aszer/etf
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(datasource): 股票info字段放到API响应最外层

Browse Source 
- yfinance_source.py: stock_info 存储在 df.attrs['info'] 中
- flask_server.py: dataframe_to_json 从 df.attrs 提取 info 放到最外层
- flask_server.py: 缓存切片函数保留 info 字段
- Dockerfile: 启用 Flask 服务作为默认 CMD（端口80）

响应结构示例:
{
  "data": [{"date": "2024-01-01", "code": "AAPL", ...}],
  "info": {"sector": "Technology", "industry": "...", ...}
}
This commit is contained in:
aszerW
2026-05-13 00:26:19 +08:00
parent 7c48e4ab21
commit ecd8d6539f
3 changed files with 80 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@@ -21,7 +21,7 @@ ENV TZ=Asia/Shanghai
EXPOSE 80
# 启动Flask数据API服务（默认端口80）
# CMD ["python", "datasource/flask_server.py", "--host", "0.0.0.0"]
CMD ["python", "datasource/flask_server.py", "--host", "0.0.0.0"]
# 运行定时任务调度器（如需使用Flask服务，取消上面注释并注释掉下面）
CMD ["python", "scripts/daily_scheduler.py", "--time", "09:00"]
# CMD ["python", "scripts/daily_scheduler.py", "--time", "09:00"]

84
datasource/flask_server.py
View File

@@ -180,8 +180,21 @@ def _slice_data_from_cache(cached_data: Dict, start: str, end: str) -> Dict:
# 从缓存数据中重建 DataFrame
records = cached_data['df_json']['data']
info_data = cached_data['df_json'].get('info', None) # 从缓存获取 info
if not records:
return cached_data
result = {
'data': [],
'count': 0,
'code': cached_data['code'],
'asset_type': cached_data['asset_type'],
'requested_range': {'start': start, 'end': end},
'available_range': {'start': cached_data['data_start'], 'end': cached_data['data_end']},
}
# 保留 info（如果有）
if info_data:
result['info'] = info_data
return result
# 转换为 DataFrame
df = pd.DataFrame(records)
@@ -189,6 +202,10 @@ def _slice_data_from_cache(cached_data: Dict, start: str, end: str) -> Dict:
df['date'] = pd.to_datetime(df['date'])
df = df.set_index('date')
# 恢复 attrs（如果有 info）
if info_data:
df.attrs['info'] = info_data
# 切片日期范围
start_dt = pd.to_datetime(start)
end_dt = pd.to_datetime(end)
@@ -199,17 +216,7 @@ def _slice_data_from_cache(cached_data: Dict, start: str, end: str) -> Dict:
# 切片（使用 loc 进行日期范围选择）
sliced_df = df.loc[start_dt:end_dt]
if len(sliced_df) == 0:
return {
'data': [],
'count': 0,
'code': cached_data['code'],
'asset_type': cached_data['asset_type'],
'requested_range': {'start': start, 'end': end},
'available_range': {'start': cached_data['data_start'], 'end': cached_data['data_end']},
}
# 转换为 JSON 格式
# 转换为 JSON 格式（dataframe_to_json 会处理 df.attrs['info']）
result = dataframe_to_json(sliced_df)
result['code'] = cached_data['code']
result['asset_type'] = cached_data['asset_type']
@@ -337,10 +344,37 @@ def get_cache_info() -> Dict:
# DataFrame 转换
# ============================================================
class JSONEncoder(json.JSONEncoder):
"""自定义 JSON 编码器，处理特殊类型"""
def default(self, obj):
# 处理 pandas Timestamp
if hasattr(obj, 'isoformat'):
return obj.isoformat()
# 处理 numpy 类型
if hasattr(obj, 'item'):
return obj.item()
# 处理 NaN/Infinity
if isinstance(obj, float):
if obj != obj: # NaN
return None
if obj == float('inf'):
return None
if obj == float('-inf'):
return None
return super().default(obj)
def dataframe_to_json(df: pd.DataFrame) -> Dict:
"""将 DataFrame 转换为 JSON 可序列化的字典"""
"""将 DataFrame 转换为 JSON 可序列化的字典
如果 df.attrs 中有 info 字段，会放到最外层返回
"""
if df is None or len(df) == 0:
return {"data": [], "count": 0}
result = {"data": [], "count": 0}
# 即使空数据也返回 info（如果有）
if hasattr(df, 'attrs') and 'info' in df.attrs:
result['info'] = df.attrs['info']
return result
# 重置索引
df_reset = df.reset_index()
@@ -357,18 +391,32 @@ def dataframe_to_json(df: pd.DataFrame) -> Dict:
except Exception:
pass
# 转换为字典列表
records = df_reset.to_dict(orient='records')
# 处理特殊值（NaN, Infinity）
df_clean = df_reset.copy()
for col in df_clean.columns:
if df_clean[col].dtype in ['float64', 'float32']:
df_clean[col] = df_clean[col].replace([float('inf'), float('-inf')], None)
df_clean[col] = df_clean[col].where(df_clean[col].notna(), None)
return {
# 转换为字典列表
records = df_clean.to_dict(orient='records')
# 构建返回结果
result = {
"data": records,
"count": len(records),
"columns": list(df_reset.columns),
"columns": list(df_clean.columns),
"date_range": {
"start": df.index.min().strftime('%Y-%m-%d') if len(df) > 0 else None,
"end": df.index.max().strftime('%Y-%m-%d') if len(df) > 0 else None,
}
}
# 将 info 从 df.attrs 放到最外层
if hasattr(df, 'attrs') and 'info' in df.attrs:
result['info'] = df.attrs['info']
return result
def validate_date(date_str: str) -> bool:

12
datasource/yfinance_source.py
View File

@@ -55,6 +55,7 @@ class YFinanceSource:
Returns:
DataFrame with columns: date, open, high, low, close, volume
股票元信息存储在 df.attrs['info'] 中
"""
import yfinance as yf
@@ -67,6 +68,13 @@ class YFinanceSource:
try:
ticker = yf.Ticker(yf_code)
# 获取股票信息（仅对股票/ETF有效，指数可能没有）
stock_info = {}
try:
stock_info = ticker.info or {}
except Exception:
pass # 指数可能没有info
# end_date 需要加一天（yfinance的end是排他的）
end_dt = datetime.strptime(end_date, "%Y-%m-%d") + timedelta(days=1)
@@ -96,6 +104,10 @@ class YFinanceSource:
# 添加代码列
df["code"] = code
# 将股票信息存储到 DataFrame.attrs 中（最外层结构）
df.attrs['info'] = stock_info
df.attrs['code'] = code
return df[['code', 'open', 'high', 'low', 'close', 'volume']]
except Exception as e: