1.代码

import requests
from bs4 import BeautifulSoup
import re
def fetch_page(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    else:
        print(f"请求失败，状态码：{response.status_code}")
        return None
def parse_content(html):
    soup = BeautifulSoup(html, 'lxml')
    data = soup.select('.Artical_Content')  # 假设需要提取的元素有 class="detail-con"
    return data

def save_to_file(data, file_path):
    with open(file_path, 'a+', encoding="UTF-8") as file:
        file.write("")
        for item in data:
            text = item.get_text().strip()
            file.write(text + "\n")
def main():
    url = "https://china.chinadaily.com.cn/a/202503/06/WS67c99c29a310510f19eea2b5.html"
    html = fetch_page(url)
    if html:
        data = parse_content(html)
        file_path = 'E:\\新闻内容.txt'
        save_to_file(data, file_path)
        print("数据已成功保存到文件！")

if __name__ == "__main__":
    main()

2.运行结果