349 lines
10 KiB
Python
349 lines
10 KiB
Python
"""发票信息提取器：从网站提取发票信息。"""
|
||
|
||
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
|
||
|
||
Returns:
|
||
发票信息列表
|
||
"""
|
||
invoices = []
|
||
|
||
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):
|
||
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 page_row=%s error=%s", i, str(e))
|
||
continue
|
||
|
||
has_next = await _has_next_page(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_invoice_detail(page: Any, invoice_index: int = 0) -> Optional[Dict[str, Any]]:
|
||
"""提取单个发票的详细信息。
|
||
|
||
Args:
|
||
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))
|
||
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
|
||
|
||
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_invoice_items(page: Any) -> List[Dict[str, str]]:
|
||
"""提取发票商品明细。"""
|
||
items = []
|
||
|
||
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
|
||
|
||
except Exception:
|
||
return []
|
||
|
||
|
||
async def _has_next_page(page: Any) -> bool:
|
||
"""检查是否有下一页。"""
|
||
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
|
||
except Exception:
|
||
return False
|
||
|
||
|
||
async def _click_next_page(page: Any) -> bool:
|
||
"""点击下一页按钮。"""
|
||
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
|
||
|
||
|
||
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
|
||
|
||
|
||
def format_invoice_data(invoices: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||
"""格式化发票数据为结构化格式。"""
|
||
return {
|
||
"total_count": len(invoices),
|
||
"invoices": invoices,
|
||
"extraction_complete": True,
|
||
} |