akshare 1.12.95__py3-none-any.whl → 1.15.72__py3-none-any.whl

akshare/index/index_cflp.py

@@ -5,11 +5,12 @@ Date: 2021/12/27 15:47
 Desc: 中国公路物流运价、运量指数
 http://index.0256.cn/expx.htm
 """
+
 import pandas as pd
 import requests
 
 
-def index_cflp_price(symbol: str = "周指数") -> pd.DataFrame:
+def index_price_cflp(symbol: str = "周指数") -> pd.DataFrame:
     """
     中国公路物流运价指数
     http://index.0256.cn/expx.htm
@@ -38,7 +39,8 @@ def index_cflp_price(symbol: str = "周指数") -> pd.DataFrame:
     headers = {
         "Origin": "http://index.0256.cn",
         "Referer": "http://index.0256.cn/expx.htm",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/90.0.4430.212 Safari/537.36",
     }
     r = requests.post(url, data=params, headers=headers)
     data_json = r.json()
@@ -51,14 +53,14 @@ def index_cflp_price(symbol: str = "周指数") -> pd.DataFrame:
         ]
     ).T
     temp_df.columns = ["日期", "定基指数", "环比指数", "同比指数"]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"]).dt.date
-    temp_df["定基指数"] = pd.to_numeric(temp_df["定基指数"])
-    temp_df["环比指数"] = pd.to_numeric(temp_df["环比指数"])
-    temp_df["同比指数"] = pd.to_numeric(temp_df["同比指数"])
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["定基指数"] = pd.to_numeric(temp_df["定基指数"], errors="coerce")
+    temp_df["环比指数"] = pd.to_numeric(temp_df["环比指数"], errors="coerce")
+    temp_df["同比指数"] = pd.to_numeric(temp_df["同比指数"], errors="coerce")
     return temp_df
 
 
-def index_cflp_volume(symbol: str = "月指数") -> pd.DataFrame:
+def index_volume_cflp(symbol: str = "月指数") -> pd.DataFrame:
     """
     中国公路物流运量指数
     http://index.0256.cn/expx.htm
@@ -86,7 +88,8 @@ def index_cflp_volume(symbol: str = "月指数") -> pd.DataFrame:
     headers = {
         "Origin": "http://index.0256.cn",
         "Referer": "http://index.0256.cn/expx.htm",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/90.0.4430.212 Safari/537.36",
     }
     r = requests.post(url, data=params, headers=headers)
     data_json = r.json()
@@ -99,31 +102,31 @@ def index_cflp_volume(symbol: str = "月指数") -> pd.DataFrame:
         ]
     ).T
     temp_df.columns = ["日期", "定基指数", "环比指数", "同比指数"]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"]).dt.date
-    temp_df["定基指数"] = pd.to_numeric(temp_df["定基指数"])
-    temp_df["环比指数"] = pd.to_numeric(temp_df["环比指数"])
-    temp_df["同比指数"] = pd.to_numeric(temp_df["同比指数"])
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["定基指数"] = pd.to_numeric(temp_df["定基指数"], errors="coerce")
+    temp_df["环比指数"] = pd.to_numeric(temp_df["环比指数"], errors="coerce")
+    temp_df["同比指数"] = pd.to_numeric(temp_df["同比指数"], errors="coerce")
     return temp_df
 
 
 if __name__ == "__main__":
-    index_cflp_price_df = index_cflp_price(symbol="周指数")
-    print(index_cflp_price_df)
+    index_price_cflp_df = index_price_cflp(symbol="周指数")
+    print(index_price_cflp_df)
 
-    index_cflp_price_df = index_cflp_price(symbol="月指数")
-    print(index_cflp_price_df)
+    index_price_cflp_df = index_price_cflp(symbol="月指数")
+    print(index_price_cflp_df)
 
-    index_cflp_price_df = index_cflp_price(symbol="季度指数")
-    print(index_cflp_price_df)
+    index_price_cflp_df = index_price_cflp(symbol="季度指数")
+    print(index_price_cflp_df)
 
-    index_cflp_price_df = index_cflp_price(symbol="年度指数")
-    print(index_cflp_price_df)
+    index_price_cflp_df = index_price_cflp(symbol="年度指数")
+    print(index_price_cflp_df)
 
-    index_cflp_volume_df = index_cflp_volume(symbol="月指数")
-    print(index_cflp_volume_df)
+    index_volume_cflp_df = index_volume_cflp(symbol="月指数")
+    print(index_volume_cflp_df)
 
-    index_cflp_volume_df = index_cflp_volume(symbol="季度指数")
-    print(index_cflp_volume_df)
+    index_volume_cflp_df = index_volume_cflp(symbol="季度指数")
+    print(index_volume_cflp_df)
 
-    index_cflp_volume_df = index_cflp_volume(symbol="年度指数")
-    print(index_cflp_volume_df)
+    index_volume_cflp_df = index_volume_cflp(symbol="年度指数")
+    print(index_volume_cflp_df)

akshare/index/index_cni.py

@@ -5,6 +5,7 @@ Date: 2024/1/14 18:00
 Desc: 国证指数
 http://www.cnindex.com.cn/index.html
 """
+
 import zipfile
 from io import BytesIO
 
@@ -68,14 +69,16 @@ def index_all_cni() -> pd.DataFrame:
             "自由流通市值",
         ]
     ]
-    temp_df['成交量'] = temp_df['成交量'] / 100000
-    temp_df['成交额'] = temp_df['成交额'] / 100000000
-    temp_df['总市值'] = temp_df['总市值'] / 100000000
-    temp_df['自由流通市值'] = temp_df['自由流通市值'] / 100000000
+    temp_df["成交量"] = temp_df["成交量"] / 100000
+    temp_df["成交额"] = temp_df["成交额"] / 100000000
+    temp_df["总市值"] = temp_df["总市值"] / 100000000
+    temp_df["自由流通市值"] = temp_df["自由流通市值"] / 100000000
     return temp_df
 
 
-def index_hist_cni(symbol: str = "399001", start_date: str = "20230114", end_date: str = "20240114") -> pd.DataFrame:
+def index_hist_cni(
+    symbol: str = "399001", start_date: str = "20230114", end_date: str = "20240114"
+) -> pd.DataFrame:
     """
     指数历史行情数据
     http://www.cnindex.com.cn/module/index-detail.html?act_menu=1&indexCode=399001
@@ -128,19 +131,19 @@ def index_hist_cni(symbol: str = "399001", start_date: str = "20230114", end_dat
     temp_df["涨跌幅"] = temp_df["涨跌幅"].str.replace("%", "")
     temp_df["涨跌幅"] = temp_df["涨跌幅"].astype("float")
     temp_df["涨跌幅"] = temp_df["涨跌幅"] / 100
-    temp_df.sort_values(['日期'], inplace=True, ignore_index=True)
-    temp_df['日期'] = pd.to_datetime(temp_df['日期'], errors="coerce").dt.date
-    temp_df['开盘价'] = pd.to_numeric(temp_df['开盘价'], errors="coerce")
-    temp_df['最高价'] = pd.to_numeric(temp_df['最高价'], errors="coerce")
-    temp_df['最低价'] = pd.to_numeric(temp_df['最低价'], errors="coerce")
-    temp_df['收盘价'] = pd.to_numeric(temp_df['收盘价'], errors="coerce")
-    temp_df['涨跌幅'] = pd.to_numeric(temp_df['涨跌幅'], errors="coerce")
-    temp_df['成交量'] = pd.to_numeric(temp_df['成交量'], errors="coerce")
-    temp_df['成交额'] = pd.to_numeric(temp_df['成交额'], errors="coerce")
+    temp_df.sort_values(["日期"], inplace=True, ignore_index=True)
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["开盘价"] = pd.to_numeric(temp_df["开盘价"], errors="coerce")
+    temp_df["最高价"] = pd.to_numeric(temp_df["最高价"], errors="coerce")
+    temp_df["最低价"] = pd.to_numeric(temp_df["最低价"], errors="coerce")
+    temp_df["收盘价"] = pd.to_numeric(temp_df["收盘价"], errors="coerce")
+    temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"], errors="coerce")
+    temp_df["成交量"] = pd.to_numeric(temp_df["成交量"], errors="coerce")
+    temp_df["成交额"] = pd.to_numeric(temp_df["成交额"], errors="coerce")
     return temp_df
 
 
-def index_detail_cni(symbol: str = '399005', date: str = '202011') -> pd.DataFrame:
+def index_detail_cni(symbol: str = "399001", date: str = "202404") -> pd.DataFrame:
     """
     国证指数-样本详情-指定日期的样本成份
     http://www.cnindex.com.cn/module/index-detail.html?act_menu=1&indexCode=399001
@@ -151,97 +154,88 @@ def index_detail_cni(symbol: str = '399005', date: str = '202011') -> pd.DataFra
     :return: 指定日期的样本成份
     :rtype: pandas.DataFrame
     """
-    url = 'http://www.cnindex.com.cn/sample-detail/download'
-    params = {
-        'indexcode': symbol,
-        'dateStr': '-'.join([date[:4], date[4:]])
-    }
+    url = "http://www.cnindex.com.cn/sample-detail/download"
+    params = {"indexcode": symbol, "dateStr": "-".join([date[:4], date[4:]])}
     r = requests.get(url, params=params)
     temp_df = pd.read_excel(BytesIO(r.content))
-    temp_df['样本代码'] = temp_df['样本代码'].astype(str).str.zfill(6)
+    temp_df["样本代码"] = temp_df["样本代码"].astype(str).str.zfill(6)
     temp_df.columns = [
-        '日期',
-        '样本代码',
-        '样本简称',
-        '所属行业',
-        '自由流通市值',
-        '总市值',
-        '权重',
+        "日期",
+        "样本代码",
+        "样本简称",
+        "所属行业",
+        "总市值",
+        "权重",
     ]
-    temp_df['自由流通市值'] = pd.to_numeric(temp_df['自由流通市值'], errors="coerce")
-    temp_df['总市值'] = pd.to_numeric(temp_df['总市值'], errors="coerce")
-    temp_df['权重'] = pd.to_numeric(temp_df['权重'], errors="coerce")
+    temp_df["总市值"] = pd.to_numeric(temp_df["总市值"], errors="coerce")
+    temp_df["权重"] = pd.to_numeric(temp_df["权重"], errors="coerce")
     return temp_df
 
 
-def index_detail_hist_cni(symbol: str = '399001', date: str = "") -> pd.DataFrame:
+def index_detail_hist_cni(symbol: str = "399001", date: str = "") -> pd.DataFrame:
     """
     国证指数-样本详情-历史样本
     http://www.cnindex.com.cn/module/index-detail.html?act_menu=1&indexCode=399001
-    :param date: 指数代码
-    :type date: str
-    :param symbol: 指数代码
+    :param symbol: 指数代码; "399001"
     :type symbol: str
+    :param date: 指定月份; "202201", 为空返回所有数据
+    :type date: str
     :return: 历史样本
     :rtype: pandas.DataFrame
     """
     if date:
-        url = 'http://www.cnindex.com.cn/sample-detail/detail'
+        url = "http://www.cnindex.com.cn/sample-detail/detail"
         params = {
-            'indexcode': symbol,
-            'dateStr': '-'.join([date[:4], date[4:]]),
-            'pageNum': '1',
-            'rows': '50000',
+            "indexcode": symbol,
+            "dateStr": "-".join([date[:4], date[4:]]),
+            "pageNum": "1",
+            "rows": "50000",
         }
         r = requests.get(url, params=params)
         data_json = r.json()
-        temp_df = pd.DataFrame(data_json['data']['rows'])
+        temp_df = pd.DataFrame(data_json["data"]["rows"])
         temp_df.columns = [
-            '-',
-            '-',
-            '日期',
-            '样本代码',
-            '样本简称',
-            '所属行业',
-            '-',
-            '自由流通市值',
-            '总市值',
-            '权重',
-            '-',
+            "-",
+            "-",
+            "日期",
+            "样本代码",
+            "样本简称",
+            "所属行业",
+            "-",
+            "总市值",
+            "权重",
+            "-",
+        ]
+        temp_df = temp_df[
+            [
+                "日期",
+                "样本代码",
+                "样本简称",
+                "所属行业",
+                "总市值",
+                "权重",
+            ]
         ]
-        temp_df = temp_df[[
-            '日期',
-            '样本代码',
-            '样本简称',
-            '所属行业',
-            '自由流通市值',
-            '总市值',
-            '权重',
-        ]]
     else:
-        url = 'http://www.cnindex.com.cn/sample-detail/download-history'
-        params = {
-            'indexcode': symbol
-        }
+        url = "http://www.cnindex.com.cn/sample-detail/download-history"
+        params = {"indexcode": symbol}
         r = requests.get(url, params=params)
         temp_df = pd.read_excel(BytesIO(r.content))
-    temp_df['样本代码'] = temp_df['样本代码'].astype(str).str.zfill(6)
+    temp_df["样本代码"] = temp_df["样本代码"].astype(str).str.zfill(6)
     temp_df.columns = [
-        '日期',
-        '样本代码',
-        '样本简称',
-        '所属行业',
-        '自由流通市值',
-        '总市值',
-        '权重',
+        "日期",
+        "样本代码",
+        "样本简称",
+        "所属行业",
+        "总市值",
+        "权重",
     ]
-    temp_df['自由流通市值'] = pd.to_numeric(temp_df['自由流通市值'])
-    temp_df['总市值'] = pd.to_numeric(temp_df['总市值'])
-    temp_df['权重'] = pd.to_numeric(temp_df['权重'])
+    temp_df["总市值"] = pd.to_numeric(temp_df["总市值"])
+    temp_df["权重"] = pd.to_numeric(temp_df["权重"])
     return temp_df
 
 
-def index_detail_hist_adjust_cni(symbol: str = '399005') -> pd.DataFrame:
+def index_detail_hist_adjust_cni(symbol: str = "399005") -> pd.DataFrame:
     """
     国证指数-样本详情-历史调样
     http://www.cnindex.com.cn/module/index-detail.html?act_menu=1&indexCode=399005
@@ -250,16 +244,18 @@ def index_detail_hist_adjust_cni(symbol: str = '399005') -> pd.DataFrame:
     :return: 历史调样
     :rtype: pandas.DataFrame
     """
-    url = 'http://www.cnindex.com.cn/sample-detail/download-adjustment'
-    params = {
-        'indexcode': symbol
-    }
+    url = "http://www.cnindex.com.cn/sample-detail/download-adjustment"
+    params = {"indexcode": symbol}
     r = requests.get(url, params=params)
     try:
-        temp_df = pd.read_excel(BytesIO(r.content), engine="openpyxl")
-    except zipfile.BadZipFile as e:
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter(action="ignore", category=UserWarning)
+            temp_df = pd.read_excel(BytesIO(r.content), engine="openpyxl")
+    except zipfile.BadZipFile:
         return pd.DataFrame()
-    temp_df['样本代码'] = temp_df['样本代码'].astype(str).str.zfill(6)
+    temp_df["样本代码"] = temp_df["样本代码"].astype(str).str.zfill(6)
     return temp_df
 
 
@@ -267,14 +263,16 @@ if __name__ == "__main__":
     index_all_cni_df = index_all_cni()
     print(index_all_cni_df)
 
-    index_hist_cni_df = index_hist_cni(symbol="399005", start_date="20230114", end_date="20240114")
+    index_hist_cni_df = index_hist_cni(
+        symbol="399005", start_date="20230114", end_date="20240114"
+    )
     print(index_hist_cni_df)
 
-    index_detail_cni_df = index_detail_cni(symbol='399001', date='202011')
+    index_detail_cni_df = index_detail_cni(symbol="399001", date="202404")
     print(index_detail_cni_df)
 
-    index_detail_hist_cni_df = index_detail_hist_cni(symbol='399005', date='202201')
+    index_detail_hist_cni_df = index_detail_hist_cni(symbol="399101", date="202404")
     print(index_detail_hist_cni_df)
 
-    index_detail_hist_adjust_cni_df = index_detail_hist_adjust_cni(symbol='399005')
+    index_detail_hist_adjust_cni_df = index_detail_hist_adjust_cni(symbol="399005")
     print(index_detail_hist_adjust_cni_df)

akshare/index/index_cons.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/1/5 17:00
+Date: 2024/6/17 14:00
 Desc: 股票指数成份股数据, 新浪有两个接口, 这里使用老接口:
 新接口：https://vip.stock.finance.sina.com.cn/mkt/#zhishu_000001
 老接口：https://vip.stock.finance.sina.com.cn/corp/view/vII_NewestComponent.php?page=1&indexid=399639
 """
+
 import math
 from io import BytesIO, StringIO
 
@@ -27,7 +28,10 @@ def index_stock_cons_sina(symbol: str = "000300") -> pd.DataFrame:
     """
     if symbol == "000300":
         symbol = "hs300"
-        url = "https://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php/Market_Center.getHQNodeStockCountSimple"
+        url = (
+            "https://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php"
+            "/Market_Center.getHQNodeStockCountSimple"
+        )
         params = {"node": f"{symbol}"}
         r = requests.get(url, params=params)
         page_num = math.ceil(int(r.json()) / 80) + 1
@@ -45,7 +49,7 @@ def index_stock_cons_sina(symbol: str = "000300") -> pd.DataFrame:
             }
             r = requests.get(url, params=params)
             temp_df = pd.concat(
-                [temp_df, pd.DataFrame(demjson.decode(r.text))], ignore_index=True
+                objs=[temp_df, pd.DataFrame(demjson.decode(r.text))], ignore_index=True
             )
         return temp_df
 
@@ -59,7 +63,8 @@ def index_stock_cons_sina(symbol: str = "000300") -> pd.DataFrame:
         "_s_r_a": "setlen",
     }
     r = requests.get(url, params=params)
-    return pd.DataFrame(demjson.decode(r.text))
+    temp = pd.DataFrame(demjson.decode(r.text))
+    return temp
 
 
 def index_stock_info() -> pd.DataFrame:
@@ -110,7 +115,8 @@ def index_stock_cons(symbol: str = "399639") -> pd.DataFrame:
         r = requests.get(url)
         r.encoding = "gb2312"
         temp_df = pd.concat(
-            [temp_df, pd.read_html(StringIO(r.text), header=1)[3]], ignore_index=True
+            objs=[temp_df, pd.read_html(StringIO(r.text), header=1)[3]],
+            ignore_index=True,
         )
     temp_df = temp_df.iloc[:, :3]
     temp_df["品种代码"] = temp_df["品种代码"].astype(str).str.zfill(6)
@@ -126,7 +132,10 @@ def index_stock_cons_csindex(symbol: str = "000300") -> pd.DataFrame:
     :return: 最新指数的成份股
     :rtype: pandas.DataFrame
     """
-    url = f"https://csi-web-dev.oss-cn-shanghai-finance-1-pub.aliyuncs.com/static/html/csindex/public/uploads/file/autofile/cons/{symbol}cons.xls"
+    url = (
+        f"https://oss-ch.csindex.com.cn/static/"
+        f"html/csindex/public/uploads/file/autofile/cons/{symbol}cons.xls"
+    )
     r = requests.get(url)
     temp_df = pd.read_excel(BytesIO(r.content))
     temp_df.columns = [
@@ -140,7 +149,9 @@ def index_stock_cons_csindex(symbol: str = "000300") -> pd.DataFrame:
         "交易所",
         "交易所英文名称",
     ]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"], format="%Y%m%d").dt.date
+    temp_df["日期"] = pd.to_datetime(
+        temp_df["日期"], format="%Y%m%d", errors="coerce"
+    ).dt.date
     temp_df["指数代码"] = temp_df["指数代码"].astype(str).str.zfill(6)
     temp_df["成分券代码"] = temp_df["成分券代码"].astype(str).str.zfill(6)
     return temp_df
@@ -155,7 +166,10 @@ def index_stock_cons_weight_csindex(symbol: str = "000300") -> pd.DataFrame:
     :return: 最新指数的成份股权重
     :rtype: pandas.DataFrame
     """
-    url = f"https://csi-web-dev.oss-cn-shanghai-finance-1-pub.aliyuncs.com/static/html/csindex/public/uploads/file/autofile/closeweight/{symbol}closeweight.xls"
+    url = (
+        f"https://oss-ch.csindex.com.cn/static/html/csindex/"
+        f"public/uploads/file/autofile/closeweight/{symbol}closeweight.xls"
+    )
     r = requests.get(url)
     temp_df = pd.read_excel(BytesIO(r.content))
     temp_df.columns = [
@@ -170,10 +184,12 @@ def index_stock_cons_weight_csindex(symbol: str = "000300") -> pd.DataFrame:
         "交易所英文名称",
         "权重",
     ]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"], format="%Y%m%d").dt.date
+    temp_df["日期"] = pd.to_datetime(
+        temp_df["日期"], format="%Y%m%d", errors="coerce"
+    ).dt.date
     temp_df["指数代码"] = temp_df["指数代码"].astype(str).str.zfill(6)
     temp_df["成分券代码"] = temp_df["成分券代码"].astype(str).str.zfill(6)
-    temp_df["权重"] = pd.to_numeric(temp_df["权重"])
+    temp_df["权重"] = pd.to_numeric(temp_df["权重"], errors="coerce")
     return temp_df