133 lines
4.4 KiB
Python
133 lines
4.4 KiB
Python
# coding=utf-8
|
|
import hashlib
|
|
import logging
|
|
import os
|
|
import sys
|
|
import uuid
|
|
from datetime import datetime
|
|
|
|
# Ensure sys path includes root for imports if not already
|
|
project_root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
if project_root not in sys.path:
|
|
sys.path.append(project_root)
|
|
|
|
from DbKit.Db import Db
|
|
from Config.Config import DB_URL
|
|
from Model.StationProfile import StationProfile
|
|
from Model.StationStatus import StationStatus
|
|
from Model.StationPriceSchedule import StationPriceSchedule
|
|
|
|
# 配置日志
|
|
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class YiLaiTeService:
|
|
def __init__(self):
|
|
self.db = Db(db_url=DB_URL)
|
|
self.station_profile_model = StationProfile()
|
|
self.station_status_model = StationStatus()
|
|
self.station_price_schedule_model = StationPriceSchedule()
|
|
self.operator = "驿来特"
|
|
|
|
def generate_id(self):
|
|
return str(uuid.uuid4())
|
|
|
|
def get_hash(self, s: str) -> str:
|
|
return hashlib.md5(s.encode('utf-8')).hexdigest()
|
|
|
|
def _to_float(self, value) -> float:
|
|
"""
|
|
从字符串中提取浮点数，过滤掉非数字字符
|
|
"""
|
|
if value is None:
|
|
return 0.0
|
|
if isinstance(value, (int, float)):
|
|
return float(value)
|
|
|
|
import re
|
|
try:
|
|
# 提取第一个匹配的数字部分（包含小数点）
|
|
match = re.search(r"[-+]?\d*\.?\d+", str(value))
|
|
if match:
|
|
return float(match.group())
|
|
return 0.0
|
|
except:
|
|
return 0.0
|
|
|
|
async def init_db(self):
|
|
await self.db.init_db()
|
|
|
|
async def close_db(self):
|
|
await self.db.close()
|
|
|
|
async def log_task_start(self, task_id):
|
|
"""记录任务开始"""
|
|
from datetime import datetime
|
|
try:
|
|
await self.db.save("t_crawl_task_log", {
|
|
"task_id": task_id,
|
|
"operator": self.operator,
|
|
"start_time": datetime.now(),
|
|
"status": "running"
|
|
}, "task_id")
|
|
except Exception as e:
|
|
logger.error(f"记录任务开始日志失败: {e}")
|
|
|
|
async def log_task_end(self, task_id, count, status, error_msg=None):
|
|
"""记录任务结束"""
|
|
from datetime import datetime
|
|
try:
|
|
end_time = datetime.now()
|
|
# 假设 start_time 已经在数据库中，我们可以通过 task_id 更新
|
|
# 这里的 duration 计算可以在 SQL 中做，或者先查出来再算
|
|
await self.db.update("t_crawl_task_log", {
|
|
"task_id": task_id,
|
|
"end_time": end_time,
|
|
"station_count": count,
|
|
"status": status,
|
|
"error_msg": error_msg
|
|
}, "task_id")
|
|
except Exception as e:
|
|
logger.error(f"更新任务结束日志失败: {e}")
|
|
|
|
async def process_price_detail_data(self, station_name, hourly_schedule) -> bool:
|
|
"""
|
|
直接保存已处理好的小时段价格数据
|
|
"""
|
|
if not station_name or not hourly_schedule:
|
|
return False
|
|
|
|
station_hash = self.get_hash(station_name)
|
|
now = datetime.now()
|
|
|
|
async with await self.db.get_session() as session:
|
|
# 1. 保存 Profile (如果不存在)
|
|
profile_id = self.generate_id()
|
|
await self.station_profile_model.save(
|
|
session=session,
|
|
id=profile_id,
|
|
station_hash=station_hash,
|
|
operator=self.operator,
|
|
station_name=station_name,
|
|
valid_start_time=now
|
|
)
|
|
|
|
# 2. 保存价格
|
|
schedule_id = self.generate_id()
|
|
await self.station_price_schedule_model.save(
|
|
session=session,
|
|
id=schedule_id,
|
|
station_hash=station_hash,
|
|
schedule_json=hourly_schedule,
|
|
valid_start_time=now
|
|
)
|
|
await session.commit()
|
|
return True
|
|
|
|
async def process_station_list_vl(self, image_path, json_metadata, device_info=None, max_count=None) -> list:
|
|
"""
|
|
基于 VL 模式处理场站列表 (整页识别)
|
|
"""
|
|
# 驿来特目前逻辑待实现，先占位
|
|
return []
|