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

akshare/news/news_cctv.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2022/5/26 15:42
+Date: 2024/4/25 17:00
 Desc: 新闻联播文字稿
-https://tv.cctv.com/lm/xwlb/?spm=C52056131267.P4y8I53JvSWE.0.0
+https://tv.cctv.com/lm/xwlb
 """
+
 import re
 
 import pandas as pd
@@ -13,28 +14,28 @@ from bs4 import BeautifulSoup
 from tqdm import tqdm
 
 
-def news_cctv(date: str = "20130308") -> pd.DataFrame:
+def news_cctv(date: str = "20240424") -> pd.DataFrame:
     """
     新闻联播文字稿
-    https://tv.cctv.com/lm/xwlb/?spm=C52056131267.P4y8I53JvSWE.0.0
+    https://tv.cctv.com/lm/xwlb
     :param date: 需要获取数据的日期; 目前 20160203 年后
     :type date: str
     :return: 新闻联播文字稿
     :rtype: pandas.DataFrame
     """
     if int(date) <= int("20130708"):
-        url = f"http://cctv.cntv.cn/lm/xinwenlianbo/{date}.shtml"
+        url = f"https://cctv.cntv.cn/lm/xinwenlianbo/{date}.shtml"
         r = requests.get(url)
         r.encoding = "gbk"
         raw_list = re.findall(r"title_array_01\((.*)", r.text)
         page_url = [
-            re.findall("(http.*)", item)[0].split("'")[0]
-            for item in raw_list[1:]
+            re.findall("(http.*)", item)[0].split("'")[0] for item in raw_list[1:]
         ]
         title_list = []
         content_list = []
         headers = {
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,"
+            "image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
             "Accept-Encoding": "gzip, deflate",
             "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
             "Cache-Control": "no-cache",
@@ -43,7 +44,8 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
             "Pragma": "no-cache",
             "Proxy-Connection": "keep-alive",
             "Upgrade-Insecure-Requests": "1",
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/92.0.4515.159 Safari/537.36",
         }
         for page in tqdm(page_url, leave=False):
             try:
@@ -52,9 +54,7 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
                 soup = BeautifulSoup(r.text, "lxml")
                 title = soup.find("h3").text
                 content = soup.find("div", attrs={"class": "cnt_bd"}).text
-                title_list.append(
-                    title.strip("[视频]").strip().replace("\n", " ")
-                )
+                title_list.append(title.strip("[视频]").strip().replace("\n", " "))
                 content_list.append(
                     content.strip()
                     .strip("央视网消息(新闻联播)：")
@@ -63,29 +63,30 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
                     .strip()
                     .replace("\n", " ")
                 )
-            except:
+            except:  # noqa: E722
                 continue
         temp_df = pd.DataFrame(
-            [[date] * len(title_list), title_list, content_list],
+            data=[[date] * len(title_list), title_list, content_list],
             index=["date", "title", "content"],
         ).T
         return temp_df
 
     elif int(date) < int("20160203"):
-        url = f"http://cctv.cntv.cn/lm/xinwenlianbo/{date}.shtml"
+        url = f"https://cctv.cntv.cn/lm/xinwenlianbo/{date}.shtml"
         r = requests.get(url)
         r.encoding = "utf-8"
         soup = BeautifulSoup(r.text, "lxml")
         page_url = [
             item.find("a")["href"]
             for item in soup.find(
-                "div", attrs={"id": "contentELMT1368521805488378"}
+                name="div", attrs={"id": "contentELMT1368521805488378"}
             ).find_all("li")[1:]
         ]
         title_list = []
         content_list = []
         headers = {
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,"
+            "image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
             "Accept-Encoding": "gzip, deflate",
             "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
             "Cache-Control": "no-cache",
@@ -94,18 +95,17 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
             "Pragma": "no-cache",
             "Proxy-Connection": "keep-alive",
             "Upgrade-Insecure-Requests": "1",
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/92.0.4515.159 Safari/537.36",
         }
         for page in tqdm(page_url, leave=False):
             try:
                 r = requests.get(page, headers=headers)
                 r.encoding = "utf-8"
-                soup = BeautifulSoup(r.text, "lxml")
+                soup = BeautifulSoup(r.text, features="lxml")
                 title = soup.find("h3").text
-                content = soup.find("div", attrs={"class": "cnt_bd"}).text
-                title_list.append(
-                    title.strip("[视频]").strip().replace("\n", " ")
-                )
+                content = soup.find(name="div", attrs={"class": "cnt_bd"}).text
+                title_list.append(title.strip("[视频]").strip().replace("\n", " "))
                 content_list.append(
                     content.strip()
                     .strip("央视网消息(新闻联播)：")
@@ -114,10 +114,10 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
                     .strip()
                     .replace("\n", " ")
                 )
-            except:
+            except:  # noqa: E722
                 continue
         temp_df = pd.DataFrame(
-            [[date] * len(title_list), title_list, content_list],
+            data=[[date] * len(title_list), title_list, content_list],
             index=["date", "title", "content"],
         ).T
         return temp_df
@@ -130,7 +130,8 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
         title_list = []
         content_list = []
         headers = {
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,"
+            "image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
             "Accept-Encoding": "gzip, deflate",
             "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
             "Cache-Control": "no-cache",
@@ -139,26 +140,25 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
             "Pragma": "no-cache",
             "Proxy-Connection": "keep-alive",
             "Upgrade-Insecure-Requests": "1",
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/92.0.4515.159 Safari/537.36",
         }
         for page in tqdm(page_url, leave=False):
             try:
                 r = requests.get(page, headers=headers)
                 r.encoding = "utf-8"
-                soup = BeautifulSoup(r.text, "lxml")
+                soup = BeautifulSoup(r.text, features="lxml")
                 if soup.find("h3"):
                     title = soup.find("h3").text
                 else:
-                    title = soup.find("div", attrs={"class": "tit"}).text
-                if soup.find("div", attrs={"class": "cnt_bd"}):
-                    content = soup.find("div", attrs={"class": "cnt_bd"}).text
+                    title = soup.find(name="div", attrs={"class": "tit"}).text
+                if soup.find(name="div", attrs={"class": "cnt_bd"}):
+                    content = soup.find(name="div", attrs={"class": "cnt_bd"}).text
                 else:
                     content = soup.find(
-                        "div", attrs={"class": "content_area"}
+                        name="div", attrs={"class": "content_area"}
                     ).text
-                title_list.append(
-                    title.strip("[视频]").strip().replace("\n", " ")
-                )
+                title_list.append(title.strip("[视频]").strip().replace("\n", " "))
                 content_list.append(
                     content.strip()
                     .strip("央视网消息(新闻联播)：")
@@ -167,15 +167,15 @@ def news_cctv(date: str = "20130308") -> pd.DataFrame:
                     .strip()
                     .replace("\n", " ")
                 )
-            except:
+            except:  # noqa: E722
                 continue
         temp_df = pd.DataFrame(
-            [[date] * len(title_list), title_list, content_list],
+            data=[[date] * len(title_list), title_list, content_list],
             index=["date", "title", "content"],
         ).T
         return temp_df
 
 
 if __name__ == "__main__":
-    news_cctv_df = news_cctv(date="20220525")
+    news_cctv_df = news_cctv(date="20240424")
     print(news_cctv_df)

akshare/news/news_stock.py

@@ -1,39 +1,75 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2022/11/12 20:59
+Date: 2025/12/23 17:15
 Desc: 个股新闻数据
-https://so.eastmoney.com/news/s?keyword=%E4%B8%AD%E5%9B%BD%E4%BA%BA%E5%AF%BF&pageindex=1&searchrange=8192&sortfiled=4
+https://so.eastmoney.com/news/s?keyword=603777
 """
+
 import json
 
 import pandas as pd
-import requests
+from curl_cffi import requests
 
 
-def stock_news_em(symbol: str = "300059") -> pd.DataFrame:
+def stock_news_em(symbol: str = "603777") -> pd.DataFrame:
     """
     东方财富-个股新闻-最近 100 条新闻
-    https://so.eastmoney.com/news/s?keyword=%E4%B8%AD%E5%9B%BD%E4%BA%BA%E5%AF%BF&pageindex=1&searchrange=8192&sortfiled=4
+    https://so.eastmoney.com/news/s?keyword=603777
     :param symbol: 股票代码
     :type symbol: str
     :return: 个股新闻
     :rtype: pandas.DataFrame
     """
     url = "https://search-api-web.eastmoney.com/search/jsonp"
+    inner_param = {
+        "uid": "",
+        "keyword": symbol,
+        "type": ["cmsArticleWebOld"],
+        "client": "web",
+        "clientType": "web",
+        "clientVersion": "curr",
+        "param": {
+            "cmsArticleWebOld": {
+                "searchScope": "default",
+                "sort": "default",
+                "pageIndex": 1,
+                "pageSize": 10,
+                "preTag": "<em>",
+                "postTag": "</em>"
+            }
+        }
+    }
     params = {
-        "cb": "jQuery3510875346244069884_1668256937995",
-        "param": '{"uid":"",'
-        + f'"keyword":"{symbol}"'
-        + ',"type":["cmsArticleWebOld"],"client":"web","clientType":"web","clientVersion":"curr","param":{"cmsArticleWebOld":{"searchScope":"default","sort":"default","pageIndex":1,"pageSize":100,"preTag":"<em>","postTag":"</em>"}}}',
-        "_": "1668256937996",
+        "cb": "jQuery35101792940631092459_1764599530165",
+        "param": json.dumps(inner_param, ensure_ascii=False),  # 保留中文,
+        "_": "1764599530176"
+    }
+    headers = {
+        "accept": "*/*",
+        "accept-encoding": "gzip, deflate, br, zstd",
+        "accept-language": "en,zh-CN;q=0.9,zh;q=0.8",
+        "cache-control": "no-cache",
+        "connection": "keep-alive",
+        "cookie": "qgqp_b_id=652bf4c98a74e210088f372a17d4e27b; st_nvi=ulN5JAj9FUocz3p4klMME9f20; emshistory=%5B%22603777%22%5D; nid18=010d039dd427dc4d187090491f47d7ad; nid18_create_time=1764582801999; gviem=gSdeY51VWSuTzM3kWaagtf560; gviem_create_time=1764582801999; st_si=55269775884615; st_pvi=66803244437563; st_sp=2025-11-19%2014%3A19%3A16; st_inirUrl=https%3A%2F%2Fso.eastmoney.com%2Fnews%2Fs; st_sn=2; st_psi=20251201223210488-118000300905-0940816858; st_asi=delete",
+        "host": "search-api-web.eastmoney.com",
+        "pragma": "no-cache",
+        "referer": "https://so.eastmoney.com/news/s?keyword=603777",
+        "sec-ch-ua": "\"Chromium\";v=\"142\", \"Google Chrome\";v=\"142\", \"Not_A Brand\";v=\"99\"",
+        "sec-ch-ua-mobile": "?0",
+        "sec-ch-ua-platform": "\"Windows\"",
+        "sec-fetch-dest": "script",
+        "sec-fetch-mode": "no-cors",
+        "sec-fetch-site": "same-site",
+        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36"
     }
-    r = requests.get(url, params=params)
+    r = requests.get(url, params=params, headers=headers)
     data_text = r.text
     data_json = json.loads(
-        data_text.strip("jQuery3510875346244069884_1668256937995(")[:-1]
+        data_text.strip("jQuery35101792940631092459_1764599530165(")[:-1]
     )
     temp_df = pd.DataFrame(data_json["result"]["cmsArticleWebOld"])
+    temp_df["url"] = "http://finance.eastmoney.com/a/" + temp_df["code"] + ".html"
     temp_df.rename(
         columns={
             "date": "发布时间",
@@ -83,5 +119,5 @@ def stock_news_em(symbol: str = "300059") -> pd.DataFrame:
 
 
 if __name__ == "__main__":
-    stock_news_em_df = stock_news_em(symbol="300059")
+    stock_news_em_df = stock_news_em(symbol="603777")
     print(stock_news_em_df)

akshare/nlp/nlp_interface.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 """
-Date: 2020/11/27 14:02
+Date: 2024/7/6 14:02
 Desc: ownthink-knowledge graph
 https://ownthink.com/
 https://www.ownthink.com/docs/kg/
 """
+
 import pandas as pd
 import requests
 
@@ -28,7 +29,7 @@ def nlp_ownthink(word: str = "人工智能", indicator: str = "entity") -> pd.Da
     r = requests.post(url, data=payload)
     if not r.json()["data"]:
         print("Can not find the resource, please type into the correct word")
-        return None
+        return pd.DataFrame()
     if indicator == "entity":
         return r.json()["data"]["entity"]
     if indicator == "desc":
@@ -48,18 +49,16 @@ def nlp_answer(question: str = "人工智能") -> str:
     :return: indicator data
     :rtype: list or dict or pandas.DataFrame
     """
-    url = 'https://api.ownthink.com/bot'
-    params = {
-        'spoken': question
-    }
+    url = "https://api.ownthink.com/bot"
+    params = {"spoken": question}
     r = requests.get(url, params=params)
     json_data = r.json()
-    answer = json_data['data']['info']['text']
+    answer = json_data["data"]["info"]["text"]
     return answer
 
 
 if __name__ == "__main__":
-    nlp_ownthink_df = nlp_ownthink(word="人工智能", indicator="tag")
+    nlp_ownthink_df = nlp_ownthink(word="人工智能", indicator="entity")
     print(nlp_ownthink_df)
 
     nlp_answer_df = nlp_answer(question="姚明的身高")

akshare/option/cons.py

@@ -4,6 +4,7 @@
 Date: 2019/9/30 13:58
 Desc: 期权配置文件
 """
+
 import datetime
 import json
 import os
@@ -38,21 +39,22 @@ SH_OPTION_PAYLOAD = {
     "select": "select: code,name,last,change,chg_rate,amp_rate,volume,amount,prev_close"
 }
 
-SH_OPTION_PAYLOAD_OTHER = {
-    "select": "contractid,last,chg_rate,presetpx,exepx"
-}
-
+SH_OPTION_PAYLOAD_OTHER = {"select": "contractid,last,chg_rate,presetpx,exepx"}
 
 
 # 大连商品交易所
-DCE_OPTION_URL = "http://www.dce.com.cn/publicweb/quotesdata/dayQuotesCh.html"
-DCE_DAILY_OPTION_URL = "http://www.dce.com.cn/publicweb/quotesdata/exportDayQuotesChData.html"
+DCE_OPTION_URL = "http://portal.dce.com.cn/publicweb/quotesdata/dayQuotesCh.html"
+DCE_DAILY_OPTION_URL = (
+    "http://portal.dce.com.cn/publicweb/quotesdata/exportDayQuotesChData.html"
+)
 
 # 上海期货交易所
-SHFE_OPTION_URL = "http://www.shfe.com.cn/data/dailydata/option/kx/kx{}.dat"
+SHFE_OPTION_URL = "https://tsite.shfe.com.cn/data/dailydata/option/kx/kx{}.dat"
 
 # 郑州商品交易所
-CZCE_DAILY_OPTION_URL_3 = "http://www.czce.com.cn/cn/DFSStaticFiles/Option/{}/{}/OptionDataDaily.txt"
+CZCE_DAILY_OPTION_URL_3 = (
+    "http://www.czce.com.cn/cn/DFSStaticFiles/Option/{}/{}/OptionDataDaily.txt"
+)
 
 # PAYLOAD
 SHFE_HEADERS = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
@@ -74,10 +76,8 @@ def convert_date(date):
             groups = match.groups()
             if len(groups) == 3:
                 return datetime.date(
-                    year=int(
-                        groups[0]), month=int(
-                        groups[1]), day=int(
-                        groups[2]))
+                    year=int(groups[0]), month=int(groups[1]), day=int(groups[2])
+                )
     return None
 
 

akshare/option/option_comm_qihuo.py

@@ -0,0 +1,86 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+"""
+Date: 2024/7/5 15:00
+Desc: 九期网-商品期权手续费
+https://www.9qihuo.com/qiquanshouxufei
+"""
+
+from functools import lru_cache
+from io import StringIO
+
+import pandas as pd
+import requests
+from bs4 import BeautifulSoup
+
+
+@lru_cache()
+def option_comm_symbol() -> pd.DataFrame:
+    import urllib3
+
+    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+    url = "https://www.9qihuo.com/qiquanshouxufei"
+    r = requests.get(url, verify=False)
+    soup = BeautifulSoup(r.text, features="lxml")
+    name = [
+        item.string.strip()
+        for item in soup.find(name="div", attrs={"id": "inst_list"}).find_all(name="a")
+    ]
+    code = [
+        item["href"].split("?")[1].split("=")[1]
+        for item in soup.find(name="div", attrs={"id": "inst_list"}).find_all(name="a")
+    ]
+    temp_df = pd.DataFrame([name, code]).T
+    temp_df.columns = ["品种名称", "品种代码"]
+    return temp_df
+
+
+def option_comm_info(symbol: str = "工业硅期权") -> pd.DataFrame:
+    """
+    九期网-商品期权手续费
+    https://www.9qihuo.com/qiquanshouxufei
+    :param symbol: choice of {"所有", "上海期货交易所", "大连商品交易所", "郑州商品交易所", "上海国际能源交易中心", "广州期货交易所"}
+    :type symbol: str
+    :return: 期权手续费
+    :rtype: pandas.DataFrame
+    """
+    import urllib3
+
+    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+    symbol_df = option_comm_symbol()
+    symbol_str = symbol_df[symbol_df["品种名称"].str.contains(symbol)][
+        "品种代码"
+    ].values[0]
+    params = {"heyue": symbol_str}
+    url = "https://www.9qihuo.com/qiquanshouxufei"
+    r = requests.get(url, params=params, verify=False)
+    temp_df = pd.read_html(StringIO(r.text))[0]
+    market_symbol = temp_df.iloc[0, 0]
+    columns = temp_df.iloc[2, :]
+    temp_df = temp_df.iloc[3:, :]
+    temp_df.columns = columns
+    temp_df["交易所"] = market_symbol
+    temp_df.reset_index(drop=True, inplace=True)
+    temp_df.index.name = None
+    temp_df.columns.name = None
+    temp_df["现价"] = pd.to_numeric(temp_df["现价"], errors="coerce")
+    temp_df["成交量"] = pd.to_numeric(temp_df["成交量"], errors="coerce")
+    temp_df["每跳毛利/元"] = pd.to_numeric(temp_df["每跳毛利/元"], errors="coerce")
+    temp_df["每跳净利/元"] = pd.to_numeric(temp_df["每跳净利/元"], errors="coerce")
+    soup = BeautifulSoup(r.text, features="lxml")
+    raw_date_text = soup.find(name="a", attrs={"id": "dlink"}).previous
+    comm_update_time = raw_date_text.split("，")[0].strip("（手续费更新时间：")
+    price_update_time = (
+        raw_date_text.split("，")[1].strip("价格更新时间：").strip("。）")
+    )
+    temp_df["手续费更新时间"] = comm_update_time
+    temp_df["价格更新时间"] = price_update_time
+    return temp_df
+
+
+if __name__ == "__main__":
+    option_comm_symbol_df = option_comm_symbol()
+    print(option_comm_symbol_df)
+
+    option_comm_info_df = option_comm_info(symbol="工业硅期权")
+    print(option_comm_info_df)