1. 需要的类包

import pandas as pd
import requests

2. 请求地址

通过分析，数据可以直接从接口获取，无需解析页面标签，直接取出我们需要的数据即可。

def fetch_hot_news(api_url):
    response = requests.get(api_url)

    if response.status_code == 200:
        data = response.json()
        hot_news = data.get("data", {}).get("hotNews", [])
        return hot_news
    else:
        print(f"Failed to retrieve data. Status code: {response.status_code}")
        return []

3. 导出表格

def export_to_excel(hot_news_data):
    if not hot_news_data:
        return

    # Add the missing URL field
    base_url = "https://www.xxx.cn/newsDetail_forward_" #澎某pai
    hot_news_data = [{
        **news,
        "URL": f"{base_url}{news['contId']}"
    } for news in hot_news_data]

    # Create a DataFrame
    df = pd.DataFrame(hot_news_data)

    # Choose only relevant columns
    relevant_columns = ["contId", "name", "pubTime", "URL"]
    df = df[relevant_columns]

    # Export to Excel
    df.to_excel("pengpai-top.xlsx", index=False)
    print("Data exported to Excel successfully.")

处理url

def main():
    api_url = "https:/xx/wwwIndex/xxx" #分析得到的需要请求的接口地址
    hot_news_data = fetch_hot_news(api_url)

    if hot_news_data:
        export_to_excel(hot_news_data)
    else:
        print("No hot news data found.")

4. 成果展示