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

akshare/stock_feature/stock_research_report_em.py

@@ -1,19 +1,24 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/8/20 20:00
+Date: 2025/2/28 13:00
 Desc: 东方财富网-数据中心-研究报告-个股研报
 https://data.eastmoney.com/report/stock.jshtml
 """
+
+import datetime
 import pandas as pd
 import requests
-from tqdm import tqdm
+
+from akshare.utils.tqdm import get_tqdm
 
 
 def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
     """
     东方财富网-数据中心-研究报告-个股研报
     https://data.eastmoney.com/report/stock.jshtml
+    :param symbol: 个股代码
+    :type symbol: str
     :return: 个股研报
     :rtype: pandas.DataFrame
     """
@@ -25,7 +30,7 @@ def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
         "rating": "*",
         "ratingChange": "*",
         "beginTime": "2000-01-01",
-        "endTime": "2025-01-01",
+        "endTime": f"{datetime.datetime.now().year + 1}-01-01",
         "pageNo": "1",
         "fields": "",
         "qType": "0",
@@ -35,12 +40,13 @@ def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
         "p": "1",
         "pageNum": "1",
         "pageNumber": "1",
-        "_": "1692533168153",
     }
     r = requests.get(url, params=params)
     data_json = r.json()
     total_page = data_json["TotalPage"]
+    current_year = data_json["currentYear"]
     big_df = pd.DataFrame()
+    tqdm = get_tqdm()
     for page in tqdm(range(1, total_page + 1), leave=False):
         params.update(
             {
@@ -53,9 +59,18 @@ def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
         r = requests.get(url, params=params)
         data_json = r.json()
         temp_df = pd.DataFrame(data_json["data"])
-        big_df = pd.concat([big_df, temp_df], axis=0, ignore_index=True)
+        big_df = pd.concat(objs=[big_df, temp_df], axis=0, ignore_index=True)
     big_df.reset_index(inplace=True)
     big_df["index"] = big_df["index"] + 1
+    predict_this_year_eps_title = f"{current_year}-盈利预测-收益"
+    predict_this_year_pe_title = f"{current_year}-盈利预测-市盈率"
+    predict_next_year_eps_title = f"{current_year + 1}-盈利预测-收益"
+    predict_next_year_pe_title = f"{current_year + 1}-盈利预测-市盈率"
+    predict_next_two_year_eps_title = f"{current_year + 2}-盈利预测-收益"
+    predict_next_two_year_pe_title = f"{current_year + 2}-盈利预测-市盈率"
+    big_df["pdfUrl"] = big_df["infoCode"].apply(
+        lambda x: f"https://pdf.dfcfw.com/pdf/H3_{x}_1.pdf"
+    )
     big_df.rename(
         columns={
             "index": "序号",
@@ -68,12 +83,12 @@ def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
             "publishDate": "日期",
             "infoCode": "-",
             "column": "-",
-            "predictNextTwoYearEps": "-",
-            "predictNextTwoYearPe": "-",
-            "predictNextYearEps": "2024-盈利预测-收益",
-            "predictNextYearPe": "2024-盈利预测-市盈率",
-            "predictThisYearEps": "2023-盈利预测-收益",
-            "predictThisYearPe": "2023-盈利预测-市盈率",
+            "predictNextTwoYearEps": predict_next_two_year_eps_title,
+            "predictNextTwoYearPe": predict_next_two_year_pe_title,
+            "predictNextYearEps": predict_next_year_eps_title,
+            "predictNextYearPe": predict_next_year_pe_title,
+            "predictThisYearEps": predict_this_year_eps_title,
+            "predictThisYearPe": predict_this_year_pe_title,
             "predictLastYearEps": "-",
             "predictLastYearPe": "-",
             "actualLastTwoYearEps": "-",
@@ -110,6 +125,7 @@ def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
             "authorID": "-",
             "count": "近一月个股研报数",
             "orgType": "-",
+            "pdfUrl": "报告PDF链接",
         },
         inplace=True,
     )
@@ -122,20 +138,39 @@ def stock_research_report_em(symbol: str = "000001") -> pd.DataFrame:
             "东财评级",
             "机构",
             "近一月个股研报数",
-            "2023-盈利预测-收益",
-            "2023-盈利预测-市盈率",
-            "2024-盈利预测-收益",
-            "2024-盈利预测-市盈率",
+            predict_this_year_eps_title,
+            predict_this_year_pe_title,
+            predict_next_year_eps_title,
+            predict_next_year_pe_title,
+            predict_next_two_year_eps_title,
+            predict_next_two_year_pe_title,
             "行业",
             "日期",
+            "报告PDF链接",
         ]
     ]
     big_df["日期"] = pd.to_datetime(big_df["日期"], errors="coerce").dt.date
-    big_df["近一月个股研报数"] = pd.to_numeric(big_df["近一月个股研报数"], errors="coerce")
-    big_df["2023-盈利预测-收益"] = pd.to_numeric(big_df["2023-盈利预测-收益"], errors="coerce")
-    big_df["2023-盈利预测-市盈率"] = pd.to_numeric(big_df["2023-盈利预测-市盈率"], errors="coerce")
-    big_df["2024-盈利预测-收益"] = pd.to_numeric(big_df["2024-盈利预测-收益"], errors="coerce")
-    big_df["2024-盈利预测-市盈率"] = pd.to_numeric(big_df["2024-盈利预测-市盈率"], errors="coerce")
+    big_df["近一月个股研报数"] = pd.to_numeric(
+        big_df["近一月个股研报数"], errors="coerce"
+    )
+    big_df[predict_this_year_eps_title] = pd.to_numeric(
+        big_df[predict_this_year_eps_title], errors="coerce"
+    )
+    big_df[predict_this_year_pe_title] = pd.to_numeric(
+        big_df[predict_this_year_pe_title], errors="coerce"
+    )
+    big_df[predict_next_year_eps_title] = pd.to_numeric(
+        big_df[predict_next_year_eps_title], errors="coerce"
+    )
+    big_df[predict_next_year_pe_title] = pd.to_numeric(
+        big_df[predict_next_year_pe_title], errors="coerce"
+    )
+    big_df[predict_next_two_year_eps_title] = pd.to_numeric(
+        big_df[predict_next_two_year_eps_title], errors="coerce"
+    )
+    big_df[predict_next_two_year_pe_title] = pd.to_numeric(
+        big_df[predict_next_two_year_pe_title], errors="coerce"
+    )
     return big_df
 
 

akshare/stock_feature/stock_sns_sseinfo.py

@@ -1,17 +1,19 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2023/8/4 19:20
+Date: 2024/5/21 19:20
 Desc: 上证e互动-提问与回答
 https://sns.sseinfo.com/
 """
+
 import warnings
 from functools import lru_cache
 
 import pandas as pd
 import requests
 from bs4 import BeautifulSoup
-from tqdm import tqdm
+
+from akshare.utils.tqdm import get_tqdm
 
 
 @lru_cache()
@@ -31,19 +33,20 @@ def _fetch_stock_uid() -> dict:
     }
     uid_list = list()
     code_list = list()
+    tqdm = get_tqdm()
     for page in tqdm(range(1, 73), leave=False):
         data.update({"page": page})
         r = requests.post(url, data=data)
         data_json = r.json()
-        soup = BeautifulSoup(data_json["content"], "lxml")
-        soup.find_all("a", attrs={"rel": "tag"})
+        soup = BeautifulSoup(data_json["content"], features="lxml")
+        soup.find_all(name="a", attrs={"rel": "tag"})
         uid_list.extend(
-            [item["uid"] for item in soup.find_all("a", attrs={"rel": "tag"})]
+            [item["uid"] for item in soup.find_all(name="a", attrs={"rel": "tag"})]
         )
         code_list.extend(
             [
                 item.find("img")["src"].split("?")[0].split("/")[-1].split(".")[0]
-                for item in soup.find_all("a", attrs={"rel": "tag"})
+                for item in soup.find_all(name="a", attrs={"rel": "tag"})
             ]
         )
     code_uid_map = dict(zip(code_list, uid_list))
@@ -79,18 +82,18 @@ def stock_sns_sseinfo(symbol: str = "603119") -> pd.DataFrame:
         else:
             page += 1
         r = requests.post(url, params=params)
-        soup = BeautifulSoup(r.text, "lxml")
+        soup = BeautifulSoup(r.text, features="lxml")
         content_list = [
             item.get_text().strip()
-            for item in soup.find_all("div", attrs={"class": "m_feed_txt"})
+            for item in soup.find_all(name="div", attrs={"class": "m_feed_txt"})
         ]
         date_list = [
             item.get_text().strip().split("\n")[0]
-            for item in soup.find_all("div", attrs={"class": "m_feed_from"})
+            for item in soup.find_all(name="div", attrs={"class": "m_feed_from"})
         ]
         source_list = [
             item.get_text().strip().split("\n")[2]
-            for item in soup.find_all("div", attrs={"class": "m_feed_from"})
+            for item in soup.find_all(name="div", attrs={"class": "m_feed_from"})
         ]
         q_list = [
             item.split(")")[1]
@@ -113,7 +116,7 @@ def stock_sns_sseinfo(symbol: str = "603119") -> pd.DataFrame:
         s_q_list = [item for index, item in enumerate(source_list) if index % 2 == 0]
         s_a_list = [item for index, item in enumerate(source_list) if index % 2 != 0]
         author_name = [
-            item["title"] for item in soup.find_all("a", attrs={"rel": "face"})
+            item["title"] for item in soup.find_all(name="a", attrs={"rel": "face"})
         ]
         temp_df = pd.DataFrame(
             [
@@ -139,7 +142,7 @@ def stock_sns_sseinfo(symbol: str = "603119") -> pd.DataFrame:
             "回答来源",
             "用户名",
         ]
-        big_df = pd.concat([big_df, temp_df], ignore_index=True)
+        big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
     return big_df
 
 

akshare/stock_feature/stock_sy_em.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2024/4/21 17:30
+Date: 2024/9/15 15:30
 Desc: 东方财富网-数据中心-特色数据-商誉
 东方财富网-数据中心-特色数据-商誉-A股商誉市场概况: https://data.eastmoney.com/sy/scgk.html
 东方财富网-数据中心-特色数据-商誉-商誉减值预期明细: https://data.eastmoney.com/sy/yqlist.html
@@ -12,7 +12,8 @@ Desc: 东方财富网-数据中心-特色数据-商誉
 
 import pandas as pd
 import requests
-from tqdm import tqdm
+
+from akshare.utils.tqdm import get_tqdm
 
 
 def stock_sy_profile_em() -> pd.DataFrame:
@@ -80,7 +81,7 @@ def stock_sy_profile_em() -> pd.DataFrame:
     return data_df
 
 
-def stock_sy_yq_em(date: str = "20221231") -> pd.DataFrame:
+def stock_sy_yq_em(date: str = "20240630") -> pd.DataFrame:
     """
     东方财富网-数据中心-特色数据-商誉-商誉减值预期明细
     https://data.eastmoney.com/sy/yqlist.html
@@ -104,12 +105,13 @@ def stock_sy_yq_em(date: str = "20221231") -> pd.DataFrame:
     data_json = r.json()
     big_df = pd.DataFrame()
     total_page = int(data_json["result"]["pages"])
+    tqdm = get_tqdm()
     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"])
-        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
     big_df.rename(
@@ -188,7 +190,7 @@ def stock_sy_yq_em(date: str = "20221231") -> pd.DataFrame:
     return big_df
 
 
-def stock_sy_jz_em(date: str = "20230331") -> pd.DataFrame:
+def stock_sy_jz_em(date: str = "20240630") -> pd.DataFrame:
     """
     东方财富网-数据中心-特色数据-商誉-个股商誉减值明细
     https://data.eastmoney.com/sy/jzlist.html
@@ -212,12 +214,13 @@ def stock_sy_jz_em(date: str = "20230331") -> pd.DataFrame:
     data_json = r.json()
     big_df = pd.DataFrame()
     total_page = int(data_json["result"]["pages"])
+    tqdm = get_tqdm()
     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"])
-        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
     big_df.rename(
@@ -312,12 +315,13 @@ def stock_sy_em(date: str = "20231231") -> pd.DataFrame:
     data_json = r.json()
     big_df = pd.DataFrame()
     total_page = int(data_json["result"]["pages"])
+    tqdm = get_tqdm()
     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"])
-        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
     big_df.rename(
@@ -379,7 +383,7 @@ def stock_sy_em(date: str = "20231231") -> pd.DataFrame:
     return big_df
 
 
-def stock_sy_hy_em(date: str = "20231231") -> pd.DataFrame:
+def stock_sy_hy_em(date: str = "20240930") -> pd.DataFrame:
     """
     东方财富网-数据中心-特色数据-商誉-行业商誉
     https://data.eastmoney.com/sy/hylist.html
@@ -403,12 +407,13 @@ def stock_sy_hy_em(date: str = "20231231") -> pd.DataFrame:
     data_json = r.json()
     big_df = pd.DataFrame()
     total_page = int(data_json["result"]["pages"])
+    tqdm = get_tqdm()
     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"])
-        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, drop=True)
     big_df.rename(
         columns={
@@ -447,17 +452,17 @@ def stock_sy_hy_em(date: str = "20231231") -> pd.DataFrame:
 
 
 if __name__ == "__main__":
-    stock_em_sy_profile_df = stock_sy_profile_em()
-    print(stock_em_sy_profile_df)
+    stock_sy_profile_em_df = stock_sy_profile_em()
+    print(stock_sy_profile_em_df)
 
-    stock_sy_yq_em_df = stock_sy_yq_em(date="20221231")
+    stock_sy_yq_em_df = stock_sy_yq_em(date="20240630")
     print(stock_sy_yq_em_df)
 
-    stock_sy_jz_em_df = stock_sy_jz_em(date="20230630")
+    stock_sy_jz_em_df = stock_sy_jz_em(date="20240630")
     print(stock_sy_jz_em_df)
 
-    stock_sy_em_df = stock_sy_em(date="20231231")
+    stock_sy_em_df = stock_sy_em(date="20240630")
     print(stock_sy_em_df)
 
-    stock_sy_hy_em_df = stock_sy_hy_em(date="20231231")
+    stock_sy_hy_em_df = stock_sy_hy_em(date="20240930")
     print(stock_sy_hy_em_df)