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

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,
-    }
+    }