akshare 1.14.49__py3-none-any.whl → 1.17.99__py3-none-any.whl

akshare/index/index_sugar.py

@@ -5,6 +5,7 @@ Date: 2023/6/19 17:00
 Desc: 沐甜科技数据中心-中国食糖指数
 https://www.msweet.com.cn/mtkj/sjzx13/index.html
 """
+
 import requests
 import pandas as pd
 
@@ -93,12 +94,25 @@ def index_outer_quote_sugar_msweet() -> pd.DataFrame:
     temp_df = pd.concat(
         [pd.DataFrame(data_json["category"]), pd.DataFrame(data_json["data"])], axis=1
     )
-    temp_df.columns = ["日期", "巴西糖进口成本", "泰国糖进口利润空间", "巴西糖进口利润空间", "泰国糖进口成本", "日照现货价"]
+    temp_df.columns = [
+        "日期",
+        "巴西糖进口成本",
+        "泰国糖进口利润空间",
+        "巴西糖进口利润空间",
+        "泰国糖进口成本",
+        "日照现货价",
+    ]
     temp_df["日期"] = temp_df["日期"].str.replace("/", "-")
     temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
-    temp_df["巴西糖进口成本"] = pd.to_numeric(temp_df["巴西糖进口成本"], errors="coerce")
-    temp_df["泰国糖进口利润空间"] = pd.to_numeric(temp_df["泰国糖进口利润空间"], errors="coerce")
-    temp_df["巴西糖进口利润空间"] = pd.to_numeric(temp_df["巴西糖进口利润空间"], errors="coerce")
+    temp_df["巴西糖进口成本"] = pd.to_numeric(
+        temp_df["巴西糖进口成本"], errors="coerce"
+    )
+    temp_df["泰国糖进口利润空间"] = pd.to_numeric(
+        temp_df["泰国糖进口利润空间"], errors="coerce"
+    )
+    temp_df["巴西糖进口利润空间"] = pd.to_numeric(
+        temp_df["巴西糖进口利润空间"], errors="coerce"
+    )
     temp_df["泰国糖进口成本"] = pd.to_numeric(temp_df["泰国糖进口成本"])
     temp_df["日照现货价"] = pd.to_numeric(temp_df["日照现货价"], errors="coerce")
     return temp_df

akshare/index/index_sw.py

@@ -95,6 +95,9 @@ def sw_index_second_info() -> pd.DataFrame:
     )
     code = [item.get_text() for item in code_raw]
     name = [item.get_text().split("(")[0] for item in name_raw]
+    parent_name = [
+        item.find("span").get_text().split("(")[0][1:-1] for item in name_raw
+    ]
     num = [item.get_text().split("(")[1].split(")")[0] for item in name_raw]
     num_1 = [
         item.find_all("span", attrs={"class": "value"})[0].get_text().strip()
@@ -112,10 +115,11 @@ def sw_index_second_info() -> pd.DataFrame:
         item.find_all("span", attrs={"class": "value"})[3].get_text().strip()
         for item in value_raw
     ]
-    temp_df = pd.DataFrame([code, name, num, num_1, num_2, num_3, num_4]).T
+    temp_df = pd.DataFrame([code, name, parent_name, num, num_1, num_2, num_3, num_4]).T
     temp_df.columns = [
         "行业代码",
         "行业名称",
+        "上级行业",
         "成份个数",
         "静态市盈率",
         "TTM(滚动)市盈率",
@@ -153,6 +157,9 @@ def sw_index_third_info() -> pd.DataFrame:
     )
     code = [item.get_text() for item in code_raw]
     name = [item.get_text().split("(")[0] for item in name_raw]
+    parent_name = [
+        item.find("span").get_text().split("(")[0][1:-1] for item in name_raw
+    ]
     num = [item.get_text().split("(")[1].split(")")[0] for item in name_raw]
     num_1 = [
         item.find_all("span", attrs={"class": "value"})[0].get_text().strip()
@@ -170,10 +177,11 @@ def sw_index_third_info() -> pd.DataFrame:
         item.find_all("span", attrs={"class": "value"})[3].get_text().strip()
         for item in value_raw
     ]
-    temp_df = pd.DataFrame([code, name, num, num_1, num_2, num_3, num_4]).T
+    temp_df = pd.DataFrame([code, name, parent_name, num, num_1, num_2, num_3, num_4]).T
     temp_df.columns = [
         "行业代码",
         "行业名称",
+        "上级行业",
         "成份个数",
         "静态市盈率",
         "TTM(滚动)市盈率",

akshare/index/index_yw.py

@@ -1,14 +1,18 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/4/17 19:17
+Date: 2025/5/3 
 Desc: 义乌小商品指数
-https://www.ywindex.com/Home/Product/index/
+目前可以通过这些接口直接请求到 JSON 数据
+周价格指数：https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/history/piweek?gcCode=
+月价格指数：https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/history/month?gcCode=
+月景气指数：https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/history/bi?gcCode=
+上涨：https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/get/rise
+下跌：https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/get/drop
 """
 
 import pandas as pd
 import requests
-from bs4 import BeautifulSoup
 
 
 def index_yw(symbol: str = "月景气指数") -> pd.DataFrame:
@@ -21,85 +25,58 @@ def index_yw(symbol: str = "月景气指数") -> pd.DataFrame:
     :rtype: pandas.DataFrame
     """
     import urllib3
-
-    # 禁用InsecureRequestWarning
     urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-    name_num_dict = {
-        "周价格指数": 1,
-        "月价格指数": 3,
-        "月景气指数": 5,
-    }
-    url = "https://www.ywindex.com/Home/Product/index/"
-    res = requests.get(url, verify=False)
-    soup = BeautifulSoup(res.text, features="lxml")
-    table_name = (
-        soup.find_all(attrs={"class": "tablex"})[name_num_dict[symbol]]
-        .get_text()
-        .split("\n\n\n\n\n")[2]
-        .split("\n")
-    )
-    table_content = (
-        soup.find_all(attrs={"class": "tablex"})[name_num_dict[symbol]]
-        .get_text()
-        .split("\n\n\n\n\n")[3]
-        .split("\n\n")
-    )
+
     if symbol == "月景气指数":
-        table_df = pd.DataFrame([item.split("\n") for item in table_content]).iloc[
-            :, :5
-        ]
-        table_df.columns = ["期数", "景气指数", "规模指数", "效益指数", "市场信心指数"]
-        table_df["期数"] = pd.to_datetime(table_df["期数"], errors="coerce").dt.date
-        table_df["景气指数"] = pd.to_numeric(table_df["景气指数"], errors="coerce")
-        table_df["规模指数"] = pd.to_numeric(table_df["规模指数"], errors="coerce")
-        table_df["效益指数"] = pd.to_numeric(table_df["效益指数"], errors="coerce")
-        table_df["市场信心指数"] = pd.to_numeric(
-            table_df["市场信心指数"], errors="coerce"
-        )
-        table_df.sort_values(["期数"], inplace=True, ignore_index=True)
-        return table_df
-    elif symbol == "周价格指数":
-        table_df = pd.DataFrame([item.split("\n") for item in table_content]).iloc[
-            :, :6
-        ]
-        table_df.columns = table_name
-        table_df["期数"] = pd.to_datetime(table_df["期数"], errors="coerce").dt.date
-        table_df["价格指数"] = pd.to_numeric(table_df["价格指数"], errors="coerce")
-        table_df["场内价格指数"] = pd.to_numeric(
-            table_df["场内价格指数"], errors="coerce"
-        )
-        table_df["网上价格指数"] = pd.to_numeric(
-            table_df["网上价格指数"], errors="coerce"
-        )
-        table_df["订单价格指数"] = pd.to_numeric(
-            table_df["订单价格指数"], errors="coerce"
-        )
-        table_df["出口价格指数"] = pd.to_numeric(
-            table_df["出口价格指数"], errors="coerce"
+        url = "https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/history/bi?gcCode="
+        r = requests.get(url, verify=False)
+        data_json = r.json()
+        temp_df = pd.DataFrame(data_json["data"])
+        temp_df = temp_df[["indextimeno", "totalindex", "scopeindex", "benifitindex", "confidentindex"]]
+        temp_df.columns = ["期数", "景气指数", "规模指数", "效益指数", "市场信心指数"]
+        temp_df["期数"] = pd.to_datetime(temp_df["期数"], errors="coerce").dt.date
+        temp_df["景气指数"] = pd.to_numeric(temp_df["景气指数"], errors="coerce")
+        temp_df["规模指数"] = pd.to_numeric(temp_df["规模指数"], errors="coerce")
+        temp_df["效益指数"] = pd.to_numeric(temp_df["效益指数"], errors="coerce")
+        temp_df["市场信心指数"] = pd.to_numeric(
+            temp_df["市场信心指数"], errors="coerce"
         )
-        table_df.sort_values(["期数"], inplace=True, ignore_index=True)
-        return table_df
-    elif symbol == "月价格指数":
-        table_df = pd.DataFrame([item.split("\n") for item in table_content]).iloc[
-            :, :6
-        ]
-        table_df.columns = table_name
-        table_df["期数"] = pd.to_datetime(table_df["期数"], errors="coerce").dt.date
-        table_df["价格指数"] = pd.to_numeric(table_df["价格指数"], errors="coerce")
-        table_df["场内价格指数"] = pd.to_numeric(
-            table_df["场内价格指数"], errors="coerce"
+        temp_df.sort_values(["期数"], inplace=True, ignore_index=True)
+        return temp_df
+    else:
+        symbol_map = {
+            "周价格指数": "piweek",
+            "月价格指数": "month"
+        }
+        url = f"https://apiserver.chinagoods.com/yiwuindex/v1/active/industry/class/history/{symbol_map[symbol]}?gcCode="
+        r = requests.get(url, verify=False)
+        data_json = r.json()
+        columns_name = {
+            "indextimeno": "期数",
+            "totalpriceindex": "价格指数",
+            "stockdealpriceindex": "场内价格指数",
+            "netdealpriceindex": "网上价格指数",
+            "orderdealpriceindex": "订单价格指数",
+            "outdealpriceindex": "出口价格指数",
+        }
+        temp_df = pd.DataFrame(data_json["data"])
+        temp_df.columns = [columns_name[name] for name in temp_df.columns]
+        temp_df["期数"] = pd.to_datetime(temp_df["期数"], errors="coerce").dt.date
+        temp_df["价格指数"] = pd.to_numeric(temp_df["价格指数"], errors="coerce")
+        temp_df["场内价格指数"] = pd.to_numeric(
+            temp_df["场内价格指数"], errors="coerce"
         )
-        table_df["网上价格指数"] = pd.to_numeric(
-            table_df["网上价格指数"], errors="coerce"
+        temp_df["网上价格指数"] = pd.to_numeric(
+            temp_df["网上价格指数"], errors="coerce"
         )
-        table_df["订单价格指数"] = pd.to_numeric(
-            table_df["订单价格指数"], errors="coerce"
+        temp_df["订单价格指数"] = pd.to_numeric(
+            temp_df["订单价格指数"], errors="coerce"
         )
-        table_df["出口价格指数"] = pd.to_numeric(
-            table_df["出口价格指数"], errors="coerce"
+        temp_df["出口价格指数"] = pd.to_numeric(
+            temp_df["出口价格指数"], errors="coerce"
         )
-        table_df.sort_values(["期数"], inplace=True, ignore_index=True)
-        return table_df
+        temp_df.sort_values(by=["期数"], inplace=True, ignore_index=True)
+        return temp_df
 
 
 if __name__ == "__main__":
@@ -111,3 +88,4 @@ if __name__ == "__main__":
 
     index_yw_df = index_yw(symbol="月景气指数")
     print(index_yw_df)
+    

akshare/index/index_zh_em.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/12/11 20:20
+Date: 2025/3/11 17:00
 Desc: 东方财富网-指数行情数据
 """
 
@@ -10,6 +10,8 @@ from functools import lru_cache
 import pandas as pd
 import requests
 
+from akshare.utils.func import fetch_paginated_data
+
 
 @lru_cache()
 def index_code_id_map_em() -> dict:
@@ -22,69 +24,18 @@ def index_code_id_map_em() -> dict:
     url = "https://80.push2.eastmoney.com/api/qt/clist/get"
     params = {
         "pn": "1",
-        "pz": "10000",
-        "po": "1",
-        "np": "1",
-        "ut": "bd1d9ddb04089700cf9c27f6f7426281",
-        "fltt": "2",
-        "invt": "2",
-        "fid": "f3",
-        "fs": "m:1 t:2,m:1 t:23",
-        "fields": "f12",
-        "_": "1623833739532",
-    }
-    r = requests.get(url, params=params)
-    data_json = r.json()
-    if not data_json["data"]["diff"]:
-        return dict()
-    temp_df = pd.DataFrame(data_json["data"]["diff"])
-    temp_df["market_id"] = 1
-    temp_df.columns = ["sh_code", "sh_id"]
-    code_id_dict = dict(zip(temp_df["sh_code"], temp_df["sh_id"]))
-    params = {
-        "pn": "1",
-        "pz": "10000",
-        "po": "1",
-        "np": "1",
-        "ut": "bd1d9ddb04089700cf9c27f6f7426281",
-        "fltt": "2",
-        "invt": "2",
-        "fid": "f3",
-        "fs": "m:0 t:6,m:0 t:80",
-        "fields": "f12",
-        "_": "1623833739532",
-    }
-    r = requests.get(url, params=params)
-    data_json = r.json()
-    if not data_json["data"]["diff"]:
-        return dict()
-    temp_df_sz = pd.DataFrame(data_json["data"]["diff"])
-    temp_df_sz["sz_id"] = 0
-    code_id_dict.update(dict(zip(temp_df_sz["f12"], temp_df_sz["sz_id"])))
-    params = {
-        "pn": "1",
-        "pz": "10000",
+        "pz": "100",
         "po": "1",
         "np": "1",
         "ut": "bd1d9ddb04089700cf9c27f6f7426281",
         "fltt": "2",
         "invt": "2",
         "fid": "f3",
-        "fs": "m:0 t:81 s:2048",
-        "fields": "f12",
-        "_": "1623833739532",
-    }
-    r = requests.get(url, params=params)
-    data_json = r.json()
-    if not data_json["data"]["diff"]:
-        return dict()
-    temp_df_sz = pd.DataFrame(data_json["data"]["diff"])
-    temp_df_sz["bj_id"] = 0
-    code_id_dict.update(dict(zip(temp_df_sz["f12"], temp_df_sz["bj_id"])))
-    code_id_dict = {
-        key: value - 1 if value == 1 else value + 1
-        for key, value in code_id_dict.items()
+        "fs": "b:MK0010,m:1+t:1,m:0 t:5,m:1+s:3,m:0+t:5,m:2",
+        "fields": "f3,f12,f13",
     }
+    temp_df = fetch_paginated_data(url, params)
+    code_id_dict = dict(zip(temp_df["f12"], temp_df["f13"]))
     return code_id_dict
 
 
@@ -121,7 +72,6 @@ def index_zh_a_hist(
             "fqt": "0",
             "beg": "0",
             "end": "20500000",
-            "_": "1623766962675",
         }
     except KeyError:
         params = {
@@ -133,7 +83,6 @@ def index_zh_a_hist(
             "fqt": "0",
             "beg": "0",
             "end": "20500000",
-            "_": "1623766962675",
         }
         r = requests.get(url, params=params)
         data_json = r.json()
@@ -147,7 +96,6 @@ def index_zh_a_hist(
                 "fqt": "0",
                 "beg": "0",
                 "end": "20500000",
-                "_": "1623766962675",
             }
             r = requests.get(url, params=params)
             data_json = r.json()
@@ -161,7 +109,6 @@ def index_zh_a_hist(
                     "fqt": "0",
                     "beg": "0",
                     "end": "20500000",
-                    "_": "1623766962675",
                 }
                 r = requests.get(url, params=params)
                 data_json = r.json()
@@ -175,7 +122,6 @@ def index_zh_a_hist(
                         "fqt": "0",
                         "beg": "0",
                         "end": "20500000",
-                        "_": "1623766962675",
                     }
     r = requests.get(url, params=params)
     data_json = r.json()
@@ -194,7 +140,6 @@ def index_zh_a_hist(
             "fqt": "0",
             "beg": "0",
             "end": "20500000",
-            "_": "1623766962675",
         }
         r = requests.get(url, params=params)
         data_json = r.json()
@@ -257,21 +202,17 @@ def index_zh_a_hist_min_em(
             params = {
                 "fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
                 "fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
-                "ut": "fa5fd1943c7b386f172d6893dbfba10b",
                 "iscr": "0",
                 "ndays": "5",
                 "secid": f"{code_id_dict[symbol]}.{symbol}",
-                "_": "1623766962675",
             }
         except KeyError:
             params = {
                 "fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
                 "fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
-                "ut": "fa5fd1943c7b386f172d6893dbfba10b",
                 "iscr": "0",
                 "ndays": "5",
                 "secid": f"1.{symbol}",
-                "_": "1623766962675",
             }
             r = requests.get(url, params=params)
             data_json = r.json()
@@ -279,11 +220,9 @@ def index_zh_a_hist_min_em(
                 params = {
                     "fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
                     "fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
-                    "ut": "fa5fd1943c7b386f172d6893dbfba10b",
                     "iscr": "0",
                     "ndays": "5",
                     "secid": f"0.{symbol}",
-                    "_": "1623766962675",
                 }
                 r = requests.get(url, params=params)
                 data_json = r.json()
@@ -291,11 +230,9 @@ def index_zh_a_hist_min_em(
                     params = {
                         "fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
                         "fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
-                        "ut": "fa5fd1943c7b386f172d6893dbfba10b",
                         "iscr": "0",
                         "ndays": "5",
                         "secid": f"47.{symbol}",
-                        "_": "1623766962675",
                     }
         r = requests.get(url, params=params)
         data_json = r.json()
@@ -310,7 +247,7 @@ def index_zh_a_hist_min_em(
             "最低",
             "成交量",
             "成交额",
-            "最新价",
+            "均价",
         ]
         temp_df.index = pd.to_datetime(temp_df["时间"], errors="coerce")
         temp_df = temp_df[start_date:end_date]
@@ -321,11 +258,11 @@ def index_zh_a_hist_min_em(
         temp_df["最低"] = pd.to_numeric(temp_df["最低"], 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["最新价"] = pd.to_numeric(temp_df["最新价"], errors="coerce")
+        temp_df["均价"] = pd.to_numeric(temp_df["均价"], errors="coerce")
         temp_df["时间"] = pd.to_datetime(temp_df["时间"]).astype(str)
         return temp_df
     else:
-        url = "http://push2his.eastmoney.com/api/qt/stock/kline/get"
+        url = "https://push2his.eastmoney.com/api/qt/stock/kline/get"
         try:
             params = {
                 "secid": f"{code_id_dict[symbol]}.{symbol}",
@@ -336,7 +273,6 @@ def index_zh_a_hist_min_em(
                 "fqt": "1",
                 "beg": "0",
                 "end": "20500000",
-                "_": "1630930917857",
             }
         except:  # noqa: E722
             params = {
@@ -348,7 +284,6 @@ def index_zh_a_hist_min_em(
                 "fqt": "1",
                 "beg": "0",
                 "end": "20500000",
-                "_": "1630930917857",
             }
             r = requests.get(url, params=params)
             data_json = r.json()
@@ -362,7 +297,6 @@ def index_zh_a_hist_min_em(
                     "fqt": "1",
                     "beg": "0",
                     "end": "20500000",
-                    "_": "1630930917857",
                 }
                 r = requests.get(url, params=params)
                 data_json = r.json()
@@ -376,7 +310,6 @@ def index_zh_a_hist_min_em(
                         "fqt": "1",
                         "beg": "0",
                         "end": "20500000",
-                        "_": "1630930917857",
                     }
         r = requests.get(url, params=params)
         data_json = r.json()
@@ -430,7 +363,7 @@ def index_zh_a_hist_min_em(
 
 if __name__ == "__main__":
     index_zh_a_hist_df = index_zh_a_hist(
-        symbol="800000",
+        symbol="932000",
         period="daily",
         start_date="19700101",
         end_date="22220101",
@@ -438,9 +371,9 @@ if __name__ == "__main__":
     print(index_zh_a_hist_df)
 
     index_zh_a_hist_min_em_df = index_zh_a_hist_min_em(
-        symbol="000001",
+        symbol="000003",
         period="1",
-        start_date="2024-03-20 09:30:00",
-        end_date="2024-03-20 19:00:00",
+        start_date="2025-03-17 09:30:00",
+        end_date="2025-03-17 19:00:00",
     )
     print(index_zh_a_hist_min_em_df)

akshare/interest_rate/interbank_rate_em.py

@@ -85,7 +85,6 @@ def rate_interbank(
         "p": "1",
         "pageNo": "1",
         "pageNum": "1",
-        "_": "1653376974939",
     }
     r = requests.get(url, params=params)
     data_json = r.json()

akshare/movie/jm.js

@@ -2254,4 +2254,3 @@ var webDES = function() {
     ;
 }
   , webInstace = new webDES();
-

akshare/news/__init__.py

@@ -2,5 +2,5 @@
 # -*- coding:utf-8 -*-
 """
 Date: 2020/10/18 12:54
-Desc: 
+Desc:
 """