添加批量行情解析API和分页功能修复
This commit is contained in:
龙大
parent
446cd32484
commit
9e237c88a4
|
|
@ -0,0 +1,2 @@
|
||||||
|
from app.models.deal_info import DealInfo
|
||||||
|
from app.models.models import User, Collection
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
# 资讯API路由
|
# 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 sqlalchemy.orm import Session, joinedload
|
||||||
from typing import List, Optional
|
from typing import List, Optional
|
||||||
from pydantic import BaseModel
|
from pydantic import BaseModel
|
||||||
|
|
@ -1082,3 +1082,179 @@ def get_seek_list_all(
|
||||||
content=result,
|
content=result,
|
||||||
headers={"X-Total-Pages": str(total_pages), "X-Total-Count": str(total_count)}
|
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}
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue