#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2025/11/20 120:15
Desc: 个股新闻数据
https://so.eastmoney.com/news/s?keyword=603777
"""

import json

import pandas as pd
import requests


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=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"
    params = {
        "cb": "jQuery3510875346244069884_1668256937995",
        "param": '{"uid":"",'
                 + f'"keyword":"{symbol}"'
                 + ',"type":["cmsArticle"],"client":"web","clientType":"web","clientVersion":"curr",'
                 + '"param":{"cmsArticle":{"searchScope":"default","sort":"default","pageIndex":1,'
                 + '"pageSize":100,"preTag":"<em>","postTag":"</em>"}}}',
    }
    r = requests.get(url, params=params)
    data_text = r.text
    data_json = json.loads(
        data_text.strip("jQuery3510875346244069884_1668256937995(")[:-1]
    )
    temp_df = pd.DataFrame(data_json["result"]["cmsArticle"])
    temp_df["url"] = "http://finance.eastmoney.com/a/" + temp_df["code"] + ".html"
    temp_df.rename(
        columns={
            "date": "发布时间",
            "mediaName": "文章来源",
            "code": "-",
            "title": "新闻标题",
            "content": "新闻内容",
            "url": "新闻链接",
            "image": "-",
        },
        inplace=True,
    )
    temp_df["关键词"] = symbol
    temp_df = temp_df[
        [
            "关键词",
            "新闻标题",
            "新闻内容",
            "发布时间",
            "文章来源",
            "新闻链接",
        ]
    ]
    temp_df["新闻标题"] = (
        temp_df["新闻标题"]
        .str.replace(r"\(<em>", "", regex=True)
        .str.replace(r"</em>\)", "", regex=True)
    )
    temp_df["新闻标题"] = (
        temp_df["新闻标题"]
        .str.replace(r"<em>", "", regex=True)
        .str.replace(r"</em>", "", regex=True)
    )
    temp_df["新闻内容"] = (
        temp_df["新闻内容"]
        .str.replace(r"\(<em>", "", regex=True)
        .str.replace(r"</em>\)", "", regex=True)
    )
    temp_df["新闻内容"] = (
        temp_df["新闻内容"]
        .str.replace(r"<em>", "", regex=True)
        .str.replace(r"</em>", "", regex=True)
    )
    temp_df["新闻内容"] = temp_df["新闻内容"].str.replace(r"\u3000", "", regex=True)
    temp_df["新闻内容"] = temp_df["新闻内容"].str.replace(r"\r\n", " ", regex=True)
    return temp_df


if __name__ == "__main__":
    stock_news_em_df = stock_news_em(symbol="603777")
    print(stock_news_em_df)