akshare 1.12.99__py3-none-any.whl → 1.15.72__py3-none-any.whl

akshare/index/index_yw.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/6/12 14:17
+Date: 2024/4/17 19:17
 Desc: 义乌小商品指数
 https://www.ywindex.com/Home/Product/index/
 """
+
 import pandas as pd
 import requests
 from bs4 import BeautifulSoup
@@ -19,14 +20,18 @@ def index_yw(symbol: str = "月景气指数") -> pd.DataFrame:
     :return: 指数结果
     :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 = "http://www.ywindex.com/Home/Product/index/"
+    url = "https://www.ywindex.com/Home/Product/index/"
     res = requests.get(url, verify=False)
-    soup = BeautifulSoup(res.text, "lxml")
+    soup = BeautifulSoup(res.text, features="lxml")
     table_name = (
         soup.find_all(attrs={"class": "tablex"})[name_num_dict[symbol]]
         .get_text()
@@ -44,38 +49,56 @@ def index_yw(symbol: str = "月景气指数") -> pd.DataFrame:
             :, :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"]).dt.date
-        table_df["景气指数"] = pd.to_numeric(table_df["景气指数"])
-        table_df["规模指数"] = pd.to_numeric(table_df["规模指数"])
-        table_df["效益指数"] = pd.to_numeric(table_df["效益指数"])
-        table_df["市场信心指数"] = pd.to_numeric(table_df["市场信心指数"])
-        table_df.sort_values(['期数'], inplace=True, ignore_index=True)
+        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"]).dt.date
-        table_df["价格指数"] = pd.to_numeric(table_df["价格指数"])
-        table_df["场内价格指数"] = pd.to_numeric(table_df["场内价格指数"])
-        table_df["网上价格指数"] = pd.to_numeric(table_df["网上价格指数"])
-        table_df["订单价格指数"] = pd.to_numeric(table_df["订单价格指数"])
-        table_df["出口价格指数"] = pd.to_numeric(table_df["出口价格指数"])
-        table_df.sort_values(['期数'], inplace=True, ignore_index=True)
+        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"
+        )
+        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"]).dt.date
-        table_df["价格指数"] = pd.to_numeric(table_df["价格指数"])
-        table_df["场内价格指数"] = pd.to_numeric(table_df["场内价格指数"])
-        table_df["网上价格指数"] = pd.to_numeric(table_df["网上价格指数"])
-        table_df["订单价格指数"] = pd.to_numeric(table_df["订单价格指数"])
-        table_df["出口价格指数"] = pd.to_numeric(table_df["出口价格指数"])
-        table_df.sort_values(['期数'], inplace=True, ignore_index=True)
+        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"
+        )
+        table_df.sort_values(["期数"], inplace=True, ignore_index=True)
         return table_df
 
 

akshare/index/index_zh_a_scope.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+"""
+Date: 2024/4/17 19:00
+Desc: 数库-A股新闻情绪指数
+https://www.chinascope.com/reasearch.html
+"""
+
+import pandas as pd
+import requests
+
+
+def index_news_sentiment_scope() -> pd.DataFrame:
+    """
+    数库-A股新闻情绪指数
+    https://www.chinascope.com/reasearch.html
+    :return: A股新闻情绪指数
+    :rtype: pandas.DataFrame
+    """
+    url = "https://www.chinascope.com/inews/senti/index"
+    params = {"period": "YEAR"}
+    r = requests.get(url=url, params=params)
+    data_json = r.json()
+    temp_df = pd.DataFrame(data_json)
+    temp_df.rename(
+        columns={
+            "tradeDate": "日期",
+            "maIndex1": "市场情绪指数",
+            "marketClose": "沪深300指数",
+        },
+        inplace=True,
+    )
+    temp_df = temp_df[
+        [
+            "日期",
+            "市场情绪指数",
+            "沪深300指数",
+        ]
+    ]
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["市场情绪指数"] = pd.to_numeric(temp_df["市场情绪指数"], errors="coerce")
+    temp_df["沪深300指数"] = pd.to_numeric(temp_df["沪深300指数"], errors="coerce")
+    return temp_df
+
+
+if __name__ == "__main__":
+    index_news_sentiment_scope_df = index_news_sentiment_scope()
+    print(index_news_sentiment_scope_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: 2025/1/10 18:10
 Desc: 东方财富网-指数行情数据
 """
 
@@ -85,6 +85,8 @@ def index_code_id_map_em() -> dict:
         key: value - 1 if value == 1 else value + 1
         for key, value in code_id_dict.items()
     }
+    # 单独增加品种
+    code_id_dict.update({"932000": 2})
     return code_id_dict
 
 
@@ -438,9 +440,9 @@ 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="932000",
         period="1",
-        start_date="2024-03-20 09:30:00",
-        end_date="2024-03-20 19:00:00",
+        start_date="2025-01-10 09:30:00",
+        end_date="2025-01-10 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",
@@ -87,6 +91,7 @@ def rate_interbank(
     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 +104,7 @@ 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 +124,9 @@ 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/movie_yien.py

@@ -5,13 +5,14 @@ Date: 2024/2/20 14:00
 Desc: 电影票房数据
 https://ys.endata.cn/BoxOffice/Movie
 """
+
 import datetime
 import json
 import os
 
 import pandas as pd
 import requests
-from py_mini_racer import py_mini_racer
+import py_mini_racer
 
 
 def _get_js_path(name: str = "", module_file: str = "") -> str:
@@ -77,7 +78,7 @@ def decrypt(origin_data: str = "") -> str:
 def movie_boxoffice_realtime() -> pd.DataFrame:
     """
     电影票房-实时票房
-    https://www.endata.com.cn/BoxOffice/BO/RealTime/reTimeBO.html
+    https://ys.endata.cn/BoxOffice/Movie
     :return: 实时票房数据
     :rtype: pandas.DataFrame
     """
@@ -93,8 +94,18 @@ def movie_boxoffice_realtime() -> pd.DataFrame:
     data_json = json.loads(decrypt(r.text))
     temp_df = pd.DataFrame(data_json["Data"]["Table1"])
     temp_df = temp_df.iloc[:, :7]
-    temp_df.columns = ["排序", "_", "影片名称", "实时票房", "累计票房", "上映天数", "票房占比"]
-    temp_df = temp_df[["排序", "影片名称", "实时票房", "票房占比", "上映天数", "累计票房"]]
+    temp_df.columns = [
+        "排序",
+        "_",
+        "影片名称",
+        "实时票房",
+        "累计票房",
+        "上映天数",
+        "票房占比",
+    ]
+    temp_df = temp_df[
+        ["排序", "影片名称", "实时票房", "票房占比", "上映天数", "累计票房"]
+    ]
     return temp_df
 
 
@@ -139,7 +150,17 @@ def movie_boxoffice_daily(date: str = "20240219") -> pd.DataFrame:
         "口碑指数",
     ]
     temp_df = temp_df[
-        ["排序", "影片名称", "单日票房", "环比变化", "累计票房", "平均票价", "场均人次", "口碑指数", "上映天数"]
+        [
+            "排序",
+            "影片名称",
+            "单日票房",
+            "环比变化",
+            "累计票房",
+            "平均票价",
+            "场均人次",
+            "口碑指数",
+            "上映天数",
+        ]
     ]
     return temp_df
 
@@ -179,12 +200,22 @@ def movie_boxoffice_weekly(date: str = "20240218") -> pd.DataFrame:
         "口碑指数",
     ]
     temp_df = temp_df[
-        ["排序", "影片名称", "排名变化", "单周票房", "环比变化", "累计票房", "平均票价", "场均人次", "口碑指数",
-         "上映天数"]
+        [
+            "排序",
+            "影片名称",
+            "排名变化",
+            "单周票房",
+            "环比变化",
+            "累计票房",
+            "平均票价",
+            "场均人次",
+            "口碑指数",
+            "上映天数",
+        ]
     ]
-    temp_df['单周票房'] = pd.to_numeric(temp_df['单周票房'], errors="coerce")
-    temp_df['环比变化'] = pd.to_numeric(temp_df['环比变化'], errors="coerce")
-    temp_df['累计票房'] = pd.to_numeric(temp_df['累计票房'], errors="coerce")
+    temp_df["单周票房"] = pd.to_numeric(temp_df["单周票房"], errors="coerce")
+    temp_df["环比变化"] = pd.to_numeric(temp_df["环比变化"], errors="coerce")
+    temp_df["累计票房"] = pd.to_numeric(temp_df["累计票房"], errors="coerce")
     return temp_df
 
 
@@ -220,9 +251,19 @@ def movie_boxoffice_monthly(date: str = "20240218") -> pd.DataFrame:
         "口碑指数",
     ]
     temp_df = temp_df[
-        ["排序", "影片名称", "单月票房", "月度占比", "平均票价", "场均人次", "上映日期", "口碑指数", "月内天数"]
+        [
+            "排序",
+            "影片名称",
+            "单月票房",
+            "月度占比",
+            "平均票价",
+            "场均人次",
+            "上映日期",
+            "口碑指数",
+            "月内天数",
+        ]
     ]
-    temp_df['上映日期'] = pd.to_datetime(temp_df['上映日期'], errors="coerce").dt.date
+    temp_df["上映日期"] = pd.to_datetime(temp_df["上映日期"], errors="coerce").dt.date
     return temp_df
 
 
@@ -258,8 +299,19 @@ def movie_boxoffice_yearly(date: str = "20240218") -> pd.DataFrame:
         "_",
     ]
     temp_df["排序"] = range(1, len(temp_df) + 1)
-    temp_df = temp_df[["排序", "影片名称", "类型", "总票房", "平均票价", "场均人次", "国家及地区", "上映日期"]]
-    temp_df['上映日期'] = pd.to_datetime(temp_df['上映日期'], errors="coerce").dt.date
+    temp_df = temp_df[
+        [
+            "排序",
+            "影片名称",
+            "类型",
+            "总票房",
+            "平均票价",
+            "场均人次",
+            "国家及地区",
+            "上映日期",
+        ]
+    ]
+    temp_df["上映日期"] = pd.to_datetime(temp_df["上映日期"], errors="coerce").dt.date
     return temp_df
 
 
@@ -298,9 +350,19 @@ def movie_boxoffice_yearly_first_week(date: str = "20201018") -> pd.DataFrame:
     ]
     temp_df["排序"] = range(1, len(temp_df) + 1)
     temp_df = temp_df[
-        ["排序", "影片名称", "类型", "首周票房", "占总票房比重", "场均人次", "国家及地区", "上映日期", "首周天数"]
+        [
+            "排序",
+            "影片名称",
+            "类型",
+            "首周票房",
+            "占总票房比重",
+            "场均人次",
+            "国家及地区",
+            "上映日期",
+            "首周天数",
+        ]
     ]
-    temp_df['上映日期'] = pd.to_datetime(temp_df['上映日期'], errors="coerce").dt.date
+    temp_df["上映日期"] = pd.to_datetime(temp_df["上映日期"], errors="coerce").dt.date
     return temp_df
 
 
@@ -336,7 +398,9 @@ def movie_boxoffice_cinema_daily(date: str = "20240219") -> pd.DataFrame:
         "场均人次",
         "上座率",
     ]
-    temp_df = temp_df[["排序", "影院名称", "单日票房", "单日场次", "场均人次", "场均票价", "上座率"]]
+    temp_df = temp_df[
+        ["排序", "影院名称", "单日票房", "单日场次", "场均人次", "场均票价", "上座率"]
+    ]
     return temp_df
 
 
@@ -378,7 +442,17 @@ def movie_boxoffice_cinema_weekly(date: str = "20240219") -> pd.DataFrame:
         "单日单厅票房",
         "单日单厅场次",
     ]
-    temp_df = temp_df[["排序", "影院名称", "当周票房", "单银幕票房", "场均人次", "单日单厅票房", "单日单厅场次"]]
+    temp_df = temp_df[
+        [
+            "排序",
+            "影院名称",
+            "当周票房",
+            "单银幕票房",
+            "场均人次",
+            "单日单厅票房",
+            "单日单厅场次",
+        ]
+    ]
     return temp_df
 
 

akshare/movie/video_yien.py

@@ -8,12 +8,13 @@ Desc: 艺恩
 综艺节目
 https://www.endata.com.cn/Video/index.html
 """
+
 import json
 import os
 
 import pandas as pd
 import requests
-from py_mini_racer import py_mini_racer
+import py_mini_racer
 
 
 def _get_js_path(name: str = "", module_file: str = "") -> str:
@@ -75,8 +76,19 @@ def video_tv() -> pd.DataFrame:
     data_json = json.loads(decrypt(r.text))
     temp_df = pd.DataFrame(data_json["Data"]["Table"])
     report_date = data_json["Data"]["Table1"][0]["MaxDate"]
-    temp_df.columns = ["排序", "名称", "类型", "播映指数", "用户热度", "媒体热度", "观看度", "好评度"]
-    temp_df = temp_df[["排序", "名称", "类型", "播映指数", "媒体热度", "用户热度", "好评度", "观看度"]]
+    temp_df.columns = [
+        "排序",
+        "名称",
+        "类型",
+        "播映指数",
+        "用户热度",
+        "媒体热度",
+        "观看度",
+        "好评度",
+    ]
+    temp_df = temp_df[
+        ["排序", "名称", "类型", "播映指数", "媒体热度", "用户热度", "好评度", "观看度"]
+    ]
     temp_df["统计日期"] = report_date
     return temp_df
 
@@ -95,8 +107,19 @@ def video_variety_show() -> pd.DataFrame:
     data_json = json.loads(decrypt(r.text))
     temp_df = pd.DataFrame(data_json["Data"]["Table"])
     report_date = data_json["Data"]["Table1"][0]["MaxDate"]
-    temp_df.columns = ["排序", "名称", "类型", "播映指数", "用户热度", "媒体热度", "观看度", "好评度"]
-    temp_df = temp_df[["排序", "名称", "类型", "播映指数", "媒体热度", "用户热度", "好评度", "观看度"]]
+    temp_df.columns = [
+        "排序",
+        "名称",
+        "类型",
+        "播映指数",
+        "用户热度",
+        "媒体热度",
+        "观看度",
+        "好评度",
+    ]
+    temp_df = temp_df[
+        ["排序", "名称", "类型", "播映指数", "媒体热度", "用户热度", "好评度", "观看度"]
+    ]
     temp_df["统计日期"] = report_date
     return temp_df