def stock_zh_a_cdr_daily(
symbol: str = "sh689009", start_date: str = "19900101", end_date: str = "22201116"
) -> pd.DataFrame:
"""
新浪财经-A股-CDR个股的历史行情数据, 大量抓取容易封 IP
# TODO 观察复权情况
https://finance.sina.com.cn/realstock/company/sh689009/nc.shtml
:param start_date: 20201103; 开始日期
:type start_date: str
:param end_date: 20201103; 结束日期
:type end_date: str
:param symbol: sh689009
:type symbol: str
:return: specific data
:rtype: pandas.DataFrame
"""
res = requests.get(zh_sina_a_stock_hist_url.format(symbol))
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call(
"d", res.text.split("=")[1].split(";")[0].replace('"', "")
) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df = data_df.astype("float")
temp_df = data_df[start_date:end_date]
temp_df["open"] = round(temp_df["open"], 2)
temp_df["high"] = round(temp_df["high"], 2)
temp_df["low"] = round(temp_df["low"], 2)
temp_df["close"] = round(temp_df["close"], 2)
return temp_df
def stock_zh_a_daily(
symbol: str = "sz000001",
start_date: str = "19900101",
end_date: str = "21000118",
adjust: str = "",
) -> pd.DataFrame:
"""
新浪财经-A股-个股的历史行情数据, 大量抓取容易封 IP
https://finance.sina.com.cn/realstock/company/sh689009/nc.shtml
:param start_date: 20201103; 开始日期
:type start_date: str
:param end_date: 20201103; 结束日期
:type end_date: str
:param symbol: sh600000
:type symbol: str
:param adjust: 默认为空: 返回不复权的数据; qfq: 返回前复权后的数据; hfq: 返回后复权后的数据; hfq-factor: 返回后复权因子; hfq-factor: 返回前复权因子
:type adjust: str
:return: specific data
:rtype: pandas.DataFrame
"""
def _fq_factor(method):
if method == "hfq":
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"]
)
if hfq_factor_df.shape[0] == 0:
raise ValueError("sina hfq factor not available")
hfq_factor_df.columns = ["date", "hfq_factor"]
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
del hfq_factor_df["date"]
return hfq_factor_df
else:
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"]
)
if qfq_factor_df.shape[0] == 0:
raise ValueError("sina hfq factor not available")
qfq_factor_df.columns = ["date", "qfq_factor"]
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
del qfq_factor_df["date"]
return qfq_factor_df
if adjust in ("hfq-factor", "qfq-factor"):
return _fq_factor(adjust.split("-")[0])
res = requests.get(zh_sina_a_stock_hist_url.format(symbol))
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call(
"d", res.text.split("=")[1].split(";")[0].replace('"', "")
) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df = data_df.astype("float")
r = requests.get(zh_sina_a_stock_amount_url.format(symbol, symbol))
amount_data_json = demjson.decode(r.text[r.text.find("["): r.text.rfind("]") + 1])
amount_data_df = pd.DataFrame(amount_data_json)
amount_data_df.index = pd.to_datetime(amount_data_df.date)
del amount_data_df["date"]
temp_df = pd.merge(
data_df, amount_data_df, left_index=True, right_index=True, how="outer"
)
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["amount"] = temp_df["amount"] * 10000
temp_df["turnover"] = temp_df["volume"] / temp_df["amount"]
temp_df.columns = [
"open",
"high",
"low",
"close",
"volume",
"outstanding_share",
"turnover",
]
if adjust == "":
temp_df = temp_df[start_date:end_date]
temp_df.drop_duplicates(subset=["open", "high", "low", "close"], inplace=True)
temp_df["open"] = round(temp_df["open"], 2)
temp_df["high"] = round(temp_df["high"], 2)
temp_df["low"] = round(temp_df["low"], 2)
temp_df["close"] = round(temp_df["close"], 2)
temp_df.dropna(inplace=True)
temp_df.drop_duplicates(inplace=True)
return temp_df
if adjust == "hfq":
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"]
)
hfq_factor_df.columns = ["date", "hfq_factor"]
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
del hfq_factor_df["date"]
temp_df = pd.merge(
temp_df, hfq_factor_df, left_index=True, right_index=True, how="outer"
)
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df.dropna(inplace=True)
temp_df.drop_duplicates(subset=["open", "high", "low", "close", "volume"], inplace=True)
temp_df["open"] = temp_df["open"] * temp_df["hfq_factor"]
temp_df["high"] = temp_df["high"] * temp_df["hfq_factor"]
temp_df["close"] = temp_df["close"] * temp_df["hfq_factor"]
temp_df["low"] = temp_df["low"] * temp_df["hfq_factor"]
temp_df = temp_df.iloc[:, :-1]
temp_df = temp_df[start_date:end_date]
temp_df["open"] = round(temp_df["open"], 2)
temp_df["high"] = round(temp_df["high"], 2)
temp_df["low"] = round(temp_df["low"], 2)
temp_df["close"] = round(temp_df["close"], 2)
temp_df.dropna(inplace=True)
return temp_df
if adjust == "qfq":
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"]
)
qfq_factor_df.columns = ["date", "qfq_factor"]
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
del qfq_factor_df["date"]
temp_df = pd.merge(
temp_df, qfq_factor_df, left_index=True, right_index=True, how="outer"
)
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df.dropna(inplace=True)
temp_df.drop_duplicates(subset=["open", "high", "low", "close", "volume"], inplace=True)
temp_df["open"] = temp_df["open"] / temp_df["qfq_factor"]
temp_df["high"] = temp_df["high"] / temp_df["qfq_factor"]
temp_df["close"] = temp_df["close"] / temp_df["qfq_factor"]
temp_df["low"] = temp_df["low"] / temp_df["qfq_factor"]
temp_df = temp_df.iloc[:, :-1]
temp_df = temp_df[start_date:end_date]
temp_df["open"] = round(temp_df["open"], 2)
temp_df["high"] = round(temp_df["high"], 2)
temp_df["low"] = round(temp_df["low"], 2)
temp_df["close"] = round(temp_df["close"], 2)
temp_df.dropna(inplace=True)
return temp_df
def stock_zh_a_daily(symbol: str = "sz000613",
adjust: str = "") -> pd.DataFrame:
"""
新浪财经-A股-个股的历史行情数据, 大量抓取容易封IP
:param symbol: sh600000
:type symbol: str
:param adjust: 默认为空: 返回不复权的数据; qfq: 返回前复权后的数据; hfq: 返回后复权后的数据; hfq-factor: 返回后复权因子; hfq-factor: 返回前复权因子
:type adjust: str
:return: specific data
:rtype: pandas.DataFrame
"""
res = requests.get(zh_sina_a_stock_hist_url.format(symbol))
js_code = execjs.compile(hk_js_decode)
dict_list = js_code.call("d",
res.text.split("=")[1].split(";")[0].replace(
'"', "")) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df["date"] = data_df["date"].str.split("T", expand=True).iloc[:, 0]
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df = data_df.astype("float")
r = requests.get(zh_sina_a_stock_amount_url.format(symbol, symbol))
amount_data_json = demjson.decode(
r.text[r.text.find("["):r.text.rfind("]") + 1])
amount_data_df = pd.DataFrame(amount_data_json)
amount_data_df.index = pd.to_datetime(amount_data_df.date)
del amount_data_df["date"]
temp_df = pd.merge(data_df,
amount_data_df,
left_index=True,
right_index=True,
how="outer")
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["amount"] = temp_df["amount"] * 10000
temp_df["turnover"] = temp_df["volume"] / temp_df["amount"]
temp_df.columns = [
"open",
"high",
"low",
"close",
"volume",
"outstanding_share",
"turnover",
]
if adjust == "":
return temp_df
if adjust == "hfq":
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"])
hfq_factor_df.columns = ["date", "hfq_factor"]
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
del hfq_factor_df["date"]
temp_df = pd.merge(temp_df,
hfq_factor_df,
left_index=True,
right_index=True,
how="left")
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["open"] = temp_df["open"] * temp_df["hfq_factor"]
temp_df["high"] = temp_df["high"] * temp_df["hfq_factor"]
temp_df["close"] = temp_df["close"] * temp_df["hfq_factor"]
temp_df["low"] = temp_df["low"] * temp_df["hfq_factor"]
return temp_df.iloc[:, :-1]
if adjust == "qfq":
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"])
qfq_factor_df.columns = ["date", "qfq_factor"]
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
del qfq_factor_df["date"]
temp_df = pd.merge(temp_df,
qfq_factor_df,
left_index=True,
right_index=True,
how="left")
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["open"] = temp_df["open"] / temp_df["qfq_factor"]
temp_df["high"] = temp_df["high"] / temp_df["qfq_factor"]
temp_df["close"] = temp_df["close"] / temp_df["qfq_factor"]
temp_df["low"] = temp_df["low"] / temp_df["qfq_factor"]
return temp_df.iloc[:, :-1]
if adjust == "hfq-factor":
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"])
hfq_factor_df.columns = ["date", "hfq_factor"]
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
del hfq_factor_df["date"]
return hfq_factor_df
if adjust == "qfq-factor":
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])["data"])
qfq_factor_df.columns = ["date", "qfq_factor"]
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
del qfq_factor_df["date"]
return qfq_factor_df
def stock_zh_a_daily(symbol="sh600000", factor=""):
"""
从新浪财经-A股获取某个股票的历史行情数据, 大量抓取容易封IP
:param symbol: str sh600000
:param factor: str 默认为空, 不复权; qfq, 前复权因子; hfq, 后复权因子;
:return: pandas.DataFrame
不复权数据
open high low close volume
date
1999-11-10 29.50 29.80 27.00 27.75 174085100
1999-11-11 27.58 28.38 27.53 27.71 29403500
1999-11-12 27.86 28.30 27.77 28.05 15008000
1999-11-15 28.20 28.25 27.70 27.75 11921100
1999-11-16 27.88 27.97 26.48 26.55 23223100
... ... ... ... ...
2019-10-30 12.75 12.79 12.52 12.59 53734730
2019-10-31 12.68 12.70 12.50 12.51 33347533
2019-11-01 12.50 12.83 12.44 12.75 62705733
2019-11-04 12.75 12.89 12.69 12.74 49737996
2019-11-05 12.74 13.19 12.69 12.95 74274389
后复权因子
date hfq_factor
0 2019-06-11 12.7227249211316980
1 2018-07-13 12.3391802422000990
2 2017-05-25 12.2102441895126000
3 2016-06-23 9.2710670167499010
4 2015-06-23 8.1856186501361000
5 2014-06-24 7.8226125975203010
6 2013-06-03 7.2881483827828000
7 2012-06-26 6.9052943607646000
8 2011-06-03 6.6571999525935000
9 2010-06-10 5.0588982345161000
10 2009-06-09 3.8599078005559000
11 2008-04-24 2.7363470981385000
12 2007-07-18 2.0953391363342000
13 2006-05-25 2.0866878599662000
14 2006-05-12 2.0595609177866000
15 2005-05-12 1.5842776290666000
16 2004-05-20 1.5573493974111000
17 2003-06-23 1.5391056877503000
18 2002-08-22 1.5263436173709000
19 2000-07-06 1.0065019505852000
20 1999-11-10 1.0000000000000000
21 1900-01-01 1.0000000000000000
前复权因子
date qfq_factor
0 2019-06-11 1.0000000000000000
1 2018-07-13 1.0310834813499000
2 2017-05-25 1.0419713745004000
3 2016-06-23 1.3723042771825000
4 2015-06-23 1.5542777479525000
5 2014-06-24 1.6264035528443000
6 2013-06-03 1.7456731467196000
7 2012-06-26 1.8424594602978000
8 2011-06-03 1.9111225457747000
9 2010-06-10 2.5149201133019000
10 2009-06-09 3.2961214563983000
11 2008-04-24 4.6495289028892000
12 2007-07-18 6.0719168083645000
13 2006-05-25 6.0970905928105000
14 2006-05-12 6.1773967505679000
15 2005-05-12 8.0306157757383010
16 2004-05-20 8.1694736854052000
17 2003-06-23 8.2663101191762000
18 2002-08-22 8.3354264245204000
19 2000-07-06 12.6405367756464000
20 1999-11-10 12.7227249211316980
21 1900-01-01 12.7227249211316980
"""
res = requests.get(zh_sina_a_stock_hist_url.format(symbol))
js_code = execjs.compile(hk_js_decode)
dict_list = js_code.call(
'd', res.text.split("=")[1].split(";")[0].replace(
'"', "")) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df["date"] = data_df["date"].str.split("T", expand=True).iloc[:, 0]
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df.astype("float")
if not factor:
return data_df
if factor == "hfq":
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])['data'])
hfq_factor_df.columns = ["date", "hfq_factor"]
return hfq_factor_df
if factor == "qfq":
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])['data'])
qfq_factor_df.columns = ["date", "qfq_factor"]
return qfq_factor_df
def stock_zh_a_daily(symbol: str = "sh600751",
adjust: str = "") -> pd.DataFrame:
"""
新浪财经-A股-个股的历史行情数据, 大量抓取容易封IP
:param symbol: sh600000
:type symbol: str
:param adjust: 默认为空: 返回不复权的数据; qfq: 返回前复权后的数据; hfq: 返回后复权后的数据; hfq-factor: 返回后复权因子; hfq-factor: 返回前复权因子
:type adjust: str
:return: specific data
:rtype: pandas.DataFrame
"""
def _fq_factor(method):
if method == 'hfq':
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])['data'])
if hfq_factor_df.shape[0] == 0:
raise ValueError('sina hfq factor not available')
hfq_factor_df.columns = ["date", "hfq_factor"]
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
del hfq_factor_df["date"]
return hfq_factor_df
else:
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])['data'])
if qfq_factor_df.shape[0] == 0:
raise ValueError('sina hfq factor not available')
qfq_factor_df.columns = ["date", "qfq_factor"]
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
del qfq_factor_df["date"]
return qfq_factor_df
if adjust in ("hfq-factor", "qfq-factor"):
return _fq_factor(adjust.split('-')[0])
res = requests.get(zh_sina_a_stock_hist_url.format(symbol))
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call('d',
res.text.split("=")[1].split(";")[0].replace(
'"', "")) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df = data_df.astype("float")
r = requests.get(zh_sina_a_stock_amount_url.format(symbol, symbol))
amount_data_json = demjson.decode(
r.text[r.text.find("["):r.text.rfind("]") + 1])
amount_data_df = pd.DataFrame(amount_data_json)
amount_data_df.index = pd.to_datetime(amount_data_df.date)
del amount_data_df["date"]
temp_df = pd.merge(data_df,
amount_data_df,
left_index=True,
right_index=True,
how="outer")
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["amount"] = temp_df["amount"] * 10000
temp_df["turnover"] = temp_df["volume"] / temp_df["amount"]
temp_df.columns = [
'open', 'high', 'low', 'close', 'volume', 'outstanding_share',
'turnover'
]
if adjust == "":
return temp_df
if adjust == "hfq":
res = requests.get(zh_sina_a_stock_hfq_url.format(symbol))
hfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])['data'])
hfq_factor_df.columns = ["date", "hfq_factor"]
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
del hfq_factor_df["date"]
temp_df = pd.merge(temp_df,
hfq_factor_df,
left_index=True,
right_index=True,
how="outer")
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["open"] = temp_df["open"] * temp_df["hfq_factor"]
temp_df["high"] = temp_df["high"] * temp_df["hfq_factor"]
temp_df["close"] = temp_df["close"] * temp_df["hfq_factor"]
temp_df["low"] = temp_df["low"] * temp_df["hfq_factor"]
temp_df.dropna(how="any", inplace=True)
return temp_df.iloc[:, :-1]
if adjust == "qfq":
res = requests.get(zh_sina_a_stock_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(
eval(res.text.split("=")[1].split("\n")[0])['data'])
qfq_factor_df.columns = ["date", "qfq_factor"]
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
del qfq_factor_df["date"]
temp_df = pd.merge(temp_df,
qfq_factor_df,
left_index=True,
right_index=True,
how="outer")
temp_df.fillna(method="ffill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["open"] = temp_df["open"] / temp_df["qfq_factor"]
temp_df["high"] = temp_df["high"] / temp_df["qfq_factor"]
temp_df["close"] = temp_df["close"] / temp_df["qfq_factor"]
temp_df["low"] = temp_df["low"] / temp_df["qfq_factor"]
temp_df.dropna(how="any", inplace=True)
return temp_df.iloc[:, :-1]
