如何下载一个文件后抓取它的href，没有http或https在里面

import requests
from bs4 import BeautifulSoup

# 发送HTTP请求获取文件内容
response = requests.get('http://example.com/file.html')

# 解析文件内容，提取href
soup = BeautifulSoup(response.text, 'html.parser')
hrefs = [a['href'] for a in soup.find_all('a')]

# 处理没有http或https的href，构建完整的URL
base_url = 'http://example.com'
complete_hrefs = [base_url + href if not href.startswith('http') else href for href in hrefs]

# 下载文件
for href in complete_hrefs:
    response = requests.get(href)
    filename = href.split('/')[-1]  # 提取文件名
    with open(filename, 'wb') as f:
        f.write(response.content)