akshare 1.12.99__py3-none-any.whl → 1.15.73__py3-none-any.whl

akshare/bond/bond_issue_cninfo.py

@@ -1,15 +1,14 @@
 # -*- coding:utf-8 -*-
 # !/usr/bin/env python
 """
-Date: 2023/6/12 15:00
+Date: 2024/6/19 22:00
 Desc: 巨潮资讯-数据中心-专题统计-债券报表-债券发行
 http://webapi.cninfo.com.cn/#/thematicStatistics
 """
-import time
 
 import pandas as pd
 import requests
-from py_mini_racer import py_mini_racer
+import py_mini_racer
 
 from akshare.datasets import get_ths_js
 
@@ -23,7 +22,7 @@ def _get_file_content_cninfo(file: str = "cninfo.js") -> str:
     :rtype: str
     """
     setting_file_path = get_ths_js(file)
-    with open(setting_file_path) as f:
+    with open(setting_file_path, encoding="utf-8") as f:
         file_data = f.read()
     return file_data
 
@@ -58,7 +57,8 @@ def bond_treasure_issue_cninfo(
         "Pragma": "no-cache",
         "Proxy-Connection": "keep-alive",
         "Referer": "http://webapi.cninfo.com.cn/",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/93.0.4577.63 Safari/537.36",
         "X-Requested-With": "XMLHttpRequest",
     }
     params = {
@@ -107,8 +107,12 @@ def bond_treasure_issue_cninfo(
             "债券名称",
         ]
     ]
-    temp_df["发行起始日"] = pd.to_datetime(temp_df["发行起始日"], errors="coerce").dt.date
-    temp_df["发行终止日"] = pd.to_datetime(temp_df["发行终止日"], errors="coerce").dt.date
+    temp_df["发行起始日"] = pd.to_datetime(
+        temp_df["发行起始日"], errors="coerce"
+    ).dt.date
+    temp_df["发行终止日"] = pd.to_datetime(
+        temp_df["发行终止日"], errors="coerce"
+    ).dt.date
     temp_df["缴款日"] = pd.to_datetime(temp_df["缴款日"], errors="coerce").dt.date
     temp_df["公告日期"] = pd.to_datetime(temp_df["公告日期"], errors="coerce").dt.date
     temp_df["计划发行总量"] = pd.to_numeric(temp_df["计划发行总量"], errors="coerce")
@@ -133,7 +137,6 @@ def bond_local_government_issue_cninfo(
     :rtype: pandas.DataFrame
     """
     url = "http://webapi.cninfo.com.cn/api/sysapi/p_sysapi1121"
-    random_time_str = str(int(time.time()))
     js_code = py_mini_racer.MiniRacer()
     js_content = _get_file_content_cninfo("cninfo.js")
     js_code.eval(js_content)
@@ -150,7 +153,8 @@ def bond_local_government_issue_cninfo(
         "Pragma": "no-cache",
         "Proxy-Connection": "keep-alive",
         "Referer": "http://webapi.cninfo.com.cn/",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/93.0.4577.63 Safari/537.36",
         "X-Requested-With": "XMLHttpRequest",
     }
     params = {
@@ -199,8 +203,12 @@ def bond_local_government_issue_cninfo(
             "债券名称",
         ]
     ]
-    temp_df["发行起始日"] = pd.to_datetime(temp_df["发行起始日"], errors="coerce").dt.date
-    temp_df["发行终止日"] = pd.to_datetime(temp_df["发行终止日"], errors="coerce").dt.date
+    temp_df["发行起始日"] = pd.to_datetime(
+        temp_df["发行起始日"], errors="coerce"
+    ).dt.date
+    temp_df["发行终止日"] = pd.to_datetime(
+        temp_df["发行终止日"], errors="coerce"
+    ).dt.date
     temp_df["缴款日"] = pd.to_datetime(temp_df["缴款日"], errors="coerce").dt.date
     temp_df["公告日期"] = pd.to_datetime(temp_df["公告日期"], errors="coerce").dt.date
     temp_df["计划发行总量"] = pd.to_numeric(temp_df["计划发行总量"], errors="coerce")
@@ -241,7 +249,8 @@ def bond_corporate_issue_cninfo(
         "Pragma": "no-cache",
         "Proxy-Connection": "keep-alive",
         "Referer": "http://webapi.cninfo.com.cn/",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/93.0.4577.63 Safari/537.36",
         "X-Requested-With": "XMLHttpRequest",
     }
     params = {
@@ -295,8 +304,12 @@ def bond_corporate_issue_cninfo(
         ]
     ]
     temp_df["公告日期"] = pd.to_datetime(temp_df["公告日期"], errors="coerce").dt.date
-    temp_df["交易所网上发行起始日"] = pd.to_datetime(temp_df["交易所网上发行起始日"], errors="coerce").dt.date
-    temp_df["交易所网上发行终止日"] = pd.to_datetime(temp_df["交易所网上发行终止日"], errors="coerce").dt.date
+    temp_df["交易所网上发行起始日"] = pd.to_datetime(
+        temp_df["交易所网上发行起始日"], errors="coerce"
+    ).dt.date
+    temp_df["交易所网上发行终止日"] = pd.to_datetime(
+        temp_df["交易所网上发行终止日"], errors="coerce"
+    ).dt.date
     temp_df["计划发行总量"] = pd.to_numeric(temp_df["计划发行总量"], errors="coerce")
     temp_df["实际发行总量"] = pd.to_numeric(temp_df["实际发行总量"], errors="coerce")
     temp_df["发行面值"] = pd.to_numeric(temp_df["发行面值"], errors="coerce")
@@ -336,7 +349,8 @@ def bond_cov_issue_cninfo(
         "Pragma": "no-cache",
         "Proxy-Connection": "keep-alive",
         "Referer": "http://webapi.cninfo.com.cn/",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/93.0.4577.63 Safari/537.36",
         "X-Requested-With": "XMLHttpRequest",
     }
     params = {
@@ -418,23 +432,47 @@ def bond_cov_issue_cninfo(
         ]
     ]
     temp_df["公告日期"] = pd.to_datetime(temp_df["公告日期"], errors="coerce").dt.date
-    temp_df["发行起始日"] = pd.to_datetime(temp_df["发行起始日"], errors="coerce").dt.date
-    temp_df["发行终止日"] = pd.to_datetime(temp_df["发行终止日"], errors="coerce").dt.date
-    temp_df["转股开始日期"] = pd.to_datetime(temp_df["转股开始日期"], errors="coerce").dt.date
-    temp_df["转股终止日期"] = pd.to_datetime(temp_df["转股终止日期"], errors="coerce").dt.date
-    temp_df["转股终止日期"] = pd.to_datetime(temp_df["转股终止日期"], errors="coerce").dt.date
-    temp_df["网上申购日期"] = pd.to_datetime(temp_df["网上申购日期"], errors="coerce").dt.date
-    temp_df["网上申购中签结果公告日及退款日"] = pd.to_datetime(temp_df["网上申购中签结果公告日及退款日"], errors="coerce").dt.date
-    temp_df["债权登记日"] = pd.to_datetime(temp_df["债权登记日"], errors="coerce").dt.date
-    temp_df["优先申购日"] = pd.to_datetime(temp_df["优先申购日"], errors="coerce").dt.date
-    temp_df["优先申购缴款日"] = pd.to_datetime(temp_df["优先申购缴款日"], errors="coerce").dt.date
+    temp_df["发行起始日"] = pd.to_datetime(
+        temp_df["发行起始日"], errors="coerce"
+    ).dt.date
+    temp_df["发行终止日"] = pd.to_datetime(
+        temp_df["发行终止日"], errors="coerce"
+    ).dt.date
+    temp_df["转股开始日期"] = pd.to_datetime(
+        temp_df["转股开始日期"], errors="coerce"
+    ).dt.date
+    temp_df["转股终止日期"] = pd.to_datetime(
+        temp_df["转股终止日期"], errors="coerce"
+    ).dt.date
+    temp_df["转股终止日期"] = pd.to_datetime(
+        temp_df["转股终止日期"], errors="coerce"
+    ).dt.date
+    temp_df["网上申购日期"] = pd.to_datetime(
+        temp_df["网上申购日期"], errors="coerce"
+    ).dt.date
+    temp_df["网上申购中签结果公告日及退款日"] = pd.to_datetime(
+        temp_df["网上申购中签结果公告日及退款日"], errors="coerce"
+    ).dt.date
+    temp_df["债权登记日"] = pd.to_datetime(
+        temp_df["债权登记日"], errors="coerce"
+    ).dt.date
+    temp_df["优先申购日"] = pd.to_datetime(
+        temp_df["优先申购日"], errors="coerce"
+    ).dt.date
+    temp_df["优先申购缴款日"] = pd.to_datetime(
+        temp_df["优先申购缴款日"], errors="coerce"
+    ).dt.date
     temp_df["计划发行总量"] = pd.to_numeric(temp_df["计划发行总量"], errors="coerce")
     temp_df["实际发行总量"] = pd.to_numeric(temp_df["实际发行总量"], errors="coerce")
     temp_df["发行面值"] = pd.to_numeric(temp_df["发行面值"], errors="coerce")
     temp_df["发行价格"] = pd.to_numeric(temp_df["发行价格"], errors="coerce")
     temp_df["初始转股价格"] = pd.to_numeric(temp_df["初始转股价格"], errors="coerce")
-    temp_df["网上申购数量上限"] = pd.to_numeric(temp_df["网上申购数量上限"], errors="coerce")
-    temp_df["网上申购数量下限"] = pd.to_numeric(temp_df["网上申购数量下限"], errors="coerce")
+    temp_df["网上申购数量上限"] = pd.to_numeric(
+        temp_df["网上申购数量上限"], errors="coerce"
+    )
+    temp_df["网上申购数量下限"] = pd.to_numeric(
+        temp_df["网上申购数量下限"], errors="coerce"
+    )
     temp_df["网上申购单位"] = pd.to_numeric(temp_df["网上申购单位"], errors="coerce")
     temp_df["配售价格"] = pd.to_numeric(temp_df["配售价格"], errors="coerce")
     return temp_df
@@ -464,7 +502,8 @@ def bond_cov_stock_issue_cninfo() -> pd.DataFrame:
         "Pragma": "no-cache",
         "Proxy-Connection": "keep-alive",
         "Referer": "http://webapi.cninfo.com.cn/",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/93.0.4577.63 Safari/537.36",
         "X-Requested-With": "XMLHttpRequest",
     }
     r = requests.post(url, headers=headers)
@@ -500,8 +539,12 @@ def bond_cov_stock_issue_cninfo() -> pd.DataFrame:
         ]
     ]
     temp_df["公告日期"] = pd.to_datetime(temp_df["公告日期"], errors="coerce").dt.date
-    temp_df["自愿转换期起始日"] = pd.to_datetime(temp_df["自愿转换期起始日"], errors="coerce").dt.date
-    temp_df["自愿转换期终止日"] = pd.to_datetime(temp_df["自愿转换期终止日"], errors="coerce").dt.date
+    temp_df["自愿转换期起始日"] = pd.to_datetime(
+        temp_df["自愿转换期起始日"], errors="coerce"
+    ).dt.date
+    temp_df["自愿转换期终止日"] = pd.to_datetime(
+        temp_df["自愿转换期终止日"], errors="coerce"
+    ).dt.date
     temp_df["转股价格"] = pd.to_numeric(temp_df["转股价格"], errors="coerce")
     return temp_df
 

akshare/bond/bond_zh_cov.py

@@ -11,7 +11,7 @@ import re
 
 import pandas as pd
 import requests
-from py_mini_racer import py_mini_racer
+import py_mini_racer
 
 from akshare.bond.cons import (
     zh_sina_bond_hs_cov_count_url,

akshare/bond/bond_zh_sina.py

@@ -1,16 +1,17 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/2/28 23:00
+Date: 2024/6/18 18:30
 Desc: 新浪财经-债券-沪深债券-实时行情数据和历史行情数据
 https://vip.stock.finance.sina.com.cn/mkt/#hs_z
 """
+
 import datetime
 import re
 
 import pandas as pd
 import requests
-from py_mini_racer import py_mini_racer
+import py_mini_racer
 
 from akshare.bond.cons import (
     zh_sina_bond_hs_count_url,
@@ -41,7 +42,7 @@ def get_zh_bond_hs_page_count() -> int:
         return int(page_count) + 1
 
 
-def bond_zh_hs_spot() -> pd.DataFrame:
+def bond_zh_hs_spot(start_page: str = "1", end_page: str = "10") -> pd.DataFrame:
     """
     新浪财经-债券-沪深债券-实时行情数据, 大量抓取容易封IP
     https://vip.stock.finance.sina.com.cn/mkt/#hs_z
@@ -49,59 +50,64 @@ def bond_zh_hs_spot() -> pd.DataFrame:
     :rtype: pandas.DataFrame
     """
     page_count = get_zh_bond_hs_page_count()
+    page_count = int(page_count)
     zh_sina_bond_hs_payload_copy = zh_sina_bond_hs_payload.copy()
     tqdm = get_tqdm()
     big_df = pd.DataFrame()
-    for page in tqdm(range(1, page_count + 1), leave=False):
+    start_page = int(start_page)
+    end_page = int(end_page) + 1 if int(end_page) + 1 <= page_count else page_count
+    for page in tqdm(range(start_page, end_page), leave=False):
         zh_sina_bond_hs_payload_copy.update({"page": page})
         r = requests.get(zh_sina_bond_hs_url, params=zh_sina_bond_hs_payload_copy)
         data_json = demjson.decode(r.text)
         temp_df = pd.DataFrame(data_json)
         big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
     big_df.columns = [
-        '代码',
-        '-',
-        '名称',
-        '最新价',
-        '涨跌额',
-        '涨跌幅',
-        '买入',
-        '卖出',
-        '昨收',
-        '今开',
-        '最高',
-        '最低',
-        '成交量',
-        '成交额',
-        '-',
-        '-',
-        '-',
-        '-',
-        '-',
-        '-',
+        "代码",
+        "-",
+        "名称",
+        "最新价",
+        "涨跌额",
+        "涨跌幅",
+        "买入",
+        "卖出",
+        "昨收",
+        "今开",
+        "最高",
+        "最低",
+        "成交量",
+        "成交额",
+        "-",
+        "-",
+        "-",
+        "-",
+        "-",
+        "-",
+    ]
+    big_df = big_df[
+        [
+            "代码",
+            "名称",
+            "最新价",
+            "涨跌额",
+            "涨跌幅",
+            "买入",
+            "卖出",
+            "昨收",
+            "今开",
+            "最高",
+            "最低",
+            "成交量",
+            "成交额",
+        ]
     ]
-    big_df = big_df[[
-        '代码',
-        '名称',
-        '最新价',
-        '涨跌额',
-        '涨跌幅',
-        '买入',
-        '卖出',
-        '昨收',
-        '今开',
-        '最高',
-        '最低',
-        '成交量',
-        '成交额',
-    ]]
-    big_df['买入'] = pd.to_numeric(big_df['买入'], errors="coerce")
-    big_df['卖出'] = pd.to_numeric(big_df['卖出'], 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['最新价'] = pd.to_numeric(big_df['最新价'], errors="coerce")
+    big_df["买入"] = pd.to_numeric(big_df["买入"], errors="coerce")
+    big_df["卖出"] = pd.to_numeric(big_df["卖出"], 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["最新价"] = pd.to_numeric(big_df["最新价"], errors="coerce")
     return big_df
 
 
@@ -126,15 +132,15 @@ def bond_zh_hs_daily(symbol: str = "sh010107") -> pd.DataFrame:
     )  # 执行 js 解密代码
     data_df = pd.DataFrame(dict_list)
     data_df["date"] = pd.to_datetime(data_df["date"], errors="coerce").dt.date
-    data_df['open'] = pd.to_numeric(data_df['open'], errors="coerce")
-    data_df['high'] = pd.to_numeric(data_df['high'], errors="coerce")
-    data_df['low'] = pd.to_numeric(data_df['low'], errors="coerce")
-    data_df['close'] = pd.to_numeric(data_df['close'], errors="coerce")
+    data_df["open"] = pd.to_numeric(data_df["open"], errors="coerce")
+    data_df["high"] = pd.to_numeric(data_df["high"], errors="coerce")
+    data_df["low"] = pd.to_numeric(data_df["low"], errors="coerce")
+    data_df["close"] = pd.to_numeric(data_df["close"], errors="coerce")
     return data_df
 
 
 if __name__ == "__main__":
-    bond_zh_hs_spot_df = bond_zh_hs_spot()
+    bond_zh_hs_spot_df = bond_zh_hs_spot(start_page="1", end_page="5")
     print(bond_zh_hs_spot_df)
 
     bond_zh_hs_daily_df = bond_zh_hs_daily(symbol="sh010107")

akshare/cal/rv.py

@@ -0,0 +1,170 @@
+"""
+Yang-Zhang-s-Realized-Volatility-Automated-Estimation-in-Python
+https://github.com/hugogobato/Yang-Zhang-s-Realized-Volatility-Automated-Estimation-in-Python
+论文地址：https://www.jstor.org/stable/10.1086/209650
+"""
+
+import warnings
+
+import numpy as np
+import pandas as pd
+
+
+def rv_from_stock_zh_a_hist_min_em(
+    symbol="000001",
+    start_date="2021-10-20 09:30:00",
+    end_date="2024-11-01 15:00:00",
+    period="1",
+    adjust="hfq",
+) -> pd.DataFrame:
+    """
+    从东方财富网获取股票的分钟级历史行情数据,并进行数据清洗和格式化为计算 yz 已实现波动率所需的数据格式
+    https://quote.eastmoney.com/concept/sh603777.html?from=classic
+    :param symbol: 股票代码,如"000001"
+    :type symbol: str
+    :param start_date: 开始日期时间,格式"YYYY-MM-DD HH:MM:SS"
+    :type start_date: str
+    :param end_date: 结束日期时间,格式"YYYY-MM-DD HH:MM:SS"
+    :type end_date: str
+    :param period: 时间周期,可选{'1','5','15','30','60'}分钟
+    :type period: str
+    :param adjust: 复权方式,可选{'','qfq'(前复权),'hfq'(后复权)}
+    :type adjust: str
+    :return: 整理后的分钟行情数据,包含Date(索引),Open,High,Low,Close列
+    :rtype: pandas.DataFrame
+    """
+    from akshare.stock_feature.stock_hist_em import stock_zh_a_hist_min_em
+
+    temp_df = stock_zh_a_hist_min_em(
+        symbol=symbol,
+        start_date=start_date,
+        end_date=end_date,
+        period=period,
+        adjust=adjust,
+    )
+    temp_df.rename(
+        columns={
+            "时间": "Date",
+            "开盘": "Open",
+            "最高": "High",
+            "最低": "Low",
+            "收盘": "Close",
+        },
+        inplace=True,
+    )
+    temp_df = temp_df[temp_df["Open"] != 0]
+    temp_df["Date"] = pd.to_datetime(temp_df["Date"])
+    temp_df.set_index(keys="Date", inplace=True)
+    return temp_df
+
+
+def rv_from_futures_zh_minute_sina(
+    symbol: str = "IF2008", period: str = "5"
+) -> pd.DataFrame:
+    """
+    从新浪财经获取期货的分钟级历史行情数据,并进行数据清洗和格式化
+    https://vip.stock.finance.sina.com.cn/quotes_service/view/qihuohangqing.html#titlePos_3
+    :param symbol: 期货合约代码,如"IF2008"代表沪深300期货2020年8月合约
+    :type symbol: str
+    :param period: 时间周期,可选{'1','5','15','30','60'}分钟
+    :type period: str
+    :return: 整理后的分钟行情数据,包含Date(索引),Open,High,Low,Close列
+    :rtype: pandas.DataFrame
+    """
+    from akshare.futures.futures_zh_sina import futures_zh_minute_sina
+
+    temp_df = futures_zh_minute_sina(symbol=symbol, period=period)
+    temp_df.rename(
+        columns={
+            "datetime": "Date",
+            "open": "Open",
+            "high": "High",
+            "low": "Low",
+            "close": "Close",
+        },
+        inplace=True,
+    )
+    temp_df["Date"] = pd.to_datetime(temp_df["Date"])
+    temp_df.set_index(keys="Date", inplace=True)
+    return temp_df
+
+
+def volatility_yz_rv(data: pd.DataFrame) -> pd.DataFrame:
+    """
+    波动率-已实现波动率-Yang-Zhang 已实现波动率(Yang-Zhang Realized Volatility)
+    https://github.com/hugogobato/Yang-Zhang-s-Realized-Volatility-Automated-Estimation-in-Python
+    论文地址：https://www.jstor.org/stable/10.1086/209650
+    基于以下公式计算:
+    RV^2 = Vo + k*Vc + (1-k)*Vrs
+    其中:
+    - Vo: 隔夜波动率, Vo = 1/(n-1)*sum(Oi-Obar)^2
+        Oi为标准化开盘价, Obar为标准化开盘价均值
+    - Vc: 收盘波动率, Vc = 1/(n-1)*sum(ci-Cbar)^2
+        ci为标准化收盘价, Cbar为标准化收盘价均值
+    - k: 权重系数, k = 0.34/(1.34+(n+1)/(n-1))
+        n为样本数量
+    - Vrs: Rogers-Satchell波动率代理, Vrs = ui(ui-ci)+di(di-ci)
+        ui = ln(Hi/Oi), ci = ln(Ci/Oi), di = ln(Li/Oi), oi = ln(Oi/Ci-1)
+        Hi/Li/Ci/Oi分别为最高价/最低价/收盘价/开盘价
+
+    :param data: 包含 OHLC(开高低收) 价格的 pandas.DataFrame
+    :type data: pandas.DataFrame
+    :return: 包含 Yang-Zhang 实现波动率的 pandas.DataFrame
+    :rtype: pandas.DataFrame
+
+    要求输入数据包含以下列:
+    - Open: 开盘价
+    - High: 最高价
+    - Low: 最低价
+    - Close: 收盘价
+    # yang_zhang_rv formula is give as:
+    # RV^2 = Vo + k*Vc + (1-k)*Vrs
+    # where Vo = 1/(n-1)*sum(Oi-Obar)^2
+    # with oi = normalized opening price at time t and Obar = mean of normalized opening prices
+    # Vc = = 1/(n-1)*sum(ci-Cbar)^2
+    # with ci = normalized close price at time t and Cbar = mean of normalized close prices
+    # k = 0.34/(1.34+(n+1)/(n-1))
+    # with n = total number of days or time periods considered
+    # Vrs (Rogers & Satchell RV proxy) = ui(ui-ci)+di(di-ci)
+    # with ui = ln(Hi/Oi), ci = ln(Ci/Oi), di=(Li/Oi), oi = ln(Oi/Ci-1)
+    # where Hi = high price at time t and Li = low price at time t
+    """ ""
+    warnings.filterwarnings("ignore")
+
+    data["ui"] = np.log(np.divide(data["High"][1:], data["Open"][1:]))
+    data["ci"] = np.log(np.divide(data["Close"][1:], data["Open"][1:]))
+    data["di"] = np.log(np.divide(data["Low"][1:], data["Open"][1:]))
+    data["oi"] = np.log(np.divide(data["Open"][1:], data["Close"][: len(data) - 1]))
+    data = data[1:]
+    data["RS"] = data["ui"] * (data["ui"] - data["ci"]) + data["di"] * (
+        data["di"] - data["ci"]
+    )
+    rs_var = data["RS"].groupby(pd.Grouper(freq="1D")).mean().dropna()
+    vc_and_vo = data[["oi", "ci"]].groupby(pd.Grouper(freq="1D")).var().dropna()
+    n = int(len(data) / len(rs_var))
+    k = 0.34 / (1.34 + (n + 1) / (n - 1))
+    yang_zhang_rv = np.sqrt((1 - k) * rs_var + vc_and_vo["oi"] + vc_and_vo["ci"] * k)
+    yang_zhang_rv_df = pd.DataFrame(yang_zhang_rv)
+    yang_zhang_rv_df.rename(columns={0: "yz_rv"}, inplace=True)
+    yang_zhang_rv_df.reset_index(inplace=True)
+    yang_zhang_rv_df.columns = ["date", "rv"]
+    yang_zhang_rv_df["date"] = pd.to_datetime(
+        yang_zhang_rv_df["date"], errors="coerce"
+    ).dt.date
+    return yang_zhang_rv_df
+
+
+if __name__ == "__main__":
+    futures_df = rv_from_futures_zh_minute_sina(symbol="IF2008", period="1")
+    volatility_yz_rv_df = volatility_yz_rv(data=futures_df)
+    print(volatility_yz_rv_df)
+
+    stock_df = rv_from_stock_zh_a_hist_min_em(
+        symbol="000001",
+        start_date="2021-10-20 09:30:00",
+        end_date="2024-11-01 15:00:00",
+        period="5",
+        adjust="",
+    )
+    volatility_yz_rv_df = volatility_yz_rv(data=stock_df)
+    print(volatility_yz_rv_df)

akshare/cost/cost_living.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/1/20 23:30
+Date: 2024/8/28 15:20
 Desc: 世界各大城市生活成本数据
 https://expatistan.com/cost-of-living/index
 """
+
 from io import StringIO
 
 import pandas as pd
@@ -20,14 +21,14 @@ def _get_region() -> dict:
     """
     url = "https://www.expatistan.com/cost-of-living/index"
     r = requests.get(url)
-    soup = BeautifulSoup(r.text, "lxml")
+    soup = BeautifulSoup(r.text, features="lxml")
     half_url_list = [
         item["href"]
-        for item in soup.find("ul", attrs={"class": "regions"}).find_all("a")
+        for item in soup.find(name="ul", attrs={"class": "regions"}).find_all("a")
     ]
     name_list = [
         item["href"].split("/")[-1]
-        for item in soup.find("ul", attrs={"class": "regions"}).find_all("a")
+        for item in soup.find(name="ul", attrs={"class": "regions"}).find_all("a")
     ]
     name_url_dict = dict(zip(name_list, half_url_list))
     name_url_dict["world"] = "/cost-of-living/index"
@@ -38,7 +39,8 @@ def cost_living(symbol: str = "world") -> pd.DataFrame:
     """
     国家或地区生活成本数据
     https://expatistan.com/cost-of-living/index
-    :param symbol: choice of {"europe", "north-america", "latin-america", "asia", "middle-east", "africa", "oceania", "world"}
+    :param symbol: choice of {"europe", "north-america", "latin-america",
+    "asia", "middle-east", "africa", "oceania", "world"}
     :type symbol: str
     :return: 国家或地区生活成本数据
     :rtype: pandas.DataFrame

akshare/currency/currency_safe.py

@@ -1,10 +1,11 @@
 # -*- coding:utf-8 -*-
 # !/usr/bin/env python
 """
-Date: 2023/9/17 17:08
+Date: 2024/4/29 17:00
 Desc: 人民币汇率中间价
 https://www.safe.gov.cn/safe/rmbhlzjj/index.html
 """
+
 import re
 from datetime import datetime
 from io import StringIO
@@ -24,11 +25,11 @@ def currency_boc_safe() -> pd.DataFrame:
     url = "https://www.safe.gov.cn/safe/2020/1218/17833.html"
     r = requests.get(url)
     r.encoding = "utf8"
-    soup = BeautifulSoup(r.text, "lxml")
-    content = soup.find("a", string=re.compile("人民币汇率"))["href"]
+    soup = BeautifulSoup(r.text, features="lxml")
+    content = soup.find(name="a", string=re.compile("人民币汇率"))["href"]
     url = f"https://www.safe.gov.cn{content}"
     temp_df = pd.read_excel(url)
-    temp_df.sort_values(["日期"], inplace=True)
+    temp_df.sort_values(by=["日期"], inplace=True)
     temp_df.reset_index(inplace=True, drop=True)
     start_date = (
         (pd.Timestamp(temp_df["日期"].tolist()[-1]) + pd.Timedelta(days=1))
@@ -44,9 +45,9 @@ def currency_boc_safe() -> pd.DataFrame:
     }
     r = requests.post(url, data=payload)
     current_temp_df = pd.read_html(StringIO(r.text))[-1]
-    current_temp_df.sort_values(["日期"], inplace=True)
+    current_temp_df.sort_values(by=["日期"], inplace=True)
     current_temp_df.reset_index(inplace=True, drop=True)
-    big_df = pd.concat([temp_df, current_temp_df], ignore_index=True)
+    big_df = pd.concat(objs=[temp_df, current_temp_df], ignore_index=True)
     column_name_list = big_df.columns[1:]
     for item in column_name_list:
         big_df[item] = pd.to_numeric(big_df[item], errors="coerce")

akshare/data/cninfo.js

@@ -5998,4 +5998,19 @@ function my_decode(data) {
         }
     );
     return encrypted.toString(CryptoJS.enc.Utf8);
+}
+
+function new_my_decode(data) {
+    let key = CryptoJS.enc.Utf8.parse('bieyanjiulexixishuibatoufameill1'); // 密钥需要是32字节，这里可能需要调整
+    let iv = CryptoJS.enc.Utf8.parse('nengnongchulainbl1'); // 向量通常是16字节
+    let decrypted = CryptoJS.AES.decrypt(
+        data,
+        key,
+        {
+            iv: iv,
+            mode: CryptoJS.mode.CBC,
+            padding: CryptoJS.pad.Pkcs7
+        }
+    );
+    return decrypted.toString(CryptoJS.enc.Utf8);
 }