知微
fa45d8aa5f
- health_checklist.json: 192.168.1.122→node122
- ocr_client.py: docstring IP→node122
- docs/market-data-requirements.md: IP→node122
- 所有API调用通过ProxyHandler({})绕过系统代理
Privoxy对node122:18003返回500，直连正常
276 lines
10 KiB
Python
276 lines
10 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding:utf-8 -*-
|
|
"""
|
|
Date: 2026/3/15 23:00
|
|
Desc: 新浪财经-港股-实时行情数据和历史行情数据(包含前复权和后复权因子)
|
|
https://stock.finance.sina.com.cn/hkstock/quotes/00700.html
|
|
"""
|
|
|
|
import pandas as pd
|
|
from py_mini_racer import MiniRacer
|
|
import requests
|
|
|
|
from akshare.stock.cons import (
|
|
hk_js_decode,
|
|
hk_sina_stock_hist_url,
|
|
hk_sina_stock_hist_hfq_url,
|
|
hk_sina_stock_hist_qfq_url,
|
|
)
|
|
from akshare.utils.tqdm import get_tqdm
|
|
|
|
|
|
def stock_hk_spot() -> pd.DataFrame:
|
|
"""
|
|
新浪财经-港股的所有港股的实时行情数据
|
|
https://vip.stock.finance.sina.com.cn/mkt/#qbgg_hk
|
|
:return: 实时行情数据
|
|
:rtype: pandas.DataFrame
|
|
"""
|
|
url = "https://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php/Market_Center.getHKStockData"
|
|
params = {
|
|
"page": "1",
|
|
"num": "60",
|
|
"sort": "symbol",
|
|
"asc": "1",
|
|
"node": "qbgg_hk",
|
|
"_s_r_a": "init",
|
|
}
|
|
big_df = pd.DataFrame()
|
|
tqdm = get_tqdm()
|
|
for page in tqdm(range(1, 100), leave=False):
|
|
params["page"] = str(page)
|
|
r = requests.get(url, params=params)
|
|
data_json = r.json()
|
|
if not data_json:
|
|
break
|
|
temp_df = pd.DataFrame(data_json)
|
|
big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
|
|
|
|
big_df.columns = [
|
|
"代码",
|
|
"中文名称",
|
|
"英文名称",
|
|
"交易类型",
|
|
"最新价",
|
|
"昨收",
|
|
"今开",
|
|
"最高",
|
|
"最低",
|
|
"成交量",
|
|
"-",
|
|
"成交额",
|
|
"日期时间",
|
|
"买一",
|
|
"卖一",
|
|
"-",
|
|
"-",
|
|
"-",
|
|
"-",
|
|
"-",
|
|
"涨跌额",
|
|
"涨跌幅",
|
|
"-",
|
|
"-",
|
|
]
|
|
big_df = big_df[
|
|
[
|
|
"日期时间",
|
|
"代码",
|
|
"中文名称",
|
|
"英文名称",
|
|
"交易类型",
|
|
"最新价",
|
|
"涨跌额",
|
|
"涨跌幅",
|
|
"昨收",
|
|
"今开",
|
|
"最高",
|
|
"最低",
|
|
"成交量",
|
|
"成交额",
|
|
"买一",
|
|
"卖一",
|
|
]
|
|
]
|
|
big_df["最新价"] = pd.to_numeric(big_df["最新价"], errors="coerce")
|
|
big_df["涨跌额"] = pd.to_numeric(big_df["涨跌额"], errors="coerce")
|
|
big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"], errors="coerce")
|
|
big_df["昨收"] = pd.to_numeric(big_df["昨收"], errors="coerce")
|
|
big_df["今开"] = pd.to_numeric(big_df["今开"], errors="coerce")
|
|
big_df["最高"] = pd.to_numeric(big_df["最高"], errors="coerce")
|
|
big_df["最低"] = pd.to_numeric(big_df["最低"], errors="coerce")
|
|
big_df["成交量"] = pd.to_numeric(big_df["成交量"], errors="coerce")
|
|
big_df["成交额"] = pd.to_numeric(big_df["成交额"], errors="coerce")
|
|
big_df["买一"] = pd.to_numeric(big_df["买一"], errors="coerce")
|
|
big_df["卖一"] = pd.to_numeric(big_df["卖一"], errors="coerce")
|
|
return big_df
|
|
|
|
|
|
def stock_hk_daily(symbol: str = "00981", adjust: str = "") -> pd.DataFrame:
|
|
"""
|
|
新浪财经-港股-个股的历史行情数据
|
|
https://stock.finance.sina.com.cn/hkstock/quotes/02912.html
|
|
:param symbol: 可以使用 ak.stock_hk_spot() 获取
|
|
:type symbol: str
|
|
:param adjust: "": 返回未复权的数据 ; qfq: 返回前复权后的数据; qfq-factor: 返回前复权因子和调整;
|
|
:type adjust: str
|
|
:return: 指定 adjust 的数据
|
|
:rtype: pandas.DataFrame
|
|
"""
|
|
r = requests.get(hk_sina_stock_hist_url.format(symbol))
|
|
js_code = MiniRacer()
|
|
js_code.eval(hk_js_decode)
|
|
dict_list = js_code.call(
|
|
"d", r.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"]).dt.date
|
|
del data_df["date"]
|
|
data_df = data_df.astype("float")
|
|
|
|
if adjust == "":
|
|
data_df.reset_index(inplace=True)
|
|
data_df["date"] = pd.to_datetime(data_df["date"]).dt.date
|
|
return data_df
|
|
|
|
if adjust == "hfq":
|
|
r = requests.get(hk_sina_stock_hist_hfq_url.format(symbol))
|
|
try:
|
|
hfq_factor_df = pd.DataFrame(
|
|
eval(r.text.split("=")[1].split("\n")[0])["data"]
|
|
)
|
|
if len(hfq_factor_df) == 1:
|
|
data_df.reset_index(inplace=True)
|
|
data_df["date"] = pd.to_datetime(data_df["date"]).dt.date
|
|
return data_df
|
|
except SyntaxError:
|
|
data_df.reset_index(inplace=True)
|
|
data_df["date"] = pd.to_datetime(data_df["date"]).dt.date
|
|
return data_df
|
|
hfq_factor_df.columns = ["date", "hfq_factor", "cash"]
|
|
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
|
|
del hfq_factor_df["date"]
|
|
|
|
# 处理复权因子
|
|
temp_date_range = pd.date_range(
|
|
"1900-01-01", hfq_factor_df.index[0].isoformat()
|
|
)
|
|
temp_df = pd.DataFrame(range(len(temp_date_range)), temp_date_range)
|
|
new_range = pd.merge(
|
|
temp_df, hfq_factor_df, left_index=True, right_index=True, how="outer"
|
|
)
|
|
new_range.ffill(inplace=True)
|
|
new_range = new_range.iloc[:, [1, 2]]
|
|
temp_df = pd.merge(
|
|
data_df, new_range, left_index=True, right_index=True, how="outer"
|
|
)
|
|
temp_df.ffill(inplace=True)
|
|
temp_df.drop_duplicates(
|
|
subset=["open", "high", "low", "close", "volume"], inplace=True
|
|
)
|
|
temp_df = temp_df.astype(float)
|
|
temp_df["open"] = temp_df["open"] * temp_df["hfq_factor"] + temp_df["cash"]
|
|
temp_df["high"] = temp_df["high"] * temp_df["hfq_factor"] + temp_df["cash"]
|
|
temp_df["close"] = temp_df["close"] * temp_df["hfq_factor"] + temp_df["cash"]
|
|
temp_df["low"] = temp_df["low"] * temp_df["hfq_factor"] + temp_df["cash"]
|
|
temp_df = temp_df.apply(lambda x: round(x, 4))
|
|
temp_df.dropna(how="any", inplace=True)
|
|
temp_df = temp_df.iloc[:, :-2]
|
|
temp_df.reset_index(inplace=True)
|
|
temp_df.rename({"index": "date"}, axis="columns", inplace=True)
|
|
temp_df["date"] = pd.to_datetime(temp_df["date"]).dt.date
|
|
return temp_df
|
|
|
|
if adjust == "qfq":
|
|
r = requests.get(hk_sina_stock_hist_qfq_url.format(symbol))
|
|
try:
|
|
qfq_factor_df = pd.DataFrame(
|
|
eval(r.text.split("=")[1].split("\n")[0])["data"]
|
|
)
|
|
if len(qfq_factor_df) == 1:
|
|
data_df.reset_index(inplace=True)
|
|
data_df["date"] = pd.to_datetime(data_df["date"]).dt.date
|
|
return data_df
|
|
|
|
except SyntaxError:
|
|
data_df.reset_index(inplace=True)
|
|
data_df["date"] = pd.to_datetime(data_df["date"]).dt.date
|
|
return data_df
|
|
qfq_factor_df.columns = ["date", "qfq_factor"]
|
|
qfq_factor_df.index = pd.to_datetime(qfq_factor_df.date)
|
|
del qfq_factor_df["date"]
|
|
|
|
temp_date_range = pd.date_range(
|
|
"1900-01-01", qfq_factor_df.index[0].isoformat()
|
|
)
|
|
temp_df = pd.DataFrame(range(len(temp_date_range)), temp_date_range)
|
|
new_range = pd.merge(
|
|
temp_df, qfq_factor_df, left_index=True, right_index=True, how="outer"
|
|
)
|
|
new_range.ffill(inplace=True)
|
|
new_range = new_range.iloc[:, [1]]
|
|
temp_df = pd.merge(
|
|
data_df, new_range, left_index=True, right_index=True, how="outer"
|
|
)
|
|
temp_df.ffill(inplace=True)
|
|
temp_df.drop_duplicates(
|
|
subset=["open", "high", "low", "close", "volume"], 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 = temp_df.apply(lambda x: round(x, 4))
|
|
temp_df.dropna(how="any", inplace=True)
|
|
temp_df = temp_df.iloc[:, :-1]
|
|
temp_df.reset_index(inplace=True)
|
|
temp_df.rename({"index": "date"}, axis="columns", inplace=True)
|
|
temp_df["date"] = pd.to_datetime(temp_df["date"]).dt.date
|
|
return temp_df
|
|
|
|
if adjust == "hfq-factor":
|
|
r = requests.get(hk_sina_stock_hist_hfq_url.format(symbol))
|
|
hfq_factor_df = pd.DataFrame(eval(r.text.split("=")[1].split("\n")[0])["data"])
|
|
hfq_factor_df.columns = ["date", "hfq_factor", "cash"]
|
|
hfq_factor_df.index = pd.to_datetime(hfq_factor_df.date)
|
|
del hfq_factor_df["date"]
|
|
hfq_factor_df.reset_index(inplace=True)
|
|
hfq_factor_df["date"] = pd.to_datetime(hfq_factor_df["date"]).dt.date
|
|
return hfq_factor_df
|
|
|
|
if adjust == "qfq-factor":
|
|
r = requests.get(hk_sina_stock_hist_qfq_url.format(symbol))
|
|
qfq_factor_df = pd.DataFrame(eval(r.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"]
|
|
qfq_factor_df.reset_index(inplace=True)
|
|
qfq_factor_df["date"] = pd.to_datetime(qfq_factor_df["date"]).dt.date
|
|
return qfq_factor_df
|
|
else:
|
|
return pd.DataFrame()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
stock_hk_daily_hfq_df = stock_hk_daily(symbol="00700", adjust="")
|
|
print(stock_hk_daily_hfq_df)
|
|
|
|
stock_hk_daily_hfq_df = stock_hk_daily(symbol="00700", adjust="hfq")
|
|
print(stock_hk_daily_hfq_df)
|
|
|
|
stock_hk_daily_hfq_df = stock_hk_daily(symbol="01591", adjust="hfq")
|
|
print(stock_hk_daily_hfq_df)
|
|
|
|
stock_hk_daily_hfq_df = stock_hk_daily(symbol="00700", adjust="qfq")
|
|
print(stock_hk_daily_hfq_df)
|
|
|
|
stock_hk_daily_df = stock_hk_daily(symbol="01302", adjust="qfq")
|
|
print(stock_hk_daily_df)
|
|
|
|
stock_hk_daily_hfq_factor_df = stock_hk_daily(symbol="00700", adjust="hfq-factor")
|
|
print(stock_hk_daily_hfq_factor_df)
|
|
|
|
stock_hk_spot_df = stock_hk_spot()
|
|
print(stock_hk_spot_df)
|