
-                self.page.fill(
-                    '#t2 input[name="expenPwTraveldetail.MONEY"]',
-                    str(item.get("reimburse_amount", "")),
-                )
-                self.page.fill(
-                    '#t2 input[name="expenPwTraveldetail.SMARK"]',
-                    str(item.get("remark", "")),
-                )
-                self.page.click("#detailAdd", timeout=3000)
-                self.page.wait_for_timeout(1000)
-
-            conference_info = travel_items.get("conference_fee") or []
-            for item in conference_info:
-                self.page.click("#insertDetail", timeout=5000)
-                self._wait_for('text="增加明细"', timeout=5000)
-                self.page.select_option("#cost", "3")
-                self.page.wait_for_timeout(500)
-                self.page.fill(
-                    '#t3 input[name="expenPwTraveldetail.HOWBILL"]',
-                    str(item.get("bill_count", "")),
-                )
-                self.page.fill(
-                    '#t3 input[name="expenPwTraveldetail.MONEY"]',
-                    str(item.get("amount", "")),
-                )
-                self.page.fill(
-                    '#t3 input[name="expenPwTraveldetail.SMARK"]',
-                    str(item.get("remark", "")),
-                )
-                self.page.click("#detailAdd", timeout=3000)
-                self.page.wait_for_timeout(1000)
-        except Exception as e:
-            log.error(f"录入总明细失败: {e}")
-            self._screenshot("item_total_error")
-            raise
-
-    def add_reimburse_items(self, invoices: list[dict[str, Any]]) -> None:
-        """录入报销明细（一条总明细）"""
-        card_amount = sum(inv["card_amount"] for inv in invoices)
-        log.info(f"录入报销明细 (合计 ¥{card_amount:.2f})...")
-
-        try:
-            self.page.click("#insertDetail", timeout=5000)
-            self._wait_for('text="经济事项名称"', timeout=5000)
-            self.page.click("#economicscode2")
-            self.page.wait_for_timeout(1000)
-
-            try:
-                self.page.wait_for_selector("#econmodal .fixed-table-body tbody tr", timeout=10000)
-                rows = self.page.query_selector_all("#econmodal .fixed-table-body tbody tr")
-                if len(rows) >= 3:
-                    rows[2].click()
-                    self.page.wait_for_timeout(1000)
-            except Exception:
-                pass
-
-            self.page.fill('input[name="expenPwCommondetail.HOWBILLS"]', f"{len(invoices)}")
-            self.page.fill("#je_zwzcdz", f"{card_amount:.2f}")
-            self.page.click("#detailAdd", timeout=3000)
-            self.page.wait_for_timeout(1000)
-
-            self._screenshot("item_total")
-        except Exception as e:
-            log.error(f"录入总明细失败: {e}")
-            self._screenshot("item_total_error")
-            raise
-
-    def fill_travel_payment(self, payment_info: list[dict[str, Any]]) -> None:
-        """录入差旅支付信息"""
-        log.info("录入差旅支付信息...")
-        try:
-            self.page.click('text="下一步(支付方式)"', timeout=5000)
-            self._wait_for('text="下一步(补助清单)"', timeout=5000)
-
-            for info in payment_info:
-                self.page.click("#insertPay", timeout=5000)
-                self.page.wait_for_timeout(1000)
-                self.page.fill("#personid2", self.config["default_name"])
-                self.page.fill("#accountname2", self.config["default_person_id"])
-                self.page.fill("#receiptdate2", _format_date(info["card_date"]))
-                self.page.fill("#localaccount2", self.config["default_card_no"])
-                self.page.fill("#receiptmoney2", str(info["card_amount"]))
-                self.page.fill("#money2", str(info["card_amount"]))
-                self.page.fill("#merchant2", info.get("merchant", ""))
-                self.page.fill("#smark2", info.get("remark", ""))
-                self.page.click("#payAdd", timeout=3000)
-                self.page.wait_for_timeout(1000)
-        except Exception as e:
-            log.error(f"支付方式录入失败: {e}")
-            self._screenshot("step5_error")
-            raise
-
-        self._screenshot("step5_done")
-
-    def fill_payment(self, invoices: list[dict[str, Any]]) -> None:
-        """录入支付信息"""
-        log.info("录入支付信息...")
-        try:
-            self.page.click('text="下一步(支付方式)"', timeout=5000)
-            self._wait_for('text="下一步(附件清单)"', timeout=5000)
-
-            for inv in invoices:
-                self.page.click("#insertPay", timeout=5000)
-                self.page.wait_for_timeout(1000)
-                self.page.fill("#personid2", inv["person_id"])
-                self.page.fill("#accountname2", inv["person_name"])
-                self.page.fill("#receiptdate2", inv["card_date"])
-                self.page.fill("#localaccount2", inv["card_no"])
-                self.page.fill("#receiptmoney2", str(inv["card_amount"]))
-                self.page.fill("#money2", str(inv["card_amount"]))
-                self.page.fill("#merchant2", inv["seller_name"])
-                self.page.fill("#smark2", inv["remark"])
-                self.page.click("#payAdd", timeout=3000)
-                self.page.wait_for_timeout(1000)
-        except Exception as e:
-            log.error(f"支付方式录入失败: {e}")
-            self._screenshot("step5_error")
-            raise
-
-        self._screenshot("step5_done")
-
-    def upload_attachments(self, invoices: list[dict[str, Any]]) -> None:
-        """上传附件"""
-        log.info("上传附件...")
-        try:
-            self.page.click("#next4", timeout=5000)
-            self._wait_for("#submit2", timeout=5000)
-
-            attachment_files = sorted((self.work_dir or Path(__file__).parent.parent).glob("*.pdf"))
-            if not attachment_files:
-                log.warning("未找到附件 PDF，跳过附件上传")
-                return
-
-            for i, inv in enumerate(invoices):
-                file_path = attachment_files[i] if i < len(attachment_files) else None
-                try:
-                    self._wait_for("#insertAcc", timeout=20000)
-                    self.page.click("#insertAcc", timeout=5000)
-                    self._wait_for("#fjlx", timeout=5000)
-                    self.page.select_option("#fjlx", "1")
-                    explanation = f"{inv['item_name']} - {inv['invoice_no']}"
-                    self.page.fill("#fpsmxx", explanation)
-                except Exception:
-                    pass
-
-                if file_path and file_path.exists():
-                    try:
-                        self.page.set_input_files("#file", str(file_path))
-                        self.page.wait_for_timeout(1000)
-                    except Exception as e:
-                        log.error(f"文件上传失败: {e}")
-                try:
-                    self.page.click("#cjtj", timeout=5000)
-                except Exception:
-                    try:
-                        self.page.press("body", "Escape")
-                    except Exception:
-                        pass
-            log.info("上传附件完成")
-        except Exception as e:
-            log.error(f"附件上传失败: {e}")
-            self._screenshot("step6_error")
-            raise
-
-        self._screenshot("step6_done")
-
-    def upload_travel_attachments(self, attachment_info: list[dict[str, Any]]) -> None:
-        """上传差旅附件"""
-        log.info("上传差旅附件...")
-        try:
-            self.page.click("#next4", timeout=5000)
-            self._wait_for("#submit2", timeout=5000)
-
-            for info in attachment_info:
-                attachment_file = self.work_dir / info["filename"]
-                self._wait_for("#insertAcc", timeout=20000)
-                self.page.click("#insertAcc", timeout=5000)
-                self._wait_for("#fjlx", timeout=5000)
-                if info["attachment_type"] == "invoice":
-                    self.page.select_option("#fjlx", "1")
-                else:
-                    self.page.select_option("#fjlx", "2")
-                self.page.fill("#fpsmxx", info["attachment_desc"])
-                if attachment_file and attachment_file.exists():
-                    self.page.set_input_files("#file", str(attachment_file))
-                    self.page.wait_for_timeout(1000)
-                    self.page.click("#cjtj", timeout=5000)
-            log.info("上传差旅附件完成")
-        except Exception as e:
-            log.error(f"差旅附件上传失败: {e}")
-            self._screenshot("travel_attachment_error")
-            raise
-        self._screenshot("travel_attachment_done")
-
-    def close(self) -> None:
-        """关闭浏览器"""
-        if self.context:
-            self.context.close()
-        if self.browser:
-            self.browser.close()
-        try:
-            self._pw_ctx.__exit__(None, None, None)
-        except Exception:
-            pass
-
-    def _wait_for(self, selector: str, timeout: int | None = None) -> None:
-        self.page.wait_for_selector(selector, timeout=timeout)
-
-    def _screenshot(self, name: str) -> None:
-        img_dir = Path(__file__).parent.parent / "images"
-        img_dir.mkdir(exist_ok=True)
-        self.page.screenshot(path=str(img_dir / f"debug_{name}.png"))
-
-    def fill_travel_subsidy(self, subsidy_info: list[dict[str, Any]]) -> None:
-        """录入差旅补助清单"""
-        log.info("录入差旅补助清单...")
-        try:
-            self.page.click("#next3", timeout=5000)
-            self._wait_for("#next4", timeout=5000)
-
-            for info in subsidy_info:
-                self.page.click("#insertSubsidy", timeout=5000)
-                self._wait_for('text="增加补助清单"', timeout=5000)
-                self.page.click("#jzg3", timeout=5000)
-                self.page.wait_for_timeout(500)
-                if info["person_name"] and info["person_name"] != "":
-                    self.page.fill("#seacher", info["person_name"])
-                elif info["person_id"] and info["person_id"] != "":
-                    self.page.fill("#seacher", info["person_id"])
-                else:
-                    raise ValueError(f"人员编号和人员姓名不能同时为空: {info}")
-                self.page.click("#cx", timeout=5000)
-                self.page.wait_for_selector("div.fixed-table-loading", state="hidden", timeout=10000)
-                self.page.click("#tableEmp tbody tr", timeout=10000)
-                self.page.wait_for_timeout(1000)
-
-                open_bank = self.page.input_value("#openbank1")
-                if not open_bank:
-                    log.info("员工开户行未填写，默认填写中国工商银行")
-                    self.page.fill("#openbank1", "中国工商银行")
-
-                self.page.fill("#startdate1", _format_date(info["start_date"]))
-                self.page.fill("#enddate1", _format_date(info["end_date"]))
-                self.page.fill("#trafficdays1", str(info["days"]))
-                self.page.fill("#fooddays1", str(info["days"]))
-                self.page.fill("#trafficnorm1", str(80))
-                self.page.fill("#foodnorm1", str(100))
-                trafficmoney = int(info["days"]) * 80
-                foodmoney = int(info["days"]) * 100
-                subsidymoney = trafficmoney + foodmoney
-                self.page.fill("#trafficmoney1", str(trafficmoney))
-                self.page.fill("#foodmoney1", str(foodmoney))
-                self.page.fill("#subsidymoney1", str(subsidymoney))
-                self.page.click("#add", timeout=3000)
-                self.page.wait_for_timeout(1000)
-        except Exception as e:
-            log.error(f"差旅补助清单录入失败: {e}")
-            self._screenshot("subsidy_error")
-            raise
-
-        self._screenshot("subsidy_done")
-
-
-# ------------------------------------------------------------------
-# 对外入口
-# ------------------------------------------------------------------
-
-
-def run_bot(config: dict[str, Any], headless: bool = False, work_dir: Path | None = None) -> None:
-    """执行完整的浏览器填报流程，根据发票类型自动路由"""
-    if not config["username"] or not config["password"]:
-        raise ValueError("缺少用户名或密码")
-
-    if not work_dir:
-        raise ValueError("缺少工作目录")
-
-    from .doc.llm_extractor import load_cache
-
-    cache_map = load_cache(work_dir)
-    doc_values = [v for k, v in cache_map.items() if k != "travel_info"]
-    invoices = [data for data in doc_values if data.get("invoice_type") not in ("application", "payment")]
-    applications = [data for data in doc_values if data.get("invoice_type") == "application"]
-
-    groups = _classify_invoice_batch(invoices)
-    travel_invoices = groups["travel"]
-    general_invoices = groups["general"]
-
-    log.info(
-        f"发票分类: 差旅 {len(travel_invoices)} 张, 普通 {len(general_invoices)} 张, "
-        f"出差事前申请单 {len(applications)} 份"
-    )
-
-    if travel_invoices and general_invoices:
-        raise ValueError(
-            f"发票类型混合（差旅 {len(travel_invoices)} 张 + 普通 {len(general_invoices)} 张），不支持混报，请分开提交"
-        )
-
-    is_travel = bool(travel_invoices)
-    travel_info: dict[str, Any] = cache_map.get("travel_info", {})
-    if is_travel and not travel_info:
-        from .doc.llm_extractor import CACHE_DIR_NAME, extract_travel_info
-
-        travel_info = extract_travel_info(source_dir=work_dir)
-        cache_dir = work_dir / CACHE_DIR_NAME
-        cache_dir.mkdir(parents=True, exist_ok=True)
-        with open(cache_dir / "travel_info.json", "w", encoding="utf-8") as f:
-            json.dump(travel_info, f, ensure_ascii=False, indent=2)
-        log.info("差旅信息已保存到缓存")
-
-    bot = ReimburseBot(config, headless=headless, work_dir=work_dir)
-    bot.work_dir = work_dir
-    try:
-        bot.launch()
-        bot.login_portal()
-
-        if is_travel:
-            log.info("处理差旅发票...")
-            bot.navigate_to_reimburse(page_key="travel_page")
-            bot.create_new_form()
-            basic_info = travel_info["basic_info"]
-            bot.fill_travel_info(basic_info)
-            travel_items = travel_info["reimbursement_details"]
-            bot.add_travel_items(travel_items)
-            payment_info = travel_info["payment_methods"]
-            bot.fill_travel_payment(payment_info)
-            subsidy_info = travel_info["subsidy_list"]
-            bot.fill_travel_subsidy(subsidy_info)
-            attachment_info = travel_info["attachments"]
-            bot.upload_travel_attachments(attachment_info)
-        else:
-            log.info("处理普通发票...")
-            bot.navigate_to_reimburse(page_key="reimburse_page")
-            bot.create_new_form()
-            bot.fill_basic_info()
-            bot.add_reimburse_items(general_invoices)
-            bot.fill_payment(general_invoices)
-            bot.upload_attachments(general_invoices)
-
-    except Exception as e:
-        log.error(f"操作失败: {e}")
-        try:
-            bot._screenshot("error")
-        except Exception:
-            pass
-        raise
-    finally:
-        bot.close()
-
-
-def run_bot_web(config: dict[str, Any], work_dir: Path) -> None:
-    """Web 模式填报 — headless，附件从指定目录读取"""
-    run_bot(config, headless=True, work_dir=work_dir)

src/bot/README.md

@@ -0,0 +1,33 @@
+---
+last_reviewed: 2026-06-12
+---
+
+# bot — 浏览器自动化填报模块
+
+使用 Playwright 操作财务报销系统，自动完成登录、填单、上传附件等操作。
+
+## 模块清单
+
+| 文件 | 说明 |
+|------|------|
+| `__init__.py` | 对外入口：`run_bot()` 和 `run_bot_web()`，负责类型判断和流程路由 |
+| `base.py` | `BaseBot` 基类：浏览器生命周期、登录、导航、截图、日期格式化 |
+| `travel.py` | 差旅报销填报流程：基本信息 → 差旅明细 → 支付方式 → 补助清单 → 附件上传 |
+| `normal.py` | 普通发票报销填报流程：基本信息 → 总明细 → 支付方式 → 附件上传 |
+
+## 架构设计
+
+```
+run_bot(config, travel_info, normal_info)
+  ├── 创建 BaseBot，启动浏览器，登录门户
+  ├── travel_info 存在 → travel.run(bot, travel_info)
+  └── normal_info 存在 → normal.run(bot, normal_info)
+```
+
+- **`BaseBot`** 只保留公共操作（launch、login、navigate、create_new_form、close、screenshot）
+- **差旅/普通流程** 作为独立函数接受 `bot: BaseBot` 参数，符合函数式编程偏好
+- **`__init__.py`** 仅做路由分发，不包含具体填报逻辑
+
+## 变更历史
+
+- **2026-06-12**：从 `bot.py` 单文件重构为 `bot/` 包，分离差旅和普通报销逻辑

src/bot/__init__.py

@@ -0,0 +1,93 @@
+"""
+浏览器自动化填报
+
+使用 Playwright 操作财务报销系统，自动完成登录、填单、上传附件等操作。
+
+对外接口:
+    run_bot(config, travel_info, normal_info)     启动浏览器并执行填报流程
+    run_bot_web(config, work_dir)                 Web 模式填报（从缓存加载信息）
+"""
+
+from pathlib import Path
+from typing import Any
+
+from .. import get_logger
+from .base import BaseBot
+
+log = get_logger("bot")
+
+
+def run_bot(
+    config: dict[str, Any],
+    headless: bool = False,
+    work_dir: Path | None = None,
+    travel_info: dict[str, Any] | None = None,
+    normal_info: dict[str, Any] | None = None,
+) -> None:
+    """执行完整的浏览器填报流程，根据发票类型自动路由
+
+    Args:
+        config: 配置字典。
+        headless: 是否无头模式。
+        work_dir: 工作目录。
+        travel_info: 差旅信息（由 pipeline 层提前提取并传入，非差旅时传 None）。
+        normal_info: 普通发票信息（由 pipeline 层提前提取并传入，非普通时传 None）。
+    """
+    if not config["username"] or not config["password"]:
+        raise ValueError("缺少用户名或密码")
+
+    if not work_dir:
+        raise ValueError("缺少工作目录")
+
+    bot = BaseBot(config, headless=headless)
+    bot.work_dir = work_dir
+
+    try:
+        bot.launch()
+        bot.login_portal()
+
+        if travel_info is not None:
+            log.info("处理差旅发票...")
+            bot.navigate_to_reimburse(page_key="travel_page")
+            bot.create_new_form()
+            from . import travel
+
+            travel.run(bot, travel_info)
+        elif normal_info is not None:
+            log.info("处理普通发票...")
+            bot.navigate_to_reimburse(page_key="reimburse_page")
+            bot.create_new_form()
+            from . import normal
+
+            normal.run(bot, normal_info)
+        else:
+            raise ValueError("缺少差旅信息（travel_info）和普通发票信息（normal_info），无法继续填报")
+
+    except Exception as e:
+        log.error(f"操作失败: {e}")
+        try:
+            bot._screenshot("error")
+        except Exception:
+            pass
+        raise
+    finally:
+        bot.close()
+
+
+def run_bot_web(config: dict[str, Any], work_dir: Path) -> None:
+    """Web 模式填报 — headless，附件从指定目录读取
+
+    Web 端的信息提取由 app.py 的管道负责，此处从缓存加载。
+    """
+    from ..doc.llm_extractor import load_cache
+
+    cache_map = load_cache(work_dir)
+    travel_info = cache_map.get("travel_info")
+    normal_info = cache_map.get("normal_info")
+    run_bot(
+        config,
+        headless=True,
+        work_dir=work_dir,
+        travel_info=travel_info,
+        normal_info=normal_info,
+    )

src/bot/base.py

@@ -0,0 +1,204 @@
+"""
+浏览器自动化填报 — 公共基类
+
+提供浏览器生命周期管理、登录、导航、截图等公共操作。
+"""
+
+from pathlib import Path
+from typing import Any
+
+from .. import get_logger
+
+log = get_logger("bot")
+
+
+# ------------------------------------------------------------------
+# 工具函数
+# ------------------------------------------------------------------
+
+
+def format_date(date_str: str) -> str:
+    """将 '2026/5/13' 或 '2026-5-13' 转为 '2026-05-13'"""
+    if not date_str:
+        return ""
+    parts = date_str.replace("-", "/").split("/")
+    if len(parts) == 3:
+        return f"{parts[0].zfill(4)}-{parts[1].zfill(2)}-{parts[2].zfill(2)}"
+    return date_str
+
+
+# ------------------------------------------------------------------
+# 基类
+# ------------------------------------------------------------------
+
+
+class BaseBot:
+    """浏览器自动化基类 — 管理浏览器生命周期与公共操作"""
+
+    def __init__(self, config: dict[str, Any], headless: bool = False) -> None:
+        self.config = config
+        self.headless = headless
+        self.work_dir: Path | None = None
+        self.browser: Any = None
+        self.context: Any = None
+        self.page: Any = None
+
+        from playwright.sync_api import sync_playwright
+
+        self._pw_ctx = sync_playwright()
+        self.pw = self._pw_ctx.__enter__()
+
+    # ---------------------------------------------------------------
+    # 浏览器生命周期
+    # ---------------------------------------------------------------
+
+    def launch(self) -> None:
+        """启动浏览器"""
+        self.browser = self.pw.chromium.launch(headless=self.headless)
+        self.context = self.browser.new_context(viewport={"width": 1360, "height": 768})
+        self.page = self.context.new_page()
+        self.page.set_default_timeout(30000)
+
+    def close(self) -> None:
+        """关闭浏览器"""
+        if self.context:
+            self.context.close()
+        if self.browser:
+            self.browser.close()
+        try:
+            self._pw_ctx.__exit__(None, None, None)
+        except Exception:
+            pass
+
+    # ---------------------------------------------------------------
+    # 登录
+    # ---------------------------------------------------------------
+
+    def login_portal(self) -> None:
+        """登录信息门户"""
+        log.info("登录信息门户...")
+
+        self.page.goto(self.config["sso_login_url"], wait_until="domcontentloaded")
+        self._wait_for('text="微信扫码登录"', timeout=5000)
+
+        try:
+            self.page.fill(
+                'input[placeholder*="工号"], input[placeholder*="学号"]',
+                self.config["username"],
+            )
+            self.page.fill('input[placeholder*="密码"]', self.config["password"])
+        except Exception:
+            log.warning("未找到登录输入框，可能已登录")
+
+        try:
+            checkbox = self.page.query_selector('input[type="checkbox"]')
+            if checkbox and not checkbox.is_checked():
+                checkbox.click()
+        except Exception:
+            pass
+
+        for selector in ['button:has-text("登录")', 'input[value="登录"]', 'text="登录"']:
+            try:
+                self.page.click(selector, timeout=3000)
+                break
+            except Exception:
+                continue
+
+        self._wait_for_portal()
+
+    def _wait_for_portal(self) -> None:
+        """等待跳转到统一信息平台"""
+        for _ in range(30):
+            self.page.wait_for_timeout(1000)
+            url = self.page.url
+            if any(
+                kw in url
+                for kw in (
+                    "tyrz.fynu.edu.cn/zs-uip",
+                    "tyrz.fynu.edu.cn/oshall",
+                    "portal",
+                )
+            ):
+                self._screenshot("portal_loaded")
+                return
+        log.error("等待门户跳转超时")
+        self._screenshot("portal_timeout")
+        raise TimeoutError("登录超时，未跳转到信息门户")
+
+    # ---------------------------------------------------------------
+    # 导航
+    # ---------------------------------------------------------------
+
+    def navigate_to_reimburse(self, page_key: str = "reimburse_page") -> None:
+        """从统一信息平台进入报销系统"""
+        log.info("进入报销系统...")
+        self._wait_for('text="快捷入口"', timeout=5000)
+
+        try:
+            self.page.click('text="财务系统"', timeout=5000)
+        except Exception:
+            log.warning("未找到财务系统入口")
+
+        new_tab = None
+        for _ in range(15):
+            self.page.wait_for_timeout(1000)
+            for p in self.context.pages:
+                if "dddl" in p.url or "210.45.32.214" in p.url:
+                    new_tab = p
+                    break
+            if new_tab:
+                break
+
+        if new_tab:
+            self.page = new_tab
+            self._wait_for('text="网络报销"', timeout=5000)
+        else:
+            log.warning(f"未找到单点登录页面，当前 URL: {self.page.url}")
+
+        for p in self.context.pages[:-1]:
+            try:
+                p.close()
+            except Exception:
+                pass
+
+        try:
+            link = self.page.query_selector('a:has(img[src*="wlbx"])')
+            if link:
+                reimburse_url = link.get_attribute("href")
+                self.page.goto(reimburse_url, wait_until="domcontentloaded", timeout=15000)
+        except Exception:
+            pass
+
+        self._wait_for('text="报销录入"', timeout=5000)
+        common_url = self.config["reimburse_url"] + self.config[page_key]
+        self.page.goto(common_url, wait_until="domcontentloaded", timeout=15000)
+        self._wait_for('text="单据状态:"', timeout=5000)
+
+    def create_new_form(self) -> None:
+        """点击「新增」创建新单据"""
+        log.info("创建新单据...")
+        self.page.wait_for_timeout(2000)
+
+        try:
+            self.page.click("#insert", timeout=5000)
+        except Exception:
+            try:
+                self.page.click("text=新增", timeout=3000)
+            except Exception as err:
+                self._screenshot("no_add_button")
+                raise RuntimeError("无法点击新增按钮") from err
+
+        self.page.wait_for_timeout(3000)
+        self._screenshot("after_add_click")
+
+    # ---------------------------------------------------------------
+    # 辅助方法
+    # ---------------------------------------------------------------
+
+    def _wait_for(self, selector: str, timeout: int | None = None) -> None:
+        self.page.wait_for_selector(selector, timeout=timeout)
+
+    def _screenshot(self, name: str) -> None:
+        img_dir = Path(__file__).parent.parent.parent / "images"
+        img_dir.mkdir(exist_ok=True)
+        self.page.screenshot(path=str(img_dir / f"debug_{name}.png"))

src/bot/normal.py

@@ -0,0 +1,176 @@
+"""
+普通报销填报流程
+
+负责普通发票报销的完整填报步骤：
+    基本信息 → 总明细 → 支付方式 → 附件上传
+"""
+
+from typing import Any
+
+from .. import get_logger
+from .base import BaseBot, format_date
+
+log = get_logger("bot.normal")
+
+
+# ------------------------------------------------------------------
+# 普通报销流程
+# ------------------------------------------------------------------
+
+
+def run(
+    bot: BaseBot,
+    normal_info: dict[str, Any],
+) -> None:
+    """执行普通发票报销填报流程
+
+    Args:
+        bot: 已启动并登录的 BaseBot 实例。
+        normal_info: 普通发票信息字典。
+    """
+    log.info("开始普通发票报销填报...")
+
+    log.info("填写基本信息...")
+    description = normal_info.get("basic_info", {}).get("reimbursement_description", "元器件采购报销")
+    fill_basic_info(bot, description)
+
+    total_invoices = normal_info.get("reimbursement_details", {}).get("total_invoices", 0)
+    total_amount = normal_info.get("reimbursement_details", {}).get("total_amount", 0)
+    log.info(f"录入普通发票总明细 (共 {total_invoices} 张, 合计 ¥{total_amount:.2f})...")
+    add_normal_item(bot, total_invoices, total_amount)
+
+    payment_info = normal_info.get("payment_methods", [])
+    log.info(f"录入普通发票支付信息 (共 {len(payment_info)} 笔)...")
+    fill_normal_payment(bot, payment_info)
+
+    log.info("上传普通发票附件...")
+    attachment_info = normal_info.get("attachments", [])
+    upload_normal_attachments(bot, attachment_info)
+
+    log.info("普通发票报销填报完成")
+
+
+# ------------------------------------------------------------------
+# 基本信息
+# ------------------------------------------------------------------
+
+
+def fill_basic_info(bot: BaseBot, description: str = "元器件采购报销") -> None:
+    """填写基本信息"""
+
+    bot.page.fill("#EXPENEXPLAIN", description)
+    bot.page.click("#PROJECTCODE", timeout=10000)
+    bot.page.wait_for_timeout(1000)
+
+    bot.page.wait_for_selector("#promodal .fixed-table-body tbody tr", timeout=10000)
+    first_row = bot.page.query_selector("#promodal .fixed-table-body tbody tr")
+
+    if first_row:
+        first_row.click()
+        bot.page.wait_for_timeout(1000)
+
+    bot.page.click("#saveAndNext", timeout=5000)
+    bot.page.wait_for_timeout(2000)
+
+    bot._screenshot("step3_done")
+
+
+# ------------------------------------------------------------------
+# 总明细
+# ------------------------------------------------------------------
+
+
+def add_normal_item(bot: BaseBot, total_invoices: int, total_amount: float) -> None:
+    """录入普通发票总明细"""
+    try:
+        bot.page.click("#insertDetail", timeout=5000)
+        bot._wait_for('text="经济事项名称"', timeout=5000)
+        bot.page.click("#economicscode2")
+        bot.page.wait_for_timeout(1000)
+
+        try:
+            bot.page.wait_for_selector("#econmodal .fixed-table-body tbody tr", timeout=10000)
+            rows = bot.page.query_selector_all("#econmodal .fixed-table-body tbody tr")
+            if len(rows) >= 3:
+                rows[2].click()
+                bot.page.wait_for_timeout(1000)
+        except Exception:
+            pass
+
+        bot.page.fill('input[name="expenPwCommondetail.HOWBILLS"]', str(total_invoices))
+        bot.page.fill("#je_zwzcdz", f"{total_amount:.2f}")
+        bot.page.click("#detailAdd", timeout=3000)
+        bot.page.wait_for_timeout(1000)
+
+        bot._screenshot("normal_item_done")
+    except Exception as e:
+        log.error(f"录入总明细失败: {e}")
+        bot._screenshot("normal_item_error")
+        raise
+
+
+# ------------------------------------------------------------------
+# 支付方式
+# ------------------------------------------------------------------
+
+
+def fill_normal_payment(bot: BaseBot, payment_info: list[dict[str, Any]]) -> None:
+    """录入普通发票支付信息"""
+    try:
+        bot.page.click('text="下一步(支付方式)"', timeout=5000)
+        bot._wait_for('text="下一步(附件清单)"', timeout=5000)
+
+        for info in payment_info:
+            bot.page.click("#insertPay", timeout=5000)
+            bot.page.wait_for_timeout(1000)
+            bot.page.fill("#personid2", bot.config["default_name"])
+            bot.page.fill("#accountname2", bot.config["default_person_id"])
+            bot.page.fill("#receiptdate2", format_date(str(info.get("card_date", ""))))
+            bot.page.fill("#localaccount2", bot.config["default_card_no"])
+            bot.page.fill("#receiptmoney2", str(info.get("card_amount", 0)))
+            bot.page.fill("#money2", str(info.get("card_amount", 0)))
+            bot.page.fill("#merchant2", str(info.get("merchant", "")))
+            bot.page.fill("#smark2", str(info.get("remark", "")))
+            bot.page.click("#payAdd", timeout=3000)
+            bot.page.wait_for_timeout(1000)
+    except Exception as e:
+        log.error(f"支付方式录入失败: {e}")
+        bot._screenshot("normal_payment_error")
+        raise
+
+    bot._screenshot("normal_payment_done")
+
+
+# ------------------------------------------------------------------
+# 附件上传
+# ------------------------------------------------------------------
+
+
+def upload_normal_attachments(bot: BaseBot, attachment_info: list[dict[str, Any]]) -> None:
+    """上传普通发票附件"""
+    log.info(f"上传普通发票附件 (共 {len(attachment_info)} 个)...")
+    try:
+        bot.page.click("#next3", timeout=5000)
+        bot._wait_for("#submit2", timeout=5000)
+
+        for info in attachment_info:
+            attachment_file = bot.work_dir / info["filename"]
+            bot._wait_for("#insertAcc", timeout=20000)
+            bot.page.click("#insertAcc", timeout=5000)
+            bot._wait_for("#fjlx", timeout=5000)
+            if info.get("attachment_type") == "invoice":
+                bot.page.select_option("#fjlx", "1")
+            else:
+                bot.page.select_option("#fjlx", "2")
+            bot.page.fill("#fpsmxx", info.get("attachment_desc", ""))
+            if attachment_file and attachment_file.exists():
+                bot.page.set_input_files("#file", str(attachment_file))
+                bot.page.wait_for_timeout(1000)
+                bot.page.click("#cjtj", timeout=5000)
+        log.info("上传普通发票附件完成")
+    except Exception as e:
+        log.error(f"附件上传失败: {e}")
+        bot._screenshot("normal_attachment_error")
+        raise
+
+    bot._screenshot("normal_attachment_done")

src/bot/travel.py

@@ -0,0 +1,295 @@
+"""
+差旅报销填报流程
+
+负责差旅报销的完整填报步骤：
+    基本信息 → 差旅明细 → 支付方式 → 补助清单 → 附件上传
+"""
+
+from typing import Any
+
+from .. import get_logger
+from .base import BaseBot, format_date
+
+log = get_logger("bot.travel")
+
+
+# ------------------------------------------------------------------
+# 差旅填报流程
+# ------------------------------------------------------------------
+
+
+def run(bot: BaseBot, travel_info: dict[str, Any]) -> None:
+    """执行差旅报销填报流程
+
+    Args:
+        bot: 已启动并登录的 BaseBot 实例。
+        travel_info: 差旅信息字典（包含 basic_info、reimbursement_details 等）。
+    """
+    log.info("开始差旅报销填报...")
+
+    log.info("填写差旅报销信息...")
+    basic_info = travel_info["basic_info"]
+    fill_travel_info(bot, basic_info)
+
+    log.info("填写差旅报销明细...")
+    travel_items = travel_info["reimbursement_details"]
+    add_travel_items(bot, travel_items)
+
+    log.info("填写差旅报销支付方式...")
+    payment_info = travel_info["payment_methods"]
+    fill_travel_payment(bot, payment_info)
+
+    log.info("填写差旅报销补助清单...")
+    subsidy_info = travel_info["subsidy_list"]
+    fill_travel_subsidy(bot, subsidy_info)
+
+    log.info("上传差旅报销附件...")
+    attachment_info = travel_info["attachments"]
+    upload_travel_attachments(bot, attachment_info)
+
+    log.info("差旅报销填报完成")
+
+
+# ------------------------------------------------------------------
+# 基本信息
+# ------------------------------------------------------------------
+
+
+def fill_travel_info(bot: BaseBot, basic_info: dict[str, Any]) -> None:
+    """填写差旅报销基本信息"""
+    try:
+        bot.page.fill("#CAUSE", basic_info.get("travel_purpose", ""))
+        bot.page.fill("#SITE", basic_info.get("travel_location", ""))
+
+        bot.page.click("#PROJECTCODE", timeout=10000)
+        bot.page.wait_for_timeout(1000)
+        bot.page.wait_for_selector("#promodal .fixed-table-body tbody tr", timeout=10000)
+        first_row = bot.page.query_selector("#promodal .fixed-table-body tbody tr")
+        if first_row:
+            first_row.click()
+            bot.page.wait_for_timeout(1000)
+
+        bot.page.fill("#THEKSRQ", format_date(basic_info.get("start_date", "")))
+        bot.page.fill("#THEJSRQ", format_date(basic_info.get("end_date", "")))
+        bot.page.click("#saveAndNext", timeout=5000)
+        bot.page.wait_for_timeout(2000)
+        bot._screenshot("travel_basic_done")
+    except Exception:
+        log.error("填写基本信息失败")
+        bot._screenshot("travel_basic_error")
+
+
+# ------------------------------------------------------------------
+# 差旅明细
+# ------------------------------------------------------------------
+
+
+def add_travel_items(bot: BaseBot, travel_items: dict[str, Any]) -> None:
+    """录入差旅报销明细"""
+    vehicle_map = {
+        "火车": "01",
+        "汽车": "02",
+        "轮船": "03",
+        "自带车": "04",
+        "公务车": "05",
+        "飞机": "06",
+        "租车": "07",
+        "自驾车": "08",
+    }
+
+    try:
+        traffic_info = travel_items.get("transport_fee") or []
+        for item in traffic_info:
+            bot.page.click("#insertDetail", timeout=5000)
+            bot._wait_for('text="增加明细"', timeout=5000)
+            bot.page.select_option("#cost", "1")
+            bot.page.wait_for_timeout(500)
+            vehicle = item.get("vehicle_type", "")
+            if vehicle in vehicle_map:
+                bot.page.select_option("#jtgj", vehicle_map[vehicle])
+
+            bot.page.fill("#ksdd", item.get("departure_place", ""))
+            bot.page.fill("#jsdd", item.get("arrival_place", ""))
+            bot.page.fill(
+                '#t1 input[name="expenPwTraveldetail.MONEY"]',
+                str(item.get("amount", "")),
+            )
+            bot.page.fill(
+                '#t1 input[name="expenPwTraveldetail.HOWBILL"]',
+                str(item.get("bill_count", "")),
+            )
+            bot.page.fill(
+                '#t1 input[name="expenPwTraveldetail.SMARK"]',
+                str(item.get("remark", "")),
+            )
+            bot.page.click("#detailAdd", timeout=3000)
+            bot.page.wait_for_timeout(1000)
+
+        hotel_info = travel_items.get("hotel_fee") or []
+        for item in hotel_info:
+            bot.page.click("#insertDetail", timeout=5000)
+            bot._wait_for('text="增加明细"', timeout=5000)
+            bot.page.select_option("#cost", "2")
+            bot.page.wait_for_timeout(500)
+            bot.page.fill("#ksrq2", format_date(str(item.get("checkin_date", ""))))
+            bot.page.fill("#jsrq2", format_date(str(item.get("checkout_date", ""))))
+            bot.page.fill("#ts2", str(item.get("days", "")))
+            bot.page.fill("#rs2", str(item.get("person_count", "")))
+            bot.page.fill(
+                '#t2 input[name="expenPwTraveldetail.FPMONEY"]',
+                str(item.get("invoice_amount", "")),
+            )
+            bot.page.fill(
+                '#t2 input[name="expenPwTraveldetail.MONEY"]',
+                str(item.get("reimburse_amount", "")),
+            )
+            bot.page.fill(
+                '#t2 input[name="expenPwTraveldetail.SMARK"]',
+                str(item.get("remark", "")),
+            )
+            bot.page.click("#detailAdd", timeout=3000)
+            bot.page.wait_for_timeout(1000)
+
+        conference_info = travel_items.get("conference_fee") or []
+        for item in conference_info:
+            bot.page.click("#insertDetail", timeout=5000)
+            bot._wait_for('text="增加明细"', timeout=5000)
+            bot.page.select_option("#cost", "3")
+            bot.page.wait_for_timeout(500)
+            bot.page.fill(
+                '#t3 input[name="expenPwTraveldetail.HOWBILL"]',
+                str(item.get("bill_count", "")),
+            )
+            bot.page.fill(
+                '#t3 input[name="expenPwTraveldetail.MONEY"]',
+                str(item.get("amount", "")),
+            )
+            bot.page.fill(
+                '#t3 input[name="expenPwTraveldetail.SMARK"]',
+                str(item.get("remark", "")),
+            )
+            bot.page.click("#detailAdd", timeout=3000)
+            bot.page.wait_for_timeout(1000)
+    except Exception as e:
+        log.error(f"录入总明细失败: {e}")
+        bot._screenshot("item_total_error")
+        raise
+
+
+# ------------------------------------------------------------------
+# 支付方式
+# ------------------------------------------------------------------
+
+
+def fill_travel_payment(bot: BaseBot, payment_info: list[dict[str, Any]]) -> None:
+    """录入差旅支付信息"""
+    try:
+        bot.page.click('text="下一步(支付方式)"', timeout=5000)
+        bot._wait_for('text="下一步(补助清单)"', timeout=5000)
+
+        for info in payment_info:
+            bot.page.click("#insertPay", timeout=5000)
+            bot.page.wait_for_timeout(1000)
+            bot.page.fill("#personid2", bot.config["default_name"])
+            bot.page.fill("#accountname2", bot.config["default_person_id"])
+            bot.page.fill("#receiptdate2", format_date(info["card_date"]))
+            bot.page.fill("#localaccount2", bot.config["default_card_no"])
+            bot.page.fill("#receiptmoney2", str(info["card_amount"]))
+            bot.page.fill("#money2", str(info["card_amount"]))
+            bot.page.fill("#merchant2", info.get("merchant", ""))
+            bot.page.fill("#smark2", info.get("remark", ""))
+            bot.page.click("#payAdd", timeout=3000)
+            bot.page.wait_for_timeout(1000)
+    except Exception as e:
+        log.error(f"支付方式录入失败: {e}")
+        bot._screenshot("step5_error")
+        raise
+
+    bot._screenshot("step5_done")
+
+
+# ------------------------------------------------------------------
+# 补助清单
+# ------------------------------------------------------------------
+
+
+def fill_travel_subsidy(bot: BaseBot, subsidy_info: list[dict[str, Any]]) -> None:
+    """录入差旅补助清单"""
+    try:
+        bot.page.click("#next3", timeout=5000)
+        bot._wait_for("#next4", timeout=5000)
+
+        for info in subsidy_info:
+            bot.page.click("#insertSubsidy", timeout=5000)
+            bot._wait_for('text="增加补助清单"', timeout=5000)
+            bot.page.click("#jzg3", timeout=5000)
+            bot.page.wait_for_timeout(500)
+            if info["person_name"] and info["person_name"] != "":
+                bot.page.fill("#seacher", info["person_name"])
+            elif info["person_id"] and info["person_id"] != "":
+                bot.page.fill("#seacher", info["person_id"])
+            else:
+                raise ValueError(f"人员编号和人员姓名不能同时为空: {info}")
+            bot.page.click("#cx", timeout=5000)
+            bot.page.wait_for_selector("div.fixed-table-loading", state="hidden", timeout=10000)
+            bot.page.click("#tableEmp tbody tr", timeout=10000)
+            bot.page.wait_for_timeout(1000)
+
+            open_bank = bot.page.input_value("#openbank1")
+            if not open_bank:
+                log.info("员工开户行未填写，默认填写中国工商银行")
+                bot.page.fill("#openbank1", "中国工商银行")
+
+            bot.page.fill("#startdate1", format_date(info["start_date"]))
+            bot.page.fill("#enddate1", format_date(info["end_date"]))
+            bot.page.fill("#trafficdays1", str(info["days"]))
+            bot.page.fill("#fooddays1", str(info["days"]))
+            bot.page.fill("#trafficnorm1", str(80))
+            bot.page.fill("#foodnorm1", str(100))
+            trafficmoney = int(info["days"]) * 80
+            foodmoney = int(info["days"]) * 100
+            subsidymoney = trafficmoney + foodmoney
+            bot.page.fill("#trafficmoney1", str(trafficmoney))
+            bot.page.fill("#foodmoney1", str(foodmoney))
+            bot.page.fill("#subsidymoney1", str(subsidymoney))
+            bot.page.click("#add", timeout=3000)
+            bot.page.wait_for_timeout(1000)
+    except Exception as e:
+        log.error(f"差旅补助清单录入失败: {e}")
+        bot._screenshot("subsidy_error")
+        raise
+
+    bot._screenshot("subsidy_done")
+
+
+# ------------------------------------------------------------------
+# 附件上传
+# ------------------------------------------------------------------
+
+
+def upload_travel_attachments(bot: BaseBot, attachment_info: list[dict[str, Any]]) -> None:
+    """上传差旅附件"""
+    try:
+        bot.page.click("#next4", timeout=5000)
+        bot._wait_for("#submit2", timeout=5000)
+
+        for info in attachment_info:
+            attachment_file = bot.work_dir / info["filename"]
+            bot._wait_for("#insertAcc", timeout=20000)
+            bot.page.click("#insertAcc", timeout=5000)
+            bot._wait_for("#fjlx", timeout=5000)
+            if info["attachment_type"] == "invoice":
+                bot.page.select_option("#fjlx", "1")
+            else:
+                bot.page.select_option("#fjlx", "2")
+            bot.page.fill("#fpsmxx", info["attachment_desc"])
+            if attachment_file and attachment_file.exists():
+                bot.page.set_input_files("#file", str(attachment_file))
+                bot.page.wait_for_timeout(1000)
+                bot.page.click("#cjtj", timeout=5000)
+        log.info("上传差旅附件完成")
+    except Exception as e:
+        log.error(f"差旅附件上传失败: {e}")
+        bot._screenshot("travel_attachment_error")
+        raise
+    bot._screenshot("travel_attachment_done")

src/doc/README.md

@@ -1,10 +1,10 @@
 ---
-last_reviewed: 2026-06-09
+last_reviewed: 2026-06-11
 ---
 
 # src/doc — 文档处理模块
 
-负责发票信息提取、基于 LLM 的支付截图信息识别、以及将数据填入 Word 出库单模板。
+负责发票信息提取、基于 LLM 的支付截图信息识别、差旅/普通报销信息提取、以及将数据填入 Word 出库单模板。
 
 ## 模块清单
 
@@ -13,12 +13,12 @@ last_reviewed: 2026-06-09
 | ------------------------ | -------------------------------------------------- |
 | `extractor.py`           | 编排入口：串联 PDF 读取 → LLM 提取 → 支付截图匹配 → 分类             |
 | `pdf.py`                 | PDF 图片渲染（PyMuPDF）                              |
-| `llm_extractor.py`       | 基于 LLM 的信息提取（发票文本 + 支付截图多模态）                      |
+| `llm_extractor.py`       | 基于 LLM 的信息提取（发票文本 + 支付截图多模态 + 差旅/普通报销信息综合提取）      |
 | `matcher.py`             | 发票与支付截图按金额匹配，回填刷卡信息至发票记录                         |
 | `invoice.py`             | 发票类型常量、分类逻辑、CSV 读写工具                               |
 | `fill_consumable_doc.py` | 将 CSV 数据填入易耗品出库单 Word 模板（pywin32 COM）              |
 | `prompt.py`              | LLM 提示词模板加载                                        |
-| `prompts/`               | 提示词模板文件（`invoice_system.md`、`travel_info_system.md`） |
+| `prompts/`               | 提示词模板文件（`invoice_system.md`、`travel_info_system.md`、`normal_info_system.md`） |
 
 
 ## 数据流
@@ -32,6 +32,11 @@ PDF 发票 → pdf.py → llm_extractor.py → [发票列表]
     invoice.py 分类 → CSV（已回填刷卡日期/卡号/金额）
               ↓
     fill_consumable_doc → 易耗品出库单.doc
+
+[发票列表 + 匹配结果] → llm_extractor.py
+              ↓
+    差旅发票 → extract_travel_info() → travel_info.json
+    普通发票 → extract_normal_info() → normal_info.json
 ```
 
 ## 依赖说明
@@ -46,3 +51,10 @@ PDF 发票 → pdf.py → llm_extractor.py → [发票列表]
 - LLM 提取不会覆盖 CSV 中已有非空字段
 - 提示词模板位于 `prompts/` 目录，由 `prompt.py` 加载
 - LLM 提取失败时直接报错，无正则回退
+
+## 变更说明（2026-06-11）
+
+- `llm_extractor.py` 新增 `extract_normal_info()`：综合普通发票、支付记录和匹配结果，提取报销说明、发票总数、总金额、支付方式、附件清单，缓存为 `normal_info.json`
+- `llm_extractor.py` 的 `load_cache()` 扩展支持加载 `normal_info.json`
+- `prompt.py` 新增 `build_normal_info_system_prompt()`：加载 `normal_info_system.md`
+- `prompts/` 新增 `normal_info_system.md`：普通发票信息提取的系统提示词

src/doc/extractor.py

@@ -51,16 +51,17 @@ def _get_cache_dir(source_dir: Path) -> Path:
 
 
 def _get_json_path(file_path: Path, cache_dir: Path) -> Path:
-    """根据文件路径生成对应的 JSON 缓存路径"""
-    return cache_dir / f"{file_path.stem}.json"
+    """根据文件路径生成对应的 JSON 缓存路径（包含后缀名以区分同名的 PDF/图片）"""
+    return cache_dir / f"{file_path.stem}{file_path.suffix}.json"
 
 
 def _save_to_cache(file_path: Path, extracted_data: dict[str, Any], cache_dir: Path) -> Path:
-    """将提取结果保存到 JSON 缓存文件，并记录源文件路径"""
+    """将提取结果保存到 JSON 缓存文件，并记录源文件路径和后缀名"""
     json_path = _get_json_path(file_path, cache_dir)
     cache_data = {
         "source_file": str(file_path),
         "source_filename": file_path.name,
+        "source_extension": file_path.suffix.lower(),
         "extracted_data": extracted_data,
     }
     with open(json_path, "w", encoding="utf-8") as f:
@@ -69,13 +70,16 @@ def _save_to_cache(file_path: Path, extracted_data: dict[str, Any], cache_dir: P
     return json_path
 
 
-def _load_from_cache(json_path: Path) -> dict[str, Any] | None:
-    """从 JSON 缓存文件加载提取结果"""
+def _load_from_cache(json_path: Path, expected_extension: str | None = None) -> dict[str, Any] | None:
+    """从 JSON 缓存文件加载提取结果，可选校验后缀名一致性"""
     if not json_path.exists():
         return None
     try:
         with open(json_path, encoding="utf-8") as f:
             cache_data: dict[str, Any] = json.load(f)
+        # 校验后缀名是否一致，防止同名不同后缀的文件误命中缓存
+        if expected_extension and cache_data.get("source_extension", "").lower() != expected_extension.lower():
+            return None
         result: dict[str, Any] | None = cache_data.get("extracted_data")
         return result
     except Exception as e:
@@ -100,7 +104,7 @@ def _extract_document(file_path: Path, cache_dir: Path) -> dict[str, str] | None
         提取结果字典，失败时返回 None。
     """
     json_path = _get_json_path(file_path, cache_dir)
-    cached = _load_from_cache(json_path)
+    cached = _load_from_cache(json_path, expected_extension=file_path.suffix.lower())
     if cached:
         cached["_source_file"] = file_path.name
         log.info(f"使用缓存: {file_path.name}")

src/doc/llm_extractor.py

@@ -26,6 +26,7 @@ from typing import Any, cast
 from .. import get_logger
 from .prompt import (
     build_invoice_system_prompt,
+    build_normal_info_system_prompt,
     build_travel_info_system_prompt,
 )
 
@@ -218,9 +219,9 @@ def load_cache(source_dir: Path) -> dict[str, Any]:
             with open(json_path, encoding="utf-8") as f:
                 cache_data = json.load(f)
 
-            # travel_info.json 结构不同，直接存储
-            if json_path.name == "travel_info.json":
-                cache_map["travel_info"] = cache_data
+            # travel_info.json / normal_info.json 结构不同，直接存储
+            if json_path.name in ("travel_info.json", "normal_info.json"):
+                cache_map[json_path.name.replace(".json", "")] = cache_data
                 continue
 
             extracted = cache_data.get("extracted_data", {})
@@ -324,3 +325,71 @@ def extract_travel_info(
     except Exception as e:
         log.error("LLM 差旅信息提取失败: %s", e)
         raise
+
+
+# ------------------------------------------------------------------
+# 普通发票信息提取
+# ------------------------------------------------------------------
+
+
+def extract_normal_info(
+    source_dir: Path | None = None,
+) -> dict[str, Any]:
+    """根据普通发票（非差旅），让 LLM 提取报销相关信息。
+
+    仅支持从 JSON 缓存加载数据。
+
+    Args:
+        source_dir: 源文件目录（必填，包含 .invoice_cache 子目录）。
+
+    Returns:
+        包含报销说明、发票总数、总金额、支付方式、附件清单等字段的字典。
+    """
+    if not source_dir:
+        log.warning("未提供 source_dir，无法加载缓存数据")
+        return {}
+
+    system_prompt = build_normal_info_system_prompt()
+
+    # 构建 source filename -> 缓存数据的映射
+    cache_map = load_cache(source_dir)
+
+    # 加载发票与支付记录的匹配结果
+    match_result = load_match_result(source_dir)
+
+    # 拼接纯文本消息
+    parts = [
+        "以下是本次报销的所有源文件及其提取出的结构化数据。"
+        "每个源文件的数据来自 OCR 识别和发票信息提取，已按文件名分组展示。"
+    ]
+
+    # 如果有匹配结果，作为额外上下文提供
+    if match_result:
+        parts.append(
+            "【发票与支付记录匹配结果】"
+            "以下数据已将发票信息与对应的支付记录进行关联匹配，"
+            "用于判断每笔支付对应的发票和商户信息。\n" + json.dumps(match_result, ensure_ascii=False, indent=2)
+        )
+
+    # 按源文件名提供结构化数据
+    for filename, extracted in cache_map.items():
+        parts.append(
+            f"【源文件: {filename}】"
+            "以下为从该文件提取的结构化发票/支付/申请单数据。\n" + json.dumps(extracted, ensure_ascii=False, indent=2)
+        )
+
+    parts.append("\n=== 请返回 JSON 格式结果 ===")
+    user_message = "\n".join(parts)
+    log.info(f"user_message: {user_message}")
+    try:
+        response = _llm_query_multimodal(
+            system_prompt=system_prompt,
+            text=user_message,
+            reasoning_effort="low",
+        )
+        result = _parse_json_response(response)
+        log.info("LLM 普通发票信息提取成功")
+        return result
+    except Exception as e:
+        log.error("LLM 普通发票信息提取失败: %s", e)
+        raise

src/doc/matcher.py

@@ -18,12 +18,13 @@
 2. 解析发票和刷卡记录的金额，进行总额校验
    - 发票总额 < 刷卡总额时发出 warning
 3. 按金额降序排序
-4. 根据数量关系选择匹配策略：
+4. 文件名匹配（最高优先级）：发票和刷卡记录的文件名（不含后缀）一致时直接匹配
+5. 根据数量关系选择匹配策略：
    - 数量相等 → 一对一匹配：按金额从大到小依次配对，相对容差内即匹配
    - 发票更多 → 一对多匹配：对每张刷卡记录贪心凑金额，相对容差内结束
-5. 构建以支付记录为主键的结果列表
-6. 未匹配的发票单独作为一条记录（无刷卡信息）
-7. 清理内部字段，输出支付记录列表
+6. 构建以支付记录为主键的结果列表
+7. 未匹配的发票单独作为一条记录（无刷卡信息）
+8. 清理内部字段，输出支付记录列表
 
 ## 容差计算
 
@@ -45,6 +46,7 @@
     match_invoices_to_cards(invoices, cards, tolerance) -> list[dict]
 """
 
+from pathlib import Path
 from typing import Any
 
 from .. import get_logger
@@ -170,10 +172,18 @@ def _match(
     """执行匹配，返回 {card_index: [invoice_indices]} 的映射
 
     tolerance 为相对容差比例（如 0.03 表示 3%）
+
+    匹配优先级（从高到低）：
+        1. 文件名匹配：发票和刷卡记录的文件名（不含后缀）一致时直接匹配
+        2. 精确匹配：金额差 <= 0.01 元
+        3. 一对一 / 一对多贪心匹配：按金额容差匹配
     """
     result: dict[int, list[int]] = {}
     assigned: set[int] = set()
 
+    # ---- 阶段 0：文件名匹配（最高优先级）----
+    _match_by_filename(invoices, cards, assigned, result)
+
     if len(invoices) == len(cards):
         _match_one_to_one(invoices, cards, tolerance, assigned, result)
     else:
@@ -182,6 +192,34 @@ def _match(
     return result
 
 
+def _match_by_filename(
+    invoices: list[dict[str, Any]],
+    cards: list[dict[str, Any]],
+    assigned: set[int],
+    result: dict[int, list[int]],
+) -> None:
+    """文件名匹配：发票和刷卡记录的文件名（不含后缀）一致时直接匹配"""
+    for card_idx, card in enumerate(cards):
+        card_name = card.get("_source_file", "")
+        if not card_name:
+            continue
+        card_stem = Path(card_name).stem
+
+        for idx, inv in enumerate(invoices):
+            if idx in assigned:
+                continue
+            inv_name = inv.get("_source_file", "")
+            if not inv_name:
+                continue
+            inv_stem = Path(inv_name).stem
+
+            if inv_stem == card_stem:
+                assigned.add(idx)
+                result[card_idx] = [idx]
+                log.info(f"[文件名匹配] {inv_name} ↔ {card_name}")
+                break
+
+
 def _match_one_to_one(
     invoices: list[dict[str, Any]],
     cards: list[dict[str, Any]],

src/doc/prompt.py

@@ -24,3 +24,8 @@ def build_invoice_system_prompt() -> str:
 def build_travel_info_system_prompt() -> str:
     """构建差旅信息提取系统提示词。"""
     return _load_prompt("travel_info_system.md")
+
+
+def build_normal_info_system_prompt() -> str:
+    """构建普通发票信息提取系统提示词。"""
+    return _load_prompt("normal_info_system.md")

src/doc/prompts/invoice_system.md

@@ -1,4 +1,4 @@
-你是财务文档信息提取助手。你的任务是从图片中提取结构化信息，可能是支付截图、银行转账记录、微信/支付宝付款凭证等，也可能是发票文件，也可能是出差事前申请单，不管任何形式都要用统一的 JSON 格式返回信息。
+你是财务文档信息提取助手。你的任务是从图片中提取结构化信息，可能是支付截图、银行转账记录、微信/支付宝付款凭证等，也可能是发票文件，也可能是出差事前申请单，也可能是易耗品、出库单，不管任何形式都要用统一的 JSON 格式返回信息。
 
 第一步要先判断是，支付记录、高铁票、酒店住宿，普通发票，然后不同类型输出的信息不同。
 
@@ -36,6 +36,11 @@
   "invoice_date": "2026-06-03",
   "total_amount": "536.00"//必填项
 }
+以下是易耗品出入库单的完整示例：
+```json
+{
+  "invoice_type": "note",//必填项且只有这一项
+}
 ```
 ## 重要规则
 - **必填项**：invoice_type、invoice_date、ride_date、departure、arrival、person_name、total_amount 字段为必填，必须填写。
@@ -85,4 +90,7 @@
 6. total_amount: 金额数字
 7. seller_name: 卖方全称
 
+如果是易耗品出入库单，返回如下字段：
+1. invoice_type: "note"  
+
 **千万注意！千万注意！**：严格只输出 JSON，不要输出任何其他文字、Markdown 标记或解释。

src/doc/prompts/normal_info_system.md

@@ -0,0 +1,78 @@
+# 普通报销信息提取系统提示词
+
+你是财务报销信息提取助手。根据发票信息和付款记录，提取报销相关的结构化数据，并以严格符合类型要求的 JSON 格式返回。
+
+> **核心原则**：类型约束为最高优先级规则，任何情况下不得违反。
+
+## 强制类型约束
+
+以下类型规则为最高优先级，任何情况下不得违反。
+
+### 1. 根节点字段（共 4 个，类型不可变更）
+
+| 字段名 | 强制类型 | 空值处理 |
+| --- | --- | --- |
+| `basic_info` | 对象 (dict) | 必填，所有子字段必须完整存在 |
+| `reimbursement_details` | 对象 (dict) | 必填，必须且仅包含下述 2 个子字段 |
+| `payment_methods` | 数组 (list) | 必填，无数据时赋值为 `[]` |
+| `attachments` | 数组 (list) | 必填，无数据时赋值为 `[]` |
+
+### 2. `reimbursement_details` 子字段（共 2 个）
+
+| 字段名 | 强制类型 | 空值处理 |
+| --- | --- | --- |
+| `total_invoices` | 数字 (int) | 必填 |
+| `total_amount` | 数字 (float) | 必填 |
+
+### 3. 禁止行为
+
+* 省略任何根节点字段或 `reimbursement_details` 的子字段
+* 将 `payment_methods` 或 `attachments` 赋值为 `null`、字符串、数字或对象
+* 在 `reimbursement_details` 中添加未定义的子字段
+* 合并不同模块的数组数据
+
+**正确示例**：
+```json
+{
+  "basic_info": {...},
+  "reimbursement_details": {...},
+  "payment_methods": [],
+  "attachments": [{"filename":"发票.pdf", ...}]
+}
+```
+
+**错误示例**：
+```json
+{
+  "basic_info": {...},
+  "reimbursement_details": {...},
+  "payment_methods": null,
+}
+```
+
+## 输入数据说明
+你会收到以下数据：
+1. **发票信息**：包含购买物品的发票信息
+2. **付款记录**：包含刷卡日期、刷卡金额、公务卡号等信息
+
+需要提取的信息：
+1. `basic_info`:(必填，每一项都必须填，给出合理的猜测)
+    1. `reimbursement_description`：根据所有信息写一句20字以内的报销说明
+2. `reimbursement_details`:(至少有一项)
+    1. `total_invoices`: 发票的总份数
+    2. `total_amount`：填写付款记录总金额
+3. `payment_methods`：（多少笔支付记录就有多少条；多项请采用上述通用 JSON 数组格式）
+    1. `card_date`：根据付款记录，格式 YYYY-M-D
+    2. `card_amount`：根据付款记录填写，单位为元，数字
+    3. `merchant`：根据发票信息推测商户信息
+    4. `remark`：说明该笔付款关联的发票信息
+4. `attachments`：（必填，用户已经告诉你所有文件了`【源文件: {filename}】`，"invoice_type": "payment"的不作为附件）
+    1. `filename`: 严格使用用户提供的原始文件名，不得修改任何字符
+    2. `attachment_type`：从以下两个选项中选择：invoice、other
+    3. `attachment_desc`：简要描述该文件的基本信息
+
+## 最终输出要求
+
+* 仅输出纯 JSON 字符串，不包含任何思考过程、解释文字或 Markdown 标记
+* JSON 语法必须正确，无多余逗号、引号等错误
+* 严格遵守所有强制性类型约束，违反类型要求的输出视为无效

src/doc/prompts/travel_info_system.md

@@ -3,7 +3,7 @@
 你是财务差旅信息提取助手。你的任务是根据发票信息、付款记录，提取出差相关的结构化信息，并以严格符合以下类型要求的 JSON 格式返回。所有类型约束为最高优先级规则，任何情况下不得违反。
 
 🔴 最高优先级：强制性类型约束（优先级高于所有其他规则）
-1. 根节点必须包含且仅包含以下 6 个字段，字段类型绝对不可变更：
+1. 根节点必须包含且仅包含以下 5 个字段，字段类型绝对不可变更：
 
     | 字段名    | 强制类型      | 空值处理规则             |
     | ------ | --------- | ------------------ |

src/pipeline.py

@@ -1,16 +1,22 @@
 """
 报销全流程编排
 
-将发票提取 → 浏览器填报串联为一条管道，
+将发票提取 → 差旅/普通信息提取 → 浏览器填报串联为一条管道，
 数据在内存中流转，同时生成 CSV 中间产物。
 
 发票类型区分：
     - 差旅发票（train/hotel）：不生成易耗品出库单，走差旅报销流程
     - 普通发票（general）：生成易耗品出库单，走普通报销流程
+
+数据流变更（2026-06-11）：
+    在发票提取和匹配完成后立即判断报销类型（差旅/普通），
+    差旅调用 LLM 提取 travel_info.json，普通预留 normal_info.json。
+    Bot 仅负责接收信息并填报，不再承担信息提取职责。
 """
 
+import json
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
 
 from . import get_logger
 from .config import load_config
@@ -22,6 +28,12 @@ from .doc.invoice import (
 from .doc.invoice import (
     save_csv as save_payment_csv,
 )
+from .doc.llm_extractor import (
+    CACHE_DIR_NAME,
+    extract_normal_info,
+    extract_travel_info,
+    load_cache,
+)
 
 
 def _classify_invoice_batch(
@@ -54,6 +66,64 @@ def _classify_from_cache(cache_path: Path) -> dict[str, list[dict[str, Any]]]:
     return _classify_invoice_batch(invoices)
 
 
+def _extract_travel_info_if_needed(groups: dict[str, list[dict[str, Any]]], cache_path: Path) -> dict[str, Any] | None:
+    """当存在差旅发票时，调用 LLM 提取差旅信息并缓存。
+
+    Returns:
+        差旅信息字典，非差旅时返回 None。
+    """
+    if not groups.get("travel"):
+        return None
+
+    from .doc.llm_extractor import CACHE_DIR_NAME, load_cache
+
+    # 检查缓存是否已有
+    cache_map = load_cache(cache_path)
+    if cache_map.get("travel_info"):
+        log.info("使用已有差旅信息缓存")
+        return cast(dict[str, Any] | None, cache_map["travel_info"])
+
+    log.info("开始提取差旅信息...")
+    travel_info = extract_travel_info(source_dir=cache_path)
+
+    # 保存到缓存
+    cache_dir = cache_path / CACHE_DIR_NAME
+    cache_dir.mkdir(parents=True, exist_ok=True)
+
+    with open(cache_dir / "travel_info.json", "w", encoding="utf-8") as f:
+        json.dump(travel_info, f, ensure_ascii=False, indent=2)
+    log.info("差旅信息已保存到缓存")
+    return travel_info
+
+
+def _extract_normal_info_if_needed(groups: dict[str, list[dict[str, Any]]], cache_path: Path) -> dict[str, Any] | None:
+    """当存在普通发票时，调用 LLM 提取普通报销信息并缓存。
+
+    Returns:
+        普通报销信息字典，非普通时返回 None。
+    """
+    if not groups.get("general"):
+        return None
+
+    # 检查缓存是否已有
+    cache_map = load_cache(cache_path)
+    if cache_map.get("normal_info"):
+        log.info("使用已有普通发票信息缓存")
+        return cast(dict[str, Any] | None, cache_map["normal_info"])
+
+    log.info("开始提取普通发票信息...")
+    normal_info = extract_normal_info(source_dir=cache_path)
+
+    # 保存到缓存
+    cache_dir = cache_path / CACHE_DIR_NAME
+    cache_dir.mkdir(parents=True, exist_ok=True)
+
+    with open(cache_dir / "normal_info.json", "w", encoding="utf-8") as f:
+        json.dump(normal_info, f, ensure_ascii=False, indent=2)
+    log.info("普通发票信息已保存到缓存")
+    return normal_info
+
+
 def run_pipeline(
     step: str = "all",
     username: str | None = None,
@@ -78,10 +148,12 @@ def run_pipeline(
     cache_path = Path(cache_dir) if cache_dir else project_dir / "scripts" / "data"
 
     # --------------------------------------------------
-    # Step 1: 发票提取
+    # Step 1: 发票提取 + 类型判断 + 信息提取
     # --------------------------------------------------
     payment_records: list[dict[str, str]] | None = None
     groups: dict[str, list[dict[str, str]]] | None = None
+    travel_info: dict[str, Any] | None = None
+    normal_info: dict[str, Any] | None = None
 
     if step in ("all", "invoice"):
         log.info("=" * 60)
@@ -101,6 +173,13 @@ def run_pipeline(
 
         log.info(f"发票分类: 差旅 {len(groups['travel'])} 张, 普通 {len(groups['general'])} 张")
 
+        # 发票提取完成后立即判断类型
+        is_travel = bool(groups["travel"]) and not bool(groups["general"])
+        if is_travel:
+            travel_info = _extract_travel_info_if_needed(groups, cache_path)
+        else:
+            normal_info = _extract_normal_info_if_needed(groups, cache_path)
+
         if step == "invoice":
             log.info("[1/2] 发票提取 完成")
             return 0
@@ -118,12 +197,17 @@ def run_pipeline(
         if groups is None:
             groups = _classify_from_cache(cache_path)
 
-        if groups["travel"] and not groups["general"]:
+        is_travel = bool(groups["travel"]) and not bool(groups["general"])
+        if is_travel:
+            if travel_info is None:
+                travel_info = _extract_travel_info_if_needed(groups, cache_path)
             log.info("检测到纯差旅发票，使用差旅报销模式")
-            run_bot(config, work_dir=cache_path)
+            run_bot(config, work_dir=cache_path, travel_info=travel_info)
         else:
+            if normal_info is None:
+                normal_info = _extract_normal_info_if_needed(groups, cache_path)
             log.info("检测到普通发票，使用普通报销模式")
-            run_bot(config, work_dir=cache_path)
+            run_bot(config, work_dir=cache_path, normal_info=normal_info)
 
         if step == "submit":
             log.info("[2/2] 报销提交 完成")

src/web/README.md

@@ -1,5 +1,5 @@
 ---
-last_reviewed: 2026-06-09
+last_reviewed: 2026-06-11
 ---
 
 # src/web 模块设计说明
@@ -29,18 +29,32 @@ src/web/
 
 ## 数据流
 
-```
-用户上传文件 → 创建 session → 文件写入 uploads/<sid>/
-     ↓
-后台线程执行管道: extract_invoices() → enrich_with_llm() → save_csv()
-     ↓
-结果写入 session 目录: invoice_summary.csv / result.json / session.log
-     ↓
-前端 SSE 轮询 result.json 变化 → 显示完成状态
-     ↓
-前端加载 CSV 数据 → 可编辑表格展示 → 用户修改后保存
-     ↓
-用户点击提交 → run_financial_submit() → bot 自动填报财务系统
+```mermaid
+graph TD
+    A[用户上传文件] --> B[创建 session]
+    B --> C[文件写入 uploads/<sid>/]
+    C --> D[后台线程执行管道]
+    D --> E["extract_invoices()"]
+    E --> F["enrich_with_llm()"]
+    F --> G["save_csv()"]
+    G --> H["结果写入 session 目录"]
+    H --> I["invoice_summary.csv"]
+    H --> J["invoice_groups.json"]
+    H --> K["result.json"]
+    H --> L["session.log"]
+    E --> M{"判断报销类型"}
+    M -->|差旅| N["extract_travel_info()"]
+    M -->|普通| O["extract_normal_info()"]
+    N --> P["travel_info.json"]
+    O --> Q["normal_info.json"]
+    K --> R["前端 SSE 轮询 → 显示完成状态"]
+    R --> S["前端加载 CSV → 可编辑表格"]
+    S --> T["用户修改后保存"]
+    T --> U["用户点击提交"]
+    U --> V["run_financial_submit()"]
+    V --> W["bot 自动填报财务系统"]
+    W --> X["差旅模式: travel_info.json → 填报差旅单 → 上传差旅附件"]
+    W --> Y["普通模式: normal_info.json → 基本信息 → 录入明细 → 支付信息 → 上传附件"]
 ```
 
 ## API 路由
@@ -70,7 +84,16 @@ src/web/
 - **差旅发票**（高铁票/酒店住宿）：不生成易耗品出库单，走差旅报销流程
 - **普通发票**：生成易耗品出库单（Word 文档），走普通报销流程
 
-`classify_invoice_batch()` 根据发票内容自动分类，`_try_fill_consumable_doc()` 仅对普通发票生成出库单。
+`extract_invoices()` 在提取阶段完成分类，结果保存为 `invoice_groups.json`（包含 `travel_count`、`general_count`、`application_count`）。后续步骤（出库单生成、财务填报）统一从该文件读取分类结果，避免重复解析 CSV 和 JSON 字段。
+
+### LLM 信息提取（2026-06-11）
+
+发票提取和匹配完成后，根据类型分流调用 LLM 提取结构化报销信息：
+
+- **差旅发票**：调用 `extract_travel_info()`，提取出差事由、地点、时间、交通/住宿明细、补助清单、支付方式、附件清单，缓存为 `travel_info.json`。
+- **普通发票**：调用 `extract_normal_info()`，提取报销说明、发票总数、总金额、支付方式、附件清单，缓存为 `normal_info.json`。
+
+Bot 填报时优先使用 LLM 提取的信息（`travel_info`/`normal_info`），降级时从缓存加载原始发票数据。
 
 ### 移动端同步
 

src/web/app.py

@@ -19,7 +19,7 @@ import threading
 import time
 import uuid
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
 from urllib.parse import quote
 
 from flask import Flask, Response, jsonify, render_template, request, stream_with_context
@@ -46,24 +46,6 @@ from src.doc.invoice import (  # noqa: E402, I001
 )
 
 
-def _classify_invoice_batch(
-    invoices: list[dict[str, str]],
-) -> dict[str, list[dict[str, str]]]:
-    """按发票类型分组"""
-    travel: list[dict[str, str]] = []
-    general: list[dict[str, str]] = []
-    application: list[dict[str, str]] = []
-    for inv in invoices:
-        inv_type = inv.get("invoice_type", "general")
-        if inv_type == "application":
-            application.append(inv)
-        elif inv_type in ("train", "hotel"):
-            travel.append(inv)
-        else:
-            general.append(inv)
-    return {"travel": travel, "general": general, "application": application}
-
-
 fill_log = get_logger("fill_consumable_doc")
 CONSUMABLE_TEMPLATE = PROJECT_ROOT / CONSUMABLE_DOC_FILENAME
 
@@ -72,11 +54,32 @@ app = Flask(__name__, template_folder="templates")
 UPLOAD_BASE = PROJECT_ROOT / "src" / "web" / "uploads"
 SESSION_LOG_FILE = "session.log"
 SESSION_RESULT_FILE = "result.json"
+INVOICE_GROUPS_FILE = "invoice_groups.json"
 
 
-# ================================================================
-# 日志收集器 — 捕获管道日志到文件，SSE 端点通过 tail -f 读取
-# ================================================================
+def _save_invoice_groups(session_dir: Path, groups: dict[str, list[dict[str, str]]]) -> None:
+    """保存发票分类结果到 session 目录的 JSON 文件"""
+    groups_path = session_dir / INVOICE_GROUPS_FILE
+    # 只保存各组的数量统计，避免重复存储完整发票数据
+    data = {
+        "travel_count": len(groups.get("travel", [])),
+        "general_count": len(groups.get("general", [])),
+        "application_count": len(groups.get("application", [])),
+    }
+    with open(groups_path, "w", encoding="utf-8") as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+
+
+def _load_invoice_groups(session_dir: Path) -> dict[str, int] | None:
+    """从 session 目录加载发票分类统计"""
+    groups_path = session_dir / INVOICE_GROUPS_FILE
+    if not groups_path.exists():
+        return None
+    try:
+        with open(groups_path, encoding="utf-8") as f:
+            return cast(dict[str, int] | None, json.load(f))
+    except Exception:
+        return None
 
 
 class _SSELogHandler(logging.Handler):
@@ -164,69 +167,33 @@ def _resolve_invoice_csv(session_dir: Path) -> Path | None:
     return None
 
 
-def _has_general_invoices(rows: list[dict[str, str]]) -> bool:
-    """检查发票列表中是否包含普通发票（需要生成易耗品出库单）"""
-    invoices = []
-    for row in rows:
-        # 支付记录格式：从 _invoices_json 还原
-        invoices_json = row.get("_invoices_json", "")
-        if invoices_json:
-            try:
-                invoices.extend(json.loads(invoices_json))
-            except json.JSONDecodeError:
-                pass
-        # 发票级别格式：直接使用
-        elif "发票类型" in row:
-            invoices.append(row)
-    if not invoices:
-        return False
-    groups = _classify_invoice_batch(invoices)
-    return len(groups["general"]) > 0
-
-
-def _get_invoice_groups(rows: list[dict[str, str]]) -> dict[str, int]:
-    """统计发票类型分布"""
-    invoices = []
-    for row in rows:
-        # 支付记录格式：从 _invoices_json 还原
-        invoices_json = row.get("_invoices_json", "")
-        if invoices_json:
-            try:
-                invoices.extend(json.loads(invoices_json))
-            except json.JSONDecodeError:
-                pass
-        # 发票级别格式：直接使用
-        elif "发票类型" in row:
-            invoices.append(row)
-    groups = _classify_invoice_batch(invoices)
-    return {
-        "travel_count": len(groups["travel"]),
-        "general_count": len(groups["general"]),
-    }
+# ================================================================
+# 出库单填写
+# ================================================================
 
 
 def _try_fill_consumable_doc(session_dir: Path, config: dict[str, Any]) -> dict[str, Any]:
     """根据 CSV 填写易耗品出库单，供会话目录下载。
 
-    仅当存在普通发票时才生成出库单。纯差旅发票跳过。
+    从 invoice_groups.json 读取分类结果，仅当存在普通发票时才生成出库单。
     """
     if not CONSUMABLE_TEMPLATE.exists():
         fill_log.warning("出库单模板不存在: %s", CONSUMABLE_TEMPLATE)
         return {"ok": False, "error": "出库单模板不存在，请将模板放在项目根目录"}
 
+    # 从统一的分类结果读取，避免重复解析 CSV/JSON
+    groups = _load_invoice_groups(session_dir)
+    if groups is None:
+        return {"ok": False, "error": "未找到发票分类数据，请先处理"}
+
+    if not groups.get("general_count", 0):
+        fill_log.info("纯差旅发票，跳过易耗品出库单生成")
+        return {"ok": False, "skipped": True, "error": "差旅发票无需生成易耗品出库单"}
+
     csv_path = _resolve_payment_csv(session_dir)
     if csv_path is None:
         return {"ok": False, "error": "未找到发票 CSV"}
 
-    # 检查是否有普通发票
-    rows = load_csv(csv_path)
-    if rows is None:
-        return {"ok": False, "error": "CSV 读取失败"}
-
-    if not _has_general_invoices(rows):
-        fill_log.info("纯差旅发票，跳过易耗品出库单生成")
-        return {"ok": False, "skipped": True, "error": "差旅发票无需生成易耗品出库单"}
-
     out_doc = session_dir / CONSUMABLE_DOC_FILENAME
     try:
         fill_log.info("开始填写出库单: %s", out_doc.name)
@@ -265,6 +232,10 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
     """在 Web 会话目录中执行发票提取，结果写入 session 目录下的文件
 
     注意：不再自动提交财务系统。提交通由 /api/submit-financial/<session_id> 触发。
+
+    在发票提取和匹配完成后立即判断报销类型：
+        - 差旅发票：调用 LLM 提取差旅信息并缓存到 travel_info.json
+        - 普通发票：无需额外提取（normal_info.json 待实现）
     """
     start = time.time()
 
@@ -281,6 +252,38 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
     if applications:
         save_application_json(applications, session_dir / "travel_applications.json")
 
+    # 保存分类结果（供后续步骤统一读取）
+    _save_invoice_groups(session_dir, groups)
+
+    # ---- Step 2: 差旅/普通信息提取 ----
+    is_travel = bool(groups.get("travel")) and not bool(groups.get("general"))
+    if is_travel:
+        from src.doc.llm_extractor import CACHE_DIR_NAME, extract_travel_info, load_cache
+
+        # 检查缓存是否已有
+        cache_map = load_cache(session_dir)
+        if not cache_map.get("travel_info"):
+            fill_log.info("开始提取差旅信息...")
+            travel_info = extract_travel_info(source_dir=session_dir)
+            cache_dir = session_dir / CACHE_DIR_NAME
+            cache_dir.mkdir(parents=True, exist_ok=True)
+            with open(cache_dir / "travel_info.json", "w", encoding="utf-8") as f:
+                json.dump(travel_info, f, ensure_ascii=False, indent=2)
+            fill_log.info("差旅信息已保存到缓存")
+    else:
+        from src.doc.llm_extractor import CACHE_DIR_NAME, extract_normal_info, load_cache
+
+        # 检查缓存是否已有
+        cache_map = load_cache(session_dir)
+        if not cache_map.get("normal_info"):
+            fill_log.info("开始提取普通发票信息...")
+            normal_info = extract_normal_info(source_dir=session_dir)
+            cache_dir = session_dir / CACHE_DIR_NAME
+            cache_dir.mkdir(parents=True, exist_ok=True)
+            with open(cache_dir / "normal_info.json", "w", encoding="utf-8") as f:
+                json.dump(normal_info, f, ensure_ascii=False, indent=2)
+            fill_log.info("普通发票信息已保存到缓存")
+
     # 统计发票总数
     invoice_count = sum(len(inv.get("_matched_invoices", [])) for inv in invoices)
 
@@ -302,7 +305,7 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
 def run_financial_submit(session_dir: Path, config: dict[str, Any]) -> dict[str, Any]:
     """执行财务系统填报（从前端确认后调用）
 
-    根据发票类型选择填报模式：
+    从 invoice_groups.json 读取分类结果，根据发票类型选择填报模式：
         - 纯差旅发票：差旅报销模式（TODO）
         - 含普通发票：普通报销模式
     """
@@ -312,14 +315,10 @@ def run_financial_submit(session_dir: Path, config: dict[str, Any]) -> dict[str,
 
     from src.bot import run_bot_web
 
-    # TODO: 改为从缓存读取或直接请求 LLM，与差旅报销保持一致
-    # bot_invoices = load_invoice_data(str(csv_path), config)
-
-    # 判断发票类型
-    rows = load_csv(csv_path)
-    if rows:
-        invoice_groups = _get_invoice_groups(rows)
-        if invoice_groups["travel_count"] and not invoice_groups["general_count"]:
+    # 从统一的分类结果读取，避免重复解析
+    groups = _load_invoice_groups(session_dir)
+    if groups:
+        if groups.get("travel_count", 0) and not groups.get("general_count", 0):
             fill_log.info("检测到纯差旅发票，使用差旅报销模式")
             # TODO: 差旅报销填报流程
         else: