def validate_date(self, day):
if day == "TODAY":
local_date_now = self.get_local_date()
return local_date_now if self.quick_dict[local_date_now] == 1 else last_tddate()
if day == "LASTCLOSEDTRADEDAY":
local_date_now = self.get_local_date()
local_time_now = self.get_local_time()
return local_date_now if self.quick_dict[local_date_now] == 1 and local_time_now >= '15:05:00' \
else last_tddate()
else:
return day # FIXME
def get_tops(date=None, retry_count=3, pause=0.001):
"""
获取每日龙虎榜列表
Parameters
--------
date:string
明细数据日期 format：YYYY-MM-DD 默认为空''
retry_count : int, 默认 3
如遇网络等问题重复执行的次数
pause : int, 默认 0
重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
Return
------
DataFrame
code：代码
name ：名称
pchange：涨跌幅
amount：龙虎榜成交额(万)
buy：买入额(万)
bratio：占总成交比例
sell：卖出额(万)
sratio ：占总成交比例
reason：上榜原因
date ：日期
"""
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
if du.is_holiday(date):
return None
for _ in range(retry_count):
time.sleep(pause)
try:
request = Request(rv.LHB_URL % (ct.P_TYPE["http"], ct.DOMAINS["em"], date))
text = urlopen(request, timeout=10).read()
text = text.decode("GBK")
html = lxml.html.parse(StringIO(text))
res = html.xpath('//table[@id="dt_1"]')
if ct.PY3:
sarr = [etree.tostring(node).decode("utf-8") for node in res]
else:
sarr = [etree.tostring(node) for node in res]
sarr = "".join(sarr)
df = pd.read_html(sarr)[0]
df.columns = [i for i in range(1, 12)]
df = df.apply(_f_rows, axis=1)
df = df.fillna(method="ffill")
df = df.drop([1, 4], axis=1)
df.columns = rv.LHB_COLS
df = df.drop_duplicates()
df["code"] = df["code"].astype(int)
df["code"] = df["code"].map(lambda x: str(x).zfill(6))
df["date"] = date
except:
pass
else:
return df
raise IOError(ct.NETWORK_URL_ERROR_MSG)
def get_tops(date = None):
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
if(du.is_holiday(date)):
return None
request = Request(rv.LHB_URL%(ct.P_TYPE['http'], ct.DOMAINS['em'], date))
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
html = lxml.html.parse(StringIO(text))
res = html.xpath("//table[@id=\"dt_1\"]")
if ct.PY3:
sarr = [etree.tostring(node).decode('utf-8') for node in res]
else:
sarr = [etree.tostring(node) for node in res]
sarr = ''.join(sarr)
df = pd.read_html(sarr)[0]
df.columns = [i for i in range(1,12)]
df = df.apply(_f_rows, axis=1)
df = df.fillna(method='ffill')
df = df.drop([1, 4], axis=1)
df.columns = rv.LHB_COLS
df = df.drop_duplicates()
df['code'] = df['code'].astype(int)
df['code'] = df['code'].map(lambda x: str(x).zfill(6))
df['date'] = date
return df
def top_detail(code, date=None, retry_count= 3, pause= 0.001):
"""
根据指定日期，指定股票的龙虎榜交易细节
Parameters
--------
code: string
指定股票代码
date: string
指定日期
retry_count : int, 默认 3
如遇网络等问题重复执行的次数
pause : int, 默认 0
重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
Return
--------
code:代码
name:名称
bamount:累积买入额(万)
bcount:买入次数
samount:累积卖出额(万)
scount:卖出次数
net:净额(万)
"""
if code is None or code == "":
return None
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
date = du.today()
else:
if(du.is_holiday(date)):
return None
time.sleep(pause)
try:
request = Request(rv.LHB_SINA_URL2%(ct.P_TYPE['http'], ct.DOMAINS['vsf'], code, date))
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
text = text.split('details=')[1][2:-2]
text = eval(text, type('Dummy', (dict,),
dict(__getitem__ = lambda s, n:n))())
text = json.dumps(text)
text = json.loads(text)
buy_df = pd.DataFrame(text['buy'], columns=rv.LHB_TMP_DETAIL_COLS)
buy_df['type'] = 'buy'
sell_df = pd.DataFrame(text['sell'], columns=rv.LHB_TMP_DETAIL_COLS)
sell_df['type'] = 'sell'
#LHB_DETAIL_COLS = ['code', 'type', 'insCode', 'insName', 'bamount', 'samount', 'net']
df = sell_df.append(buy_df)
df.columns = rv.LHB_DETAIL_COLS
df['bamount'] = df['bamount'].astype(float)
df['samount'] = df['samount'].astype(float)
df['net'] = df['net'].astype(float)
df['date'] = date
except Exception as e:
print e
else:
return df
raise IOError(ct.NETWORK_URL_ERROR_MSG)
def get_day_all(date=None):
"""
获取每日收盘行情
Parameters:
-------------
date:交易日期，格式:YYYY-MM-DD
Return:
-------------
DataFrame
code 代码, name 名称, p_change 涨幅%,
price 现价, change 涨跌, open 今开, high 最高,
low 最低, preprice 昨收, pe 市盈(动),
volratio 量比, turnover 换手%, range 振幅%%,
volume 总量, selling 内盘, buying 外盘,
amount 总金额, totals 总股本(万), industry 细分行业,
area 地区, floats 流通股本(万), fvalues 流通市值,
abvalues AB股总市值, avgprice 均价, strength 强弱度%,
activity 活跃度, avgturnover 笔换手, attack 攻击波%,
interval3 近3月涨幅 ，interval 近6月涨幅
"""
wdate = du.last_tddate() if date is None else date
wdate = wdate.replace('-', '')
if wdate < '20170614':
return None
datepre = '' if date is None else wdate[0:4] + wdate[4:6] + '/'
df = pd.read_csv(ct.ALL_DAY_FILE%(datepre, \
'hq' if date is None else wdate), \
dtype={'code':'object'})
return df
def get_day_all(date=None):
"""
获取每日收盘行情
Parameters:
-------------
date:交易日期，格式:YYYY-MM-DD
Return:
-------------
DataFrame
code 代码, name 名称, p_change 涨幅%,
price 现价, change 涨跌, open 今开, high 最高,
low 最低, preprice 昨收, pe 市盈(动),
volratio 量比, turnover 换手%, range 振幅%%,
volume 总量, selling 内盘, buying 外盘,
amount 总金额, totals 总股本(万), industry 细分行业,
area 地区, floats 流通股本(万), fvalues 流通市值,
abvalues AB股总市值, avgprice 均价, strength 强弱度%,
activity 活跃度, avgturnover 笔换手, attack 攻击波%,
interval3 近3月涨幅 ，interval 近6月涨幅
"""
wdate = du.last_tddate() if date is None else date
wdate = wdate.replace('-', '')
if wdate < '20170614':
return None
datepre = '' if date is None else wdate[0:4] + wdate[4:6] + '/'
df = pd.read_csv(ct.ALL_DAY_FILE%(datepre, \
'hq' if date is None else wdate), \
dtype={'code':'object'})
return df
def get_stock_basics(date=None):
"""
获取沪深上市公司基本情况
Parameters
date:日期YYYY-MM-DD，默认为上一个交易日，目前只能提供2016-08-09之后的历史数据
Return
--------
DataFrame
code,代码
name,名称
industry,细分行业
area,地区
pe,市盈率
outstanding,流通股本
totals,总股本(万)
totalAssets,总资产(万)
liquidAssets,流动资产
fixedAssets,固定资产
reserved,公积金
reservedPerShare,每股公积金
eps,每股收益
bvps,每股净资
pb,市净率
timeToMarket,上市日期
"""
wdate = du.last_tddate() if date is None else date
wdate = wdate.replace('-', '')
if wdate < '20160809':
return None
datepre = '' if date is None else wdate[0:4] + wdate[4:6] + '/'
request = Request(ct.ALL_STOCK_BASICS_FILE %
(datepre, '' if date is None else wdate),
headers=ua.get_ua())
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
text = text.replace('--', '')
df = pd.read_csv(StringIO(text), dtype={'code': 'object'})
df = df.set_index('code')
return df
def get_stock_basics(date=None):
"""
获取沪深上市公司基本情况
Parameters
date:日期YYYY-MM-DD，默认为上一个交易日，目前只能提供2016-08-09之后的历史数据
Return
--------
DataFrame
code,代码
name,名称
industry,细分行业
area,地区
pe,市盈率
outstanding,流通股本
totals,总股本(万)
totalAssets,总资产(万)
liquidAssets,流动资产
fixedAssets,固定资产
reserved,公积金
reservedPerShare,每股公积金
eps,每股收益
bvps,每股净资
pb,市净率
timeToMarket,上市日期
"""
wdate = du.last_tddate() if date is None else date
wdate = wdate.replace('-', '')
if wdate < '20160809':
return None
datepre = '' if date is None else wdate[0:4] + wdate[4:6] + '/'
request = Request(ct.ALL_STOCK_BASICS_FILE%(datepre, '' if date is None else wdate))
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
text = text.replace('--', '')
df = pd.read_csv(StringIO(text), dtype={'code':'object'})
df = df.set_index('code')
return df
def top_list(date=None, retry_count=3, pause=0.001):
"""
获取每日龙虎榜列表
Parameters
--------
date:string
明细数据日期 format：YYYY-MM-DD 如果为空，返回最近一个交易日的数据
retry_count : int, 默认 3
如遇网络等问题重复执行的次数
pause : int, 默认 0
重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
Return
------
DataFrame
code：代码
name ：名称
pchange：涨跌幅
amount：龙虎榜成交额(万)
buy：买入额(万)
bratio：占总成交比例
sell：卖出额(万)
sratio ：占总成交比例
reason：上榜原因
date ：日期
"""
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
date = du.today()
else:
if (du.is_holiday(date)):
return None
for _ in range(retry_count):
time.sleep(pause)
try:
request = Request(
rv.LHB_URL % (ct.P_TYPE['http'], ct.DOMAINS['em'], date, date))
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
text = text.split('_1=')[1]
text = eval(
text,
type('Dummy', (dict, ), dict(__getitem__=lambda s, n: n))())
text = json.dumps(text)
text = json.loads(text)
df = pd.DataFrame(text['data'], columns=rv.LHB_TMP_COLS)
df.columns = rv.LHB_COLS
df['buy'] = df['buy'].astype(float)
df['sell'] = df['sell'].astype(float)
df['amount'] = df['amount'].astype(float)
df['Turnover'] = df['Turnover'].astype(float)
df['bratio'] = df['buy'] / df['Turnover']
df['sratio'] = df['sell'] / df['Turnover']
df['bratio'] = df['bratio'].map(ct.FORMAT)
df['sratio'] = df['sratio'].map(ct.FORMAT)
df['date'] = date
for col in ['amount', 'buy', 'sell']:
df[col] = df[col].astype(float)
df[col] = df[col] / 10000
df[col] = df[col].map(ct.FORMAT)
df = df.drop('Turnover', axis=1)
except:
pass
else:
return df
raise IOError(ct.NETWORK_URL_ERROR_MSG)
def top_list(date = None, retry_count=3, pause=0.001):
"""
获取每日龙虎榜列表
Parameters
--------
date:string
明细数据日期 format：YYYY-MM-DD 如果为空，返回最近一个交易日的数据
retry_count : int, 默认 3
如遇网络等问题重复执行的次数
pause : int, 默认 0
重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
Return
------
DataFrame
code：代码
name ：名称
pchange：涨跌幅
amount：龙虎榜成交额(万)
buy：买入额(万)
bratio：占总成交比例
sell：卖出额(万)
sratio ：占总成交比例
reason：上榜原因
date ：日期
"""
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
date = du.today()
else:
if(du.is_holiday(date)):
return None
for _ in range(retry_count):
time.sleep(pause)
try:
request = Request(rv.LHB_URL%(ct.P_TYPE['http'], ct.DOMAINS['em'], date))
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
html = lxml.html.parse(StringIO(text))
res = html.xpath("//table[@id=\"dt_1\"]")
if ct.PY3:
sarr = [etree.tostring(node).decode('utf-8') for node in res]
else:
sarr = [etree.tostring(node) for node in res]
sarr = ''.join(sarr)
df = pd.read_html(sarr)[0]
df.columns = [i for i in range(1,12)]
df = df.apply(_f_rows, axis=1)
df = df.fillna(method='ffill')
df = df.drop([1, 4], axis=1)
df.columns = rv.LHB_COLS
df = df.drop_duplicates()
df['code'] = df['code'].astype(int)
df['code'] = df['code'].map(lambda x: str(x).zfill(6))
df['date'] = date
except:
pass
else:
return df
raise IOError(ct.NETWORK_URL_ERROR_MSG)
def top_list(date = None, retry_count=3, pause=0.001):
"""
获取每日龙虎榜列表
Parameters
--------
date:string
明细数据日期 format：YYYY-MM-DD 如果为空，返回最近一个交易日的数据
retry_count : int, 默认 3
如遇网络等问题重复执行的次数
pause : int, 默认 0
重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
Return
------
DataFrame
code：代码
name ：名称
pchange：涨跌幅
amount：龙虎榜成交额(万)
buy：买入额(万)
bratio：占总成交比例
sell：卖出额(万)
sratio ：占总成交比例
reason：上榜原因
date ：日期
"""
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
date = du.today()
else:
if(du.is_holiday(date)):
return None
for _ in range(retry_count):
time.sleep(pause)
try:
request = Request(rv.LHB_URL%(ct.P_TYPE['http'], ct.DOMAINS['em'], date, date))
text = urlopen(request, timeout=10).read()
text = text.decode('GBK')
text = text.split('_1=')[1]
text = eval(text, type('Dummy', (dict,),
dict(__getitem__ = lambda s, n:n))())
text = json.dumps(text)
text = json.loads(text)
df = pd.DataFrame(text['data'], columns=rv.LHB_TMP_COLS)
df.columns = rv.LHB_COLS
df['buy'] = df['buy'].astype(float)
df['sell'] = df['sell'].astype(float)
df['amount'] = df['amount'].astype(float)
df['Turnover'] = df['Turnover'].astype(float)
df['bratio'] = df['buy'] / df['Turnover']
df['sratio'] = df['sell'] /df['Turnover']
df['bratio'] = df['bratio'].map(ct.FORMAT)
df['sratio'] = df['sratio'].map(ct.FORMAT)
df['date'] = date
for col in ['amount', 'buy', 'sell']:
df[col] = df[col].astype(float)
df[col] = df[col] / 10000
df[col] = df[col].map(ct.FORMAT)
df = df.drop('Turnover', axis=1)
except:
pass
else:
return df
raise IOError(ct.NETWORK_URL_ERROR_MSG)
import tushare as ts
import TsExt as te
from datetime import date
from sqlalchemy import create_engine
from tushare.util import dateu as du
import pandas as pd
if __name__ == '__main__':
engine = create_engine(
'mysql+pymysql://root:[email protected]/tushare?charset=utf8')
if date.today() == ts.util.dateu.last_tddate():
for code in ts.get_stock_basics().index:
tt = te.stk_get_today_ticks(code)
print(code + tt)
df = te.stk_get_today_all(engine=engine)
pd.io.sql.execute(
'delete from stk_today_all where date = \'' + du.last_tddate() + '\'',
engine)
df.to_sql('stk_today_all', engine, if_exists='append')
def gen_date_list(self, goal, t='TODAY', in_mkt=False):
# TODO
if goal == "T" and t == 'TODAY':
return [self.get_local_date()] if not in_mkt else [last_tddate()]
from sqlalchemy import create_engine
from tushare.util import dateu as du
import threading
import time
import TsExt as te
from util.util import last_tddate_delta
if __name__ == '__main__':
engine = create_engine('mysql+pymysql://root:[email protected]/tushare?charset=utf8')
td = du.today()
if(du.is_holiday(td) | int(du.get_hour()) < 16):
dt = du.last_tddate()
else:
dt = td
print(dt)
"""数据表
stk_lhb_broker_detail 龙虎榜股票营业部买入详细情况
stk_k_line_data 股票K线数据
"""
"""
获取股票基本信息
"""
df = te.stk_get_basics(engine)
from datetime import date, timedelta
# df = ts.get_hist_data('002024')
# df2 = df.sort_index()
# ma50 = ta.MA(df2['close'],timeperiod=50,matype=0)
# v_ma50 = ta.MA(df2['volume'],timeperiod=50,matype=0)
# df2['ma50'] = round(ma50,2)
# df2['vma50'] = round(v_ma50,2)
# df2 = df2.fillna(0)
# print(df2)
tod = date.today()
yed = tod + timedelta(days=-1)
df = ts.get_today_all()
df.set_index(['code'], inplace=True)
df['last_vol'] = 'NaN'
# print(df.dtype)
for stkcode in ts.get_stock_basics().index:
try:
print("############" + stkcode + "###################")
df2 = ts.get_hist_data(stkcode, start=str(yed), end=str(yed))
df.at[stkcode, 'last_vol'] = df2.at[du.last_tddate(), 'volume']
# print(df.at[stkcode,'volume'],df.at[stkcode,'last_vol'])
if ((df.at[stkcode, 'volume'] / df.at[stkcode, 'last_vol']) > 2
and df.at[stkcode, 'changepercent'] > 0):
print(df.loc[stkcode])
except Exception as e:
print(e)
def stk_get_today_all(engine):
df = ts.get_today_all()
df['date'] = du.last_tddate()
return df
def last_tddate_delta(t):
tt = du.last_tddate()
tt2 = datetime.datetime.strptime(tt, '%Y-%m-%d').date()
tt_delta = tt2 + datetime.timedelta(days=t)
return tt_delta
def lhb_details(retry_count=3, pause=0.001, code=None, date=None):
"""
获取最近一个交易日龙虎榜上榜个股的交易详情. 包括买1-5和卖1-5的买入及卖出量,营业部名称.
可选参数:
证券代码(code): 指定代码用于只获取该证券的交易详情.省略的话会返回当日所有上榜证券的交易详情
日期(date): 获取指定日期的交易详情.默认为最近一个交易日
返回值:
----------
code:股票代码
name:股票名称
date:交易日期
买1-5营业部名称及买入和卖出额及净额(万)
卖1-5营业部名称及买入和卖出额净额(万)
"""
if date is None:
if du.get_hour() < 18:
date = du.last_tddate()
else:
date = du.today()
else:
if (du.is_holiday(date)):
return None
if code is None:
print('请输入股票代码,比如： lhb_details(000001)')
raise SystemExit(5)
lhb_details_url = 'http://vip.stock.finance.sina.com.cn/q/api/jsonp.php/var%20details=/InvestConsultService.getLHBComBSData?symbol=%s&tradedate=%s&type=01'
text = urlopen(lhb_details_url % (code, date), timeout=10).read()
text = text.decode('GBK')
text = text.split('details=')[1]
text = eval(text,
type('Dummy', (dict, ), dict(__getitem__=lambda s, n: n))())
text = json.dumps(text)
text = json.loads(text)
## text['buy'] = list of dicts
## text['sell'] = list of dicts
#for i in range(len(text['buy'])):
# for key in text['buy'][i].keys():
# print(text['buy'][i][key],end=' ')
# print()
#SYMBOL sellAmount buyAmount comCode type netAmount comName
#000973 7.6802 2101.4900 80291363 01 2093.8098 浙商证券股份有限公司临安万马路证券营业部
#000973 0.0000 1777.2700 80348499 01 1777.27 华泰证券股份有限公司浙江分公司
#000973 317.3780 2069.5400 80127954 01 1752.162 安信证券股份有限公司南昌胜利路证券营业部
#000973 0.9050 1389.3300 80564863 01 1388.425 华鑫证券有限责任公司郑州普惠路证券营业部
#000973 39.0354 1239.5100 80034811 01 1200.4746 财通证券股份有限公司绍兴人民中路证券营业部
print('%4s %6s %10s %10s %10s %s' %
('买入榜', '股票代码', '卖出额(万)', '买入额(万)', '买入净额(万)', '营业部名称'))
for i in range(len(text['buy'])):
print('%-4d %-8s %-10s %-10s %-12s %s' %(i+1,text['buy'][i]['SYMBOL'],text['buy'][i]['sellAmount'],\
text['buy'][i]['buyAmount'],text['buy'][i]['netAmount'],text['buy'][i]['comName']))
#1 000973 7.6802 2101.4900 2093.8098 浙商证券股份有限公司临安万马路证券营业部
#2 000973 0.0000 1777.2700 1777.27 华泰证券股份有限公司浙江分公司
#3 000973 317.3780 2069.5400 1752.162 安信证券股份有限公司南昌胜利路证券营业部
#4 000973 0.9050 1389.3300 1388.425 华鑫证券有限责任公司郑州普惠路证券营业部
#5 000973 39.0354 1239.5100 1200.4746 财通证券股份有限公司绍兴人民中路证券营业部
print('%4s %6s %10s %10s %10s %s' %
('卖出榜', '股票代码', '卖出额(万)', '买入额(万)', '买入净额(万)', '营业部名称'))
for i in range(len(text['sell'])):
print('%-4d %-8s %-10s %-10s %-12s %s' %(i+1,text['sell'][i]['SYMBOL'],text['sell'][i]['sellAmount'],\
text['sell'][i]['buyAmount'],text['sell'][i]['netAmount'],text['sell'][i]['comName']))
