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

akshare/stock_fundamental/stock_finance_ths.py

@@ -1,19 +1,22 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/11/20 13:20
+Date: 2024/11/2 15:20
 Desc: 同花顺-财务指标-主要指标
 https://basic.10jqka.com.cn/new/000063/finance.html
 """
+
 import json
 
 import pandas as pd
 import requests
 from bs4 import BeautifulSoup
 
+from akshare.utils.cons import headers
+
 
 def stock_financial_abstract_ths(
-        symbol: str = "000063", indicator: str = "按报告期"
+    symbol: str = "000063", indicator: str = "按报告期"
 ) -> pd.DataFrame:
     """
     同花顺-财务指标-主要指标
@@ -26,14 +29,9 @@ def stock_financial_abstract_ths(
     :rtype: pandas.DataFrame
     """
     url = f"https://basic.10jqka.com.cn/new/{symbol}/finance.html"
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                      "AppleWebKit/537.36 (KHTML, like Gecko) "
-                      "Chrome/89.0.4389.90 Safari/537.36",
-    }
     r = requests.get(url, headers=headers)
-    soup = BeautifulSoup(r.text, "lxml")
-    data_text = soup.find("p", attrs={"id": "main"}).string
+    soup = BeautifulSoup(r.text, features="lxml")
+    data_text = soup.find(name="p", attrs={"id": "main"}).string
     data_json = json.loads(data_text)
     df_index = [
         item[0] if isinstance(item, list) else item for item in data_json["title"]
@@ -57,7 +55,7 @@ def stock_financial_abstract_ths(
 
 
 def stock_financial_debt_ths(
-        symbol: str = "000063", indicator: str = "按报告期"
+    symbol: str = "000063", indicator: str = "按报告期"
 ) -> pd.DataFrame:
     """
     同花顺-财务指标-资产负债表
@@ -71,13 +69,8 @@ def stock_financial_debt_ths(
     :rtype: pandas.DataFrame
     """
     url = f"https://basic.10jqka.com.cn/api/stock/finance/{symbol}_debt.json"
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                      "AppleWebKit/537.36 (KHTML, like Gecko) "
-                      "Chrome/89.0.4389.90 Safari/537.36",
-    }
     r = requests.get(url, headers=headers)
-    data_json = json.loads(json.loads(r.text)['flashData'])
+    data_json = json.loads(json.loads(r.text)["flashData"])
     df_index = [
         item[0] if isinstance(item, list) else item for item in data_json["title"]
     ]
@@ -96,7 +89,7 @@ def stock_financial_debt_ths(
 
 
 def stock_financial_benefit_ths(
-        symbol: str = "000063", indicator: str = "按报告期"
+    symbol: str = "000063", indicator: str = "按报告期"
 ) -> pd.DataFrame:
     """
     同花顺-财务指标-利润表
@@ -110,13 +103,8 @@ def stock_financial_benefit_ths(
     :rtype: pandas.DataFrame
     """
     url = f"https://basic.10jqka.com.cn/api/stock/finance/{symbol}_benefit.json"
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                      "AppleWebKit/537.36 (KHTML, like Gecko) "
-                      "Chrome/89.0.4389.90 Safari/537.36",
-    }
     r = requests.get(url, headers=headers)
-    data_json = json.loads(json.loads(r.text)['flashData'])
+    data_json = json.loads(json.loads(r.text)["flashData"])
     df_index = [
         item[0] if isinstance(item, list) else item for item in data_json["title"]
     ]
@@ -139,7 +127,7 @@ def stock_financial_benefit_ths(
 
 
 def stock_financial_cash_ths(
-        symbol: str = "000063", indicator: str = "按报告期"
+    symbol: str = "000063", indicator: str = "按报告期"
 ) -> pd.DataFrame:
     """
     同花顺-财务指标-现金流量表
@@ -153,13 +141,8 @@ def stock_financial_cash_ths(
     :rtype: pandas.DataFrame
     """
     url = f"https://basic.10jqka.com.cn/api/stock/finance/{symbol}_cash.json"
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                      "AppleWebKit/537.36 (KHTML, like Gecko) "
-                      "Chrome/89.0.4389.90 Safari/537.36",
-    }
     r = requests.get(url, headers=headers)
-    data_json = json.loads(json.loads(r.text)['flashData'])
+    data_json = json.loads(json.loads(r.text)["flashData"])
     df_index = [
         item[0] if isinstance(item, list) else item for item in data_json["title"]
     ]
@@ -181,6 +164,102 @@ def stock_financial_cash_ths(
     return temp_df
 
 
+def stock_management_change_ths(symbol: str = "688981") -> pd.DataFrame:
+    """
+    同花顺-公司大事-高管持股变动
+    https://basic.10jqka.com.cn/new/688981/event.html
+    :param symbol: 股票代码
+    :type symbol: str
+    :return: 同花顺-公司大事-高管持股变动
+    :rtype: pandas.DataFrame
+    """
+    url = f"https://basic.10jqka.com.cn/new/{symbol}/event.html"
+    r = requests.get(url, headers=headers)
+    r.encoding = "gb2312"
+    soup = BeautifulSoup(r.text, features="lxml")
+    soup_find = soup.find(name="table", attrs={"class": "data_table_1 m_table m_hl"})
+    if soup_find is not None:
+        content_list = [item.text.strip() for item in soup_find]
+        column_names = content_list[1].split("\n")
+        row = (
+            content_list[3]
+            .replace(" ", "")
+            .replace("\t", "")
+            .replace("\n\n", "")
+            .replace("   ", "\n")
+            .replace("\n\n", "\n")
+            .split("\n")
+        )
+        row = [item for item in row if item != ""]
+        new_rows = []
+        step = len(column_names)
+        for i in range(0, len(row), step):
+            new_rows.append(row[i : i + step])
+        temp_df = pd.DataFrame(new_rows, columns=column_names)
+        temp_df.sort_values(by="变动日期", ignore_index=True, inplace=True)
+        temp_df["变动日期"] = pd.to_datetime(
+            temp_df["变动日期"], errors="coerce"
+        ).dt.date
+        temp_df.rename(
+            columns={
+                "变动数量（股）": "变动数量",
+                "交易均价（元）": "交易均价",
+                "剩余股数（股）": "剩余股数",
+            },
+            inplace=True,
+        )
+        return temp_df
+    return pd.DataFrame()
+
+
+def stock_shareholder_change_ths(symbol: str = "688981") -> pd.DataFrame:
+    """
+    同花顺-公司大事-股东持股变动
+    https://basic.10jqka.com.cn/new/688981/event.html
+    :param symbol: 股票代码
+    :type symbol: str
+    :return: 同花顺-公司大事-股东持股变动
+    :rtype: pandas.DataFrame
+    """
+    url = f"https://basic.10jqka.com.cn/new/{symbol}/event.html"
+    r = requests.get(url, headers=headers)
+    r.encoding = "gb2312"
+    soup = BeautifulSoup(r.text, features="lxml")
+    soup_find = soup.find(name="table", attrs={"class": "m_table data_table_1 m_hl"})
+    if soup_find is not None:
+        content_list = [item.text.strip() for item in soup_find]
+        column_names = content_list[1].split("\n")
+        row = (
+            content_list[3]
+            .replace("\t", "")
+            .replace("\n\n", "")
+            .replace("   ", "\n")
+            .replace(" ", "")
+            .replace("\n\n", "\n")
+            .split("\n")
+        )
+        row = [item for item in row if item != ""]
+        new_rows = []
+        step = len(column_names)
+        for i in range(0, len(row), step):
+            new_rows.append(row[i : i + step])
+        temp_df = pd.DataFrame(new_rows, columns=column_names)
+        temp_df.sort_values(by="公告日期", ignore_index=True, inplace=True)
+        temp_df["公告日期"] = pd.to_datetime(
+            temp_df["公告日期"], errors="coerce"
+        ).dt.date
+        temp_df.rename(
+            columns={
+                "变动数量(股)": "变动数量",
+                "交易均价(元)": "交易均价",
+                "剩余股份总数(股)": "剩余股份总数",
+            },
+            inplace=True,
+        )
+        return temp_df
+    return pd.DataFrame()
+
+
 if __name__ == "__main__":
     stock_financial_abstract_ths_df = stock_financial_abstract_ths(
         symbol="000063", indicator="按报告期"
@@ -198,7 +277,7 @@ if __name__ == "__main__":
     print(stock_financial_abstract_ths_df)
 
     stock_financial_debt_ths_df = stock_financial_debt_ths(
-        symbol="000063", indicator="按报告期"
+        symbol="002004", indicator="按报告期"
     )
     print(stock_financial_debt_ths_df)
 
@@ -236,3 +315,9 @@ if __name__ == "__main__":
         symbol="000063", indicator="按单季度"
     )
     print(stock_financial_cash_ths_df)
+
+    stock_management_change_ths_df = stock_management_change_ths(symbol="688981")
+    print(stock_management_change_ths_df)
+
+    stock_shareholder_change_ths_df = stock_shareholder_change_ths(symbol="688981")
+    print(stock_shareholder_change_ths_df)

akshare/stock_fundamental/stock_mda_ym.py

@@ -1,10 +1,11 @@
 # -*- coding:utf-8 -*-
 # !/usr/bin/env python
 """
-Date: 2024/2/14 12:30
+Date: 2024/9/3 21:00
 Desc: 益盟-F10-管理层讨论与分析
 https://f10.emoney.cn/f10/zbyz/1000001
 """
+
 import pandas as pd
 import requests
 from bs4 import BeautifulSoup
@@ -21,7 +22,7 @@ def stock_mda_ym(symbol: str = "000001") -> pd.DataFrame:
     """
     url = f"http://f10.emoney.cn/f10/zygc/{symbol}"
     r = requests.get(url)
-    soup = BeautifulSoup(r.text, "lxml")
+    soup = BeautifulSoup(r.text, features="lxml")
     year_list = [
         item.text.strip()
         for item in soup.find(attrs={"class": "swlab_t"}).find_all("li")
@@ -32,9 +33,10 @@ def stock_mda_ym(symbol: str = "000001") -> pd.DataFrame:
     ]
     big_df = pd.DataFrame([year_list, talk_list]).T
     big_df.columns = ["报告期", "内容"]
+    big_df.sort_values(by=["报告期"], ignore_index=True, inplace=True)
     return big_df
 
 
 if __name__ == "__main__":
-    stock_mda_ym_df = stock_mda_ym(symbol="000002")
+    stock_mda_ym_df = stock_mda_ym(symbol="000001")
     print(stock_mda_ym_df)

akshare/stock_fundamental/stock_notice.py

@@ -1,19 +1,23 @@
 # -*- coding:utf-8 -*-
 # !/usr/bin/env python
 """
-Date: 2022/5/13 19:25
+Date: 2024/6/13 13:00
 Desc: 东方财富网-数据中心-公告大全-沪深 A 股公告
-http://data.eastmoney.com/notices/hsa/5.html
+https://data.eastmoney.com/notices/hsa/5.html
 """
+
+import math
+
 import pandas as pd
 import requests
-from tqdm import tqdm
+
+from akshare.utils.tqdm import get_tqdm
 
 
 def stock_notice_report(symbol: str = "全部", date: str = "20220511") -> pd.DataFrame:
     """
     东方财富网-数据中心-公告大全-沪深京 A 股公告
-    http://data.eastmoney.com/notices/hsa/5.html
+    https://data.eastmoney.com/notices/hsa/5.html
     :param symbol: 报告类型; choice of {"全部", "重大事项", "财务报告", "融资公告", "风险提示", "资产重组", "信息变更", "持股变动"}
     :type symbol: str
     :param date: 制定日期
@@ -21,7 +25,7 @@ def stock_notice_report(symbol: str = "全部", date: str = "20220511") -> pd.Da
     :return: 沪深京 A 股公告
     :rtype: pandas.DataFrame
     """
-    url = "http://np-anotice-stock.eastmoney.com/api/security/ann"
+    url = "https://np-anotice-stock.eastmoney.com/api/security/ann"
     report_map = {
         "全部": "0",
         "财务报告": "1",
@@ -45,11 +49,9 @@ def stock_notice_report(symbol: str = "全部", date: str = "20220511") -> pd.Da
     }
     r = requests.get(url, params=params)
     data_json = r.json()
-    import math
-
     total_page = math.ceil(data_json["data"]["total_hits"] / 100)
-
     big_df = pd.DataFrame()
+    tqdm = get_tqdm()
     for page in tqdm(range(1, int(total_page) + 1), leave=False):
         params.update(
             {
@@ -66,16 +68,16 @@ def stock_notice_report(symbol: str = "全部", date: str = "20220511") -> pd.Da
             temp_columns_df = pd.DataFrame(
                 [item["columns"][0] for item in data_json["data"]["list"]]
             )
-        except:
+        except:  # noqa: E722
             continue
         del temp_df["codes"]
         del temp_df["columns"]
-        temp_df = pd.concat([temp_df, temp_columns_df, temp_codes_df], axis=1)
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
+        temp_df = pd.concat(objs=[temp_df, temp_columns_df, temp_codes_df], axis=1)
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
 
     big_df.rename(
         columns={
-            "art_code": "_",
+            "art_code": "编码",
             "display_time": "-",
             "eiTime": "-",
             "notice_date": "公告日期",
@@ -90,6 +92,8 @@ def stock_notice_report(symbol: str = "全部", date: str = "20220511") -> pd.Da
         },
         inplace=True,
     )
+    url = "https://data.eastmoney.com/notices/detail/"
+    big_df["网址"] = url + big_df["代码"] + "/" + big_df["编码"] + ".html"
     big_df = big_df[
         [
             "代码",
@@ -97,17 +101,27 @@ def stock_notice_report(symbol: str = "全部", date: str = "20220511") -> pd.Da
             "公告标题",
             "公告类型",
             "公告日期",
+            "网址",
         ]
     ]
-    big_df["公告日期"] = pd.to_datetime(big_df["公告日期"]).dt.date
+    big_df["公告日期"] = pd.to_datetime(big_df["公告日期"], errors="coerce").dt.date
     return big_df
 
 
 if __name__ == "__main__":
-    stock_notice_report_df = stock_notice_report(symbol='财务报告', date="20220511")
+    stock_notice_report_df = stock_notice_report(symbol="财务报告", date="20240612")
     print(stock_notice_report_df)
 
-    item_list = ["全部", "财务报告", "融资公告", "风险提示", "信息变更", "重大事项", "资产重组", "持股变动"]
+    item_list = [
+        "全部",
+        "财务报告",
+        "融资公告",
+        "风险提示",
+        "信息变更",
+        "重大事项",
+        "资产重组",
+        "持股变动",
+    ]
     for temp_item in item_list:
         stock_notice_report_df = stock_notice_report(symbol=temp_item, date="20220511")
         print(stock_notice_report_df)

akshare/stock_fundamental/stock_profit_forecast_em.py

@@ -5,6 +5,7 @@ Date: 2024/1/6 15:00
 Desc: 东方财富网-数据中心-研究报告-盈利预测
 https://data.eastmoney.com/report/profitforecast.jshtml
 """
+
 import pandas as pd
 import requests
 
@@ -15,7 +16,8 @@ def stock_profit_forecast_em(symbol: str = "") -> pd.DataFrame:
     """
     东方财富网-数据中心-研究报告-盈利预测
     https://data.eastmoney.com/report/profitforecast.jshtml
-    :param symbol: "", 默认为获取全部数据; symbol="船舶制造", 则获取具体行业板块的数据; 行业板块可以通过 ak.stock_board_industry_name_em() 接口获取
+    :param symbol: "", 默认为获取全部数据; symbol="船舶制造", 则获取具体行业板块的数据;
+    行业板块可以通过 ak.stock_board_industry_name_em() 接口获取
     :type symbol: str
     :return: 盈利预测
     :rtype: pandas.DataFrame
@@ -34,7 +36,6 @@ def stock_profit_forecast_em(symbol: str = "") -> pd.DataFrame:
     }
     if symbol:
         params.update({"filter": f'(INDUSTRY_BOARD="{symbol}")'})
-
     r = requests.get(url, params=params)
     data_json = r.json()
     page_num = int(data_json["result"]["pages"])
@@ -52,7 +53,7 @@ def stock_profit_forecast_em(symbol: str = "") -> pd.DataFrame:
         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.reset_index(inplace=True)
     big_df["index"] = big_df.index + 1
@@ -94,7 +95,6 @@ def stock_profit_forecast_em(symbol: str = "") -> pd.DataFrame:
         "_",
         "_",
     ]
-
     big_df = big_df[
         [
             "序号",
@@ -112,11 +112,12 @@ def stock_profit_forecast_em(symbol: str = "") -> pd.DataFrame:
             f"{year4}预测每股收益",
         ]
     ]
-    big_df["机构投资评级(近六个月)-买入"].fillna(0, inplace=True)
-    big_df["机构投资评级(近六个月)-增持"].fillna(0, inplace=True)
-    big_df["机构投资评级(近六个月)-中性"].fillna(0, inplace=True)
-    big_df["机构投资评级(近六个月)-减持"].fillna(0, inplace=True)
-    big_df["机构投资评级(近六个月)-卖出"].fillna(0, inplace=True)
+    big_df["机构投资评级(近六个月)-买入"] = big_df[
+        "机构投资评级(近六个月)-买入"
+    ].fillna(0)
+    big_df["机构投资评级(近六个月)-增持"] = big_df[
+        "机构投资评级(近六个月)-增持"
+    ].fillna(0)
     big_df["研报数"] = pd.to_numeric(big_df["研报数"], errors="coerce")
     big_df["机构投资评级(近六个月)-买入"] = pd.to_numeric(
         big_df["机构投资评级(近六个月)-买入"], errors="coerce"
@@ -133,10 +134,27 @@ def stock_profit_forecast_em(symbol: str = "") -> pd.DataFrame:
     big_df["机构投资评级(近六个月)-卖出"] = pd.to_numeric(
         big_df["机构投资评级(近六个月)-卖出"], errors="coerce"
     )
-    big_df[f"{year1}预测每股收益"] = pd.to_numeric(big_df[f"{year1}预测每股收益"], errors="coerce")
-    big_df[f"{year2}预测每股收益"] = pd.to_numeric(big_df[f"{year2}预测每股收益"], errors="coerce")
-    big_df[f"{year3}预测每股收益"] = pd.to_numeric(big_df[f"{year3}预测每股收益"], errors="coerce")
-    big_df[f"{year4}预测每股收益"] = pd.to_numeric(big_df[f"{year4}预测每股收益"], errors="coerce")
+    big_df["机构投资评级(近六个月)-中性"] = big_df[
+        "机构投资评级(近六个月)-中性"
+    ].fillna(0)
+    big_df["机构投资评级(近六个月)-减持"] = big_df[
+        "机构投资评级(近六个月)-减持"
+    ].fillna(0)
+    big_df["机构投资评级(近六个月)-卖出"] = big_df[
+        "机构投资评级(近六个月)-卖出"
+    ].fillna(0)
+    big_df[f"{year1}预测每股收益"] = pd.to_numeric(
+        big_df[f"{year1}预测每股收益"], errors="coerce"
+    )
+    big_df[f"{year2}预测每股收益"] = pd.to_numeric(
+        big_df[f"{year2}预测每股收益"], errors="coerce"
+    )
+    big_df[f"{year3}预测每股收益"] = pd.to_numeric(
+        big_df[f"{year3}预测每股收益"], errors="coerce"
+    )
+    big_df[f"{year4}预测每股收益"] = pd.to_numeric(
+        big_df[f"{year4}预测每股收益"], errors="coerce"
+    )
     big_df.sort_values(["研报数"], ascending=False, inplace=True, ignore_index=True)
     big_df["序号"] = range(1, len(big_df) + 1)
     return big_df

akshare/stock_fundamental/stock_profit_forecast_ths.py

@@ -1,13 +1,18 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/4/9 21:44
+Date: 2024/8/28 15:00
 Desc: 同花顺-盈利预测
 https://basic.10jqka.com.cn/new/600519/worth.html
 """
+
+from io import StringIO
+
 import pandas as pd
 import requests
 
+from akshare.utils.cons import headers
+
 
 def stock_profit_forecast_ths(
     symbol: str = "600519", indicator: str = "预测年报每股收益"
@@ -23,21 +28,18 @@ def stock_profit_forecast_ths(
     :rtype: pandas.DataFrame
     """
     url = f"https://basic.10jqka.com.cn/new/{symbol}/worth.html"
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
-    }
     r = requests.get(url, headers=headers)
     r.encoding = "gbk"
     if indicator == "预测年报每股收益":
-        temp_df = pd.read_html(r.text)[0]
+        temp_df = pd.read_html(StringIO(r.text))[0]
         temp_df["年度"] = temp_df["年度"].astype(str)
         return temp_df
     if indicator == "预测年报净利润":
-        temp_df = pd.read_html(r.text)[1]
+        temp_df = pd.read_html(StringIO(r.text))[1]
         temp_df["年度"] = temp_df["年度"].astype(str)
         return temp_df
     if indicator == "业绩预测详表-机构":
-        temp_df = pd.read_html(r.text)[2]
+        temp_df = pd.read_html(StringIO(r.text))[2]
         columns_list = []
         for item in temp_df.columns:
             columns_list.append(item[1])
@@ -51,7 +53,7 @@ def stock_profit_forecast_ths(
         temp_df["报告日期"] = pd.to_datetime(temp_df["报告日期"]).dt.date
         return temp_df
     if indicator == "业绩预测详表-详细指标预测":
-        temp_df = pd.read_html(r.text)[3]
+        temp_df = pd.read_html(StringIO(r.text))[3]
         temp_df.columns = [
             item.replace("（", "-").replace("）", "") for item in temp_df.columns
         ]
@@ -59,6 +61,13 @@ def stock_profit_forecast_ths(
 
 
 if __name__ == "__main__":
-    for item in ["预测年报每股收益", "预测年报净利润", "业绩预测详表-机构", "业绩预测详表-详细指标预测"]:
-        stock_profit_forecast_ths_df = stock_profit_forecast_ths(symbol="600519", indicator=item)
+    for _item in [
+        "预测年报每股收益",
+        "预测年报净利润",
+        "业绩预测详表-机构",
+        "业绩预测详表-详细指标预测",
+    ]:
+        stock_profit_forecast_ths_df = stock_profit_forecast_ths(
+            symbol="600519", indicator=_item
+        )
         print(stock_profit_forecast_ths_df)