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

akshare/futures/futures_to_spot.py

@@ -4,6 +4,7 @@
 Date: 2024/1/22 20:30
 Desc: 期货-期转现-交割
 """
+
 from io import StringIO, BytesIO
 
 import pandas as pd
@@ -13,7 +14,7 @@ import requests
 def futures_to_spot_shfe(date: str = "202312") -> pd.DataFrame:
     """
     上海期货交易所-期转现
-    https://www.shfe.com.cn/statements/dataview.html?paramid=kx
+    https://tsite.shfe.com.cn/statements/dataview.html?paramid=kx
     1、铜、铜(BC)、铝、锌、铅、镍、锡、螺纹钢、线材、热轧卷板、天然橡胶、20号胶、低硫燃料油、燃料油、石油沥青、纸浆、不锈钢的数量单位为：吨；黄金的数量单位为：克；白银的数量单位为：千克；原油的数量单位为：桶。
     2、交割量、期转现量为单向计算。
     :param date: 年月
@@ -21,9 +22,10 @@ def futures_to_spot_shfe(date: str = "202312") -> pd.DataFrame:
     :return: 上海期货交易所期转现
     :rtype: pandas.DataFrame
     """
-    url = f"http://www.shfe.com.cn/data/instrument/ExchangeDelivery{date}.dat"
+    url = f"https://tsite.shfe.com.cn/data/instrument/ExchangeDelivery{date}.dat"
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/100.0.4896.127 Safari/537.36",
     }
     r = requests.get(url, headers=headers)
     data_json = r.json()
@@ -46,9 +48,9 @@ def futures_to_spot_shfe(date: str = "202312") -> pd.DataFrame:
             "期转现量",
         ]
     ]
-    temp_df['日期'] = pd.to_datetime(temp_df['日期'], errors="coerce").dt.date
-    temp_df['交割量'] = pd.to_numeric(temp_df['交割量'], errors="coerce")
-    temp_df['期转现量'] = pd.to_numeric(temp_df['期转现量'], errors="coerce")
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["交割量"] = pd.to_numeric(temp_df["交割量"], errors="coerce")
+    temp_df["期转现量"] = pd.to_numeric(temp_df["期转现量"], errors="coerce")
     return temp_df
 
 
@@ -84,11 +86,11 @@ def futures_delivery_dce(date: str = "202312") -> pd.DataFrame:
     temp_df["交割日期"] = (
         temp_df["交割日期"].astype(str).str.split(".", expand=True).iloc[:, 0]
     )
-    temp_df = temp_df[~temp_df['品种'].str.contains('小计|总计')]
+    temp_df = temp_df[~temp_df["品种"].str.contains("小计|总计")]
     temp_df.reset_index(inplace=True, drop=True)
-    temp_df['交割日期'] = pd.to_datetime(temp_df['交割日期'], errors="coerce").dt.date
-    temp_df['交割量'] = pd.to_numeric(temp_df['交割量'], errors="coerce")
-    temp_df['交割金额'] = pd.to_numeric(temp_df['交割金额'], errors="coerce")
+    temp_df["交割日期"] = pd.to_datetime(temp_df["交割日期"], errors="coerce").dt.date
+    temp_df["交割量"] = pd.to_numeric(temp_df["交割量"], errors="coerce")
+    temp_df["交割金额"] = pd.to_numeric(temp_df["交割金额"], errors="coerce")
     return temp_df
 
 
@@ -114,10 +116,12 @@ def futures_to_spot_dce(date: str = "202312") -> pd.DataFrame:
     temp_df["期转现发生日期"] = (
         temp_df["期转现发生日期"].astype(str).str.split(".", expand=True).iloc[:, 0]
     )
-    temp_df = temp_df[~temp_df['合约代码'].str.contains('小计|总计')]
+    temp_df = temp_df[~temp_df["合约代码"].str.contains("小计|总计")]
     temp_df.reset_index(inplace=True, drop=True)
-    temp_df['期转现发生日期'] = pd.to_datetime(temp_df['期转现发生日期'], errors="coerce").dt.date
-    temp_df['期转现数量'] = pd.to_numeric(temp_df['期转现数量'], errors="coerce")
+    temp_df["期转现发生日期"] = pd.to_datetime(
+        temp_df["期转现发生日期"], errors="coerce"
+    ).dt.date
+    temp_df["期转现数量"] = pd.to_numeric(temp_df["期转现数量"], errors="coerce")
     return temp_df
 
 
@@ -142,9 +146,9 @@ def futures_delivery_match_dce(symbol: str = "a") -> pd.DataFrame:
         temp_df["配对日期"].astype(str).str.split(".", expand=True).iloc[:, 0]
     )
     temp_df = temp_df.iloc[:-1, :]
-    temp_df['配对日期'] = pd.to_datetime(temp_df['配对日期'], errors="coerce").dt.date
-    temp_df['配对手数'] = pd.to_numeric(temp_df['配对手数'], errors="coerce")
-    temp_df['交割结算价'] = pd.to_numeric(temp_df['交割结算价'], errors="coerce")
+    temp_df["配对日期"] = pd.to_datetime(temp_df["配对日期"], errors="coerce").dt.date
+    temp_df["配对手数"] = pd.to_numeric(temp_df["配对手数"], errors="coerce")
+    temp_df["交割结算价"] = pd.to_numeric(temp_df["交割结算价"], errors="coerce")
     return temp_df
 
 
@@ -186,7 +190,7 @@ def futures_to_spot_czce(date: str = "20231228") -> pd.DataFrame:
     ]
     temp_df["合约数量"] = temp_df["合约数量"].astype(str).str.replace(",", "")
     temp_df["合约数量"] = pd.to_numeric(temp_df["合约数量"], errors="coerce")
-    temp_df = temp_df[~temp_df['合约代码'].str.contains('小计|合计')]
+    temp_df = temp_df[~temp_df["合约代码"].str.contains("小计|合计")]
     temp_df.reset_index(inplace=True, drop=True)
     return temp_df
 
@@ -208,16 +212,14 @@ def futures_delivery_match_czce(date: str = "20210106") -> pd.DataFrame:
     big_df = pd.DataFrame()
     for i, item in enumerate(index_flag):
         try:
-            temp_inner_df = temp_df[index_flag[i] + 1: index_flag[i + 1]]
-        except:
-            temp_inner_df = temp_df[index_flag[i] + 1:]
+            temp_inner_df = temp_df[index_flag[i] + 1 : index_flag[i + 1]]
+        except:  # noqa: E722
+            temp_inner_df = temp_df[index_flag[i] + 1 :]
         temp_inner_df.columns = temp_inner_df.iloc[0, :]
         temp_inner_df = temp_inner_df.iloc[1:-1, :]
         temp_inner_df.reset_index(drop=True, inplace=True)
         date_contract_str = (
-            temp_df[temp_df.iloc[:, 0].str.contains("配对日期")]
-            .iloc[:, 0]
-            .values[i]
+            temp_df[temp_df.iloc[:, 0].str.contains("配对日期")].iloc[:, 0].values[i]
         )
         inner_date = date_contract_str.split("：")[1].split(" ")[0]
         symbol = date_contract_str.split("：")[-1]
@@ -268,16 +270,17 @@ def futures_delivery_czce(date: str = "20210112") -> pd.DataFrame:
 def futures_delivery_shfe(date: str = "202312") -> pd.DataFrame:
     """
     上海期货交易所-交割情况表
-    https://www.shfe.com.cn/statements/dataview.html?paramid=kx
+    https://tsite.shfe.com.cn/statements/dataview.html?paramid=kx
     注意: 日期 -> 月度统计 -> 下拉到交割情况表
     :param date: 年月日
     :type date: str
     :return: 上海期货交易所-交割情况表
     :rtype: pandas.DataFrame
     """
-    url = f"http://www.shfe.com.cn/data/dailydata/{date}monthvarietystatistics.dat"
+    url = f"https://tsite.shfe.com.cn/data/dailydata/{date}monthvarietystatistics.dat"
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/100.0.4896.127 Safari/537.36",
     }
     r = requests.get(url, headers=headers)
     r.encoding = "utf-8"
@@ -301,10 +304,14 @@ def futures_delivery_shfe(date: str = "202312") -> pd.DataFrame:
             "交割量-累计同比",
         ]
     ]
-    temp_df['交割量-本月'] = pd.to_numeric(temp_df['交割量-本月'], errors="coerce")
-    temp_df['交割量-比重'] = pd.to_numeric(temp_df['交割量-比重'], errors="coerce")
-    temp_df['交割量-本年累计'] = pd.to_numeric(temp_df['交割量-本年累计'], errors="coerce")
-    temp_df['交割量-累计同比'] = pd.to_numeric(temp_df['交割量-累计同比'], errors="coerce")
+    temp_df["交割量-本月"] = pd.to_numeric(temp_df["交割量-本月"], errors="coerce")
+    temp_df["交割量-比重"] = pd.to_numeric(temp_df["交割量-比重"], errors="coerce")
+    temp_df["交割量-本年累计"] = pd.to_numeric(
+        temp_df["交割量-本年累计"], errors="coerce"
+    )
+    temp_df["交割量-累计同比"] = pd.to_numeric(
+        temp_df["交割量-累计同比"], errors="coerce"
+    )
     return temp_df
 
 
@@ -330,7 +337,5 @@ if __name__ == "__main__":
     futures_delivery_match_dce_df = futures_delivery_match_dce(symbol="a")
     print(futures_delivery_match_dce_df)
 
-    futures_delivery_match_czce_df = futures_delivery_match_czce(
-        date="20210106"
-    )
+    futures_delivery_match_czce_df = futures_delivery_match_czce(date="20210106")
     print(futures_delivery_match_czce_df)

akshare/futures/futures_warehouse_receipt.py

@@ -1,10 +1,10 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/1/22 18:30
+Date: 2024/4/2 22:30
 Desc: 期货-仓单日报
 上海期货交易所-仓单日报
-https://www.shfe.com.cn/statements/dataview.html?paramid=dailystock
+https://tsite.shfe.com.cn/statements/dataview.html?paramid=dailystock
 郑州商品交易所-交易数据-仓单日报
 http://www.czce.com.cn/cn/jysj/cdrb/H770310index_1.htm
 大连商品交易所-行情数据-统计数据-日统计-仓单日报
@@ -12,6 +12,7 @@ http://www.dce.com.cn/dalianshangpin/xqsj/tjsj26/rtj/cdrb/index.html
 广州期货交易所-行情数据-仓单日报
 http://www.gfex.com.cn/gfex/cdrb/hqsj_tjsj.shtml
 """
+
 import re
 from io import BytesIO, StringIO
 
@@ -30,19 +31,16 @@ def futures_czce_warehouse_receipt(date: str = "20200702") -> dict:
     """
     url = f"http://www.czce.com.cn/cn/DFSStaticFiles/Future/{date[:4]}/{date}/FutureDataWhsheet.xls"
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36"
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/83.0.4103.116 Safari/537.36"
     }
     r = requests.get(url, verify=False, headers=headers)
     temp_df = pd.read_excel(BytesIO(r.content))
-    index_list = temp_df[
-        temp_df.iloc[:, 0].str.find("品种") == 0.0
-        ].index.to_list()
+    index_list = temp_df[temp_df.iloc[:, 0].str.find("品种") == 0.0].index.to_list()
     index_list.append(len(temp_df))
     big_dict = {}
     for inner_index in range(len(index_list) - 1):
-        inner_df = temp_df[
-                   index_list[inner_index]: index_list[inner_index + 1]
-                   ]
+        inner_df = temp_df[index_list[inner_index] : index_list[inner_index + 1]]
         inner_key = re.findall(r"[a-zA-Z]+", inner_df.iloc[0, 0])[0]
         inner_df = inner_df.iloc[1:, :]
         inner_df.dropna(axis=0, how="all", inplace=True)
@@ -65,7 +63,8 @@ def futures_dce_warehouse_receipt(date: str = "20200702") -> dict:
     """
     url = "http://www.dce.com.cn/publicweb/quotesdata/wbillWeeklyQuotes.html"
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36"
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/83.0.4103.116 Safari/537.36"
     }
     params = {
         "wbillWeeklyQuotes.variety": "all",
@@ -75,9 +74,7 @@ def futures_dce_warehouse_receipt(date: str = "20200702") -> dict:
     }
     r = requests.get(url, params=params, headers=headers)
     temp_df = pd.read_html(StringIO(r.text))[0]
-    index_list = temp_df[
-        temp_df.iloc[:, 0].str.contains("小计") == 1
-        ].index.to_list()
+    index_list = temp_df[temp_df.iloc[:, 0].str.contains("小计") == 1].index.to_list()
     index_list.insert(0, 0)
     big_dict = {}
     for inner_index in range(len(index_list) - 1):
@@ -85,10 +82,14 @@ def futures_dce_warehouse_receipt(date: str = "20200702") -> dict:
             temp_index = 0
         else:
             temp_index = index_list[inner_index] + 1
-        inner_df = temp_df[temp_index: index_list[inner_index + 1] + 1]
+        inner_df = temp_df[temp_index : index_list[inner_index + 1] + 1].copy()
         inner_key = inner_df.iloc[0, 0]
         inner_df.reset_index(inplace=True, drop=True)
-        inner_df = inner_df.ffill()
+        inner_df.ffill(inplace=True)
+        # 填补 20240401 中开头没有品种的情况
+        if date == "20240401":
+            inner_df["品种"] = inner_df["品种"].fillna("玉米")
+            inner_key = inner_df.iloc[0, 0]
         big_dict[inner_key] = inner_df
     return big_dict
 
@@ -96,26 +97,23 @@ def futures_dce_warehouse_receipt(date: str = "20200702") -> dict:
 def futures_shfe_warehouse_receipt(date: str = "20200702") -> dict:
     """
     上海期货交易所指定交割仓库期货仓单日报
-    https://www.shfe.com.cn/statements/dataview.html?paramid=dailystock&paramdate=20200703
+    https://tsite.shfe.com.cn/statements/dataview.html?paramid=dailystock&paramdate=20200703
     :param date: 交易日, e.g., "20200702"
     :type date: str
     :return: 指定日期的仓单日报数据
     :rtype: dict
     """
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36"
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/83.0.4103.116 Safari/537.36"
     }
-    url = f"http://www.shfe.com.cn/data/dailydata/{date}dailystock.dat"
+    url = f"https://tsite.shfe.com.cn/data/dailydata/{date}dailystock.dat"
     if date >= "20140519":
         r = requests.get(url, headers=headers)
         data_json = r.json()
         temp_df = pd.DataFrame(data_json["o_cursor"])
-        temp_df["VARNAME"] = (
-            temp_df["VARNAME"].str.split(r"$", expand=True).iloc[:, 0]
-        )
-        temp_df["REGNAME"] = (
-            temp_df["REGNAME"].str.split(r"$", expand=True).iloc[:, 0]
-        )
+        temp_df["VARNAME"] = temp_df["VARNAME"].str.split(r"$", expand=True).iloc[:, 0]
+        temp_df["REGNAME"] = temp_df["REGNAME"].str.split(r"$", expand=True).iloc[:, 0]
         temp_df["WHABBRNAME"] = (
             temp_df["WHABBRNAME"].str.split(r"$", expand=True).iloc[:, 0]
         )
@@ -123,12 +121,12 @@ def futures_shfe_warehouse_receipt(date: str = "20200702") -> dict:
         for item in set(temp_df["VARNAME"]):
             big_dict[item] = temp_df[temp_df["VARNAME"] == item]
     else:
-        url = f"http://www.shfe.com.cn/data/dailydata/{date}dailystock.html"
+        url = f"https://tsite.shfe.com.cn/data/dailydata/{date}dailystock.html"
         r = requests.get(url, headers=headers)
         temp_df = pd.read_html(StringIO(r.text))[0]
         index_list = temp_df[
             temp_df.iloc[:, 3].str.contains("单位：") == 1
-            ].index.to_list()
+        ].index.to_list()
         big_dict = {}
         for inner_index in range(len(index_list)):
             temp_index_start = index_list[inner_index]
@@ -160,71 +158,77 @@ def futures_gfex_warehouse_receipt(date: str = "20240122") -> dict:
     """
     url = "http://www.gfex.com.cn/u/interfacesWebTdWbillWeeklyQuotes/loadList"
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36"
-    }
-    payload = {
-        "gen_date": date
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/83.0.4103.116 Safari/537.36"
     }
+    payload = {"gen_date": date}
     r = requests.post(url=url, data=payload, headers=headers)
     data_json = r.json()
-    temp_df = pd.DataFrame(data_json['data'])
-    symbol_list = list(set([item.upper() for item in temp_df['varietyOrder'].tolist() if item != ""]))
-    temp_df.rename(columns={
-        "varietyOrder": "symbol",
-        "variety": "品种",
-        "whAbbr": "仓库/分库",
-        "lastWbillQty": "昨日仓单量",
-        "wbillQty": "今日仓单量",
-        "regWbillQty": "增减",
-    }, inplace=True)
-    temp_df = temp_df[[
-        "symbol",
-        "whType",
-        "品种",
-        "仓库/分库",
-        "昨日仓单量",
-        "今日仓单量",
-        "增减",
-    ]]
-    temp_df['whType'] = pd.to_numeric(temp_df['whType'], errors="coerce")
-    temp_df.dropna(subset=["whType"], how="any", axis=0, ignore_index=True, inplace=True)
-    big_dict = dict()
-    for symbol in symbol_list:
-        inner_temp_df = temp_df[temp_df['symbol'] == symbol.lower()].copy()
-        inner_temp_df = inner_temp_df[[
+    temp_df = pd.DataFrame(data_json["data"])
+    symbol_list = list(
+        set([item.upper() for item in temp_df["varietyOrder"].tolist() if item != ""])
+    )
+    temp_df.rename(
+        columns={
+            "varietyOrder": "symbol",
+            "variety": "品种",
+            "whAbbr": "仓库/分库",
+            "lastWbillQty": "昨日仓单量",
+            "wbillQty": "今日仓单量",
+            "regWbillQty": "增减",
+        },
+        inplace=True,
+    )
+    temp_df = temp_df[
+        [
+            "symbol",
+            "whType",
             "品种",
             "仓库/分库",
             "昨日仓单量",
             "今日仓单量",
             "增减",
-        ]]
-        inner_temp_df['昨日仓单量'] = pd.to_numeric(inner_temp_df['昨日仓单量'], errors="coerce")
-        inner_temp_df['今日仓单量'] = pd.to_numeric(inner_temp_df['今日仓单量'], errors="coerce")
-        inner_temp_df['增减'] = pd.to_numeric(inner_temp_df['增减'], errors="coerce")
+        ]
+    ]
+    temp_df["whType"] = pd.to_numeric(temp_df["whType"], errors="coerce")
+    temp_df.dropna(
+        subset=["whType"], how="any", axis=0, ignore_index=True, inplace=True
+    )
+    big_dict = dict()
+    for symbol in symbol_list:
+        inner_temp_df = temp_df[temp_df["symbol"] == symbol.lower()].copy()
+        inner_temp_df = inner_temp_df[
+            [
+                "品种",
+                "仓库/分库",
+                "昨日仓单量",
+                "今日仓单量",
+                "增减",
+            ]
+        ]
+        inner_temp_df["昨日仓单量"] = pd.to_numeric(
+            inner_temp_df["昨日仓单量"], errors="coerce"
+        )
+        inner_temp_df["今日仓单量"] = pd.to_numeric(
+            inner_temp_df["今日仓单量"], errors="coerce"
+        )
+        inner_temp_df["增减"] = pd.to_numeric(inner_temp_df["增减"], errors="coerce")
         inner_temp_df.reset_index(inplace=True, drop=True)
         big_dict[symbol] = inner_temp_df
     return big_dict
 
 
 if __name__ == "__main__":
-    czce_warehouse_receipt_df = futures_czce_warehouse_receipt(
-        date="20151019"
-    )
+    czce_warehouse_receipt_df = futures_czce_warehouse_receipt(date="20151019")
     print(czce_warehouse_receipt_df)
 
-    futures_dce_warehouse_receipt_df = futures_dce_warehouse_receipt(
-        date="20200702"
-    )
+    futures_dce_warehouse_receipt_df = futures_dce_warehouse_receipt(date="20240401")
     print(futures_dce_warehouse_receipt_df)
 
-    futures_shfe_warehouse_receipt_df = futures_shfe_warehouse_receipt(
-        date="20200702"
-    )
+    futures_shfe_warehouse_receipt_df = futures_shfe_warehouse_receipt(date="20200702")
     print(futures_shfe_warehouse_receipt_df)
 
-    futures_shfe_warehouse_receipt_df = futures_shfe_warehouse_receipt(
-        date="20140516"
-    )
+    futures_shfe_warehouse_receipt_df = futures_shfe_warehouse_receipt(date="20140516")
     print(futures_shfe_warehouse_receipt_df)
 
     futures_gfex_warehouse_receipt_df = futures_gfex_warehouse_receipt(date="20240122")