def query_stock_industry(code='', date=''):
rs = bs.query_stock_industry(code, date)
while BaoStock.retried_num < BaoStock.RETRY_MAX_NUM and rs.error_code != '0':
sleep(BaoStock.RETRY_DELAY_S)
rs = bs.query_stock_industry(code, date)
BaoStock.retried_num += 1
assert('0' == rs.error_code)
BaoStock.retried_num = 0
return BaoStock.rs_to_list(rs)
def query_stock_industry(code='', date=''):
rs = bs.query_stock_industry(code, date)
while Stock.retried_num < Stock.RETRY_MAX_NUM and rs.error_code != '0':
sleep(Stock.RETRY_DELAY_S)
rs = bs.query_stock_industry(code, date)
Stock.retried_num += 1
if '0' == rs.error_code:
Stock.retried_num = 0
return Stock.rs_to_list(rs)
def query_stock_industry(code=None, date=None):
"""
行业分类
方法说明：通过API接口获取行业分类信息，更新频率：每周一更新。
返回类型：pandas的DataFrame类型。
参数含义：
code：A股股票代码，sh或sz.+6位数字代码，或者指数代码，如：sh.601398。sh：上海；sz：深圳。可以为空；
date：查询日期，格式XXXX-XX-XX，为空时默认最新日期。
"""
lg = bs.login()
if lg.error_code != '0':
logger.error('login respond error_msg:' + lg.error_msg)
rs = bs.query_stock_industry(code, date)
if rs.error_code != '0':
logger.error('query_stock_industry respond error_msg:' +
rs.error_msg)
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
bs.logout()
return result
def stock_industry(self):
'''
Return a DataFrame containing all stock industry data
戳下面这个链接
http://baostock.com/baostock/index.php/行业分类
'''
return get_data(bs.query_stock_industry())
def get(self, request, *args, **kwargs):
queryset = SharesCategory.objects.all()
if len(queryset) <= 0:
lg = bs.login()
rs = bs.query_stock_industry()
# print(rs)
data_list = []
while (rs.error_code == '0') & rs.next():
data_list.append(rs.get_row_data())
result = pd.DataFrame(data_list, columns=rs.fields)
result1 = pd.DataFrame(result['industry'])
result1['count'] = pd.Series(np.random.randint(1, 2, 4061))
result1['industryClassification'] = result[
'industryClassification']
result1 = result1.groupby('industry').sum()
shares_cate_list = []
for index, row in result1.iterrows():
cate_obj = SharesCategory(industry=index,
industryClassification='申万一级行业',
count=row['count'])
cate_obj.save()
shares_cate_list.append({
'industry': index,
'industryClassification': '申万一级行业',
'count': float(row['count'])
})
bs.logout()
return JsonResponse(shares_cate_list, safe=False)
else:
return JsonResponse([], safe=False)
def hangye():
# 登陆系统
lg = bs.login()
# 显示登陆返回信息
print('login respond error_code:' + lg.error_code)
print('login respond error_msg:' + lg.error_msg)
# 获取行业分类数据
rs = bs.query_stock_industry()
# rs = bs.query_stock_basic(code_name="浦发银行")
print('query_stock_industry error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
# 结果集输出到csv文件
result.to_csv("C:\\gupiao\\行业分类.csv", encoding="gbk", index=False)
print(result)
# 登出系统
bs.logout()
def create_stock_industry():
"""
BS-创建行业分类
"""
# 登陆系统
lg = bs.login()
# 显示登陆返回信息
print('login respond error_code:' + lg.error_code)
print('login respond error_msg:' + lg.error_msg)
# 获取行业分类数据
rs = bs.query_stock_industry()
print('query_stock_industry error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
dtype = {
'updateDate': String(10),
'code': String(9),
'code_name': String(10),
'industry': String(4),
'industryClassification': String(6)
}
result.to_sql('odl_bs_stock_industry', engine, schema=CQ_Config.DB_SCHEMA, if_exists='replace', index=False, dtype=dtype)
# 登出系统
bs.logout()
def bao_query_stock_industry() -> pd.DataFrame:
"""
获取行业分类信息
:return:
"""
df = bao.query_stock_industry().get_data()
df['code'] = df['code'].apply(lambda x: ts_code(x))
df.set_index(keys='code', drop=False, inplace=True)
return df
def get_stock_industry():
rs = BS.query_stock_industry()
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
result = PD.DataFrame(industry_list, columns=rs.fields)
print(result)
return result
def queryStockIndustry(code,date=''):
rs = bs.query_stock_industry(code=code,date=date)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
return result
def list_stocks():
bs.login()
global g_codes
rs = bs.query_stock_industry()
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
df_codes = pd.DataFrame(industry_list, columns=rs.fields)
df_codes.to_csv('./codes.csv', encoding='utf-8', index=False)
bs.logout()
return df_codes
def get_hangye_info(self):
# 获取行业分类数据
rs = bs.query_stock_industry()
print('query_stock_industry error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result2 = pd.DataFrame(industry_list, columns=rs.fields)
return result2
def query_stock_industry(self,code = None, date = None):
'''
code：A股股票代码，sh或sz.+6位数字代码，或者指数代码，如：sh.601398。sh：上海；sz：深圳。可以为空；
date：查询日期，格式XXXX-XX-XX，为空时默认最新日期。
'''
rs = bs.query_stock_industry(code = code, date = date)
self.log('query_stock_industry respond error_msg:', rs)
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
return result
def updateIndustry(conn, date):
data_df = pd.DataFrame()
codes = comm.getAllCode(conn)
for item in tqdm(codes, desc='拉取行业分类'):
code = item[0]
name = item[1]
rs = bs.query_stock_industry(code)
data_df = data_df.append(rs.get_data())
pbar = tqdm(total=data_df.shape[0], desc='行业分类入库中')
for i, row in data_df.iterrows():
k = comm.list2lower(row.index.tolist())
v = row.values.tolist()
comm.upsertRow(conn, 'stock_industry', k, v, 'code')
pbar.update(1)
def bs_save_stock_industry():
'''
获取行业信息
:return:
'''
bs.login()
rs = bs.query_stock_industry()
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
engine = create_engine(
'mysql+pymysql://root:root@localhost:3306/stock_quant?charset=utf8')
result = pd.DataFrame(industry_list, columns=rs.fields)
result.to_sql('bs_stock_industry', engine, index=True)
bs.logout()
def download_industry(date):
rs = bs.query_stock_industry('', date)
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
connect = pymssql.connect('localhost', 'sa', '12345', 'astock') # 建立连接
cursor = connect.cursor() # 创建一个游标对象,python里的sql语句都要通过cursor来执行
for industry in industry_list:
sql = 'if not exists (select *from all_stocks where code =\'%s\') insert into all_stocks(updateDate,code,code_name,industry,industryClassification) values (\'%s\',\'%s\',\'%s\',\'%s\',\'%s\') ' % (
industry[1], industry[0], industry[1], industry[2], industry[3],
industry[4])
# print(sql)
cursor.execute(sql)
connect.commit()
cursor.close()
connect.close()
def get_basic_code_info(self, kechuang=False):
rs = bs.query_stock_basic()
print('query_stock_basic respond error_msg:' + rs.error_msg)
# 打印结果集
data_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
data_list.append(rs.get_row_data())
result = pd.DataFrame(data_list, columns=rs.fields)
# 结果集输出到csv文件
# result.to_csv("D:/stock_basic.csv", encoding="gbk", index=False)
result['only_code'] = result['code'].str.lower().str.split('.').str[1]
result_stock = result[result['type'] == '1']
if kechuang:
pass
else:
result_stock = result_stock[(result_stock['only_code'].str[:2] !=
'30')]
# result_stock[('st' not in result_stock['code_name'].str.lower() )]
# result_stock['code_name']=result_stock['code_name'].str.lower()
# result_stock['st股'] = result_stock['code_name'].apply(lambda x: True if 'st' in str(x) else False )
# print(result_stock[result_stock['st股'] == False])
# result[((result['code'].str[:2] == 'sh')&(result['only_code'].str[:2] == '60'))|((result['code'].str[:2] == 'sz')&(result['only_code'].str[:2] == '00'))])
result_stock.reset_index(drop=True, inplace=True)
# 获取行业分类数据
rs = bs.query_stock_industry()
print('query_stock_industry error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result2 = pd.DataFrame(industry_list, columns=rs.fields)
result = pd.merge(
result_stock,
result2[['code', 'industry', 'industryClassification']],
how='left',
on=['code'])
# print(result.keys())
# exit()
return result
def get_stock_industry(code=None, date=None):
# 获取行业分类数据
rs = bs.query_stock_industry(code=code, date=date)
# rs = bs.query_stock_basic(code_name="浦发银行")
if rs.error_code != '0':
print('query_stock_industry respond error_code::' + rs.error_msg)
login()
return get_stock_industry(code, date)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
# 结果集输出到csv文件
return result
def dispatch_request(self):
post_data = request.get_json()
code = post_data.get('code', '')
date = post_data.get('date', '')
attr_fields = post_data.get('attr_fields', None)
rs = bs.query_stock_industry(code=code, date=date)
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
fields = ['updateDate', 'code', 'code_name', 'industry', 'industryClassification']
data = jsonWrapper(industry_list, fields)
result = {
'code': 200 if rs.error_code == '0' else rs.error_code,
'data': list(map(lambda x: { attr: x.get(attr, '') for attr in attr_fields }, data)) if attr_fields else data,
'msg': rs.error_msg
}
self.logout()
return jsonify(result)
def get_hangye():
"""
获取行业信息，返回字典 {code: bkname, ...}
:return:
"""
rs = bs.query_stock_industry()
data_list = []
while (rs.error_code == '0') & rs.next():
d = {}
r = rs.get_row_data()
for k_i in range(len(r)):
d[rs.fields[k_i]] = r[k_i]
w = {}
w['code'] = d['code'][3:]
w['name'] = d['code_name']
w['hangye'] = d['industry']
data_list.append(w)
return data_list
def download_all_k_line_data(date):
print(date)
connect = pymssql.connect('localhost', 'sa', '12345', 'astock')
cursor = connect.cursor()
delsql = 'delete day_k_line where date= \'%s\'' % (date)
print(delsql)
cursor.execute(delsql)
connect.commit()
cursor.close()
connect.close()
rs = bs.query_stock_industry('', date)
industry_list = []
while (rs.error_code == '0') & rs.next():
industry_list.append(rs.get_row_data())
# #需要借助行业代码循环
for industry in industry_list:
download_k_line_data(industry[1], date)
def save_stock_classify_info(self):
rs = bs.query_stock_industry()
print('query_history_k_data_plus respond error_code:' + rs.error_code)
print('query_history_k_data_plus respond error_msg:' + rs.error_msg)
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
i = 0
with open('stock_list_simple.txt', 'w') as fd:
for _ in industry_list:
fd.write(_[1] + '\n')
i = i + 1
print("Write done!!", i)
classify_result = self.make_classify_info(industry_list)
result = pd.DataFrame(industry_list, columns=rs.fields)
result.to_csv("stock_industry.csv", index=False)
return classify_result
def inportIndustryData(name='tb_today_industry', code=None, date=None):
configger.init()
# 显示登陆返回信息
# 结果集输出到csv文件
con = configger.engine
try:
sql = configger.lastOperateTimeSql.format(name)
lastTime = pd.read_sql(sql=sql, con=con).iloc[0, 0]
print(lastTime)
except:
print('没有操作数据')
if (lastTime == None):
lastTime = pd.to_datetime('1990-1-1 00:00:00')
if (needUpdate(lastTime, datetime.now(), True) == True):
lg = bs.login()
# 获取行业分类数据
rs = bs.query_stock_industry()
# rs = bs.query_stock_basic(code_name="浦发银行")
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
result['date'] = datetime.now().date()
result.to_sql(name=name, con=con, if_exists='append', index=False)
bs.logout()
operation = pd.DataFrame()
operation.loc[0, 'name'] = name
operation.loc[0, 'updateTime'] = datetime.now().date()
operation.to_sql(name='tb_operation_time',
con=con,
if_exists='append',
index=False)
print('industry_data_import_ok')
else:
print('无需插入')
def get_stock_industry(stock_code):
# 登陆系统
lg = bs.login()
# 显示登陆返回信息
print('login respond error_code:' + lg.error_code)
print('login respond error_msg:' + lg.error_msg)
# 获取证券基本资料
rs = bs.query_stock_industry(code=stock_code)
# rs = bs.query_stock_basic(code_name="浦发银行") # 支持模糊查询
print('query_stock_industry respond error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
data_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
data_list.append(rs.get_row_data())
result = pd.DataFrame(data_list, columns=rs.fields)
bs.logout()
return result
def get_all_stock_industries():
lg = bs.login()
print('login respond error_code:' + lg.error_code)
print('login respond error_msg:' + lg.error_msg)
# 获取行业分类数据
rs = bs.query_stock_industry(date='2020-08-01')
# rs = bs.query_stock_basic(code_name="浦发银行")
print('query_stock_industry error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
# 结果集输出到csv文件
result.to_csv(ConfigUtils.get_stock("STOCK_INDUSTRY"), index=False)
print(result)
# 登出系统
bs.logout()
def UpdateIndustryData(code='', date=''):
# 登陆系统
lg = bs.login()
# 显示登陆返回信息
# 获取行业分类数据
rs = bs.query_stock_industry(code, date)
# rs = bs.query_stock_basic(code_name="浦发银行")
needUpdate = tableNeedUpdate('tb_industry_information')
print(needUpdate)
if (needUpdate == True):
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
# 结果集输出到csv文件
# result.to_csv("D:/stock_industry.csv", encoding="gbk", index=False)
result.rename(columns={
'code_name': '名称',
'industry': '行业',
'industryClassification': '所属行业类别'
},
inplace=True)
# 登出系统
bs.logout()
print(result)
try:
result.to_sql(name='tb_industry_information',
con=configger.engine,
if_exists='append',
index=False)
saveOperationTime('tb_industry_information')
except:
print('industry 更新失败')
return result
return pd.DataFrame()
def get(self, request, *args, **kwargs):
queryset = Shares.objects.all()
if len(queryset) <= 0:
lg = bs.login()
rs = bs.query_stock_industry()
data_list = []
shares_list = []
while (rs.error_code == '0') and rs.next():
data_list.append(rs.get_row_data())
for index, item in enumerate(data_list):
shares_obj = Shares(code=item[1],
code_name=item[2],
industry=item[3])
shares_obj.save()
shares_list.append(({
'code': item[1],
'code_name': item[2],
'industry': item[3]
}))
bs.logout()
return JsonResponse(shares_list, safe=False)
else:
return JsonResponse([], safe=False)
def basic_mian():
info = request.values.get("data")
stocknumber = tostockcode(info)
stock_code = stocknumber[0:2] + '.' + stocknumber[2:]
startdate = time.strftime('%Y-%m-%d',
time.localtime(time.time() -
20 * 24 * 60 * 60)) #获取近20天的那些率
enddate = time.strftime('%Y-%m-%d', time.localtime(time.time()))
# 登陆系统
lg = bs.login()
rs2 = bs.query_history_k_data_plus(
stock_code,
"date,code,close,peTTM,pbMRQ,psTTM,pcfNcfTTM",
start_date=startdate,
end_date=enddate,
frequency="d",
adjustflag="3")
list2 = []
while (rs2.error_code == '0') & rs2.next():
# 获取一条记录，将记录合并在一起
list2.append(rs2.get_row_data())
result2 = pd.DataFrame(list2, columns=rs2.fields)
peTTM = result2[['peTTM']] #每天的滚动市盈率
psTTM = result2[['psTTM']] # 每天的滚动市销率
pcfNcfTTM = result2[['pcfNcfTTM']] # 每天的滚动市现率
pbMRQ = result2[['pbMRQ']] #每天的滚动市净率
###获取行业分类数据
rs3 = bs.query_stock_industry(code=stock_code)
list3 = []
while (rs3.error_code == '0') & rs3.next():
# 获取一条记录，将记录合并在一起
list3.append(rs3.get_row_data())
result3 = pd.DataFrame(list3, columns=rs3.fields)
hangye = result3
####添加
#industryinfo=getindustry(str(np.array(hangye)[0,3]))
stockinfo = getstock(stocknumber)
# 登出系统
bs.logout()
dic = {
'peTTM': [],
'psTTM': [],
'pcfNcfTTM': [],
'pbMRQ': [],
'hangye': [],
'stockinfo': {}
}
dic['peTTM'] = np.array(peTTM).reshape(1, len(np.array(peTTM))).tolist()[0]
dic['peTTM'] = list(
map(lambda x: eval('%.4f' % x),
map(eval, dic['peTTM']))) #list(map(eval, dic['peTTM']))
dic['psTTM'] = np.array(psTTM).reshape(1, len(np.array(psTTM))).tolist()[0]
dic['psTTM'] = list(
map(lambda x: eval('%.4f' % x),
map(eval, dic['psTTM']))) #list(map(eval, dic['psTTM']))
dic['pcfNcfTTM'] = np.array(pcfNcfTTM).reshape(1, len(
np.array(pcfNcfTTM))).tolist()[0]
dic['pcfNcfTTM'] = list(
map(lambda x: eval('%.4f' % x),
map(eval, dic['pcfNcfTTM']))) #list(map(eval, dic['pcfNcfTTM']))
dic['pbMRQ'] = np.array(pbMRQ).reshape(1, len(np.array(pbMRQ))).tolist()[0]
dic['pbMRQ'] = list(
map(lambda x: eval('%.4f' % x),
map(eval, dic['pbMRQ']))) #list(map(eval, dic['pbMRQ']))
dic['hangye'] = np.array(hangye).tolist()[0]
dic['stockinfo'] = np.array(stockinfo).tolist()
dic['stockinfo']['price'] = float(dic['stockinfo']['price'])
dic['stockinfo']['changePercent'] = float(
dic['stockinfo']['changePercent'])
dic['stockinfo']['volume'] = float(dic['stockinfo']['volume'])
dic['stockinfo']['turnover'] = float(dic['stockinfo']['turnover'])
return json.dumps(dic, ensure_ascii=False)
# 王琰的python编写
# 开发时间:2021/5/15 16:34
import baostock as bs
import pandas as pd
# 登陆系统
lg = bs.login()
# 显示登陆返回信息
print('login respond error_code:' + lg.error_code)
print('login respond error_msg:' + lg.error_msg)
# 获取行业分类数据
rs = bs.query_stock_industry()
# rs = bs.query_stock_basic(code_name="浦发银行")
print('query_stock_industry error_code:' + rs.error_code)
print('query_stock_industry respond error_msg:' + rs.error_msg)
# 打印结果集
industry_list = []
while (rs.error_code == '0') & rs.next():
# 获取一条记录，将记录合并在一起
industry_list.append(rs.get_row_data())
result = pd.DataFrame(industry_list, columns=rs.fields)
# 结果集输出到csv文件
result.to_csv("D:/stock_industry.csv", encoding="gbk", index=False)
print(result)
# 登出系统
bs.logout()
def get_stock_industry(self, code):
result = baostock.query_stock_industry(code).get_row_data()
industry = result[3]
return industry
