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

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

@@ -1,12 +1,14 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2022/5/24 20:13
+Date: 2024/5/11 22:00
 Desc: 东方财富网-经济数据-银行间拆借利率
+https://data.eastmoney.com/shibor/shibor.aspx
 """
+
 import pandas as pd
 import requests
-from tqdm import tqdm
+from akshare.utils.tqdm import get_tqdm
 
 
 def rate_interbank(
@@ -16,7 +18,7 @@ def rate_interbank(
 ):
     """
     东方财富-拆借利率一览-具体市场的具体品种的具体指标的拆借利率数据
-    具体 market 和 symbol 参见: http://data.eastmoney.com/shibor/shibor.aspx?m=sg&t=88&d=99333&cu=sgd&type=009065&p=79
+    具体 market 和 symbol 参见: https://data.eastmoney.com/shibor/shibor.aspx?m=sg&t=88&d=99333&cu=sgd&type=009065&p=79
     :param market: choice of {"上海银行同业拆借市场", "中国银行同业拆借市场", "伦敦银行同业拆借市场", "欧洲银行同业拆借市场", "香港银行同业拆借市场", "新加坡银行同业拆借市场"}
     :type market: str
     :param symbol: choice of {"Shibor人民币", "Chibor人民币", "Libor英镑", "***", "Sibor美元"}
@@ -69,9 +71,11 @@ def rate_interbank(
     url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
     params = {
         "reportName": "RPT_IMP_INTRESTRATEN",
-        "columns": "REPORT_DATE,REPORT_PERIOD,IR_RATE,CHANGE_RATE,INDICATOR_ID,LATEST_RECORD,MARKET,MARKET_CODE,CURRENCY,CURRENCY_CODE",
+        "columns": "REPORT_DATE,REPORT_PERIOD,IR_RATE,CHANGE_RATE,INDICATOR_ID,"
+        "LATEST_RECORD,MARKET,MARKET_CODE,CURRENCY,CURRENCY_CODE",
         "quoteColumns": "",
-        "filter": f"""(MARKET_CODE="{market_map[market]}")(CURRENCY_CODE="{symbol_map[symbol]}")(INDICATOR_ID="{indicator_map[indicator]}")""",
+        "filter": f"""(MARKET_CODE="{market_map[market]}")(CURRENCY_CODE="{symbol_map[symbol]}")
+        (INDICATOR_ID="{indicator_map[indicator]}")""",
         "pageNumber": "1",
         "pageSize": "500",
         "sortTypes": "-1",
@@ -81,12 +85,12 @@ def rate_interbank(
         "p": "1",
         "pageNo": "1",
         "pageNum": "1",
-        "_": "1653376974939",
     }
     r = requests.get(url, params=params)
     data_json = r.json()
     total_page = data_json["result"]["pages"]
     big_df = pd.DataFrame()
+    tqdm = get_tqdm()
     for page in tqdm(range(1, total_page + 1), leave=False):
         params.update(
             {
@@ -99,7 +103,7 @@ def rate_interbank(
         r = requests.get(url, params=params)
         data_json = r.json()
         temp_df = pd.DataFrame(data_json["result"]["data"])
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
     big_df.columns = [
         "报告日",
         "-",
@@ -119,9 +123,9 @@ def rate_interbank(
             "涨跌",
         ]
     ]
-    big_df["报告日"] = pd.to_datetime(big_df["报告日"]).dt.date
-    big_df["利率"] = pd.to_numeric(big_df["利率"])
-    big_df["涨跌"] = pd.to_numeric(big_df["涨跌"])
+    big_df["报告日"] = pd.to_datetime(big_df["报告日"], errors="coerce").dt.date
+    big_df["利率"] = pd.to_numeric(big_df["利率"], errors="coerce")
+    big_df["涨跌"] = pd.to_numeric(big_df["涨跌"], errors="coerce")
     big_df.sort_values(["报告日"], inplace=True)
     big_df.reset_index(inplace=True, drop=True)
     return big_df

akshare/movie/artist_yien.py

@@ -7,13 +7,14 @@ Desc: 艺恩-艺人
 艺人流量价值
 https://www.endata.com.cn/Marketing/Artist/business.html
 """
+
 import datetime
 import json
 import os
 
 import pandas as pd  # type: ignore
 import requests
-from py_mini_racer import py_mini_racer  # type: ignore
+import py_mini_racer  # type: ignore
 
 
 def _get_js_path(name: str = "", module_file: str = "") -> str:
@@ -80,8 +81,21 @@ def business_value_artist() -> pd.DataFrame:
     r.encoding = "utf8"
     data_json = json.loads(decrypt(r.text))
     temp_df = pd.DataFrame(data_json["Data"]["Table"])
-    temp_df.columns = ["排名", "-", "艺人", "商业价值", "-", "专业热度", "关注热度", "预测热度", "美誉度", "-"]
-    temp_df = temp_df[["排名", "艺人", "商业价值", "专业热度", "关注热度", "预测热度", "美誉度"]]
+    temp_df.columns = [
+        "排名",
+        "-",
+        "艺人",
+        "商业价值",
+        "-",
+        "专业热度",
+        "关注热度",
+        "预测热度",
+        "美誉度",
+        "-",
+    ]
+    temp_df = temp_df[
+        ["排名", "艺人", "商业价值", "专业热度", "关注热度", "预测热度", "美誉度"]
+    ]
     temp_df["统计日期"] = datetime.datetime.now().date().isoformat()
     return temp_df
 
@@ -105,8 +119,21 @@ def online_value_artist() -> pd.DataFrame:
     r.encoding = "utf8"
     data_json = json.loads(decrypt(r.text))
     temp_df = pd.DataFrame(data_json["Data"]["Table"])
-    temp_df.columns = ["排名", "-", "艺人", "-", "流量价值", "专业热度", "关注热度", "预测热度", "-", "带货力"]
-    temp_df = temp_df[["排名", "艺人", "流量价值", "专业热度", "关注热度", "预测热度", "带货力"]]
+    temp_df.columns = [
+        "排名",
+        "-",
+        "艺人",
+        "-",
+        "流量价值",
+        "专业热度",
+        "关注热度",
+        "预测热度",
+        "-",
+        "带货力",
+    ]
+    temp_df = temp_df[
+        ["排名", "艺人", "流量价值", "专业热度", "关注热度", "预测热度", "带货力"]
+    ]
     temp_df["统计日期"] = datetime.datetime.now().date().isoformat()
     return temp_df
 

akshare/movie/jm.js

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