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

akshare/economic/marco_cnbs.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/7/19 18:20
+Date: 2023/8/14 11:10
 Desc: 国家金融与发展实验室-中国宏观杠杆率数据
 http://114.115.232.154:8080/
 """
+
 import pandas as pd
 
 
@@ -50,16 +51,20 @@ def macro_cnbs() -> pd.DataFrame:
         "金融部门负债方",
     ]
     temp_df = temp_df.reindex(columns=column_order)
-
     temp_df["居民部门"] = pd.to_numeric(temp_df["居民部门"], errors="coerce")
-    temp_df["非金融企业部门"] = pd.to_numeric(temp_df["非金融企业部门"], errors="coerce")
+    temp_df["非金融企业部门"] = pd.to_numeric(
+        temp_df["非金融企业部门"], errors="coerce"
+    )
     temp_df["政府部门"] = pd.to_numeric(temp_df["政府部门"], errors="coerce")
     temp_df["中央政府"] = pd.to_numeric(temp_df["中央政府"], errors="coerce")
     temp_df["地方政府"] = pd.to_numeric(temp_df["地方政府"], errors="coerce")
     temp_df["实体经济部门"] = pd.to_numeric(temp_df["实体经济部门"], errors="coerce")
-    temp_df["金融部门资产方"] = pd.to_numeric(temp_df["金融部门资产方"], errors="coerce")
-    temp_df["金融部门负债方"] = pd.to_numeric(temp_df["金融部门负债方"], errors="coerce")
-
+    temp_df["金融部门资产方"] = pd.to_numeric(
+        temp_df["金融部门资产方"], errors="coerce"
+    )
+    temp_df["金融部门负债方"] = pd.to_numeric(
+        temp_df["金融部门负债方"], errors="coerce"
+    )
     return temp_df
 
 

akshare/energy/energy_carbon.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2022/5/25 16:05
+Date: 2024/6/25 15:00
 Desc: 碳排放交易
 北京市碳排放权电子交易平台-北京市碳排放权公开交易行情
 https://www.bjets.com.cn/article/jyxx/
@@ -18,8 +18,8 @@ http://www.cerx.cn/dailynewsOuter/index.htm
 广州碳排放权交易中心-行情信息
 http://www.cnemission.com/article/hqxx/
 """
-import re
-from functools import lru_cache
+
+from io import StringIO
 
 import pandas as pd
 import requests
@@ -27,9 +27,9 @@ from bs4 import BeautifulSoup
 from tqdm import tqdm
 
 from akshare.utils import demjson
+from akshare.utils.cons import headers
 
 
-@lru_cache()
 def energy_carbon_domestic(symbol: str = "湖北") -> pd.DataFrame:
     """
     碳交易网-行情信息
@@ -39,9 +39,7 @@ def energy_carbon_domestic(symbol: str = "湖北") -> pd.DataFrame:
     :return: 行情信息
     :rtype: pandas.DataFrame
     """
-    url = (
-        "http://k.tanjiaoyi.com:8080/KDataController/getHouseDatasInAverage.do"
-    )
+    url = "http://k.tanjiaoyi.com:8080/KDataController/getHouseDatasInAverage.do"
     params = {
         "lcnK": "53f75bfcefff58e4046ccfa42171636c",
         "brand": "TAN",
@@ -69,14 +67,13 @@ def energy_carbon_domestic(symbol: str = "湖北") -> pd.DataFrame:
             "地点",
         ]
     ]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"]).dt.date
-    temp_df["成交价"] = pd.to_numeric(temp_df["成交价"])
-    temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
-    temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["成交价"] = pd.to_numeric(temp_df["成交价"], 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")
     return temp_df
 
 
-@lru_cache()
 def energy_carbon_bj() -> pd.DataFrame:
     """
     北京市碳排放权电子交易平台-北京市碳排放权公开交易行情
@@ -85,8 +82,8 @@ def energy_carbon_bj() -> pd.DataFrame:
     :rtype: pandas.DataFrame
     """
     url = "https://www.bjets.com.cn/article/jyxx/"
-    r = requests.get(url)
-    soup = BeautifulSoup(r.text, "lxml")
+    r = requests.get(url, verify=False, headers=headers)
+    soup = BeautifulSoup(r.text, features="lxml")
     total_page = (
         soup.find("table")
         .find("script")
@@ -104,10 +101,10 @@ def energy_carbon_bj() -> pd.DataFrame:
         if i == 1:
             i = ""
         url = f"https://www.bjets.com.cn/article/jyxx/?{i}"
-        r = requests.get(url)
+        r = requests.get(url, verify=False, headers=headers)
         r.encoding = "utf-8"
-        df = pd.read_html(r.text)[0]
-        temp_df = pd.concat([temp_df, df], ignore_index=True)
+        df = pd.read_html(StringIO(r.text))[0]
+        temp_df = pd.concat(objs=[temp_df, df], ignore_index=True)
     temp_df.columns = ["日期", "成交量", "成交均价", "成交额"]
     temp_df["成交单位"] = (
         temp_df["成交额"]
@@ -125,17 +122,16 @@ def energy_carbon_bj() -> pd.DataFrame:
         .str.split("（", expand=True)
         .iloc[:, 0]
     )
-    temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
-    temp_df["成交均价"] = pd.to_numeric(temp_df["成交均价"])
+    temp_df["成交量"] = pd.to_numeric(temp_df["成交量"], errors="coerce")
+    temp_df["成交均价"] = pd.to_numeric(temp_df["成交均价"], errors="coerce")
     temp_df["成交额"] = temp_df["成交额"].str.replace(",", "")
     temp_df["成交额"] = pd.to_numeric(temp_df["成交额"], errors="coerce")
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"]).dt.date
-    temp_df.sort_values("日期", inplace=True)
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df.sort_values(by="日期", inplace=True)
     temp_df.reset_index(inplace=True, drop=True)
     return temp_df
 
 
-@lru_cache()
 def energy_carbon_sz() -> pd.DataFrame:
     """
     深圳碳排放交易所-国内碳情
@@ -144,33 +140,30 @@ def energy_carbon_sz() -> pd.DataFrame:
     :rtype: pandas.DataFrame
     """
     url = "http://www.cerx.cn/dailynewsCN/index.htm"
-    r = requests.get(url)
-    soup = BeautifulSoup(r.text, "lxml")
-    page_num = int(
-        soup.find(attrs={"class": "pagebar"}).find_all("option")[-1].text
-    )
-    big_df = pd.read_html(r.text, header=0)[0]
+    r = requests.get(url, headers=headers)
+    soup = BeautifulSoup(r.text, features="lxml")
+    page_num = int(soup.find(attrs={"class": "pagebar"}).find_all("option")[-1].text)
+    big_df = pd.read_html(StringIO(r.text), header=0)[0]
     for page in tqdm(
         range(2, page_num + 1), desc="Please wait for a moment", leave=False
     ):
         url = f"http://www.cerx.cn/dailynewsCN/index_{page}.htm"
-        r = requests.get(url)
-        temp_df = pd.read_html(r.text, header=0)[0]
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
-    big_df["交易日期"] = pd.to_datetime(big_df["交易日期"]).dt.date
-    big_df["开盘价"] = pd.to_numeric(big_df["开盘价"])
-    big_df["最高价"] = pd.to_numeric(big_df["最高价"])
-    big_df["最低价"] = pd.to_numeric(big_df["最低价"])
-    big_df["成交均价"] = pd.to_numeric(big_df["成交均价"])
-    big_df["收盘价"] = pd.to_numeric(big_df["收盘价"])
-    big_df["成交量"] = pd.to_numeric(big_df["成交量"])
-    big_df["成交额"] = pd.to_numeric(big_df["成交额"])
-    big_df.sort_values("交易日期", inplace=True)
+        r = requests.get(url, headers=headers)
+        temp_df = pd.read_html(StringIO(r.text), header=0)[0]
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
+    big_df["交易日期"] = pd.to_datetime(big_df["交易日期"], errors="coerce").dt.date
+    big_df["开盘价"] = pd.to_numeric(big_df["开盘价"], errors="coerce")
+    big_df["最高价"] = pd.to_numeric(big_df["最高价"], errors="coerce")
+    big_df["最低价"] = pd.to_numeric(big_df["最低价"], errors="coerce")
+    big_df["成交均价"] = pd.to_numeric(big_df["成交均价"], errors="coerce")
+    big_df["收盘价"] = pd.to_numeric(big_df["收盘价"], errors="coerce")
+    big_df["成交量"] = pd.to_numeric(big_df["成交量"], errors="coerce")
+    big_df["成交额"] = pd.to_numeric(big_df["成交额"], errors="coerce")
+    big_df.sort_values(by="交易日期", inplace=True)
     big_df.reset_index(inplace=True, drop=True)
     return big_df
 
 
-@lru_cache()
 def energy_carbon_eu() -> pd.DataFrame:
     """
     深圳碳排放交易所-国际碳情
@@ -179,33 +172,30 @@ def energy_carbon_eu() -> pd.DataFrame:
     :rtype: pandas.DataFrame
     """
     url = "http://www.cerx.cn/dailynewsOuter/index.htm"
-    r = requests.get(url)
-    soup = BeautifulSoup(r.text, "lxml")
-    page_num = int(
-        soup.find(attrs={"class": "pagebar"}).find_all("option")[-1].text
-    )
-    big_df = pd.read_html(r.text, header=0)[0]
+    r = requests.get(url, headers=headers)
+    soup = BeautifulSoup(r.text, features="lxml")
+    page_num = int(soup.find(attrs={"class": "pagebar"}).find_all("option")[-1].text)
+    big_df = pd.read_html(StringIO(r.text), header=0)[0]
     for page in tqdm(
         range(2, page_num + 1), desc="Please wait for a moment", leave=False
     ):
         url = f"http://www.cerx.cn/dailynewsOuter/index_{page}.htm"
         r = requests.get(url)
-        temp_df = pd.read_html(r.text, header=0)[0]
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
-    big_df["交易日期"] = pd.to_datetime(big_df["交易日期"]).dt.date
-    big_df["开盘价"] = pd.to_numeric(big_df["开盘价"])
-    big_df["最高价"] = pd.to_numeric(big_df["最高价"])
-    big_df["最低价"] = pd.to_numeric(big_df["最低价"])
-    big_df["成交均价"] = pd.to_numeric(big_df["成交均价"])
-    big_df["收盘价"] = pd.to_numeric(big_df["收盘价"])
-    big_df["成交量"] = pd.to_numeric(big_df["成交量"])
-    big_df["成交额"] = pd.to_numeric(big_df["成交额"])
-    big_df.sort_values("交易日期", inplace=True)
+        temp_df = pd.read_html(StringIO(r.text), header=0)[0]
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
+    big_df["交易日期"] = pd.to_datetime(big_df["交易日期"], errors="coerce").dt.date
+    big_df["开盘价"] = pd.to_numeric(big_df["开盘价"], errors="coerce")
+    big_df["最高价"] = pd.to_numeric(big_df["最高价"], errors="coerce")
+    big_df["最低价"] = pd.to_numeric(big_df["最低价"], errors="coerce")
+    big_df["成交均价"] = pd.to_numeric(big_df["成交均价"], errors="coerce")
+    big_df["收盘价"] = pd.to_numeric(big_df["收盘价"], errors="coerce")
+    big_df["成交量"] = pd.to_numeric(big_df["成交量"], errors="coerce")
+    big_df["成交额"] = pd.to_numeric(big_df["成交额"], errors="coerce")
+    big_df.sort_values(by="交易日期", inplace=True)
     big_df.reset_index(inplace=True, drop=True)
     return big_df
 
 
-@lru_cache()
 def energy_carbon_hb() -> pd.DataFrame:
     """
     湖北碳排放权交易中心-现货交易数据-配额-每日概况
@@ -213,66 +203,43 @@ def energy_carbon_hb() -> pd.DataFrame:
     :return: 现货交易数据-配额-每日概况行情数据
     :rtype: pandas.DataFrame
     """
-    url = "http://www.hbets.cn/list/13.html"
-    r = requests.get(url)
-    soup = BeautifulSoup(r.text, "lxml")
-    page_string = (
-        soup.find("div", attrs={"class": "page"}).find_all("span")[-1].text
+    url = "https://www.hbets.cn/"
+    r = requests.get(url, headers=headers)
+    soup = BeautifulSoup(r.text, features="lxml")
+    data_text = (
+        soup.find(name="div", attrs={"class": "threeLeft"}).find_all("script")[1].text
     )
-    page_num = int(re.findall(r"\d+", page_string)[-1])
-    columns = [
-        item.text
-        for item in soup.find("ul", attrs={"class": "title"}).find_all("li")
-    ]
-    big_df = pd.DataFrame()
-    for page in tqdm(
-        range(1, page_num + 1), desc="Please wait for a moment", leave=False
-    ):
-        url = f"http://www.hbets.cn/list/13.html"
-        params = {"page": page}
-        r = requests.get(url, params=params)
-        soup = BeautifulSoup(r.text, "lxml")
-        page_node = [
-            item
-            for item in soup.find(attrs={"class": "future_table"}).find_all(
-                attrs={"class": "cont"}
-            )
+    start_pos = data_text.find("cjj = '[") + 7  # 找到 JSON 数组开始的位置
+    end_pos = data_text.rfind("cjj =") - 31  # 找到 JSON 数组结束的位置
+    data_json = demjson.decode(data_text[start_pos:end_pos])
+    temp_df = pd.DataFrame.from_dict(data_json)
+    temp_df.rename(
+        columns={
+            "riqi": "日期",
+            "cjj": "成交价",
+            "cjl": "成交量",
+            "zx": "最新",
+            "zd": "涨跌",
+        },
+        inplace=True,
+    )
+    temp_df = temp_df[
+        [
+            "日期",
+            "成交价",
+            "成交量",
+            "最新",
+            "涨跌",
         ]
-        temp_list = []
-        for item in page_node:
-            temp_inner_list = []
-            for inner_item in item.find_all("li"):
-                temp_inner_list.append(inner_item.text)
-            temp_list.append(temp_inner_list)
-        temp_df = pd.DataFrame(temp_list)
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
-    big_df.columns = columns
-    big_df["交易品种"] = big_df["交易品种"].str.strip()
-    big_df["日期"] = pd.to_datetime(big_df["日期"]).dt.date
-    big_df["最新"] = pd.to_numeric(big_df["最新"])
-    big_df["涨跌幅"] = big_df["涨跌幅"].str.strip("%").str.strip()
-    big_df["涨跌幅"] = big_df["涨跌幅"].str.strip("%")
-    big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"])
-    big_df["最高"] = big_df["最高"].str.replace("--", "")
-    big_df["最高"] = pd.to_numeric(big_df["最高"])
-    big_df["最低"] = big_df["最低"].str.replace("--", "")
-    big_df["最低"] = pd.to_numeric(big_df["最低"])
-    big_df["成交量"] = big_df["成交量"].str.replace("--", "")
-    big_df["成交量"] = pd.to_numeric(big_df["成交量"])
-    big_df["成交额"] = big_df["成交额"].str.replace("--", "")
-    big_df["成交额"] = pd.to_numeric(big_df["成交额"])
-    big_df["昨收盘价"] = big_df["昨收盘价"].str.replace("--", "")
-    big_df["昨收盘价"] = pd.to_numeric(big_df["昨收盘价"])
-    big_df.dropna(subset=["最新"], inplace=True)
-    big_df.sort_values("日期", inplace=True)
-    big_df = big_df[
-        ["日期", "交易品种", "最新", "涨跌幅", "最高", "最低", "成交量", "成交额", "昨收盘价"]
     ]
-    big_df.reset_index(inplace=True, drop=True)
-    return big_df
+    temp_df["日期"] = pd.to_datetime(temp_df["日期"], errors="coerce").dt.date
+    temp_df["成交价"] = pd.to_numeric(temp_df["成交价"], errors="coerce")
+    temp_df["成交量"] = pd.to_numeric(temp_df["成交量"], errors="coerce")
+    temp_df["最新"] = pd.to_numeric(temp_df["最新"], errors="coerce")
+    temp_df["涨跌"] = pd.to_numeric(temp_df["涨跌"], errors="coerce")
+    return temp_df
 
 
-@lru_cache()
 def energy_carbon_gz() -> pd.DataFrame:
     """
     广州碳排放权交易中心-行情信息
@@ -287,7 +254,7 @@ def energy_carbon_gz() -> pd.DataFrame:
         "endTime": "2030-09-12",
     }
     r = requests.get(url, params=params)
-    temp_df = pd.read_html(r.text, header=0)[1]
+    temp_df = pd.read_html(StringIO(r.text), header=0)[1]
     temp_df.columns = [
         "日期",
         "品种",
@@ -300,17 +267,19 @@ def energy_carbon_gz() -> pd.DataFrame:
         "成交数量",
         "成交金额",
     ]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"], format="%Y%m%d").dt.date
-    temp_df["开盘价"] = pd.to_numeric(temp_df["开盘价"])
-    temp_df["收盘价"] = pd.to_numeric(temp_df["收盘价"])
-    temp_df["最高价"] = pd.to_numeric(temp_df["最高价"])
-    temp_df["最低价"] = pd.to_numeric(temp_df["最低价"])
-    temp_df["涨跌"] = pd.to_numeric(temp_df["涨跌"])
+    temp_df["日期"] = pd.to_datetime(
+        temp_df["日期"], format="%Y%m%d", errors="coerce"
+    ).dt.date
+    temp_df["开盘价"] = pd.to_numeric(temp_df["开盘价"], errors="coerce")
+    temp_df["收盘价"] = pd.to_numeric(temp_df["收盘价"], errors="coerce")
+    temp_df["最高价"] = pd.to_numeric(temp_df["最高价"], errors="coerce")
+    temp_df["最低价"] = pd.to_numeric(temp_df["最低价"], errors="coerce")
+    temp_df["涨跌"] = pd.to_numeric(temp_df["涨跌"], errors="coerce")
     temp_df["涨跌幅"] = temp_df["涨跌幅"].str.strip("%")
-    temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"])
-    temp_df["成交数量"] = pd.to_numeric(temp_df["成交数量"])
-    temp_df["成交金额"] = pd.to_numeric(temp_df["成交金额"])
-    temp_df.sort_values("日期", inplace=True)
+    temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"], errors="coerce")
+    temp_df["成交数量"] = pd.to_numeric(temp_df["成交数量"], errors="coerce")
+    temp_df["成交金额"] = pd.to_numeric(temp_df["成交金额"], errors="coerce")
+    temp_df.sort_values(by="日期", inplace=True)
     temp_df.reset_index(inplace=True, drop=True)
     return temp_df
 

akshare/event/migration.py

@@ -1,9 +1,10 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/9/24 16:30
+Date: 2024/5/12 22:30
 Desc: 百度地图慧眼-百度迁徙数据
 """
+
 import json
 
 import pandas as pd
@@ -92,7 +93,7 @@ def migration_scale_baidu(
 
 if __name__ == "__main__":
     migration_area_baidu_df = migration_area_baidu(
-        area="上海市", indicator="move_in", date="20230922"
+        area="杭州市", indicator="move_out", date="20240401"
     )
     print(migration_area_baidu_df)
 

akshare/exceptions.py

@@ -0,0 +1,43 @@
+"""
+AKShare 异常处理模块
+"""
+
+
+class AkshareException(Exception):
+    """Base exception for akshare library"""
+
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class APIError(AkshareException):
+    """Raised when API request fails"""
+
+    def __init__(self, message, status_code=None):
+        self.status_code = status_code
+        super().__init__(f"API Error: {message} (Status code: {status_code})")
+
+
+class DataParsingError(AkshareException):
+    """Raised when data parsing fails"""
+
+    pass
+
+
+class InvalidParameterError(AkshareException):
+    """Raised when an invalid parameter is provided"""
+
+    pass
+
+
+class NetworkError(AkshareException):
+    """Raised when network-related issues occur"""
+
+    pass
+
+
+class RateLimitError(AkshareException):
+    """Raised when API rate limit is exceeded"""
+
+    pass