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

akshare/stock_feature/stock_irm_cninfo.py

@@ -1,13 +1,15 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/8/4 19:20
+Date: 2024/5/20 16:00
 Desc: 互动易-提问与回答
 https://irm.cninfo.com.cn/
 """
+
 import pandas as pd
 import requests
-from tqdm import tqdm
+
+from akshare.utils.tqdm import get_tqdm
 
 
 def _fetch_org_id(symbol: str = "000001") -> str:
@@ -51,12 +53,13 @@ def stock_irm_cninfo(symbol: str = "002594") -> pd.DataFrame:
     total_page = int(data_json["totalPage"])
     total_page = 10 if total_page > 10 else total_page
     big_df = pd.DataFrame()
+    tqdm = get_tqdm()
     for page in tqdm(range(1, 1 + total_page), leave=False):
         params.update({"pageNum": page})
         r = requests.post(url, params=params)
         data_json = r.json()
         temp_df = pd.DataFrame(data_json["rows"])
-        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.rename(
         columns={
             "indexId": "问题编号",
@@ -111,8 +114,18 @@ def stock_irm_cninfo(symbol: str = "002594") -> pd.DataFrame:
     ]
     big_df["行业"] = [item[0] for item in big_df["行业"]]
     big_df["行业代码"] = [item[0] for item in big_df["行业代码"]]
-    big_df["提问时间"] = pd.to_datetime(big_df["提问时间"], unit="ms")
-    big_df["更新时间"] = pd.to_datetime(big_df["更新时间"], unit="ms")
+    big_df["提问时间"] = (
+        pd.to_datetime(big_df["提问时间"], unit="ms", errors="coerce")
+        .dt.tz_localize("UTC")
+        .dt.tz_convert("Asia/Shanghai")
+        .dt.strftime("%Y-%m-%d %H:%M:%S")
+    )
+    big_df["更新时间"] = (
+        pd.to_datetime(big_df["更新时间"], unit="ms", errors="coerce")
+        .dt.tz_localize("UTC")
+        .dt.tz_convert("Asia/Shanghai")
+        .dt.strftime("%Y-%m-%d %H:%M:%S")
+    )
     big_df["来源"] = big_df["来源"].map(
         {
             "2": "APP",
@@ -120,7 +133,7 @@ def stock_irm_cninfo(symbol: str = "002594") -> pd.DataFrame:
             "4": "网站",
         }
     )
-    big_df["来源"].fillna("网站", inplace=True)
+    big_df["来源"] = big_df["来源"].fillna("网站")
     return big_df
 
 
@@ -128,7 +141,7 @@ def stock_irm_ans_cninfo(symbol: str = "1513586704097333248") -> pd.DataFrame:
     """
     互动易-回答
     https://irm.cninfo.com.cn/ircs/question/questionDetail?questionId=1515236357817618432
-    :param symbol: 提问者编号; 通过 ak.stock_irm_cninfo 来获取具体的提问者编号
+    :param symbol: 提问者编号; 通过 ak.stock_irm_cninfo() 来获取具体的提问者编号
     :type symbol: str
     :return: 回答
     :rtype: str
@@ -163,8 +176,18 @@ def stock_irm_ans_cninfo(symbol: str = "1513586704097333248") -> pd.DataFrame:
             "回答时间",
         ]
     ]
-    temp_df["提问时间"] = pd.to_datetime(temp_df["提问时间"], unit="ms", errors="coerce")
-    temp_df["回答时间"] = pd.to_datetime(temp_df["回答时间"], unit="ms", errors="coerce")
+    temp_df["提问时间"] = (
+        pd.to_datetime(temp_df["提问时间"], unit="ms", errors="coerce")
+        .dt.tz_localize("UTC")
+        .dt.tz_convert("Asia/Shanghai")
+        .dt.strftime("%Y-%m-%d %H:%M:%S")
+    )
+    temp_df["回答时间"] = (
+        pd.to_datetime(temp_df["回答时间"], unit="ms", errors="coerce")
+        .dt.tz_localize("UTC")
+        .dt.tz_convert("Asia/Shanghai")
+        .dt.strftime("%Y-%m-%d %H:%M:%S")
+    )
     return temp_df
 
 

akshare/stock_feature/stock_jgdy_em.py

@@ -7,6 +7,7 @@ http://data.eastmoney.com/jgdy/
 东方财富网-数据中心-特色数据-机构调研-机构调研统计: http://data.eastmoney.com/jgdy/tj.html
 东方财富网-数据中心-特色数据-机构调研-机构调研详细: http://data.eastmoney.com/jgdy/xx.html
 """
+
 import pandas as pd
 import requests
 from tqdm import tqdm
@@ -15,34 +16,34 @@ from tqdm import tqdm
 def stock_jgdy_tj_em(date: str = "20220101") -> pd.DataFrame:
     """
     东方财富网-数据中心-特色数据-机构调研-机构调研统计
-    http://data.eastmoney.com/jgdy/tj.html
+    https://data.eastmoney.com/jgdy/tj.html
     :param date: 开始时间
     :type date: str
     :return: 机构调研统计
     :rtype: pandas.DataFrame
     """
-    url = "http://datacenter-web.eastmoney.com/api/data/v1/get"
+    url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
     params = {
-        'sortColumns': 'NOTICE_DATE,SUM,RECEIVE_START_DATE,SECURITY_CODE',
-        'sortTypes': '-1,-1,-1,1',
-        'pageSize': '500',
-        'pageNumber': '1',
-        'reportName': 'RPT_ORG_SURVEYNEW',
-        'columns': 'ALL',
-        'quoteColumns': 'f2~01~SECURITY_CODE~CLOSE_PRICE,f3~01~SECURITY_CODE~CHANGE_RATE',
-        'source': 'WEB',
-        'client': 'WEB',
-        'filter': f"""(NUMBERNEW="1")(IS_SOURCE="1")(RECEIVE_START_DATE>'{'-'.join([date[:4], date[4:6], date[6:]])}')"""
+        "sortColumns": "NOTICE_DATE,SUM,RECEIVE_START_DATE,SECURITY_CODE",
+        "sortTypes": "-1,-1,-1,1",
+        "pageSize": "500",
+        "pageNumber": "1",
+        "reportName": "RPT_ORG_SURVEYNEW",
+        "columns": "ALL",
+        "quoteColumns": "f2~01~SECURITY_CODE~CLOSE_PRICE,f3~01~SECURITY_CODE~CHANGE_RATE",
+        "source": "WEB",
+        "client": "WEB",
+        "filter": f"""(NUMBERNEW="1")(IS_SOURCE="1")(NOTICE_DATE>'{'-'.join([date[:4], date[4:6], date[6:]])}')""",
     }
     r = requests.get(url, params=params)
     data_json = r.json()
-    total_page = data_json['result']['pages']
+    total_page = data_json["result"]["pages"]
     big_df = pd.DataFrame()
-    for page in tqdm(range(1, total_page+1), leave=False):
+    for page in tqdm(range(1, total_page + 1), leave=False):
         params.update({"pageNumber": page})
         r = requests.get(url, params=params)
         data_json = r.json()
-        temp_df = pd.DataFrame(data_json['result']['data'])
+        temp_df = pd.DataFrame(data_json["result"]["data"])
         big_df = pd.concat([big_df, temp_df])
     big_df.reset_index(inplace=True)
     big_df["index"] = list(range(1, len(big_df) + 1))
@@ -96,45 +97,47 @@ def stock_jgdy_tj_em(date: str = "20220101") -> pd.DataFrame:
             "公告日期",
         ]
     ]
-    big_df['最新价'] = pd.to_numeric(big_df['最新价'], errors="coerce")
-    big_df['涨跌幅'] = pd.to_numeric(big_df['涨跌幅'], errors="coerce")
-    big_df['接待机构数量'] = pd.to_numeric(big_df['接待机构数量'], errors="coerce")
-    big_df['接待日期'] = pd.to_datetime(big_df['接待日期']).dt.date
-    big_df['公告日期'] = pd.to_datetime(big_df['公告日期']).dt.date
+    big_df["最新价"] = pd.to_numeric(big_df["最新价"], errors="coerce")
+    big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"], errors="coerce")
+    big_df["接待机构数量"] = pd.to_numeric(big_df["接待机构数量"], errors="coerce")
+    big_df["接待日期"] = pd.to_datetime(big_df["接待日期"], errors="coerce").dt.date
+    big_df["公告日期"] = pd.to_datetime(big_df["公告日期"], errors="coerce").dt.date
     return big_df
 
 
-def stock_jgdy_detail_em(date: str = "20220101") -> pd.DataFrame:
+def stock_jgdy_detail_em(date: str = "20241211") -> pd.DataFrame:
     """
     东方财富网-数据中心-特色数据-机构调研-机构调研详细
-    http://data.eastmoney.com/jgdy/xx.html
+    https://data.eastmoney.com/jgdy/xx.html
     :param date: 开始时间
     :type date: str
     :return: 机构调研详细
     :rtype: pandas.DataFrame
     """
-    url = "http://datacenter-web.eastmoney.com/api/data/v1/get"
+    url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
     params = {
-        'sortColumns': 'NOTICE_DATE,RECEIVE_START_DATE,SECURITY_CODE,NUMBERNEW',
-        'sortTypes': '-1,-1,1,-1',
-        'pageSize': '50000',
-        'pageNumber': '1',
-        'reportName': 'RPT_ORG_SURVEY',
-        'columns': 'SECUCODE,SECURITY_CODE,SECURITY_NAME_ABBR,NOTICE_DATE,RECEIVE_START_DATE,RECEIVE_OBJECT,RECEIVE_PLACE,RECEIVE_WAY_EXPLAIN,INVESTIGATORS,RECEPTIONIST,ORG_TYPE',
-        'quoteColumns': 'f2~01~SECURITY_CODE~CLOSE_PRICE,f3~01~SECURITY_CODE~CHANGE_RATE',
-        'source': 'WEB',
-        'client': 'WEB',
-        'filter': f"""(IS_SOURCE="1")(RECEIVE_START_DATE>'{'-'.join([date[:4], date[4:6], date[6:]])}')"""
+        "sortColumns": "NOTICE_DATE,RECEIVE_START_DATE,SECURITY_CODE,NUMBERNEW",
+        "sortTypes": "-1,-1,1,-1",
+        "pageSize": "50",
+        "pageNumber": "1",
+        "reportName": "RPT_ORG_SURVEY",
+        "columns": "SECUCODE,SECURITY_CODE,SECURITY_NAME_ABBR,NOTICE_DATE,RECEIVE_START_DATE,"
+        "RECEIVE_OBJECT,RECEIVE_PLACE,RECEIVE_WAY_EXPLAIN,INVESTIGATORS,RECEPTIONIST,ORG_TYPE",
+        "quoteColumns": "f2~01~SECURITY_CODE~CLOSE_PRICE,f3~01~SECURITY_CODE~CHANGE_RATE",
+        "quoteType": "0",
+        "source": "WEB",
+        "client": "WEB",
+        "filter": f"""(IS_SOURCE="1")(RECEIVE_START_DATE>'{'-'.join([date[:4], date[4:6], date[6:]])}')""",
     }
     r = requests.get(url, params=params)
     data_json = r.json()
-    total_page = data_json['result']['pages']
+    total_page = data_json["result"]["pages"]
     big_df = pd.DataFrame()
-    for page in tqdm(range(1, total_page+1), leave=False):
+    for page in tqdm(range(1, total_page + 1), leave=False):
         params.update({"pageNumber": page})
         r = requests.get(url, params=params)
         data_json = r.json()
-        temp_df = pd.DataFrame(data_json['result']['data'])
+        temp_df = pd.DataFrame(data_json["result"]["data"])
         big_df = pd.concat([big_df, temp_df])
     big_df.reset_index(inplace=True)
     big_df["index"] = list(range(1, len(big_df) + 1))
@@ -171,10 +174,10 @@ def stock_jgdy_detail_em(date: str = "20220101") -> pd.DataFrame:
             "公告日期",
         ]
     ]
-    big_df['最新价'] = pd.to_numeric(big_df['最新价'], errors="coerce")
-    big_df['涨跌幅'] = pd.to_numeric(big_df['涨跌幅'], errors="coerce")
-    big_df['调研日期'] = pd.to_datetime(big_df['调研日期']).dt.date
-    big_df['公告日期'] = pd.to_datetime(big_df['公告日期']).dt.date
+    big_df["最新价"] = pd.to_numeric(big_df["最新价"], errors="coerce")
+    big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"], errors="coerce")
+    big_df["调研日期"] = pd.to_datetime(big_df["调研日期"], errors="coerce").dt.date
+    big_df["公告日期"] = pd.to_datetime(big_df["公告日期"], errors="coerce").dt.date
     return big_df
 
 

akshare/stock_feature/stock_lh_yybpm.py

@@ -1,37 +1,40 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/5/3 20:30
+Date: 2024/5/6 20:30
 Desc: 同花顺-数据中心-营业部排名
-http://data.10jqka.com.cn/market/longhu/
+https://data.10jqka.com.cn/market/longhu/
 """
-import requests
+
+from io import StringIO
+
 import pandas as pd
-from tqdm import tqdm
+import requests
 from bs4 import BeautifulSoup
 
+from akshare.utils.tqdm import get_tqdm
+from akshare.utils.cons import headers
+
 
 def stock_lh_yyb_most() -> pd.DataFrame:
     """
     同花顺-数据中心-营业部排名-上榜次数最多
-    http://data.10jqka.com.cn/market/longhu/
+    https://data.10jqka.com.cn/market/longhu/
     :return: 上榜次数最多
     :rtype: pandas.DataFrame
     """
-    url = "http://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/sbcs/field/sbcs/sort/desc/page/1/"
-    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"
-    }
+    url = "https://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/sbcs/field/sbcs/sort/desc/page/1/"
     r = requests.get(url, headers=headers)
-    soup = BeautifulSoup(r.text, "lxml")
-    page_str = soup.find("span", attrs={"class": "page_info"}).text
+    soup = BeautifulSoup(r.text, features="lxml")
+    page_str = soup.find(name="span", attrs={"class": "page_info"}).text
     total_page = int(page_str.split("/")[1]) + 1
     big_df = pd.DataFrame()
-    for page in tqdm(range(1, total_page)):
-        url = f"http://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/sbcs/field/sbcs/sort/desc/page/{page}/"
+    tqdm = get_tqdm()
+    for page in tqdm(range(1, total_page), leave=False):
+        url = f"https://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/sbcs/field/sbcs/sort/desc/page/{page}/"
         r = requests.get(url, headers=headers)
-        temp_df = pd.read_html(r.text)[0]
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
+        temp_df = pd.read_html(StringIO(r.text))[0]
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
     big_df.reset_index(inplace=True, drop=True)
     return big_df
 
@@ -39,24 +42,22 @@ def stock_lh_yyb_most() -> pd.DataFrame:
 def stock_lh_yyb_capital() -> pd.DataFrame:
     """
     同花顺-数据中心-营业部排名-资金实力最强
-    http://data.10jqka.com.cn/market/longhu/
+    https://data.10jqka.com.cn/market/longhu/
     :return: 资金实力最强
     :rtype: pandas.DataFrame
     """
-    url = "http://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/zjsl/field/zgczje/sort/desc/page/1/"
-    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"
-    }
+    url = "https://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/zjsl/field/zgczje/sort/desc/page/1/"
     r = requests.get(url, headers=headers)
-    soup = BeautifulSoup(r.text, "lxml")
-    page_str = soup.find("span", attrs={"class": "page_info"}).text
+    soup = BeautifulSoup(r.text, features="lxml")
+    page_str = soup.find(name="span", attrs={"class": "page_info"}).text
     total_page = int(page_str.split("/")[1]) + 1
     big_df = pd.DataFrame()
-    for page in tqdm(range(1, total_page)):
-        url = f"http://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/zjsl/field/zgczje/sort/desc/page/{page}/"
+    tqdm = get_tqdm()
+    for page in tqdm(range(1, total_page), leave=False):
+        url = f"https://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/zjsl/field/zgczje/sort/desc/page/{page}/"
         r = requests.get(url, headers=headers)
-        temp_df = pd.read_html(r.text)[0]
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
+        temp_df = pd.read_html(StringIO(r.text))[0]
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
     big_df.reset_index(inplace=True, drop=True)
     return big_df
 
@@ -64,24 +65,22 @@ def stock_lh_yyb_capital() -> pd.DataFrame:
 def stock_lh_yyb_control() -> pd.DataFrame:
     """
     同花顺-数据中心-营业部排名-抱团操作实力
-    http://data.10jqka.com.cn/market/longhu/
+    https://data.10jqka.com.cn/market/longhu/
     :return: 抱团操作实力
     :rtype: pandas.DataFrame
     """
-    url = "http://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/btcz/field/xsjs/sort/desc/page/1/"
-    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"
-    }
+    url = "https://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/btcz/field/xsjs/sort/desc/page/1/"
     r = requests.get(url, headers=headers)
-    soup = BeautifulSoup(r.text, "lxml")
-    page_str = soup.find("span", attrs={"class": "page_info"}).text
+    soup = BeautifulSoup(r.text, features="lxml")
+    page_str = soup.find(name="span", attrs={"class": "page_info"}).text
     total_page = int(page_str.split("/")[1]) + 1
     big_df = pd.DataFrame()
-    for page in tqdm(range(1, total_page)):
-        url = f"http://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/btcz/field/xsjs/sort/desc/page/{page}/"
+    tqdm = get_tqdm()
+    for page in tqdm(range(1, total_page), leave=False):
+        url = f"https://data.10jqka.com.cn/ifmarket/lhbyyb/type/1/tab/btcz/field/xsjs/sort/desc/page/{page}/"
         r = requests.get(url, headers=headers)
-        temp_df = pd.read_html(r.text)[0]
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
+        temp_df = pd.read_html(StringIO(r.text))[0]
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
     big_df.reset_index(inplace=True, drop=True)
     return big_df