def get_predict_share_Sina(code, mtype):
"""
mtype:
eps--每股收益,
sales--营业收入,
np--净利润,
roe--净资产收益率
"""
pn = 1
DF = pd.DataFrame()
ws._write_head()
while True:
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vPerformancePrediction/kind/{0}/index.phtml?symbol={1}&p={2}'.format(
mtype, code, pn)
r = requests.get(url)
r = r.content.decode('gbk')
html = BeautifulSoup(r, 'lxml')
text = html.find(id='dataTable')
df = pd.read_html(str(text), header=0)[0]
if df.empty is True:
break
else:
pn = pn + 1
DF = DF.append(df)
except:
break
DF = DF.applymap(lambda x: np.where(x == '--', np.nan, x))
DF = DF.set_index('股票代码')
DF.index = DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
return DF
def margin_share(code, begin, end):
"""
datetime:日期 如2017-06-16
-----------------
Return:
DataFrame
"""
DF = pd.DataFrame()
ws._write_head()
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/rzrq/index.phtml?symbol={0}&bdate={1}&edate={2}'.format(
code, begin, end)
#print(url)
r = requests.get(url)
r = r.content.decode('gbk')
html = BeautifulSoup(r, 'lxml')
sarr = html.find(id='dataTable')
df = pd.read_html(str(sarr), header=None, skiprows=3)[0]
df = df.applymap(lambda x: np.where(x == '--', np.nan, x))
df = df.drop(0, axis=1)
#print(df.head())
df.columns = name
df = df.set_index('date')
return df
except Exception as e:
print(e)
pass
def dzjy():
"""
查询大宗交易的数据,主要是当前数据的前20页的数据
-----------------
Return:
DataFrame
"""
pn = 1
DF = pd.DataFrame()
ws._write_head()
while True:
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/dzjy/index.phtml?num=60&p={0}'.format(
pn)
r = requests.get(url)
#print(url)
r = r.content.decode('gbk')
html = BeautifulSoup(r, 'lxml')
sarr = html.find(id='dataTable')
df = pd.read_html(str(sarr), header=0)[0]
DF = DF.append(df)
pn = pn + 1
if pn > 20:
break
if df.empty is True:
break
except:
break
DF = DF.applymap(lambda x: np.where(x == '--', np.nan, x))
DF = DF.drop_duplicates()
return DF
def grow(year,quarter):
pn=1
DF=pd.DataFrame()
ws._write_head()
while True:
try:
ws._write_console()
url='http://vip.stock.finance.sina.com.cn/q/go.php/vFinanceAnalyze/kind/grow/index.phtml?s_i=&s_a=&s_c=&reportdate={0}&quarter={1}&p={2}'.format(year,quarter,pn)
r=requests.get(url,headers=hds())
r=r.content.decode('gbk')
html=BeautifulSoup(r,'lxml')
text=html.find(id='dataTable')
df=pd.read_html(str(text),header=0)[0]
if df.empty is True:
break
else:
pn = pn + 1
DF =DF.append(df)
except:
break
DF=DF.applymap(lambda x:np.where(x=='--',np.nan,x))
DF=DF.set_index('股票代码')
DF.index=DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
DF['date']=str(year)+'_'+str(quarter).zfill(2)
name=list(DF.columns)
name.remove('股票名称')
name.remove('date')
for label in name:
DF[label]=DF[label].astype(float)
return DF
def xsjj(begin,end):
"""
查询限售解禁的数据,主要是当前数据的前20页的数据
-----------------
Return:
DataFrame
"""
pn=1
DF=pd.DataFrame()
ws._write_head()
while True:
try:
ws._write_console()
url='http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/xsjj/index.phtml?bdate={0}&edate={1}&showall=%CF%D4%CA%BE%C8%AB%B2%BF&p={2}'.format(begin,end,pn)
r=requests.get(url)
#print(url)
r=r.content.decode('gbk')
html=BeautifulSoup(r,'lxml')
sarr=html.find(id='dataTable')
df=pd.read_html(str(sarr),header=0)[0]
DF =DF.append(df)
pn=pn+1
if pn > 50:
break
if df.empty is True:
break
except:
break
DF=DF.applymap(lambda x:np.where(x=='--',np.nan,x))
DF=DF.drop_duplicates()
DF['代码']=DF['代码'].map(lambda x:str(x).split('.')[0].zfill(6))
return DF
def dzjy_share(code, begin=None, end=None):
"""
查询某一区间的股票的大宗交易情况和相关数据.
datetime:日期 如2017-06-16
-----------------
Return:
DataFrame
"""
if code[0] in ['0', '2', '3']:
code = 'sz' + code
if code[0] in ['6', '9']:
code = 'sh' + code
if end == None or (dt.datetime.strptime(end, '%Y-%m-%d') <
dt.datetime.strptime(begin, '%Y-%m-%d')):
end = dt.datetime.strftime(dt.datetime.today(), '%Y-%m-%d')
if begin == None:
begin = dt.datetime.strftime(
dt.datetime.today() - dt.timedelta(days=360), '%Y-%m-%d')
pn = 1
DF = pd.DataFrame()
ws._write_head()
while True:
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/dzjy/index.phtml?symbol={0}&bdate={1}&edate={2}&p={3}'.format(
code, begin, end, pn)
#print(url)
r = requests.get(url)
r = r.content.decode('gbk')
html = BeautifulSoup(r, 'lxml')
sarr = html.find(id='dataTable')
df = pd.read_html(str(sarr), header=0)[0]
DF = DF.append(df)
pn = pn + 1
if pn > 20:
break
if df.empty is True:
break
except:
break
DF = DF.applymap(lambda x: np.where(x == '--', np.nan, x))
DF = DF.drop_duplicates()
return DF
def holders(year, quarter, mytype):
"""
mytype:主要有四种类型,jgcg,jjzc,sbzc,qfii
year: 年份
quarter:季度,分为1,2,3,4
-----------------
Return:
DataFrame
"""
pn = 1
DF = pd.DataFrame()
ws._write_head()
while True:
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vComStockHold/kind/{3}/index.phtml?symbol=%D6%A4%C8%AF%BC%F2%B3%C6%BB%F2%B4%FA%C2%EB&reportdate={0}&quarter={1}&p={2}'.format(
year, quarter, pn, mytype)
r = requests.get(url)
r = r.content.decode('gbk')
html = BeautifulSoup(r, 'lxml')
text = html.find(id='dataTable')
df = pd.read_html(str(text), header=0)[0]
#print(df)
if df.empty is True:
break
else:
pn = pn + 1
DF = DF.append(df)
except:
break
DF = DF.applymap(lambda x: np.where(x == '--', np.nan, x))
DF = DF.drop_duplicates()
print(DF)
if mytype in ['jjzc', 'sbzc', 'qfii']:
DF = DF.drop([1, 2], axis=0)
try:
DF = DF.set_index('证券代码')
DF.index = DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
except:
DF = DF.set_index('代码')
DF.index = DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
finally:
pass
return DF
def margindetail(begin, end):
"""
datetime:日期 如2017-06-16
-----------------
Return:
DataFrame
"""
days = pd.date_range(begin, end, freq='B')
DF = pd.DataFrame()
ws._write_head()
for day in days:
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/rzrq/index.phtml?tradedate={0}'.format(
day.strftime('%Y-%m-%d'))
r = requests.get(url)
r = r.content.decode('gbk')
html = lxml.html.parse(StringIO(r))
res = html.xpath("//div[@class='list']/table[2]//tr[position()>3]")
sarr = [etree.tostring(node) for node in res]
#sarr = ''.join(sarr)
#print(sarr)
sarr = ''.join(str(sarr))
sarr = '<table>%s</table>' % sarr
df = pd.read_html(sarr, header=None)[0]
df['day'] = day
#print(df)
if df.empty is False:
DF = DF.append(df)
except:
pass
DF = DF.applymap(lambda x: np.where(x == '--', np.nan, x))
DF = DF.drop_duplicates()
name.append('date')
name.insert(0, 'code')
DF.columns = name
DF['code'] = DF['code'].map(lambda x: str(x).split('.')[0].zfill(6))
DF = DF.set_index(['code', 'date'])
#print(DF)
return DF
def forcast_share(code):
DF=pd.DataFrame()
ws._write_head()
try:
ws._write_console()
url='http://vip.stock.finance.sina.com.cn/q/go.php/vFinanceAnalyze/kind/performance/index.phtml?symbol={0}'.format(code)
r=requests.get(url,headers=hds())
r=r.content.decode('gbk')
html=BeautifulSoup(r,'lxml')
text=html.find(id='dataTable')
df=pd.read_html(str(text))[0]
if df.empty is False:
DF =DF.append(df)
DF=DF.applymap(lambda x:np.where(x=='--',np.nan,x))
DF=DF.drop(8,axis=1)
DF.columns=['code','name','type','pdate','rpdate','summary','eps_l','Up_Down']
DF=DF.set_index('code')
DF.index=DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
return DF
except Exception as e:
print(e)
def holders_share(code, year, quarter, mytype):
"""
mytype:主要有四种类型,jgcg,jjzc,sbzc,qfii
year: 年份
quarter:季度,分为1,2,3,4
-----------------
Return:
DataFrame
"""
ws._write_head()
try:
ws._write_console()
url = 'http://vip.stock.finance.sina.com.cn/q/go.php/vComStockHold/kind/{3}/index.phtml?symbol={0}&reportdate={1}&quarter={2}'.format(
code, year, quarter, mytype)
r = requests.get(url)
r = r.content.decode('gbk')
html = BeautifulSoup(r, 'lxml')
text = html.find(id='dataTable')
DF = pd.read_html(str(text), header=0)[0]
except:
pass
DF = DF.applymap(lambda x: np.where(x == '--', np.nan, x))
DF = DF.drop_duplicates()
#print(DF)
if mytype in ['jjzc', 'sbzc', 'qfii']:
DF = DF.drop([1, 2], axis=0)
try:
DF = DF.set_index('证券代码')
DF.index = DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
except:
DF = DF.set_index('代码')
DF.index = DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
finally:
pass
return DF
def get_researchRate_Sina(mtype, period=10, rate=None, srate=None, zf=None):
"""
投资评级选股
------------------------------
mtype: hy,dy,gn
preiod: -1,10,30,60
rate:5,4,3,2,1
srate:5,4,3,2,1
zf:1,2,3,4,5
-----------------------------
Return:
DataFrame
code: 股票代码
name :股票名称
rate :最新评级
target: 目标价
date :评级时间
srate :综合评价
chage :平均涨幅
industry:行业
"""
burl = 'http://vip.stock.finance.sina.com.cn/q/go.php/vIR_CustomSearch/index.phtml?sr_p=%s' % period
if mtype == 'hy':
name = input("Enter name in %s" % mtype)
burl = burl + '&industry=' + hy[name]
elif mtype == 'dy':
name = input("Enter name in %s" % mtype)
burl = burl + '&zone=' + dy[name]
elif mtype == 'gn':
name = input("Enter name in %s" % mtype)
burl = burl + '&concept=' + gn[name]
else:
pass
if rate is not None:
burl = burl + '&rating=%s' % rate
if srate is not None:
burl = burl + '&srating=%s' % srate
if zf is not None:
burl = burl + '&sprice=%s' % zf
#burl=burl+'&p={0}'
#print(burl)
DF = pd.DataFrame()
ws._write_head()
pageno = 1
while True:
#print(pageno)
url = burl + '&p={0}'.format(pageno)
try:
ws._write_console()
#print(url)
r = requests.get(url)
text = r.content.decode('gbk')
items = lxml.html.parse(StringIO(text))
tb = items.xpath('//table[@class="list_table"]//tr[position()>1]')
sarr = [etree.tostring(node) for node in tb]
sarr = '<table>%s</table>' % sarr
df = pd.read_html(str(text), header=None)[0]
df = df.drop(0, axis=0)
if df.empty:
#print("No data")
break
else:
DF = DF.append(df)
pageno = pageno + 1
except:
#print(url)
break
try:
DF = DF.drop([7, 9, 10, 11, 12, 13], axis=1)
DF.columns = [
'code', 'name', 'rate', 'target', 'srate', 'chage', 'industry'
]
except:
DF.columns = [
'code', 'name', 'rate', 'target', 'date', 'srate', 'chage',
'industry'
]
pass
DF = DF.reset_index(drop=True)
#DF=DF.applymap(lambda x:np.where(x=='--',np.nan,x))
#DF=DF.set_index('股票代码')
#DF.index=DF.index.map(lambda x: str(x).split('.')[0].zfill(6))
DF = DF.replace('--', np.nan)
DF['target'] = DF['target'].map(lambda x: float(x))
return DF
