akshare 1.13.46__py3-none-any.whl → 1.17.99__py3-none-any.whl

akshare/futures/cot.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/11/15 19:30
+Date: 2025/7/21 15:00
 Desc: 期货-中国-交易所-会员持仓数据接口
 大连商品交易所、上海期货交易所、郑州商品交易所、中国金融期货交易所、广州期货交易所
 采集前 20 会员持仓数据;
@@ -69,7 +69,8 @@ def get_rank_sum_daily(
     :type end_day: str
     :param vars_list: 合约品种如 ['RB'、'AL'] 等列表为空时为所有商品
     :type vars_list: list
-    :return: pd.DataFrame
+    :return:  会员持仓排名数据
+    :rtype: pandas.DataFrame
     symbol                           标的合约                     string
     var                              商品品种                     string
     vol_top5                         成交量前5会员成交量总和         int
@@ -98,7 +99,7 @@ def get_rank_sum_daily(
                     f"{start_day.strftime('%Y-%m-%d')}日交易所数据连接失败，已超过20次，您的地址被网站墙了，请保存好返回数据，稍后从该日期起重试"
                 )
                 return records.reset_index(drop=True)
-            records = pd.concat([records, data], ignore_index=True)
+            records = pd.concat(objs=[records, data], ignore_index=True)
         else:
             warnings.warn(f"{start_day.strftime('%Y%m%d')}非交易日")
         start_day += datetime.timedelta(days=1)
@@ -116,7 +117,8 @@ def get_rank_sum(date: str = "20210525", vars_list: list = cons.contract_symbols
     :type date: date
     :param vars_list: 合约品种如 ['RB', 'AL'] 等列表为空时为所有商品
     :type vars_list: list
-    :return: pd.DataFrame
+    :return: 持仓排名数据
+    :rtype: pandas.DataFrame
     symbol                           标的合约                     string
     var                              商品品种                     string
     vol_top5                         成交量前5会员成交量总和         int
@@ -148,7 +150,7 @@ def get_rank_sum(date: str = "20210525", vars_list: list = cons.contract_symbols
             return False
         big_dict.update(data)
     if len(czce_var) > 0:
-        data = get_czce_rank_table(date)
+        data = get_rank_table_czce(date)
         if data is False:
             return False
         big_dict.update(data)
@@ -276,7 +278,7 @@ def get_shfe_rank_table(
     """
     上海期货交易所会员成交及持仓排名表
     https://www.shfe.com.cn/
-    https://www.shfe.com.cn/statements/dataview.html?paramid=kx
+    https://tsite.shfe.com.cn/statements/dataview.html?paramid=kx
     注：该交易所只公布每个品种内部的标的排名，没有公布品种的总排名
     数据从 20020107 开始，每交易日 16:30 左右更新数据
     :param date: 交易日
@@ -300,14 +302,14 @@ def get_shfe_rank_table(
     date                        日期                        string YYYYMMDD
     """
     date = cons.convert_date(date) if date is not None else datetime.date.today()
-    if date < datetime.date(2002, 1, 7):
-        print("shfe数据源开始日期为20020107，跳过")
+    if date < datetime.date(year=2002, month=1, day=7):
+        print("shfe数据源开始日期为 20020107，跳过")
         return {}
     if date.strftime("%Y%m%d") not in calendar:
         warnings.warn("%s非交易日" % date.strftime("%Y%m%d"))
         return {}
-    url = cons.SHFE_VOL_RANK_URL % (date.strftime("%Y%m%d"))
-    r = requests_link(url, "utf-8", headers=cons.shfe_headers)
+    url = cons.SHFE_VOL_RANK_URL_20250701 % (date.strftime("%Y%m%d"))
+    r = requests_link(url, encoding="utf-8", headers=cons.shfe_headers)
     try:
         context = json.loads(r.text)
     except:  # noqa: E722
@@ -403,12 +405,15 @@ def _czce_df_read(url, skip_rows, encoding="utf-8", header=0):
     return data
 
 
-def get_czce_rank_table(date: str = "20210428") -> dict:
+def get_rank_table_czce(date: str = "20251103") -> dict:
     """
     郑州商品交易所前 20 会员持仓排名数据明细
+    https://www.czce.com.cn/cn/jysj/ccpm/H077003004index_1.htm
     注：该交易所既公布了品种排名, 也公布了标的排名
     :param date: 日期 format：YYYY-MM-DD 或 YYYYMMDD 或 datetime.date对象 为空时为当天
-    :return: pd.DataFrame
+    :return: 持仓排名数据明细
+    :rtype: pandas.DataFrame
+    返回值格式
     rank                        排名                        int
     vol_party_name              成交量排序的当前名次会员        string(中文)
     vol                         该会员成交量                  int
@@ -435,13 +440,18 @@ def get_czce_rank_table(date: str = "20210428") -> dict:
     if date.strftime("%Y%m%d") not in calendar:
         warnings.warn("%s非交易日" % date.strftime("%Y%m%d"))
         return {}
-    if date >= datetime.date(2015, 10, 8):
+    if date > datetime.date(year=2025, month=11, day=1):
+        url = (
+            f"http://www.czce.com.cn/cn/DFSStaticFiles/Future/{date.year}/"
+            f"{date.isoformat().replace('-', '')}/FutureDataHolding.xlsx"
+        )
+    else:
         url = (
             f"http://www.czce.com.cn/cn/DFSStaticFiles/Future/{date.year}/"
             f"{date.isoformat().replace('-', '')}/FutureDataHolding.xls"
         )
-        r = requests.get(url, headers=headers)
-        temp_df = pd.read_excel(BytesIO(r.content))
+    r = requests.get(url, headers=headers)
+    temp_df = pd.read_excel(BytesIO(r.content))
 
     temp_pinzhong_index = [
         item + 1
@@ -509,7 +519,7 @@ def _get_dce_contract_list(date, var):
     :param var: 合约品种
     :return: list 公布了持仓排名的合约列表
     """
-    url = "http://www.dce.com.cn/publicweb/quotesdata/memberDealPosiQuotes.html"
+    url = "http://portal.dce.com.cn/publicweb/quotesdata/memberDealPosiQuotes.html"
     headers = {
         "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;"
         "q=0.8,application/signed-exchange;v=b3;q=0.9",
@@ -518,7 +528,7 @@ def _get_dce_contract_list(date, var):
         "Cache-Control": "no-cache",
         "Connection": "close",
         "Host": "www.dce.com.cn",
-        "Origin": "http://www.dce.com.cn",
+        "Origin": "http://portal.dce.com.cn",
         "Pragma": "no-cache",
         "Upgrade-Insecure-Requests": "1",
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
@@ -559,7 +569,10 @@ def get_dce_rank_table(date: str = "20230706", vars_list=cons.contract_symbols)
     注: 该交易所只公布标的合约排名
     :param date: 日期 format：YYYY-MM-DD 或 YYYYMMDD 或 datetime.date 对象, 为空时为当天
     :param vars_list: 合约品种如 RB、AL 等列表为空时为所有商品, 数据从 20060104 开始，每交易日 16:30 左右更新数据
-    :return: pandas.DataFrame
+    :return: 持仓排名
+    :rtype: pandas.DataFrame
+
+    返回值格式
     rank                        排名                        int
     vol_party_name              成交量排序的当前名次会员      string(中文)
     vol                         该会员成交量                 int
@@ -642,7 +655,7 @@ def get_dce_rank_table(date: str = "20230706", vars_list=cons.contract_symbols)
                 ].astype(float)
                 big_dict[symbol] = temp_df
             except:  # noqa: E722
-                temp_url = "http://www.dce.com.cn/publicweb/quotesdata/memberDealPosiQuotes.html"
+                temp_url = "http://portal.dce.com.cn/publicweb/quotesdata/memberDealPosiQuotes.html"
                 payload = {
                     "memberDealPosiQuotes.variety": var.lower(),
                     "memberDealPosiQuotes.trade_type": "0",
@@ -707,7 +720,9 @@ def get_cffex_rank_table(date: str = "20190805", vars_list=cons.contract_symbols
     注：该交易所既公布品种排名，也公布标的排名
     :param date: 日期 format：YYYY-MM-DD 或 YYYYMMDD 或 datetime.date对象 为空时为当天
     :param vars_list: 合约品种如RB、AL等列表 为空时为所有商品, 数据从20100416开始，每交易日16:30左右更新数据
-    :return: pd.DataFrame
+    :return: 持仓排名
+    :rtype: pandas.DataFrame
+    :rfield:
     rank                        排名                        int
     vol_party_name              成交量排序的当前名次会员        string(中文)
     vol                         该会员成交量                  int
@@ -721,6 +736,7 @@ def get_cffex_rank_table(date: str = "20190805", vars_list=cons.contract_symbols
     symbol                      标的合约                     string
     var                         品种                        string
     date                        日期                        string YYYYMMDD
+
     """
     vars_list = [i for i in vars_list if i in cons.market_exchange_symbols["cffex"]]
     date = cons.convert_date(date) if date is not None else datetime.date.today()
@@ -816,43 +832,26 @@ def futures_dce_position_rank(
     if date.strftime("%Y%m%d") not in calendar:
         warnings.warn("%s非交易日" % date.strftime("%Y%m%d"))
         return {}
-    url = "http://www.dce.com.cn/publicweb/quotesdata/exportMemberDealPosiQuotesBatchData.html"
-    headers = {
-        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;"
-        "q=0.8,application/signed-exchange;v=b3;q=0.9",
-        "Accept-Encoding": "gzip, deflate",
-        "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
-        "Cache-Control": "no-cache",
-        "Connection": "keep-alive",
-        "Content-Length": "160",
-        "Content-Type": "application/x-www-form-urlencoded",
-        "Host": "www.dce.com.cn",
-        "Origin": "http://www.dce.com.cn",
-        "Pragma": "no-cache",
-        "Referer": "http://www.dce.com.cn/publicweb/quotesdata/memberDealPosiQuotes.html",
-        "Upgrade-Insecure-Requests": "1",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
-        "Chrome/81.0.4044.138 Safari/537.36",
-    }
+    date_str = date.strftime("%Y%m%d")
+    url = "http://www.dce.com.cn/dcereport/publicweb/dailystat/memberDealPosi/batchDownload"
     payload = {
-        "memberDealPosiQuotes.variety": "a",
-        "memberDealPosiQuotes.trade_type": "0",
-        "contract.contract_id": "a2009",
-        "contract.variety_id": "a",
-        "year": date.year,
-        "month": date.month - 1,
-        "day": str(date.day).zfill(2),
-        "batchExportFlag": "batch",
+        "tradeDate": date_str,
+        "varietyId": "a",
+        "contractId": "a2601",
+        "tradeType": "1",
+        "lang": "zh",
     }
-    r = requests.post(url, payload, headers=headers)
+    r = requests.post(url, json=payload)
     big_dict = dict()
-    with zipfile.ZipFile(BytesIO(r.content), "r") as z:
+    with zipfile.ZipFile(BytesIO(r.content), mode="r") as z:
         for i in z.namelist():
-            file_name = i.encode("cp437").decode("GBK")
-            if not file_name.startswith(date.strftime("%Y%m%d")):
+            file_name = i
+            if not file_name.startswith(date_str):
                 continue
             try:
-                data = pd.read_table(z.open(i), header=None, sep="\t").iloc[:-6]
+                data = pd.read_table(z.open(i), header=None, sep="\t")
+                if sum(data.iloc[:, 0].str.find("会员类别") == 0) > 0:
+                    data = data.iloc[:-6]
                 if len(data) < 12:  # 处理没有活跃合约的情况
                     big_dict[file_name.split("_")[1]] = pd.DataFrame()
                     continue
@@ -869,12 +868,14 @@ def futures_dce_position_rank(
                 ]
                 data.reset_index(inplace=True, drop=True)
                 start_list = data[data.iloc[:, 0].str.find("名次") == 0].index.tolist()
-                end_list = data[data.iloc[:, 0].str.find("总计") == 0].index.tolist()
+                end_list = data[
+                    data.iloc[:, 0].str.contains(r"(?:总计|合计)", na=False)
+                ].index.tolist()
                 part_one = data[start_list[0] : end_list[0]].iloc[1:, :]
                 part_two = data[start_list[1] : end_list[1]].iloc[1:, :]
                 part_three = data[start_list[2] : end_list[2]].iloc[1:, :]
                 temp_df = pd.concat(
-                    [
+                    objs=[
                         part_one.reset_index(drop=True),
                         part_two.reset_index(drop=True),
                         part_three.reset_index(drop=True),
@@ -1073,7 +1074,7 @@ def futures_dce_position_rank_other(date: str = "20160104"):
         "contract": "",
     }
     r = requests.post(url, data=payload)
-    soup = BeautifulSoup(r.text, "lxml")
+    soup = BeautifulSoup(r.text, features="lxml")
     symbol_list = [
         item["onclick"].strip("javascript:setVariety(").strip("');")
         for item in soup.find_all(attrs={"class": "selBox"})[-3].find_all("input")
@@ -1091,7 +1092,7 @@ def futures_dce_position_rank_other(date: str = "20160104"):
             "contract": "",
         }
         r = requests.post(url, data=payload)
-        soup = BeautifulSoup(r.text, "lxml")
+        soup = BeautifulSoup(r.text, features="lxml")
         contract_list = [
             item["onclick"].strip("javascript:setContract_id('").strip("');")
             for item in soup.find_all(attrs={"name": "contract"})
@@ -1167,7 +1168,7 @@ def __futures_gfex_vars_list() -> list:
     return var_list
 
 
-def __futures_gfex_contract_list(symbol: str = "si", date: str = "20231113") -> list:
+def __futures_gfex_contract_list(symbol: str = "si", date: str = "20240729") -> list:
     """
     广州期货交易所-合约具体名称列表
     http://www.gfex.com.cn/gfex/rcjccpm/hqsj_tjsj.shtml
@@ -1190,6 +1191,8 @@ def __futures_gfex_contract_list(symbol: str = "si", date: str = "20231113") ->
     r = requests.post(url=url, data=payload, headers=headers)
     data_json = r.json()
     temp_df = pd.DataFrame(data_json["data"])
+    if temp_df.empty:
+        return []
     contract_list = temp_df.iloc[:, 0].tolist()
     return contract_list
 
@@ -1313,7 +1316,7 @@ def futures_gfex_position_rank(date: str = "20231113", vars_list: list = None):
                 symbol=item.lower(), date=date
             )
         except:  # noqa: E722
-            return pd.DataFrame()
+            return big_dict
         for name in futures_contract_list:
             try:
                 temp_df = __futures_gfex_contract_data(
@@ -1321,60 +1324,58 @@ def futures_gfex_position_rank(date: str = "20231113", vars_list: list = None):
                 )
                 big_dict[name] = temp_df
             except:  # noqa: E722
-                return pd.DataFrame()
+                return big_dict
     return big_dict
 
 
 if __name__ == "__main__":
     # 郑州商品交易所
-    get_czce_rank_table_first_df = get_czce_rank_table(date="20230109")
-    print(get_czce_rank_table_first_df)
+    get_rank_table_czce_df = get_rank_table_czce(date="20230109")
+    print(get_rank_table_czce_df)
 
-    get_czce_rank_table_first_df = get_czce_rank_table(date="20201026")
-    print(get_czce_rank_table_first_df)
+    get_rank_table_czce_df = get_rank_table_czce(date="20201026")
+    print(get_rank_table_czce_df)
 
     # 中国金融期货交易所
-    get_cffex_rank_table_df = get_cffex_rank_table(date="20100810")
+    get_cffex_rank_table_df = get_cffex_rank_table(date="20250721")
     print(get_cffex_rank_table_df)
 
     # 上海期货交易所
-    get_shfe_rank_table_df = get_shfe_rank_table(date="20230808")
+    get_shfe_rank_table_df = get_shfe_rank_table(date="20240509")
     print(get_shfe_rank_table_df)
 
     # 大连商品交易所-老接口
-    # get_dce_rank_table_first_df = get_dce_rank_table(date="20131227")
-    # print(get_dce_rank_table_first_df)
-    #
-    # get_dce_rank_table_second_df = get_dce_rank_table(date="20171227")
-    # print(get_dce_rank_table_second_df)
-    #
-    # get_dce_rank_table_third_df = get_dce_rank_table(date="20200929")
-    # print(get_dce_rank_table_third_df)
-    #
-    # get_dce_rank_table_third_df = get_dce_rank_table(date="20230706")
-    # print(get_dce_rank_table_third_df)
-    #
-    # get_dce_rank_table_fourth_df = get_dce_rank_table(
-    #     date="20210517", vars_list=["V"]
-    # )
-    # print(get_dce_rank_table_fourth_df)
+    get_dce_rank_table_first_df = get_dce_rank_table(date="20131227")
+    print(get_dce_rank_table_first_df)
+
+    get_dce_rank_table_second_df = get_dce_rank_table(date="20171227")
+    print(get_dce_rank_table_second_df)
+
+    get_dce_rank_table_third_df = get_dce_rank_table(date="20200929")
+    print(get_dce_rank_table_third_df)
+
+    get_dce_rank_table_third_df = get_dce_rank_table(date="20230706")
+    print(get_dce_rank_table_third_df)
+
+    get_dce_rank_table_fourth_df = get_dce_rank_table(date="20210517", vars_list=["V"])
+    print(get_dce_rank_table_fourth_df)
 
     # 大连商品交易所-新接口
-    futures_dce_detail_dict = futures_dce_position_rank(date="20230706")
+    futures_dce_detail_dict = futures_dce_position_rank(date="20240517")
     print(futures_dce_detail_dict)
 
-    # futures_dce_position_rank_other_df = futures_dce_position_rank_other(
-    #     date="20200727"
-    # )
-    # print(futures_dce_position_rank_other_df)
+    futures_dce_position_rank_other_df = futures_dce_position_rank_other(
+        date="20200727"
+    )
+    print(futures_dce_position_rank_other_df)
 
     # 广州期货交易所
-    futures_gfex_position_rank_df = futures_gfex_position_rank(date="20231113")
+    futures_gfex_position_rank_df = futures_gfex_position_rank(date="20250718")
     print(futures_gfex_position_rank_df)
 
     # 总接口
     get_rank_sum_daily_df = get_rank_sum_daily(
-        start_day="20231010",
-        end_day="20231013",
+        start_day="20251031",
+        end_day="20251103",
     )
     print(get_rank_sum_daily_df)

akshare/futures/futures_basis.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/5/11 17:30
+Date: 2024/12/12 17:00
 Desc: 生意社网站采集大宗商品现货价格及相应基差数据, 数据时间段从 20110104-至今
 备注：现期差 = 现货价格 - 期货价格(这里的期货价格为结算价)
 黄金为 元/克, 白银为 元/千克, 玻璃现货为 元/平方米, 鸡蛋现货为 元/公斤, 鸡蛋期货为 元/500千克, 其余为 元/吨.
@@ -12,6 +12,7 @@ Desc: 生意社网站采集大宗商品现货价格及相应基差数据, 数据
 发现生意社的 bugs:
 1. 2018-09-12 周三 数据缺失是因为生意社源数据在该交易日缺失: https://www.100ppi.com/sf/day-2018-09-12.html
 """
+
 import datetime
 import re
 import time
@@ -38,7 +39,8 @@ def futures_spot_price_daily(
     :param start_day: str 开始日期 format：YYYY-MM-DD 或 YYYYMMDD 或 datetime.date对象; 默认为当天
     :param end_day: str 结束数据 format：YYYY-MM-DD 或 YYYYMMDD 或 datetime.date对象; 默认为当天
     :param vars_list: list 合约品种如 [RB, AL]; 默认参数为所有商品
-    :return: pandas.DataFrame
+    :return: 基差
+    :rtype: pandas.DataFrame
     展期收益率数据:
     var               商品品种                      string
     sp                现货价格                      float
@@ -74,7 +76,9 @@ def futures_spot_price_daily(
         return temp_df
 
 
-def futures_spot_price(date: str = "20230509", vars_list: list = cons.contract_symbols) -> pd.DataFrame:
+def futures_spot_price(
+    date: str = "20240430", vars_list: list = cons.contract_symbols
+) -> pd.DataFrame:
     """
     指定交易日大宗商品现货价格及相应基差
     https://www.100ppi.com/sf/day-2017-09-12.html
@@ -96,12 +100,14 @@ def futures_spot_price(date: str = "20230509", vars_list: list = cons.contract_s
     """
     date = cons.convert_date(date) if date is not None else datetime.date.today()
     if date < datetime.date(2011, 1, 4):
-        raise Exception("数据源开始日期为 20110104, 请将获取数据时间点设置在 20110104 后")
+        raise Exception(
+            "数据源开始日期为 20110104, 请将获取数据时间点设置在 20110104 后"
+        )
     if date.strftime("%Y%m%d") not in calendar:
         warnings.warn(f"{date.strftime('%Y%m%d')}非交易日")
         return pd.DataFrame()
-    u1 = "http://www.100ppi.com/sf/"
-    u2 = f'http://www.100ppi.com/sf/day-{date.strftime("%Y-%m-%d")}.html'
+    u1 = "https://www.100ppi.com/sf/"
+    u2 = f'https://www.100ppi.com/sf/day-{date.strftime("%Y-%m-%d")}.html'
     i = 1
     while True:
         for url in [u2, u1]:
@@ -119,12 +125,16 @@ def futures_spot_price(date: str = "20230509", vars_list: list = cons.contract_s
                     return temp_df
                 else:
                     time.sleep(3)
-            except:
-                print(f"{date.strftime('%Y-%m-%d')}日生意社数据连接失败，第{str(i)}次尝试，最多5次")
+            except Exception as e:  # noqa: E722
+                print(
+                    f"{date.strftime('%Y-%m-%d')}日生意社数据连接失败[错误信息:{e}]，第{str(i)}次尝试，最多5次"
+                )
                 i += 1
                 if i > 5:
                     print(
-                        f"{date.strftime('%Y-%m-%d')}日生意社数据连接失败, 如果当前交易日是 2018-09-12, 由于生意社源数据缺失, 无法访问, 否则为重复访问已超过5次，您的地址被网站墙了，请保存好返回数据，稍后从该日期起重试"
+                        f"{date.strftime('%Y-%m-%d')}日生意社数据连接失败, 如果当前交易日是 2018-09-12, "
+                        f"由于生意社源数据缺失, 无法访问, 否则为重复访问已超过5次，您的地址被网站墙了，"
+                        f"请保存好返回数据，稍后从该日期起重试"
                     )
                     return pd.DataFrame()
 
@@ -160,11 +170,27 @@ def _check_information(df_data, date):
     ]
     records = pd.DataFrame()
     for string in df_data["symbol"].tolist():
+        news = "".join(re.findall(r"[\u4e00-\u9fa5]", string))
+        if news == "":
+            news = string.strip()
+
+        """
         if string == "PTA":
             news = "PTA"
         else:
             news = "".join(re.findall(r"[\u4e00-\u9fa5]", string))
-        if news != "" and news not in ["商品", "价格", "上海期货交易所", "郑州商品交易所", "大连商品交易所", "广州期货交易所"]:
+        """
+
+        if news != "" and news not in [
+            "商品",
+            "价格",
+            "上海期货交易所",
+            "郑州商品交易所",
+            "大连商品交易所",
+            "广州期货交易所",
+            # 某些天网站没有数据，比如 20180912，此时返回"暂无数据"，但并不是网站被墙了
+            "暂无数据",
+        ]:
             symbol = chinese_to_english(news)
             record = pd.DataFrame(df_data[df_data["symbol"] == string])
             record.loc[:, "symbol"] = symbol
@@ -177,14 +203,26 @@ def _check_information(df_data, date):
                 symbol == "FG"
             ):  # 上表中现货单位为元/平方米, 期货单位为元/吨. 换算公式：元/平方米*80=元/吨(http://www.100ppi.com/sf/959.html)
                 record.loc[:, "spot_price"] = float(record["spot_price"].iloc[0]) * 80
+            elif (
+                symbol == "LH"
+            ):  # 上表中现货单位为元/公斤, 期货单位为元/吨. 换算公式：元/公斤*1000=元/吨(http://www.100ppi.com/sf/959.html)
+                record.loc[:, "spot_price"] = float(record["spot_price"].iloc[0]) * 1000
             records = pd.concat([records, record])
 
-    records.loc[
-        :, ["near_contract_price", "dominant_contract_price", "spot_price"]
-    ] = records.loc[
-        :, ["near_contract_price", "dominant_contract_price", "spot_price"]
-    ].astype(
-        "float"
+    # 20241129:如果某日没有数据，直接返回返回空表
+    if records.empty:
+        records = df_data.iloc[0:0]
+        records["near_basis"] = pd.Series(dtype="float")
+        records["dom_basis"] = pd.Series(dtype="float")
+        records["near_basis_rate"] = pd.Series(dtype="float")
+        records["dom_basis_rate"] = pd.Series(dtype="float")
+        records["date"] = pd.Series(dtype="object")
+        return records
+
+    records.loc[:, ["near_contract_price", "dominant_contract_price", "spot_price"]] = (
+        records.loc[
+            :, ["near_contract_price", "dominant_contract_price", "spot_price"]
+        ].astype("float")
     )
 
     records.loc[:, "near_contract"] = records["near_contract"].replace(
@@ -194,9 +232,11 @@ def _check_information(df_data, date):
         r"[^0-9]*(\d*)$", r"\g<1>", regex=True
     )
 
+    records.loc[:, "near_month"] = records.loc[:, "near_contract"]
     records.loc[:, "near_contract"] = records["symbol"] + records.loc[
         :, "near_contract"
     ].astype("int").astype("str")
+    records.loc[:, "dominant_month"] = records.loc[:, "dominant_contract"]
     records.loc[:, "dominant_contract"] = records["symbol"] + records.loc[
         :, "dominant_contract"
     ].astype("int").astype("str")
@@ -232,7 +272,8 @@ def _check_information(df_data, date):
     records["dom_basis_rate"] = (
         records["dominant_contract_price"] / records["spot_price"] - 1
     )
-    records.loc[:, "date"] = date.strftime("%Y%m%d")
+    # records.loc[:, "date"] = date.strftime("%Y%m%d")
+    records.insert(0, "date", date.strftime("%Y%m%d"))
     return records
 
 
@@ -240,17 +281,17 @@ def _join_head(content: pd.DataFrame) -> List:
     headers = []
     for s1, s2 in zip(content.iloc[0], content.iloc[1]):
         if s1 != s2:
-            s = f'{s1}{s2}'
+            s = f"{s1}{s2}"
         else:
             s = s1
         headers.append(s)
     return headers
 
 
-def futures_spot_price_previous(date: str = "20220209") -> pd.DataFrame:
+def futures_spot_price_previous(date: str = "20240430") -> pd.DataFrame:
     """
     具体交易日大宗商品现货价格及相应基差
-    http://www.100ppi.com/sf/day-2017-09-12.html
+    https://www.100ppi.com/sf/day-2017-09-12.html
     :param date: 交易日; 历史日期
     :type date: str
     :return: 现货价格及相应基差
@@ -258,24 +299,49 @@ def futures_spot_price_previous(date: str = "20220209") -> pd.DataFrame:
     """
     date = cons.convert_date(date) if date is not None else datetime.date.today()
     if date < datetime.date(2011, 1, 4):
-        raise Exception("数据源开始日期为 20110104, 请将获取数据时间点设置在 20110104 后")
+        raise Exception(
+            "数据源开始日期为 20110104, 请将获取数据时间点设置在 20110104 后"
+        )
     if date.strftime("%Y%m%d") not in calendar:
         warnings.warn(f"{date.strftime('%Y%m%d')}非交易日")
-        return
-    url = date.strftime('http://www.100ppi.com/sf2/day-%Y-%m-%d.html')
+        return pd.DataFrame()
+    url = date.strftime("https://www.100ppi.com/sf2/day-%Y-%m-%d.html")
     content = pandas_read_html_link(url)
     main = content[1]
     # Header
     header = _join_head(main)
     # Values
-    values = main[main[4].str.endswith('%')]
+    values = main[main[4].str.endswith("%")]
     values.columns = header
     # Basis
-    basis = pd.concat(content[2:-1])
-    basis.columns = ['主力合约基差', '主力合约基差(%)']
-    basis['商品'] = values['商品'].tolist()
-    basis = pd.merge(values[["商品", "现货价格", "主力合约代码", "主力合约价格"]], basis)
-    basis = pd.merge(basis, values[["商品", "180日内主力基差最高", "180日内主力基差最低", "180日内主力基差平均"]])
+    # 对于没有数据的天，xml文件中没有数据，所以content[2:-1]可能为空
+    if len(content[2:-1]) > 0:
+        basis = pd.concat(content[2:-1])
+    else:
+        basis = pd.DataFrame(columns=["主力合约基差", "主力合约基差(%)"])
+
+    basis.columns = ["主力合约基差", "主力合约基差(%)"]
+    # 20241125(jasonudu)：因为部分日期，存在多个品种的现货价格，比如20151125的白糖、豆粕、豆油等，如果用商品名来merge，会出现重复列名，所以改用index来merge
+    # basis["商品"] = values["商品"].tolist()
+    basis.index = values.index
+    basis = pd.merge(
+        values[["商品", "现货价格", "主力合约代码", "主力合约价格"]],
+        basis,
+        left_index=True,
+        right_index=True,
+    )
+    basis = pd.merge(
+        basis,
+        values[
+            [
+                "180日内主力基差最高",
+                "180日内主力基差最低",
+                "180日内主力基差平均",
+            ]
+        ],
+        left_index=True,
+        right_index=True,
+    )
     basis.columns = [
         "商品",
         "现货价格",
@@ -287,18 +353,18 @@ def futures_spot_price_previous(date: str = "20220209") -> pd.DataFrame:
         "180日内主力基差最低",
         "180日内主力基差平均",
     ]
-    basis['主力合约变动百分比'] = basis['主力合约变动百分比'].str.strip("%")
+    basis["主力合约变动百分比"] = basis["主力合约变动百分比"].str.strip("%")
     return basis
 
 
 if __name__ == "__main__":
     futures_spot_price_daily_df = futures_spot_price_daily(
-        start_day="20230919", end_day="20230927", vars_list=['SR']
+        start_day="20250708", end_day="20250709", vars_list=["BZ", "RB"]
     )
     print(futures_spot_price_daily_df)
 
-    futures_spot_price_df = futures_spot_price(date="20230919")
+    futures_spot_price_df = futures_spot_price(date="20250620")
     print(futures_spot_price_df)
 
-    futures_spot_price_previous_df = futures_spot_price_previous(date='20230807')
+    futures_spot_price_previous_df = futures_spot_price_previous(date="20240430")
     print(futures_spot_price_previous_df)

akshare/futures/futures_comex_em.py

@@ -5,6 +5,7 @@ Date: 2023/11/15 18:00
 Desc: 东方财富网-数据中心-期货期权-COMEX库存数据
 https://data.eastmoney.com/pmetal/comex/by.html
 """
+
 import pandas as pd
 import requests