主要使用tushare 库来获取
import numpy as np
from pandas import Series, DataFrame
import pandas as pd
import matplotlib.pyplot as plt
from numpy.random import randn
from datetime import datetime, timedelta
from dateutil.parser import parse
from pandas.tseries.offsets import Hour, Minute, Day, MonthEnd
import pytz
import pandas.io.data as web
import tushare as ts
from sqlalchemy import create_engine
connstr='mysql://youruser:[email protected]/test?charset=utf8'
engine = create_engine(connstr)
def download_adj_data(code,start,end,engine=None):
if engine==None:
engine=create_engine(connstr)
adj_data=ts.get_h_data(code,start,end,retry_count=50, pause=0.02)
adj_data.to_sql('adj_data_' code,engine,if_exists='replace')
print ''
print 'Download ok: ',code
df=ts.get_hist_data('sh',start='2015-01-01',end='2016-10-17')
print df.index
df.to_sql('hist_data_sh',engine,if_exists='append')
exit()
'''
df=ts.get_hs300s()
df.to_csv('hs300s.csv')
df=pd.read_csv('hs300s.csv')
'''
print ts.get_hs300s()for x in df.code:
s= 'd' % x
print 'start: ' s
download_adj_data(s,'2015-01-01','2016-10-17',engine)
exit()