爬虫：模拟登录、会话维持、cookie登录、代理、禁止重定向、超时处理、重试

import requests
from requests.exceptions import RequestException
from retrying import retry

@retry
def get_page(url, headers=None, proxies=None, allow_redirects=False, timeout=10):
    try:
        response = requests.get(url, headers=headers, proxies=proxies, allow_redirects=allow_redirects, timeout=timeout)
        if response.status_code == 403:  # 如果返回403，尝试使用cookies登录
            response = login_using_cookies()
        response.raise_for_status()  # 如果响应不是200，抛出异常
        return response.text
    except RequestException as e:
        print(f"请求出错: {e}")
        raise retry  # 如果发生异常，重试

def login_using_cookies():
    # 这里应该是登录逻辑，获取cookies，并返回包含cookies的response对象
    # 假设已经实现了login函数，它返回登录后的session对象
    session = login()
    return session.get(url)  # 使用登录后的session发起请求

def login():
    # 登录逻辑实现
    pass

# 使用示例
headers = {'User-Agent': 'your_user_agent'}
proxies = {'http': 'your_proxy_http', 'https': 'your_proxy_https'}
url = 'http://yourtarget.com'

page_content = get_page(url, headers, proxies)
print(page_content)