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

akshare/air/air_hebei.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2022/3/5 12:33
+Date: 2024/4/25 17:20
 Desc: 河北省空气质量预报信息发布系统
-http://110.249.223.67/publish/
+https://110.249.223.67/publish
 每日 17 时发布
 等级划分
 1. 空气污染指数为0－50，空气质量级别为一级，空气质量状况属于优。此时，空气质量令人满意，基本无空气污染，各类人群可正常活动。
@@ -14,68 +14,94 @@ http://110.249.223.67/publish/
 6. 空气污染指数大于300，空气质量级别为六级，空气质量状况属于严重污染。此时，健康人群运动耐受力降低，有明显强烈症状，提前出现某些疾病，建议儿童、老年人和病人应当留在室内，避免体力消耗，一般人群应避免户外活动。
 发布单位：河北省环境应急与重污染天气预警中心 技术支持：中国科学院大气物理研究所 中科三清科技有限公司
 """
-from datetime import datetime
 
 import pandas as pd
 import requests
-from tqdm import tqdm
+from bs4 import BeautifulSoup
 
 
-def air_quality_hebei(symbol: str = "唐山市") -> pd.DataFrame:
+def air_quality_hebei() -> pd.DataFrame:
     """
     河北省空气质量预报信息发布系统-空气质量预报, 未来 6 天
-    http://110.249.223.67/publish/
-    :param symbol: choice of {'石家庄市', '唐山市', '秦皇岛市', '邯郸市', '邢台市', '保定市', '张家口市', '承德市', '沧州市', '廊坊市', '衡水市', '辛集市', '定州市'}
-    :type symbol: str
+    http://218.11.10.130:8080/#/application/home
     :return: city = "", 返回所有地区的数据; city="唐山市", 返回唐山市的数据
     :rtype: pandas.DataFrame
     """
-    url = "http://110.249.223.67/server/api/CityPublishInfo/GetProvinceAndCityPublishData"
-    params = {"publishDate": f"{datetime.today().strftime('%Y-%m-%d')} 16:00:00"}
-    r = requests.get(url, params=params)
-    json_data = r.json()
-    city_list = pd.DataFrame.from_dict(json_data["cityPublishDatas"], orient="columns")[
-        "CityName"
-    ].tolist()
-    outer_df = pd.DataFrame()
-    for i in tqdm(range(1, 7), leave=False):
-        inner_df = pd.DataFrame(
-            [item[f"Date{i}"] for item in json_data["cityPublishDatas"]],
-            index=city_list,
-        )
-        outer_df = pd.concat([outer_df, inner_df])
-    if symbol == "":
-        temp_df = outer_df.reset_index()
-        temp_df.columns = [
-            'city',
-            'date',
-            'pollutant',
-            'minAQI',
-            'maxAQI',
-            'level',
-        ]
-        temp_df['date'] = pd.to_datetime(temp_df['date']).dt.date
-        temp_df['minaqi'] = pd.to_numeric(temp_df['minaqi'])
-        temp_df['maxaqi'] = pd.to_numeric(temp_df['maxaqi'])
-        return temp_df
-    else:
-        temp_df = outer_df.reset_index()
-        temp_df.columns = [
-            'city',
-            'date',
-            'pollutant',
-            'minaqi',
-            'maxaqi',
-            'level',
-        ]
-        temp_df['date'] = pd.to_datetime(temp_df['date']).dt.date
-        temp_df['minaqi'] = pd.to_numeric(temp_df['minaqi'])
-        temp_df['maxaqi'] = pd.to_numeric(temp_df['maxaqi'])
-        temp_df = temp_df[temp_df['city'] == symbol]
-        temp_df.reset_index(inplace=True, drop=True)
-        return temp_df
+    url = "http://218.11.10.130:8080/api/hour/130000.xml"
+    r = requests.get(url)
+    soup = BeautifulSoup(r.content, features="xml")
+    data = []
+    cities = soup.find_all("City")
+    for city in cities:
+        pointers = city.find_all("Pointer")
+        for pointer in pointers:
+            row = {
+                "City": city.Name.text if city.Name else None,
+                "Region": pointer.Region.text if pointer.Region else None,
+                "Station": pointer.Name.text if pointer.Name else None,
+                "DateTime": pointer.DataTime.text if pointer.DataTime else None,
+                "AQI": pointer.AQI.text if pointer.AQI else None,
+                "Level": pointer.Level.text if pointer.Level else None,
+                "MaxPoll": pointer.MaxPoll.text if pointer.MaxPoll else None,
+                "Longitude": pointer.CLng.text if pointer.CLng else None,
+                "Latitude": pointer.CLat.text if pointer.CLat else None,
+            }
+            polls = pointer.find_all("Poll")
+            for poll in polls:
+                poll_name = poll.Name.text if poll.Name else None
+                poll_value = poll.Value.text if poll.Value else None
+                row[f"{poll_name}_Value"] = poll_value
+                row[f"{poll_name}_IAQI"] = poll.IAQI.text if poll.IAQI else None
+            data.append(row)
+
+    df = pd.DataFrame(data)
+    numeric_columns = ["AQI", "Longitude", "Latitude"] + [
+        col for col in df.columns if col.endswith("_Value") or col.endswith("_IAQI")
+    ]
+    for col in numeric_columns:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+
+    column_names = {
+        "City": "城市",
+        "Region": "区域",
+        "Station": "监测点",
+        "DateTime": "时间",
+        "Level": "空气质量等级",
+        "MaxPoll": "首要污染物",
+        "Longitude": "经度",
+        "Latitude": "纬度",
+        "SO2_Value": "二氧化硫_浓度",
+        "SO2_IAQI": "二氧化硫_IAQI",
+        "CO_Value": "一氧化碳_浓度",
+        "CO_IAQI": "一氧化碳_IAQI",
+        "NO2_Value": "二氧化氮_浓度",
+        "NO2_IAQI": "二氧化氮_IAQI",
+        "O3-1H_Value": "臭氧1小时_浓度",
+        "O3-1H_IAQI": "臭氧1小时_IAQI",
+        "O3-8H_Value": "臭氧8小时_浓度",
+        "O3-8H_IAQI": "臭氧8小时_IAQI",
+        "PM2.5_Value": "PM2.5_浓度",
+        "PM2.5_IAQI": "PM2.5_IAQI",
+        "PM10_Value": "PM10_浓度",
+        "PM10_IAQI": "PM10_IAQI",
+    }
+    df = df.rename(columns=column_names)
+    basic_columns = [
+        "城市",
+        "区域",
+        "监测点",
+        "时间",
+        "AQI",
+        "空气质量等级",
+        "首要污染物",
+        "经度",
+        "纬度",
+    ]
+    pollutant_columns = [col for col in df.columns if col not in basic_columns]
+    df = df[basic_columns + sorted(pollutant_columns)]
+    return df
 
 
 if __name__ == "__main__":
-    air_quality_hebei_df = air_quality_hebei(symbol="定州市")
+    air_quality_hebei_df = air_quality_hebei()
     print(air_quality_hebei_df)

akshare/air/air_zhenqi.py

@@ -1,12 +1,13 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2022/2/24 14:50
+Date: 2024/4/2 22:40
 Desc: 真气网-空气质量
 https://www.zq12369.com/environment.php
 空气质量在线监测分析平台的空气质量数据
 https://www.aqistudy.cn/
 """
+
 import json
 import os
 import re
@@ -14,7 +15,7 @@ from io import StringIO
 
 import pandas as pd
 import requests
-from py_mini_racer import py_mini_racer
+from py_mini_racer import MiniRacer
 
 from akshare.utils import demjson
 
@@ -29,9 +30,7 @@ def _get_js_path(name: str = None, module_file: str = None) -> str:
     :return: 路径
     :rtype: str
     """
-    module_folder = os.path.abspath(
-        os.path.dirname(os.path.dirname(module_file))
-    )
+    module_folder = os.path.abspath(os.path.dirname(os.path.dirname(module_file)))
     module_json_path = os.path.join(module_folder, "air", name)
     return module_json_path
 
@@ -71,6 +70,7 @@ def air_city_table() -> pd.DataFrame:
     """
     url = "https://www.zq12369.com/environment.php"
     date = "2020-05-01"
+    temp_df = None
     if len(date.split("-")) == 3:
         params = {
             "date": date,
@@ -83,13 +83,21 @@ def air_city_table() -> pd.DataFrame:
         del temp_df["降序"]
         temp_df.reset_index(inplace=True)
         temp_df["index"] = temp_df.index + 1
-        temp_df.columns = ["序号", "省份", "城市", "AQI", "空气质量", "PM2.5浓度", "首要污染物"]
+        temp_df.columns = [
+            "序号",
+            "省份",
+            "城市",
+            "AQI",
+            "空气质量",
+            "PM2.5浓度",
+            "首要污染物",
+        ]
         temp_df["AQI"] = pd.to_numeric(temp_df["AQI"])
     return temp_df
 
 
 def air_quality_watch_point(
-        city: str = "杭州", start_date: str = "20220408", end_date: str = "20220409"
+    city: str = "杭州", start_date: str = "20220408", end_date: str = "20220409"
 ) -> pd.DataFrame:
     """
     真气网-监测点空气质量-细化到具体城市的每个监测点
@@ -108,7 +116,7 @@ def air_quality_watch_point(
     end_date = "-".join([end_date[:4], end_date[4:6], end_date[6:]])
     url = "https://www.zq12369.com/api/zhenqiapi.php"
     file_data = _get_file_content(file_name="crypto.js")
-    ctx = py_mini_racer.MiniRacer()
+    ctx = MiniRacer()
     ctx.eval(file_data)
     method = "GETCITYPOINTAVG"
     ctx.call("encode_param", method)
@@ -122,12 +130,11 @@ def air_quality_watch_point(
         "city": city_param,
         "startTime": ctx.call("encode_param", start_date),
         "endTime": ctx.call("encode_param", end_date),
-        "secret": ctx.call(
-            "encode_secret", method, city_param, start_date, end_date
-        ),
+        "secret": ctx.call("encode_secret", method, city_param, start_date, end_date),
     }
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36"
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/81.0.4044.122 Safari/537.36"
     }
     r = requests.post(url, data=payload, headers=headers)
     data_text = r.text
@@ -137,10 +144,10 @@ def air_quality_watch_point(
 
 
 def air_quality_hist(
-        city: str = "杭州",
-        period: str = "day",
-        start_date: str = "20190327",
-        end_date: str = "20200427",
+    city: str = "杭州",
+    period: str = "day",
+    start_date: str = "20190327",
+    end_date: str = "20200427",
 ) -> pd.DataFrame:
     """
     真气网-空气历史数据
@@ -160,9 +167,9 @@ def air_quality_hist(
     end_date = "-".join([end_date[:4], end_date[4:6], end_date[6:]])
     url = "https://www.zq12369.com/api/newzhenqiapi.php"
     file_data = _get_file_content(file_name="outcrypto.js")
-    ctx = py_mini_racer.MiniRacer()
+    ctx = MiniRacer()
     ctx.eval(file_data)
-    appId = "4f0e3a273d547ce6b7147bfa7ceb4b6e"
+    app_id = "4f0e3a273d547ce6b7147bfa7ceb4b6e"
     method = "CETCITYPERIOD"
     timestamp = ctx.eval("timestamp = new Date().getTime()")
     p_text = json.dumps(
@@ -175,9 +182,7 @@ def air_quality_hist(
         ensure_ascii=False,
         indent=None,
     ).replace(' "', '"')
-    secret = ctx.call(
-        "hex_md5", appId + method + str(timestamp) + "WEB" + p_text
-    )
+    secret = ctx.call("hex_md5", app_id + method + str(timestamp) + "WEB" + p_text)
     payload = {
         "appId": "4f0e3a273d547ce6b7147bfa7ceb4b6e",
         "method": "CETCITYPERIOD",
@@ -200,30 +205,11 @@ def air_quality_hist(
     )
 
     headers = {
-        # 'Accept': '*/*',
-        # 'Accept-Encoding': 'gzip, deflate, br',
-        # 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
-        # 'Cache-Control': 'no-cache',
-        # 'Connection': 'keep-alive',
-        # 'Content-Length': '1174',
-        # 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
-        # 'Cookie': 'UM_distinctid=1800e5142c5b85-04b8f11aa852f3-1a343370-1fa400-1800e5142c6b7e; CNZZDATA1254317176=1502593570-1649496979-%7C1649507817; city=%E6%9D%AD%E5%B7%9E; SECKEY_ABVK=eSrbUhd28Mjo7jf8Rfh+uY5E9C+tAhQ8mOfYJHSjSfY%3D; BMAP_SECKEY=N5fGcwdWpeJW46eZRpR9GW3qdVnODGQwGm6JE0ELECQHJOTFc9MCuNdyf8OWUspFI6Xq4MMPxgVVr5I13odFOW6AQMgSPOtEvVHciC2NsQwb1pnmFtEaqyKHOUeavelt0ejBy6ETRD_4FXAhZb9FSbVIMPew7qwFX_kdPDxVJH-vHfCVhRx9XDZgb41B_T4D',
-        # 'Host': 'www.zq12369.com',
-        # 'Origin': 'https://www.zq12369.com',
-        # 'Pragma': 'no-cache',
-        # 'Referer': 'https://www.zq12369.com/environment.php?catid=4',
-        # 'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="100", "Google Chrome";v="100"',
-        # 'sec-ch-ua-mobile': '?0',
-        # 'sec-ch-ua-platform': '"Windows"',
-        # 'Sec-Fetch-Dest': 'empty',
-        # 'Sec-Fetch-Mode': 'cors',
-        # 'Sec-Fetch-Site': 'same-origin',
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)"
+        "Chrome/100.0.4896.75 Safari/537.36",
         "X-Requested-With": "XMLHttpRequest",
     }
-    params = {"param": ctx.call("AES.encrypt", need)}
     params = {"param": ctx.call("encode_param", need)}
-
     r = requests.post(url, data=params, headers=headers)
     temp_text = ctx.call("decryptData", r.text)
     data_json = demjson.decode(ctx.call("b.decode", temp_text))
@@ -304,7 +290,7 @@ if __name__ == "__main__":
         city="北京",
         period="day",
         start_date="20220801",
-        end_date="20220816",
+        end_date="20240402",
     )
     print(air_quality_hist_df)
 

akshare/air/sunrise_tad.py

@@ -1,14 +1,14 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/1/24 15:00
+Date: 2024/4/29 16:00
 Desc: 日出和日落数据
 https://www.timeanddate.com
 """
+
 from io import StringIO
 
 import pandas as pd
-import pypinyin
 import requests
 
 
@@ -31,11 +31,13 @@ def sunrise_city_list() -> list:
     city_list.extend([item.lower() for item in china_city_two_df.iloc[:, 1].tolist()])
     city_list.extend([item.lower() for item in china_city_two_df.iloc[:, 2].tolist()])
     city_list.extend([item.lower() for item in china_city_two_df.iloc[:, 3].tolist()])
-    city_list.extend([item.lower() for item in china_city_two_df.iloc[:, 4].dropna().tolist()])
+    city_list.extend(
+        [item.lower() for item in china_city_two_df.iloc[:, 4].dropna().tolist()]
+    )
     return city_list
 
 
-def sunrise_daily(date: str = "20200428", city: str = "北京") -> pd.DataFrame:
+def sunrise_daily(date: str = "20240428", city: str = "beijing") -> pd.DataFrame:
     """
     每日日出日落数据
     https://www.timeanddate.com/astronomy/china/shaoxing
@@ -46,24 +48,29 @@ def sunrise_daily(date: str = "20200428", city: str = "北京") -> pd.DataFrame:
     :return: 返回指定日期指定地区的日出日落数据
     :rtype: pandas.DataFrame
     """
-    if pypinyin.slug(city, separator='') in sunrise_city_list():
+    import urllib3
+
+    urllib3.disable_warnings()
+    if city in sunrise_city_list():
         year = date[:4]
         month = date[4:6]
-        url = f"https://www.timeanddate.com/sun/china/{pypinyin.slug(city, separator='')}?month={month}&year={year}"
-        r = requests.get(url)
+        url = f"https://www.timeanddate.com/sun/china/{city}?month={month}&year={year}"
+        r = requests.get(url, verify=False)
         table = pd.read_html(StringIO(r.text), header=2)[1]
-        month_df = table.iloc[:-1, ]
-        day_df = month_df[month_df.iloc[:, 0].astype(str).str.zfill(2) == date[6:]].copy()
+        month_df = table.iloc[:-1,]
+        day_df = month_df[
+            month_df.iloc[:, 0].astype(str).str.zfill(2) == date[6:]
+        ].copy()
         day_df.index = pd.to_datetime([date] * len(day_df), format="%Y%m%d")
         day_df.reset_index(inplace=True)
         day_df.rename(columns={"index": "date"}, inplace=True)
-        day_df['date'] = pd.to_datetime(day_df['date']).dt.date
+        day_df["date"] = pd.to_datetime(day_df["date"]).dt.date
         return day_df
     else:
         raise "请输入正确的城市名称"
 
 
-def sunrise_monthly(date: str = "20190801", city: str = "北京") -> pd.DataFrame:
+def sunrise_monthly(date: str = "20240428", city: str = "beijing") -> pd.DataFrame:
     """
     每个指定 date 所在月份的每日日出日落数据, 如果当前月份未到月底, 则以预测值填充
     https://www.timeanddate.com/astronomy/china/shaoxing
@@ -74,24 +81,32 @@ def sunrise_monthly(date: str = "20190801", city: str = "北京") -> pd.DataFram
     :return: 指定 date 所在月份的每日日出日落数据
     :rtype: pandas.DataFrame
     """
-    if pypinyin.slug(city, separator='') in sunrise_city_list():
+    import urllib3
+
+    urllib3.disable_warnings()
+    if city in sunrise_city_list():
         year = date[:4]
         month = date[4:6]
-        url = f"https://www.timeanddate.com/sun/china/{pypinyin.slug(city, separator='')}?month={month}&year={year}"
+        url = f"https://www.timeanddate.com/sun/china/{city}?month={month}&year={year}"
         r = requests.get(url)
         table = pd.read_html(StringIO(r.text), header=2)[1]
-        month_df = table.iloc[:-1, ].copy()
+        month_df = table.iloc[:-1,].copy()
         month_df.index = [date[:-2]] * len(month_df)
         month_df.reset_index(inplace=True)
-        month_df.rename(columns={"index": "date", }, inplace=True)
+        month_df.rename(
+            columns={
+                "index": "date",
+            },
+            inplace=True,
+        )
         return month_df
     else:
         raise "请输入正确的城市名称"
 
 
 if __name__ == "__main__":
-    sunrise_daily_df = sunrise_daily(date="20230220", city="北京")
+    sunrise_daily_df = sunrise_daily(date="20240428", city="beijing")
     print(sunrise_daily_df)
 
-    sunrise_monthly_df = sunrise_monthly(date="20230220", city="北京")
+    sunrise_monthly_df = sunrise_monthly(date="20240428", city="beijing")
     print(sunrise_monthly_df)

akshare/bank/bank_cbirc_2020.py

@@ -8,6 +8,7 @@ https://www.cbirc.gov.cn/cn/view/pages/ItemList.html?itemPId=923&itemId=4115&ite
 https://www.cbirc.gov.cn/cn/static/data/DocInfo/SelectByDocId/data_docId=881446.json
 2020 新接口
 """
+
 import warnings
 from io import StringIO
 
@@ -33,7 +34,7 @@ def bank_fjcf_total_num(item: str = "分局本级") -> int:
         "分局本级": "4115",
     }
     cbirc_headers = cbirc_headers_without_cookie_2020.copy()
-    main_url = "http://www.cbirc.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild"
+    main_url = "https://www.cbirc.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild"
     params = {
         "itemId": item_id_list[item],
         "pageSize": "18",
@@ -60,7 +61,7 @@ def bank_fjcf_total_page(item: str = "分局本级", begin: int = 1) -> int:
         "分局本级": "4115",
     }
     cbirc_headers = cbirc_headers_without_cookie_2020.copy()
-    main_url = "http://www.cbirc.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild"
+    main_url = "https://www.cbirc.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild"
     params = {
         "itemId": item_id_list[item],
         "pageSize": "18",
@@ -73,7 +74,7 @@ def bank_fjcf_total_page(item: str = "分局本级", begin: int = 1) -> int:
 
 
 def bank_fjcf_page_url(
-        page: int = 5, item: str = "分局本级", begin: int = 1
+    page: int = 5, item: str = "分局本级", begin: int = 1
 ) -> pd.DataFrame:
     """
     获取 首页-政务信息-行政处罚-银保监分局本级-每一页的 json 数据
@@ -92,7 +93,7 @@ def bank_fjcf_page_url(
         "分局本级": "4115",
     }
     cbirc_headers = cbirc_headers_without_cookie_2020.copy()
-    main_url = "http://www.cbirc.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild"
+    main_url = "https://www.cbirc.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild"
     temp_df = pd.DataFrame()
     for i_page in tqdm(range(begin, page + begin), leave=False):
         params = {
@@ -108,7 +109,7 @@ def bank_fjcf_page_url(
 
 
 def bank_fjcf_table_detail(
-        page: int = 5, item: str = "分局本级", begin: int = 1
+    page: int = 5, item: str = "分局本级", begin: int = 1
 ) -> pd.DataFrame:
     """
     获取 首页-政务信息-行政处罚-银保监分局本级-XXXX行政处罚信息公开表 数据
@@ -124,7 +125,7 @@ def bank_fjcf_table_detail(
     id_list = bank_fjcf_page_url(page=page, item=item, begin=begin)["docId"]
     big_df = pd.DataFrame()
     for item in id_list:
-        url = f"http://www.cbirc.gov.cn/cn/static/data/DocInfo/SelectByDocId/data_docId={item}.json"
+        url = f"https://www.cbirc.gov.cn/cn/static/data/DocInfo/SelectByDocId/data_docId={item}.json"
         res = requests.get(url)
         try:
             table_list = pd.read_html(StringIO(res.json()["data"]["docClob"]))[0]
@@ -146,7 +147,9 @@ def bank_fjcf_table_detail(
                 table_list = table_list[2:]
                 table_list.insert(2, pd.NA)
             else:
-                print(f"{item} 异常，请通过 https://www.cbirc.gov.cn/cn/view/pages/ItemDetail.html?docId={item} 查看")
+                print(
+                    f"{item} 异常，请通过 https://www.cbirc.gov.cn/cn/view/pages/ItemDetail.html?docId={item} 查看"
+                )
                 continue
 
             # 部分会变成嵌套列表, 这里还原
@@ -159,7 +162,7 @@ def bank_fjcf_table_detail(
             table_df.columns = ["内容"]
             big_df = pd.concat(objs=[big_df, table_df.T], ignore_index=True)
             # 解决有些页面缺少字段的问题, 都放到 try 里面
-        except:
+        except:  # noqa: E722
             warnings.warn(f"{item} 不是表格型数据，将跳过采集")
             continue
     if big_df.empty:
@@ -182,5 +185,5 @@ def bank_fjcf_table_detail(
 
 
 if __name__ == "__main__":
-    bank_fjcf_table_detail_df = bank_fjcf_table_detail(page=1, item="机关", begin=11)
+    bank_fjcf_table_detail_df = bank_fjcf_table_detail(page=1, item="机关", begin=1)
     print(bank_fjcf_table_detail_df)

akshare/bond/bond_cb_ths.py

@@ -1,24 +1,26 @@
 # -*- coding:utf-8 -*-
 # !/usr/bin/env python
 """
-Date: 2023/5/4 22:46
+Date: 2024/8/14 11:30
 Desc: 同花顺-数据中心-可转债
-http://data.10jqka.com.cn/ipo/bond/
+https://data.10jqka.com.cn/ipo/bond/
 """
-import requests
+
 import pandas as pd
+import requests
 
 
 def bond_zh_cov_info_ths() -> pd.DataFrame:
     """
     同花顺-数据中心-可转债
-    http://data.10jqka.com.cn/ipo/bond/
+    https://data.10jqka.com.cn/ipo/bond/
     :return: 可转债行情
     :rtype: pandas.DataFrame
     """
-    url = "http://data.10jqka.com.cn/ipo/kzz/"
+    url = "https://data.10jqka.com.cn/ipo/kzz/"
     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",
+        "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 = r.json()
@@ -67,12 +69,18 @@ def bond_zh_cov_info_ths() -> pd.DataFrame:
             "中签率",
         ]
     ]
-    temp_df["申购日期"] = pd.to_datetime(temp_df["申购日期"], format="%Y-%m-%d").dt.date
-    temp_df["中签公布日"] = pd.to_datetime(temp_df["中签公布日"], format="%Y-%m-%d").dt.date
+    temp_df["申购日期"] = pd.to_datetime(
+        temp_df["申购日期"], format="%Y-%m-%d", errors="coerce"
+    ).dt.date
+    temp_df["中签公布日"] = pd.to_datetime(
+        temp_df["中签公布日"], format="%Y-%m-%d", errors="coerce"
+    ).dt.date
     temp_df["上市日期"] = pd.to_datetime(
         temp_df["上市日期"], format="%Y-%m-%d", errors="coerce"
     ).dt.date
-    temp_df["到期时间"] = pd.to_datetime(temp_df["到期时间"], format="%Y-%m-%d").dt.date
+    temp_df["到期时间"] = pd.to_datetime(
+        temp_df["到期时间"], format="%Y-%m-%d", errors="coerce"
+    ).dt.date
     temp_df["每股获配额"] = pd.to_numeric(temp_df["每股获配额"], errors="coerce")
     temp_df["计划发行量"] = pd.to_numeric(temp_df["计划发行量"], errors="coerce")
     temp_df["实际发行量"] = pd.to_numeric(temp_df["实际发行量"], errors="coerce")