从多个urls中提取标题和表体(使用漂亮汤)到dataframe

from bs4 import BeautifulSoup
import requests
import pandas as pd

def extract_data(url):
    # 发送HTTP请求获取网页内容
    response = requests.get(url)
    # 使用漂亮汤解析网页内容
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # 提取标题
    title = soup.title.text
    
    # 提取表体
    body = soup.body.text
    
    return title, body

def main(urls):
    # 创建一个空的DataFrame
    df = pd.DataFrame(columns=['Title', 'Body'])
    
    # 遍历每个url
    for url in urls:
        # 提取标题和表体
        title, body = extract_data(url)
        
        # 将结果添加到DataFrame中
        df = df.append({'Title': title, 'Body': body}, ignore_index=True)
    
    return df

urls = ['url1', 'url2', 'url3']  # 替换为实际的urls

df = main(urls)
print(df)