添加批量行情解析API和分页功能修复

backend/app/models/__init__.py

@@ -0,0 +1,2 @@
+from app.models.deal_info import DealInfo
+from app.models.models import User, Collection

backend/app/routers/information.py

@@ -1,5 +1,5 @@
 # 资讯API路由
-from fastapi import APIRouter, Depends, HTTPException, Query
+from fastapi import APIRouter, Depends, HTTPException, Query, Body
 from sqlalchemy.orm import Session, joinedload
 from typing import List, Optional
 from pydantic import BaseModel
@@ -1082,3 +1082,179 @@ def get_seek_list_all(
         content=result,
         headers={"X-Total-Pages": str(total_pages), "X-Total-Count": str(total_count)}
     )
+def parse_deals_locally(text: str, default_packaging: str = '', default_date: str = '', default_platform: str = ''):
+    """本地正则解析批量行情文本"""
+    import re
+    from datetime import datetime
+    results = []
+    
+    # 尝试从文本中提取日期（可能出现在标题或时间戳中）
+    # 格式如: 3月29日, 2026年3月29日, 2026-03-29
+    date_patterns = [
+        r'(\d{1,2})月(\d{1,2})日',
+        r'(\d{4})年(\d{1,2})月(\d{1,2})日',
+        r'(\d{4})-(\d{1,2})-(\d{1,2})'
+    ]
+    
+    extracted_date = None
+    for pattern in date_patterns:
+        match = re.search(pattern, text)
+        if match:
+            try:
+                if len(match.groups()) == 2:
+                    # 3月29日 - 使用当前年份
+                    extracted_date = f"2026-{int(match.group(1)):02d}-{int(match.group(2)):02d}"
+                elif len(match.groups()) == 3:
+                    if int(match.group(1)) > 2000:
+                        # 2026年3月29日
+                        extracted_date = f"{match.group(1)}-{int(match.group(2)):02d}-{int(match.group(3)):02d}"
+                    else:
+                        # 3月29日格式
+                        extracted_date = f"2026-{int(match.group(1)):02d}-{int(match.group(2)):02d}"
+                break
+            except:
+                pass
+    
+    # 默认使用今天
+    default_date = datetime.now().strftime('%Y-%m-%d')
+    deal_date = extracted_date or default_date
+    
+    lines = text.strip().split('\n')
+    
+    for line in lines:
+        line = line.strip()
+        if not line or 'J0' not in line:
+            continue
+        
+        # 提取冠字号 J0 + 8-9位数字
+        serial_match = re.search(r'J0(\d{8,9})', line)
+        if not serial_match:
+            continue
+        
+        serial_num = serial_match.group(1)
+        if len(serial_num) == 9:
+            serial_num = serial_num[:8]
+        serial = 'J0' + serial_num
+        
+        # 提取价格 ¥xxx,xxx 或 xxx,xxx（必须在J0之后）
+        serial_pos = line.find(serial)
+        after_serial = line[serial_pos + len(serial):]
+        price_match = re.search(r'[¥￥]?\s*([1-9][\d,]{2,})', after_serial)
+        if not price_match:
+            continue
+        price = int(price_match.group(1).replace(',', ''))
+        
+        # 提取卖家（价格后面的中文字符）
+        after_price_pos = after_serial.find(price_match.group(0)) + len(price_match.group(0))
+        after_price = after_serial[after_price_pos:]
+        seller_match = re.search(r'([^\d\s¥￥]+?)(?:\s*$|\s*\n)', after_price)
+        seller = seller_match.group(1).strip() if seller_match else ''
+        
+        # 分类判断
+        digits = serial_num
+        d = digits
+        category = '通货'
+        if not any(c in d for c in ['1','2','3','4','5','7']): category = '圆圆号'
+        elif not any(c in d for c in ['2','3','4','5','7']): category = '倒置号'
+        elif not any(c in d for c in ['1','2','3','4','7']): category = '金马王'
+        elif not any(c in d for c in ['2','3','4','7']): category = '金马号'
+        elif not any(c in d for c in ['1','2','4','5','7']): category = '金山王'
+        elif not any(c in d for c in ['1','2','4','7']): category = '天马王'
+        elif not any(c in d for c in ['2','4','5','7']): category = '金山号'
+        elif not any(c in d for c in ['2','4','7']): category = '天马号'
+        elif not any(c in d for c in ['1','3','4','5','7']): category = '朦胧王'
+        elif not any(c in d for c in ['3','4','5','7']): category = '朦胧号'
+        elif not any(c in d for c in ['1','3','4','7']): category = '如意号'
+        elif not any(c in d for c in ['3','4','7']): category = '钻石号'
+        elif not any(c in d for c in ['4','7']): category = '永恒号'
+        elif '4' not in d: category = '带7号'
+        
+        # 提取评级机构 PCGS/PMG/ACG/爱藏
+        grade = ''
+        grading_company = ''
+        packaging = '单张'
+        
+        if 'PC69' in line or 'PC68' in line or 'PC67' in line:
+            grade_match = re.search(r'PC(6[789]|5\d?)', line)
+            grade = 'PC' + grade_match.group(1) if grade_match else ''
+            grading_company = 'PCGS'
+        elif 'PMG68' in line or 'PMG67' in line:
+            grade_match = re.search(r'PMG(6[789]|5\d?)', line)
+            grade = 'PMG' + grade_match.group(1) if grade_match else ''
+            grading_company = 'PMG'
+        elif 'ACG' in line:
+            grade_match = re.search(r'ACG(6[789]|5\d?)', line)
+            grade = 'ACG' + grade_match.group(1) if grade_match else ''
+            grading_company = 'ACG'
+        elif '爱藏67+' in line:
+            grade = '67+'
+            grading_company = '爱藏'
+        elif '爱藏67' in line:
+            grade = '67'
+            grading_company = '爱藏'
+        
+        # 判断包装类型
+        packaging = '单张'
+        
+        # 如果传入了默认包装类型，先使用默认
+        if default_packaging:
+            packaging = default_packaging
+        
+        # 简化识别：带"刀"字=标百，带"标"字=标十
+        if '刀' in line:
+            packaging = '标百'
+        elif '标' in line:
+            packaging = '标十'
+        
+        # 尾号判断：如果冠字号尾号是01/11/21/31/41/51/61/71/81/91，且有刀/标字样，基本确认是标百
+        if len(serial_num) >= 2:
+            tail = serial_num[-2:]
+            if tail in ['01', '11', '21', '31', '41', '51', '61', '71', '81', '91']:
+                if '刀' in line or ('标' in line and packaging == '单张'):
+                    packaging = '标百'
+                    packaging = '标百'
+        
+        # 如果没有刀/标字样，但尾号是01且没有其他特征，可能是标百
+        if packaging == '单张' and len(serial_num) >= 2:
+            tail = serial_num[-2:]
+            if tail == '01':
+                # 检查是否在特定语境下
+                packaging = '标百'
+        
+        # 计算尾号和大小号
+        tail_number = ''
+        size_type = ''
+        if packaging == '标十' and len(serial_num) >= 2:
+            tail_number = serial_num[-2:]
+            size_type = tail_number in ['01','11','21','31','41','51'] and '小号' or '大号'
+        elif packaging == '标百' and len(serial_num) >= 3:
+            tail_number = serial_num[-3:]
+            size_type = tail_number in ['101','201','301','401','501'] and '小号' or '大号'
+        
+        results.append({
+            'serial': serial,
+            'price': price,
+            'category': category,
+            'seller': seller,
+            'packaging': packaging,
+            'grade': grade,
+            'grading_company': grading_company,
+            'deal_date': deal_date or default_date,  # 成交时间
+            'entry_date': default_date,  # 录入时间
+            'is_graded': bool(grade),
+            'tail_number': tail_number,  # 尾号
+            'size_type': size_type,  # 大小号
+            'platform': default_platform  # 平台
+        })
+    
+    return results
+
+@router.post("/batch-parse-local")
+async def batch_parse_deals_local(request: dict = Body(...)):
+    """本地正则解析批量行情文本（无需AI）"""
+    text = request.get('text', '')
+    default_packaging = request.get('defaultPackaging', '')
+    default_date = request.get('defaultDate', '')
+    default_platform = request.get('defaultPlatform', '')
+    results = parse_deals_locally(text, default_packaging, default_date, default_platform)
+    return {"success": True, "data": results}