wehub/pythonstock--stock
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 13:10:28 +08:00
commit c2acfb5f2d
267 changed files with 15542 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/libs/common.py
+242
View File
@@ -0,0 +1,242 @@
#!/usr/local/bin/python
# -*- coding: utf-8 -*-
# apk add py-mysqldb or
import platform
import datetime
import time
import sys
import os
import MySQLdb
from sqlalchemy import create_engine
from sqlalchemy.types import NVARCHAR
from sqlalchemy import inspect
import pandas as pd
import traceback
import akshare as ak
# 使用环境变量获得数据库。兼容开发模式可docker模式。
MYSQL_HOST = os.environ.get('MYSQL_HOST') if (os.environ.get('MYSQL_HOST') != None) else "mysqldb"
MYSQL_USER = os.environ.get('MYSQL_USER') if (os.environ.get('MYSQL_USER') != None) else "root"
MYSQL_PWD = os.environ.get('MYSQL_PWD') if (os.environ.get('MYSQL_PWD') != None) else "mysqldb"
MYSQL_DB = os.environ.get('MYSQL_DB') if (os.environ.get('MYSQL_DB') != None) else "stock_data"
MYSQL_PORT = os.environ.get('MYSQL_PORT') if (os.environ.get('MYSQL_PORT') != None) else "3306"
print("MYSQL_HOST :", MYSQL_HOST, ",MYSQL_USER :", MYSQL_USER, ",MYSQL_DB :", MYSQL_DB)
MYSQL_CONN_URL = "mysql+mysqldb://" + MYSQL_USER + ":" + MYSQL_PWD + "@" + MYSQL_HOST + ":" + MYSQL_PORT + "/" + MYSQL_DB + "?charset=utf8mb4"
print("MYSQL_CONN_URL :", MYSQL_CONN_URL)
__version__ = "2.0.0"
# 每次发布时候更新。
# https://docs.sqlalchemy.org/en/20/errors.html#error-e3q8
#
def engine():
engine = create_engine(MYSQL_CONN_URL, pool_size=10, max_overflow=20)
#encoding='utf8', convert_unicode=True)
return engine
def engine_to_db(to_db):
MYSQL_CONN_URL_NEW = "mysql+mysqldb://" + MYSQL_USER + ":" + MYSQL_PWD + "@" + MYSQL_HOST + ":" + MYSQL_PORT + "/" + to_db + "?charset=utf8mb4"
engine = create_engine(MYSQL_CONN_URL_NEW, pool_size=10, max_overflow=20)
#encoding='utf8', convert_unicode=True)
return engine
# 通过数据库链接 engine。
def conn():
try:
db = MySQLdb.connect(MYSQL_HOST, MYSQL_USER, MYSQL_PWD, MYSQL_DB, charset="utf8")
# db.autocommit = True
except Exception as e:
print("conn error :", e)
db.autocommit(on=True)
return db.cursor()
# 定义通用方法函数，插入数据库表，并创建数据库主键，保证重跑数据的时候索引唯一。
def insert_db(data, table_name, write_index, primary_keys):
# 插入默认的数据库。
insert_other_db(MYSQL_DB, data, table_name, write_index, primary_keys)
# 增加一个插入到其他数据库的方法。
def insert_other_db(to_db, data, table_name, write_index, primary_keys):
# 定义engine
engine_mysql = engine_to_db(to_db)
# 使用 http://docs.sqlalchemy.org/en/latest/core/reflection.html
# 使用检查检查数据库表是否有主键。
insp = inspect(engine_mysql)
col_name_list = data.columns.tolist()
# 如果有索引，把索引增加到varchar上面。
if write_index:
# 插入到第一个位置：
col_name_list.insert(0, data.index.name)
print(col_name_list)
data.to_sql(name=table_name, con=engine_mysql, schema=to_db, if_exists='append',
dtype={col_name: NVARCHAR(length=255) for col_name in col_name_list}, index=write_index)
# print(insp.get_pk_constraint(table_name))
# print()
# print(type(insp))
# 判断是否存在主键
if insp.get_pk_constraint(table_name)['constrained_columns'] == []:
with engine_mysql.connect() as con:
# 执行数据库插入数据。
try:
con.execute('ALTER TABLE `%s` ADD PRIMARY KEY (%s);' % (table_name, primary_keys))
except Exception as e:
print("################## ADD PRIMARY KEY ERROR :", e)
# 插入数据。
def insert(sql, params=()):
with conn() as db:
print("insert sql:" + sql)
try:
db.execute(sql, params)
except Exception as e:
print("error :", e)
# 查询数据
def select(sql, params=()):
with conn() as db:
print("select sql:" + sql)
try:
db.execute(sql, params)
except Exception as e:
print("error :", e)
result = db.fetchall()
return result
# 计算数量
def select_count(sql, params=()):
with conn() as db:
print("select sql:" + sql)
try:
db.execute(sql, params)
except Exception as e:
print("error :", e)
result = db.fetchall()
# 只有一个数组中的第一个数据
if len(result) == 1:
return int(result[0][0])
else:
return 0
# 通用函数。获得日期参数。
def run_with_args(run_fun):
tmp_datetime_show = datetime.datetime.now() # 修改成默认是当日执行 + datetime.timedelta()
tmp_hour_int = int(tmp_datetime_show.strftime("%H"))
if tmp_hour_int < 12 :
# 判断如果是每天 中午 12 点之前运行，跑昨天的数据。
tmp_datetime_show = (tmp_datetime_show + datetime.timedelta(days=-1))
tmp_datetime_str = tmp_datetime_show.strftime("%Y-%m-%d %H:%M:%S.%f")
print("\n######################### hour_int %d " % tmp_hour_int)
str_db = "MYSQL_HOST :" + MYSQL_HOST + ", MYSQL_USER :" + MYSQL_USER + ", MYSQL_DB :" + MYSQL_DB
print("\n######################### " + str_db + " ######################### ")
print("\n######################### begin run %s %s #########################" % (run_fun, tmp_datetime_str))
start = time.time()
# 要支持数据重跑机制，将日期传入。循环次数
if len(sys.argv) == 3:
# python xxx.py 2017-07-01 10
tmp_year, tmp_month, tmp_day = sys.argv[1].split("-")
loop = int(sys.argv[2])
tmp_datetime = datetime.datetime(int(tmp_year), int(tmp_month), int(tmp_day))
for i in range(0, loop):
# 循环插入多次数据，重复跑历史数据使用。
# time.sleep(5)
tmp_datetime_new = tmp_datetime + datetime.timedelta(days=i)
try:
run_fun(tmp_datetime_new)
except Exception as e:
print("error :", e)
traceback.print_exc()
elif len(sys.argv) == 2:
# python xxx.py 2017-07-01
tmp_year, tmp_month, tmp_day = sys.argv[1].split("-")
tmp_datetime = datetime.datetime(int(tmp_year), int(tmp_month), int(tmp_day))
try:
run_fun(tmp_datetime)
except Exception as e:
print("error :", e)
traceback.print_exc()
else:
# tmp_datetime = datetime.datetime.now() + datetime.timedelta(days=-1)
try:
run_fun(tmp_datetime_show) # 使用当前时间
except Exception as e:
print("error :", e)
traceback.print_exc()
print("######################### finish %s , use time: %s #########################" % (
tmp_datetime_str, time.time() - start))
# 设置基础目录，每次加载使用。
bash_stock_tmp = "/data/cache/hist_data_cache/%s/%s/"
if not os.path.exists(bash_stock_tmp):
os.makedirs(bash_stock_tmp) # 创建多个文件夹结构。
print("######################### init tmp dir #########################")
# 增加读取股票缓存方法。加快处理速度。
def get_hist_data_cache(code, date_start, date_end):
cache_dir = bash_stock_tmp % (date_end[0:7], date_end)
# 如果没有文件夹创建一个。月文件夹和日文件夹。方便删除。
# print("cache_dir:", cache_dir)
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
cache_file = cache_dir + "%s^%s.gzip.pickle" % (date_end, code)
# 如果缓存存在就直接返回缓存数据。压缩方式。
if os.path.isfile(cache_file):
print("######### read from cache #########", cache_file)
return pd.read_pickle(cache_file, compression="gzip")
else:
# https://akshare.akfamily.xyz/data/index/index.html#id4
# 获取历史行情，em
#stock = ak.stock_zh_a_hist(symbol= code, start_date=date_start,
# end_date=date_end, adjust="")
code = gp_type_szsh(code)+ code
print("######### get data, write cache #########", code, date_start, date_end)
stock = ak.stock_zh_index_daily_em(symbol= code,
start_date=date_start.replace("-", ""), end_date=date_end.replace("-", ""))
print(stock)
if stock is None or stock.empty:
return None
stock.columns = ['date', 'open', 'close', 'high', 'low', 'volume', 'amount']
# 数据返回的是带 0 列是索引，第一列是 date 日期
# date open close high low volume amount
# 0 2024-09-20 9.81 9.90 9.90 9.78 797297 7.851212e+08
stock.set_index('date', inplace=True)
#stock = stock.sort_index(0) # 将数据按照日期排序下。
print(stock)
stock.to_pickle(cache_file, compression="gzip")
return stock
# 沪市股票包含上证主板和科创板和B股：沪市主板股票代码是60开头、科创板股票代码是688开头、B股代码900开头。
# 深市股票包含主板、中小板、创业板和B股：深市主板股票代码是000开头、中小板股票代码002开头、创业板300开头、B股代码200开头
# print(gp_type_szsh('002340'))
#
def gp_type_szsh(gp):
if gp.find('60',0,3)==0:
gp_type='sh'
elif gp.find('688',0,4)==0:
gp_type='sh'
elif gp.find('900',0,4)==0:
gp_type='sh'
elif gp.find('00',0,3)==0:
gp_type='sz'
elif gp.find('300',0,4)==0:
gp_type='sz'
elif gp.find('200',0,4)==0:
gp_type='sz'
return gp_type