def get_company_info():
api = TdxHq_API()
if api.connect('119.147.212.81', 7709):
print(api.get_company_info_category(TDXParams.MARKET_SZ,
'000001')) #查询公司信息目录,参数：市场代码， 股票代码
api.get_company_info_content(0, '000001',
os.getcwd() + "/tdx_file/" + '000001.txt',
0, 100) #读取公司信息详情，参数文件路径不知干什么
print(api.get_finance_info(0, '000001')) #读取财务信息
api.disconnect()
class TdxData:
def __init__(self):
self.api = TdxHq_API(heartbeat=True)
self.dbUtil = DBUtil.getInstance()
def get_security_quotes(self, code, type):
return self.api.get_security_quotes([(type, code)])
# 支持板块及个股
def days(self, code, type, bk=False, all=False, day=5):
category = int(config.getByKey('TDX_CATEGORY'))
try:
with self.api.connect(TDX_IP, TDX_PORT):
data = []
if all:
if bk:
for i in range(10):
data += self.api.get_index_bars(
category, type, code, (9 - i) * 800, 800)
else:
for i in range(10):
data += self.api.get_security_bars(
category, type, code, (9 - i) * 800, 800)
if len(data) > 0:
df = self.api.to_df(data).drop([
'amount', 'year', 'month', 'day', 'hour', 'minute'
],
axis=1)
df['trade_date'] = df['datetime'].apply(
lambda x: x[0:10].replace('-', ''))
df = df.drop(['datetime'], axis=1)
df = df.sort_values(by=['trade_date'],
axis=0,
ascending=False)
return df
else:
return self.api.to_df(data)
else:
if bk:
data = self.api.get_index_bars(category, type, code, 0,
day) # 返回DataFrame
else:
data = self.api.get_security_bars(
category, type, code, 0, day)
if len(data) > 0:
df = self.api.to_df(data).drop([
'amount', 'year', 'month', 'day', 'hour', 'minute'
],
axis=1)
df['trade_date'] = df['datetime'].apply(
lambda x: x[0:10].replace('-', ''))
df = df.drop(['datetime'], axis=1)
df = df.sort_values(by=['trade_date'],
axis=0,
ascending=False)
return df
else:
return self.api.to_df(data)
except Exception as e:
logging.info("暂不支持类型,代码：%s:%s" % (code, e))
return self.api.to_df([])
# F10 查询公司信息目录
def get_company_info_category(self, code, type):
with self.api.connect(TDX_IP, TDX_PORT):
df = pd.DataFrame(self.api.get_company_info_category(type, code))
df['txt'] = None
return df
return []
def get_company_info_content(self, code, type, df):
with self.api.connect(TDX_IP, TDX_PORT):
return self.api.get_company_info_content(type, code,
df['filename'].values[0],
df['start'].values[0],
df['length'].values[0])
return ""
# 查询财务数据
def get_finance_info(self, code, type):
with self.api.connect(TDX_IP, TDX_PORT):
return self.api.get_finance_info(type, code)
return ''
# 每年更新一次，板块个股关系
def updateBk(self):
with self.api.connect(TDX_IP, TDX_PORT):
"""
# 获取股票所属板块信息
# 板块相关参数
BLOCK_SZ = "block_zs.dat"
BLOCK_FG = "block_fg.dat"
BLOCK_GN = "block_gn.dat"
BLOCK_DEFAULT = "block.dat"
"""
bk_zs = self.api.to_df(
self.api.get_and_parse_block_info("block_zs.dat")) #指数板块
bk_fg = self.api.to_df(
self.api.get_and_parse_block_info("block_fg.dat")) #风格板块
bk_gn = self.api.to_df(
self.api.get_and_parse_block_info("block_gn.dat")) #概念板块
bk_default = self.api.to_df(
self.api.get_and_parse_block_info("block.dat")) # 默认
self.dbUtil.to_sql(bk_gn,
'stock_bk_gn',
if_exists='replace',
index=False,
dtype=STOCK_BK_DTYPE)
self.dbUtil.to_sql(bk_fg,
'stock_bk_fg',
if_exists='replace',
index=False,
dtype=STOCK_BK_DTYPE)
self.dbUtil.to_sql(bk_zs,
'stock_bk_zs',
if_exists='replace',
index=False,
dtype=STOCK_BK_DTYPE)
self.dbUtil.to_sql(bk_default,
'stock_bk_default',
if_exists='replace',
index=False,
dtype=STOCK_BK_DTYPE)
# 获取股票列表
tmp1 = self.api.to_df(self.api.get_security_list(0, 0)) # 深圳
tmp1['type'] = 0
tmp2 = self.api.to_df(self.api.get_security_list(1, 0)) # 上海
tmp2['type'] = 1
tmp = tmp1.append(tmp2)
self.dbUtil.to_sql(tmp,
'stock_bk',
if_exists='replace',
index=False,
dtype=STOCK_BK)
def updateGD(self, code, type):
url = 'http://emweb.securities.eastmoney.com/PC_HSF10/ShareholderResearch/ShareholderResearchAjax?code=%s%s' % (
type.lower(), code)
html = urllib.request.urlopen(url).read()
# 将字符串转换成字典
data = json.loads(html.decode('utf-8'))
# gdrs 股东人数,sdgd 十大股东 ，sdltgd 十大流通股东
df_gdrs = pd.DataFrame(data['gdrs'])
df_gdrs['code'] = code
try:
db_df_gdrs = self.dbUtil.read_sql(
"select * from stock_gdrs where code ='%s'" % code)
# 数据合并
df_gdrs = df_gdrs.append(db_df_gdrs).drop_duplicates(
subset=['code', 'rq', 'gdmc'], keep='last')
except Exception as e:
pass
self.dbUtil.to_sql(df_gdrs,
'stock_gdrs',
if_exists='append',
index=False,
dtype=STOCK_GDRS_DTYPE)
sdgd = []
for i in range(len(data['sdgd'])):
sdgd += data['sdgd'][i]['sdgd']
df_sdgd = pd.DataFrame(sdgd)
df_sdgd['code'] = code
try:
db_df_sdgd = self.dbUtil.read_sql(
"select * from stock_sdgd where code ='%s'" % code)
df_sdgd = df_sdgd.append(db_df_sdgd).drop_duplicates(
subset=['code', 'rq', 'gdmc'], keep='last')
except Exception as e:
pass
self.dbUtil.to_sql(df_sdgd,
'stock_sdgd',
if_exists='append',
index=False,
dtype=STOCK_SDGD_DTYPE)
sdltgd = []
for i in range(len(data['sdltgd'])):
sdltgd += data['sdltgd'][i]['sdltgd']
df_sdltgd = pd.DataFrame(sdltgd)
df_sdltgd['code'] = code
# 获取后与数据库中的数据进行merge,首次表不存在，会抛异常
try:
db_df_sdltgd = self.dbUtil.read_sql(
"select * from stock_sdltgd where code ='%s'" % code)
df_sdltgd = df_sdltgd.append(db_df_sdltgd).drop_duplicates(
subset=['code', 'rq', 'gdmc'], keep='last')
except Exception as e:
pass
self.dbUtil.to_sql(df_sdltgd,
'stock_sdltgd',
if_exists='append',
index=False,
dtype=STOCK_SDGD_DTYPE)
# 没季度更新一次
def updateGDs(self):
codes = self.dbUtil.read_sql("select ts_code from stock_basic")
tmp = codes['ts_code'].str.split('.', expand=True)
for index, row in tmp.iterrows():
try:
self.updateGD(row[0], row[1])
logging.info('%s更新结束,当前索引%s' % (row[0], index))
except Exception as e:
logging.info('%s更新失败,当前索引%s' % (row[0], index))
# 分红
# 分红地址http://data.eastmoney.com/yjfp/201812.html
def updateFh(self, rq):
url = 'http://data.eastmoney.com/DataCenter_V3/yjfp/getlist.ashx?filter=(ReportingPeriod=^%s^)' % rq
html = requests.get(url)
# 将字符串转换成字典
data = json.loads(html.text)['data']
if len(data) == 0:
return 0
df = pd.DataFrame(data)
df['ReportingPeriod'] = df['ReportingPeriod'].apply(lambda x: x[0:10])
# 首次需要将df_fh制空，因为表还不存在
if self.dbUtil.is_exist("stock_fh"):
db_fh = self.dbUtil.read_sql(
"select * from stock_fh where ReportingPeriod = '%s'" %
df['ReportingPeriod'][0])
if db_fh.empty: # 不存在当前日期的分红信息，进行拼接
self.dbUtil.to_sql(df,
'stock_fh',
if_exists='append',
index=False)
return 1
else:
pass
else:
self.dbUtil.to_sql(df, 'stock_fh', if_exists='append', index=False)
return 1
# 更新历年分红
def updateFhYears(self):
now = int(time.strftime("%Y", time.localtime())) + 1
lastYear = int(self._getFhMaxYear())
for i in range(lastYear, now): #初始化时开启
type = self.updateFh('%s-06-30' % i)
logging.info('%s-06-30%s' % (i, '成功' if type == 1 else '失败'))
self.updateFh('%s-12-31' % i)
logging.info('%s-12-31%s' % (i, '成功' if type == 1 else '失败'))
def _getFhMaxYear(self):
if self.dbUtil.is_exist('stock_fh'):
try:
df = self.dbUtil.read_sql(
'select substr(max(t.ReportingPeriod ),0,5) year from stock_fh t'
)
return df['year'][0].values
except Exception as e:
pass
return 1991
@classmethod
def getInstance(cls):
if not hasattr(TdxData, "_instance"):
TdxData._instance = TdxData()
return TdxData._instance
class StdQuotes(object):
"""股票市场实时行情"""
bestip = ('47.103.48.45', 7709)
def __init__(self, **kwargs):
try:
default = settings.get('SERVER').get('HQ')[0]
self.bestip = config.get('BESTIP').get('HQ', default)
except ValueError:
self.config = None
self.client = TdxHq_API(**kwargs)
def traffic(self):
with self.client.connect(*self.bestip):
return self.client.get_traffic_stats()
def quotes(self, symbol=[]):
'''
获取实时日行情数据
:param symbol: 股票代码
:return: pd.dataFrame or None
'''
logger.debug(type(logger))
if type(symbol) is str:
symbol = [symbol]
with self.client.connect(*self.bestip):
symbol = get_stock_markets(symbol)
result = self.client.get_security_quotes(symbol)
return to_data(result)
def bars(self, symbol='000001', frequency='9', start='0', offset='100'):
'''
获取实时日K线数据
:param symbol: 股票代码
:param frequency: 数据类别
:param market: 证券市场
:param start: 开始位置
:param offset: 每次获取条数
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_security_bars(int(frequency), int(market),
str(symbol), int(start),
int(offset))
return to_data(result)
def stock_count(self, market=MARKET_SH):
'''
获取市场股票数量
:param market: 股票市场代码 sh 上海， sz 深圳
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
result = self.client.get_security_count(market=market)
return result
def stocks(self, market=MARKET_SH):
'''
获取股票列表
:param market:
:return:
'''
with self.client.connect(*self.bestip):
counts = self.client.get_security_count(market=market)
stocks = None
for start in tqdm(range(0, counts, 1000)):
result = self.client.get_security_list(market=market,
start=start)
stocks = pandas.concat(
[stocks, to_data(result)],
ignore_index=True) if start > 1 else to_data(result)
return stocks
def index_bars(self,
symbol='000001',
frequency='9',
start='0',
offset='100'):
'''
获取指数k线
:param symbol:
:param frequency:
:param start:
:param offset:
:return:
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_index_bars(frequency=frequency,
market=market,
code=symbol,
start=start,
count=offset)
return to_data(result)
def minute(self, symbol=''):
'''
获取实时分时数据
:param market: 证券市场
:param symbol: 股票代码
:return: pd.DataFrame
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_minute_time_data(market=market,
code=symbol)
return to_data(result)
def minutes(self, symbol='', date='20191023'):
'''
分时历史数据
:param market:
:param symbol:
:param date:
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_history_minute_time_data(market=market,
code=symbol,
date=date)
return to_data(result)
def transaction(self, symbol='', start=0, offset=10):
'''
查询分笔成交
:param market: 市场代码
:param symbol: 股票代码
:param start: 起始位置
:param offset: 请求数量
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_transaction_data(int(market), symbol,
int(start), int(offset))
return to_data(result)
def transactions(self, symbol='', start=0, offset=10, date='20170209'):
'''
查询历史分笔成交
参数：市场代码， 股票代码，起始位置，日期 数量 如： 0,000001,0,10,20170209
:param symbol: 股票代码
:param start: 起始位置
:param offset: 数量
:param date: 日期
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol, string=False)
result = self.client.get_history_transaction_data(market=market,
code=symbol,
start=start,
count=offset,
date=date)
return to_data(result)
def F10C(self, symbol=''):
'''
查询公司信息目录
:param market: 市场代码
:param symbol: 股票代码
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_company_info_category(int(market), symbol)
return result
def F10(self, symbol='', name=''):
'''
读取公司信息详情
:param name: 公司 F10 标题
:param symbol: 股票代码
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
result = {}
market = get_stock_market(symbol, string=False)
frequency = self.client.get_company_info_category(
int(market), symbol)
if name:
for x in frequency:
if x['name'] == name:
return self.client.get_company_info_content(
market=market,
code=symbol,
filename=x['filename'],
start=x['start'],
length=x['length'])
for x in frequency:
result[x['name']] = self.client.get_company_info_content(
market=market,
code=symbol,
filename=x['filename'],
start=x['start'],
length=x['length'])
else:
pass
return result
def xdxr(self, symbol=''):
'''
读取除权除息信息
:param market: 市场代码
:param symbol: 股票代码
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_xdxr_info(int(market), symbol)
return to_data(result)
def finance(self, symbol='000001'):
'''
读取财务信息
:param symbol:
:return:
'''
with self.client.connect(*self.bestip):
market = get_stock_market(symbol)
result = self.client.get_finance_info(market=market, code=symbol)
return to_data(result)
def k(self, symbol='', begin=None, end=None):
'''
读取k线信息
:param symbol:
:param begin: 开始日期
:param end: 截止日期
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
result = self.client.get_k_data(symbol, begin, end)
return to_data(result)
def index(self,
symbol='000001',
market=MARKET_SH,
frequency='9',
start=1,
offset=2):
'''
获取指数k线
K线种类:
- 0 5分钟K线
- 1 15分钟K线
- 2 30分钟K线
- 3 1小时K线
- 4 日K线
- 5 周K线
- 6 月K线
- 7 1分钟
- 8 1分钟K线
- 9 日K线
- 10 季K线
- 11 年K线
:param symbol: 股票代码
:param frequency: 数据类别
:param market: 证券市场
:param start: 开始位置
:param offset: 每次获取条数
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
result = self.client.get_index_bars(int(frequency), int(market),
str(symbol), int(start),
int(offset))
return to_data(result)
def block(self, tofile="block.dat"):
'''
获取证券板块信息
:param tofile:
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
result = self.client.get_and_parse_block_info(tofile)
return to_data(result)
def test_all_functions(multithread, heartbeat, auto_retry, raise_exception):
api = TdxHq_API(multithread=multithread, heartbeat=heartbeat,
auto_retry=auto_retry, raise_exception=raise_exception)
with api.connect(time_out=30):
log.info("获取股票行情")
stocks = api.get_security_quotes([(0, "000001"), (1, "600300")])
assert stocks is not None
assert type(stocks) is list
# 方法2
stocks = api.get_security_quotes(0, "000001")
assert stocks is not None
assert type(stocks) is list
# 方法3
stocks = api.get_security_quotes((0, "000001"))
assert stocks is not None
assert type(stocks) is list
log.info("获取k线")
data = api.get_security_bars(9, 0, '000001', 4, 3)
assert data is not None
assert type(data) is list
assert len(data) == 3
log.info("获取 深市 股票数量")
assert api.get_security_count(0) > 0
log.info("获取股票列表")
stocks = api.get_security_list(1, 0)
assert stocks is not None
assert type(stocks) is list
assert len(stocks) > 0
log.info("获取指数k线")
data = api.get_index_bars(9, 1, '000001', 1, 2)
assert data is not None
assert type(data) is list
assert len(data) == 2
log.info("查询分时行情")
data = api.get_minute_time_data(TDXParams.MARKET_SH, '600300')
assert data is not None
log.info("查询历史分时行情")
data = api.get_history_minute_time_data(
TDXParams.MARKET_SH, '600300', 20161209)
assert data is not None
assert type(data) is list
assert len(data) > 0
log.info("查询分时成交")
data = api.get_transaction_data(TDXParams.MARKET_SZ, '000001', 0, 30)
assert data is not None
assert type(data) is list
log.info("查询历史分时成交")
data = api.get_history_transaction_data(
TDXParams.MARKET_SZ, '000001', 0, 10, 20170209)
assert data is not None
assert type(data) is list
assert len(data) == 10
log.info("查询公司信息目录")
data = api.get_company_info_category(TDXParams.MARKET_SZ, '000001')
assert data is not None
assert type(data) is list
assert len(data) > 0
start = data[0]['start']
length = data[0]['length']
log.info("读取公司信息-最新提示")
data = api.get_company_info_content(
0, '000001', '000001.txt', start, length)
assert data is not None
assert len(data) > 0
log.info("读取除权除息信息")
data = api.get_xdxr_info(1, '600300')
assert data is not None
assert type(data) is list
assert len(data) > 0
log.info("读取财务信息")
data = api.get_finance_info(0, '000001')
assert data is not None
assert type(data) is OrderedDict
assert len(data) > 0
log.info("日线级别k线获取函数")
data = api.get_k_data('000001', '2017-07-01', '2017-07-10')
assert type(data) is pd.DataFrame
assert len(data) == 6
log.info("获取板块信息")
data = api.get_and_parse_block_info(TDXParams.BLOCK_FG)
assert data is not None
assert type(data) is list
assert len(data) > 0
print("获取指数k线")
data = api.get_index_bars(9, 1, '000001', 1, 2)
print(data)
print("查询分时行情")
data = api.get_minute_time_data(1, '600300')
print(data)
print("查询历史分时行情")
data = api.get_history_minute_time_data(1, '600300', 20161209)
print(data)
print("查询分时成交")
data = api.get_transaction_data(1, '000002', 0, 30)
print(data)
print("查询历史分时成交")
data = api.get_history_transaction_data(2, '600302', 0, 10, 20170209)
print(data)
print("查询公司信息目录")
data = api.get_company_info_category(1, '000003')
print(data)
print("读取公司信息-最新提示")
data = api.get_company_info_content(0, '000001', '000001.txt', 0, 10)
print(data)
print("读取除权除息信息")
data = api.get_xdxr_info(1, '600300')
print(data)
print("读取财务信息")
data = api.get_finance_info(0, '000001')
print(data)
print("日线级别k线获取函数")
data = api.get_k_data('000001', '2005-07-01', '2017-07-10')
print(data)
class StdQuotes(object):
"""股票市场实时行情"""
# __slots__ =
def __init__(self, **kwargs):
self.config = None
try:
self.config = json.loads(
os.path.join(os.environ['HOME'], '.mootdx/config.josn'))
except Exception as e:
self.config = None
self.client = TdxHq_API(**kwargs)
if not self.config:
self.bestip = os.environ.setdefault("MOOTDX_SERVER",
'202.108.253.131:7709')
self.bestip = self.bestip.split(':')
self.bestip[1] = int(self.bestip[1])
else:
self.bestip = self.config.get('SERVER')
# K线
def bars(self, symbol='000001', category='9', start='0', offset='100'):
'''
获取实时日K线数据
:param symbol: 股票代码
:param category: 数据类别
:param market: 证券市场
:param start: 开始位置
:param offset: 每次获取条数
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_security_bars(int(category), int(market),
str(symbol), int(start),
int(offset))
return self.client.to_df(data)
# 分时数据
def minute(self, symbol=''):
'''
获取实时分时数据
:param market: 证券市场
:param symbol: 股票代码
:return: pd.DataFrame
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_minute_time_data(int(market), symbol)
return self.client.to_df(data)
# 分时历史数据
def minute_his(self, symbol='', datetime='20161209'):
'''
分时历史数据
:param market:
:param symbol:
:param datetime:
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_history_minute_time_data(
int(market), symbol, datetime)
return self.client.to_df(data)
def trans(self, symbol='', start=0, offset=10):
'''
查询分笔成交
:param market: 市场代码
:param symbol: 股票代码
:param start: 起始位置
:param offset: 请求数量
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_transaction_data(int(market), symbol,
int(start), int(market))
return self.client.to_df(data)
def trans_his(self, symbol='', start=0, offset=10, date=''):
'''
查询历史分笔成交
:param market: 市场代码
:param symbol: 股票代码
:param start: 起始位置
:param offset: 数量
:param date: 日期
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_history_transaction_data(
int(market), symbol, int(start), int(offset), date)
return self.client.to_df(data)
def company(self, symbol='', detail='category', *args, **kwargs):
'''
企业信息获取
:param symbol:
:param detail:
:param args:
:param kwargs:
:return:
'''
pass
def company_category(self, symbol=''):
'''
查询公司信息目录
:param market: 市场代码
:param symbol: 股票代码
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_company_info_category(int(market), symbol)
return self.client.to_df(data)
def company_content(self, symbol='', file='', start=0, offset=10):
'''
读取公司信息详情
:param market: 市场代码
:param symbol: 股票代码
:param file: 文件名
:param start: 起始位置
:param offset: 数量
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_company_info_content(
int(market), symbol, file, int(start), int(offset))
return self.client.to_df(data)
def xdxr(self, symbol=''):
'''
读取除权除息信息
:param market: 市场代码
:param symbol: 股票代码
:return: pd.dataFrame or None
'''
market = get_stock_market(symbol)
with self.client.connect(*self.bestip):
data = self.client.get_xdxr_info(int(market), symbol)
return self.client.to_df(data)
def k(self, symbol='', begin=None, end=None):
'''
读取k线信息
:param symbol:
:param begin:
:param end:
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
data = self.client.get_k_data(symbol, begin, end)
return data
def index(self,
symbol='000001',
market='sh',
category='9',
start='0',
offset='100'):
'''
获取指数k线
K线种类:
- 0 5分钟K线
- 1 15分钟K线
- 2 30分钟K线
- 3 1小时K线
- 4 日K线
- 5 周K线
- 6 月K线
- 7 1分钟
- 8 1分钟K线
- 9 日K线
- 10 季K线
- 11 年K线
:param symbol: 股票代码
:param category: 数据类别
:param market: 证券市场
:param start: 开始位置
:param offset: 每次获取条数
:return: pd.dataFrame or None
'''
market = 1 if market == 'sh' else 0
with self.client.connect(*self.bestip):
data = self.client.get_index_bars(int(category), int(market),
str(symbol), int(start),
int(offset))
return self.client.to_df(data)
def block(self, tofile="block.dat"):
'''
获取证券板块信息
:param tofile:
:return: pd.dataFrame or None
'''
with self.client.connect(*self.bestip):
data = self.client.get_and_parse_block_info(tofile)
return self.client.to_df(data)
def batch(self, method='', offset=100, *args, **kwargs):
'''
批量下载相关数据
:param method:
:param offset:
:return:
'''
pass
class TdxHelper:
ip_list = [{
'ip': '119.147.212.81',
'port': 7709
}, {
'ip': '60.12.136.250',
'port': 7709
}]
def __init__(self):
#连接tdx接口
self.api = TdxHq_API()
if not self.api.connect('60.12.136.250', 7709):
print("服务器连接失败！")
# pandas数据显示设置
pd.set_option('display.max_columns', None) # 显示所有列
#pd.set_option('display.max_rows', None) # 显示所有行
# mysql对象
self.mysql = mysqlHelper(config.mysql_host, config.mysql_username,
bluedothe.mysql_password, config.mysql_dbname)
# pandas的mysql对象
self.engine = create_engine(
f'mysql+pymysql://{config.mysql_username}:{bluedothe.mysql_password}@{config.mysql_host}/{config.mysql_dbname}?charset=utf8'
)
#断开tdx接口连接
def close_connect(self):
self.api.disconnect()
#获取k线，最后一个参数day,说明需要获取的数量，本接口只获取从最近交易日往前的数据
#输入参数：五个参数分别为：category（k线),市场代码(0:深圳，1:上海),股票代码,开始位置(从最近交易日向前取，0表示最近交易日),返回的记录条数
#K线种类: 0 5分钟K线; 1 15分钟K线; 2 30分钟K线; 3 1小时K线; 4 日K线;5 周K线;6 月K线;7 1分钟;8 1分钟K线; 9 日K线;10 季K线;11 年K线
#返回值：open,close,high,low,vol,amount,year,month,day,hour,minute,datetime
# csv格式：code,ts_code,trade_date(缩写）,trade_time,time_index,open,high,low,close,amount,volume
def get_security_bars(self, category, market, code, start=0, count=240):
dict = {0: 'SZ', 1: 'SH'}
ts_code = code + "." + dict[market]
order = [
'code', 'ts_code', 'trade_date', 'trade_time', 'time_index',
'open', 'high', 'low', 'close', 'amount', 'volume'
]
#df = self.api.get_security_bars(9, 0, '000001', 0, 10) # 返回普通list
df = self.api.to_df(
self.api.get_security_bars(category, market, code, start,
count)) # 返回DataFrame
if df.empty: return df
df.insert(0, 'ts_code', ts_code)
df.insert(0, 'code', code)
df['trade_time'] = df['datetime'].apply(lambda x: str(x)[11:19])
df['time_index'] = df['trade_time'].apply(
lambda x: datatime_util.stockTradeTime2Index(x))
df['trade_date'] = df['datetime'].apply(
lambda x: (str(x)[0:10]).replace('-', ''))
df.rename(columns={'vol': 'volume'}, inplace=True)
df.drop(['year', 'month', 'day', 'hour', 'minute', 'datetime'],
axis=1,
inplace=True)
df['volume'] = df['volume'].apply(lambda x: int(x)) #取整
df.loc[df['amount'] == 5.877471754111438e-39,
'amount'] = 0 #列值根据条件筛选后修改为0
df = df[order]
filename = config.tdx_csv_minline1_all + ts_code + ".csv"
if os.path.isfile(filename):
df.to_csv(filename,
index=False,
mode='a',
header=False,
sep=',',
encoding="utf_8_sig")
else:
df.to_csv(filename,
index=False,
mode='w',
header=True,
sep=',',
encoding="utf_8_sig")
print("新增加的一分钟all股票数据：", filename)
# 获取1分钟k线，最后一个参数说明需要获取的数量，本接口只获取从最近交易日往前的数据
# 输入参数：五个参数分别为：category（k线),市场代码(0:深圳，1:上海),股票代码,开始位置(从最近交易日向前取，0表示最近交易日),返回的记录条数
# K线种类: 0 5分钟K线; 1 15分钟K线; 2 30分钟K线; 3 1小时K线; 4 日K线;5 周K线;6 月K线;7 1分钟;8 1分钟K线; 9 日K线;10 季K线;11 年K线
# 返回值：open,close,high,low,vol,amount,year,month,day,hour,minute,datetime
# csv格式：code,ts_code,trade_date(缩写）,trade_time,time_index,open,high,low,close,amount,volume
def get_security_bars_minute1(self, category, market, code, start, count):
dict = {0: 'SZ', 1: 'SH'}
ts_code = code + "." + dict[market]
order = [
'code', 'ts_code', 'trade_date', 'trade_time', 'time_index',
'open', 'high', 'low', 'close', 'amount', 'volume'
]
# df = self.api.get_security_bars(9, 0, '000001', 0, 10) # 返回普通list
df = self.api.to_df(
self.api.get_security_bars(category, market, code, start,
count)) # 返回DataFrame
if df.empty: return
df.insert(0, 'ts_code', ts_code)
df.insert(0, 'code', code)
df['trade_time'] = df['datetime'].apply(lambda x: str(x)[11:19])
df['time_index'] = df['trade_time'].apply(
lambda x: datatime_util.stockTradeTime2Index(x))
df['trade_date'] = df['datetime'].apply(
lambda x: (str(x)[0:10]).replace('-', ''))
df.rename(columns={'vol': 'volume'}, inplace=True)
df.drop(['year', 'month', 'day', 'hour', 'minute', 'datetime'],
axis=1,
inplace=True)
df['volume'] = df['volume'].apply(lambda x: int(x)) # 取整
df.loc[df['amount'] == 5.877471754111438e-39,
'amount'] = 0 # 列值根据条件筛选后修改为0
df = df[order]
#过滤掉停牌的数据，在tdx中，停牌股票也能取到数据，价格是前一交易日的收盘价，所以只能用成交量或成交金额为0来判断
#1按日期分组后取出成交量为0的日期；2循环过滤掉成交量为0的日期的数据。
dfg = df.groupby(by='trade_date').mean() #分组
dfg['trade_date'] = dfg.index
dfg = dfg[dfg.volume == 0] #条件过滤，保留满足条件的数据
for trade_date in dfg['trade_date'].values:
df = df[(df['trade_date'] != trade_date)] # 每个条件要用括号()括起来
return df
#可以获取多只股票的行情信息
#返回值：market,code,active1,price,last_close,open,high,low,reversed_bytes0,reversed_bytes1,vol,cur_vol,amount,s_vol,
#reversed_bytes2,reversed_bytes3,bid1,ask1,bid_vol1,ask_vol1,bid2,ask2,bid_vol2,ask_vol2,bid3,ask3,bid_vol3,ask_vol3,bid4,
#ask4,bid_vol4,ask_vol4,bid5,ask5,bid_vol5,ask_vol5,reversed_bytes4,reversed_bytes5,reversed_bytes6,reversed_bytes7,
#reversed_bytes8,reversed_bytes9,active2
def get_security_quotes(self):
df = self.api.to_df(
self.api.get_security_quotes([(0, '000001'), (1, '600300')]))
print(df)
# 获取市场股票数量
#返回值：value
def get_security_count(self):
df = self.api.to_df(self.api.get_security_count(0)) #0 - 深圳， 1 - 上海
print(df)
# 获取股票列表，返回值里面除了股票，还有国债等
#返回值：code,volunit,decimal_point,name,pre_close
def get_security_list(self):
df = self.api.to_df(self.api.get_security_list(
0, 10000)) # 市场代码, 起始位置 如： 0,0 或 1,100
print(df)
# 获取指数k线
#输入参数同股票k线接口
# 返回值：open,close,high,low,vol,amount,year,month,day,hour,minute,datetime,up_count down_count
def get_index_bars(self):
index_dict_cn = {
"上证指数": "999999",
"深证成指": "399001",
"中小板指": "399005",
"创业板指": "399006",
"深证综指": "399106",
"上证50": "000016",
"沪深300": "000300"
}
index_dict = {
"sh": "999999",
"sz": "399001",
"zxb": "399005",
"cyb": "399006",
"szz": "399106",
"sz50": "000016",
"hs300": "000300"
}
for key in index_dict.keys():
df = self.api.to_df(
self.api.get_index_bars(9, 1, index_dict[key], 0, 2))
print(df)
# 查询分时行情，最近交易日的数据，一分钟一条记录
#返回值：price,vol
def get_minute_time_data(self):
df = self.api.to_df(self.api.get_minute_time_data(
1, '600300')) #市场代码， 股票代码
print(df)
# 查询历史分时行情
# 返回值：price,vol
def get_history_minute_time_data(self):
df = self.api.to_df(
self.api.get_history_minute_time_data(TDXParams.MARKET_SH,
'603887',
20200420)) #市场代码， 股票代码，时间
print(df)
# 查询分笔成交，最近交易日数据
#返回值：time，price，vol，num，buyorsell
def get_transaction_data(self):
df = self.api.to_df(
self.api.get_transaction_data(TDXParams.MARKET_SZ, '000001', 0,
30)) #市场代码， 股票代码，起始位置， 数量
print(df)
# 查询历史分笔成交
#返回值:time,price,vol,buyorsell
def get_history_transaction_data(self):
df = self.api.to_df(
self.api.get_history_transaction_data(
TDXParams.MARKET_SZ, '000001', 0, 10,
20170209)) #市场代码， 股票代码，起始位置，日期 数量
print(df)
# 查询公司信息目录,返回的不是具体数据
#返回值:name,filename,start,length
def get_company_info_category(self):
df = self.api.to_df(
self.api.get_company_info_category(TDXParams.MARKET_SZ,
'000001')) #市场代码， 股票代码
print(df)
# 读取公司信息详情
#返回值:value
def get_company_info_content(self):
df = self.api.to_df(
self.api.get_company_info_content(
0, '000001', '000001.txt', 0,
1000)) #市场代码， 股票代码, 文件名, 起始位置， 数量
print(df)
# 读取除权除息信息
#返回值:year,month,day,category,name,fenhong,peigujia,songzhuangu,peigu
def get_xdxr_info(self):
df = self.api.to_df(self.api.get_xdxr_info(1, '600300')) #市场代码， 股票代码
print(df)
# 读取财务信息
#返回值:market,code,liutongguben,province,industry,updated_date,ipo_date,zongguben,guojiagu,faqirenfarengu,farengu,bgu,hgu,zhigonggu,
#zongzichan,liudongzichan,gudingzichan,wuxingzichan,gudongrenshu,liudongfuzhai,changqifuzhai,zibengongjijin,jingzichan,zhuyingshouru,
#zhuyinglirun,yingshouzhangkuan,yingyelirun,touzishouyu,jingyingxianjinliu,zongxianjinliu,cunhuo,lirunzonghe,shuihoulirun,jinglirun,weifenlirun,baoliu1,baoliu2
def get_finance_info(self):
df = self.api.to_df(self.api.get_finance_info(1,
'600300')) #市场代码， 股票代码
print(df)
# 读取k线信息
# 返回值:value
def get_k_data(self):
df = self.api.to_df(
self.api.get_k_data('600300', '2017-07-03',
'2017-07-10')) #股票代码， 开始时间， 结束时间
print(df)
# 读取板块信息
#返回值：blockname, block_type, code_index, code
""" BLOCK_SZ = "block_zs.dat";BLOCK_FG = "block_fg.dat";BLOCK_GN = "block_gn.dat";BLOCK_DEFAULT = "block.dat" """
def get_and_parse_block_info(self):
##指数板块 风格板块 概念板块 一般板块
block_filename = [
"block_zs.dat", "block_fg.dat", "block_gn.dat", "block.dat"
]
for block in block_filename:
df = self.api.to_df(
self.api.get_and_parse_block_info(block)) #板块文件名称
filename = config.tdx_csv_block + block[0:-4] + ".csv"
if os.path.isfile(filename):
os.remove(filename)
df.to_csv(filename,
index=False,
mode='w',
header=True,
sep=',',
encoding="utf_8_sig")
else:
df.to_csv(filename,
index=False,
mode='w',
header=True,
sep=',',
encoding="utf_8_sig")
# 读取板块信息，多个类型封装到一个df对象中返回
# 返回值：data_source, block_category, block_type, block_name, block_code, ts_code, create_time
def update_block_member(self):
##指数板块 风格板块 概念板块 一般板块
#block_filename = ["block_zs.dat", "block_fg.dat", "block_gn.dat", "block.dat"]
block_filename = ["block_zs.dat", "block_fg.dat",
"block_gn.dat"] #block.dat中的数据都包含在其他版块里了，这个可以去掉
data_source = "tdx"
dfall = None
for block in block_filename:
df = self.api.to_df(
self.api.get_and_parse_block_info(block)) # 板块文件名称
df['data_source'] = data_source
if block == "block.dat":
df['block_category'] = data_source + ".yb"
else:
df['block_category'] = data_source + "." + block[6:8]
df['block_type'] = df['block_type'].map(lambda x: str(x))
df['block_type'] = df['block_category'].str.cat(
df['block_type'], sep=".") #, sep = "."
df['block_code'] = "" #使用pd直接插入到数据库时，字段不能是None值
df['ts_code'] = df['code'].apply(lambda x: x + ".SH"
if x[0:1] == "6" else x + ".SZ")
if (dfall is not None) and (not dfall.empty):
dfall = dfall.append(df, ignore_index=True)
else:
dfall = df
if (dfall is None) or (dfall.empty): return None
dfall.rename(columns={'blockname': 'block_name'}, inplace=True)
dfall['create_time'] = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
dfall = dfall[[
'data_source', 'block_category', 'block_type', 'block_name',
'block_code', 'ts_code', 'create_time'
]] #列重排序
#分组统计
dfg = dfall.groupby(by=[
'data_source', 'block_category', 'block_type', 'block_name',
'block_code'
],
as_index=False).count() # 分组求每组数量
dfg.rename(columns={'ts_code': 'member_count'},
inplace=True) #ts_code列数值为汇总值，需要重命名
dfg['create_time'] = time.strftime(
'%Y-%m-%d %H:%M:%S',
time.localtime(time.time())) #create_time列数值为汇总值，需要重新赋值
delete_condition = f"data_source = '{data_source}'"
mysql_script.df2db_update(delete_condition=delete_condition,
block_basic_df=dfg,
block_member_df=dfall)
return (len(dfg), len(dfall))
#获取一段时间的1分钟数据，因为每次调用接口只能返回3天的分钟数据（240*3)，需要分多次调用
#返回值：0没有提取到数据；1提取到数据
def get_minute1_data(self, category, market, code, start_date, end_date):
init_start_date = start_date.replace('-', '')
init_end_date = end_date.replace('-', '')
day = datatime_util.diffrentPeriod(datatime_util.DAILY, start_date,
end_date)
df = self.get_security_bars_minute1(category, market, code, 0,
240 * 3) # 返回DataFrame
if df is None or df.empty:
print('{0}没有交易数据'.format(code))
return 0
print(market, '--', code, '--', start_date, '--', end_date)
#print("最大值：",df.groupby('datetime').max())
#print(df.describe()) #df数据统计
data_start_date = df.min()['trade_date']
data_end_date = df.max()['trade_date']
start_date = start_date.replace('-', '')
end_date = end_date.replace('-', '')
if data_end_date < start_date or end_date < data_start_date:
print("采集时间在数据范围之外，退出函数")
return 0
elif end_date > data_end_date:
end_date = data_end_date
if start_date < data_start_date:
#最近三天的数据中，去掉无用的数据后即是最终数据
#需要取的数据还有三天前的数据，需要继续向前取
n = (day - 3) // 3
m = (day - 3) % 3
for i in range(0, n):
dfn = self.get_security_bars_minute1(category, market, code,
240 * 3 * (i + 1),
240 * 3) # 返回DataFrame
if (dfn is not None) and (not dfn.empty):
df = dfn.append(df, ignore_index=True)
if m > 0:
dfn = self.get_security_bars_minute1(category, market, code,
240 * 3 * (n + 1),
240 * m)
if (dfn is not None) and (not dfn.empty):
df = dfn.append(df, ignore_index=True)
df = df.sort_values(by=['trade_date', 'time_index'],
axis=0,
ascending=True)
#过滤掉start_date, end_date之外的数据
df = df[(df['trade_date'] >= str(init_start_date)) &
(df['trade_date'] <= str(init_end_date))] #每个条件要用括号()括起来
dict = {0: 'SZ', 1: 'SH'}
ts_code = code + "." + dict[market]
filename = config.tdx_csv_minline1_all + ts_code + ".csv"
if os.path.isfile(filename):
df.to_csv(filename,
index=False,
mode='a',
header=False,
sep=',',
encoding="utf_8_sig")
print("更新一分钟all股票数据：", filename)
else:
df.to_csv(filename,
index=False,
mode='w',
header=True,
sep=',',
encoding="utf_8_sig")
print("新增加的一分钟all股票数据：", filename)
if len(sys.argv) > 1:
zone, code = sys.argv[1].split('.')
if zone == 'sz':
market = 0
api = TdxHq_API()
api.connect('119.147.212.81', 7709)
info = api.get_company_info_category(market, code)
for i in info:
#for k in i.keys():
#print(k,i[k])
#name,filename,start,length
info2 = api.get_company_info_content(market, code, i['filename'],
i['start'], i['length'])
print(info2)
def get_data(fname):
content = fname.decode('utf-8')
print(content)
def get_and_parse_block_info(client, blockfile):
try:
meta = client.get_block_info_meta(blockfile)
except Exception as e:
return None
if not meta:
