PYTHON 3-如何web抓取受密码保护的网站？

import requests
from bs4 import BeautifulSoup
from getpass import getpass

login_url = "https://example.com/login"  # 替换为实际登录页面的URL
username = "your_username"  # 替换为实际用户名
password = getpass("Enter your password: ")

login_data = {
    "username": username,
    "password": password
}

session = requests.Session()
session.post(login_url, data=login_data)

target_url = "https://example.com/protected-page"  # 替换为实际受保护页面的URL

response = session.get(target_url)
soup = BeautifulSoup(response.text, "html.parser")

# 在这里进行解析和提取所需的数据

# 示例：提取页面标题
title = soup.title.text
print("Page title:", title)