python爬虫：模拟网站登录，获取指定页面信息

import requests
from bs4 import BeautifulSoup

# 登录页面的URL
login_url = 'login-url'

# 登录所需的用户名和密码
payload = {
    "username": "1",
    "password": "2",
}

# 创建一个会话对象来保持登录状态
session = requests.Session()

# 发送POST请求来模拟登录
login_response = session.post(login_url, data=payload)

# 检查登录是否成功（可以根据返回的内容或状态码来判断）
if 'Welcome' in login_response.text:
    print('登录成功')
else:
    print('登录失败')

# 访问需要登录才能访问的页面
target_url = 'https://target-url'
response = session.get(target_url)


# 处理获取到的网页内容
if response.status_code == 200:
    # 使用Beautiful Soup解析网页内容
    soup = BeautifulSoup(response.text, 'html.parser')

    # 进一步解析网页以提取更多信息
    issueList = []
    # 例如，提取所有链接
    tables = soup.find_all('table')
    for table in tables:
        trs = table.find_all('tr')
        for tr in trs:
            issueClass = {}
            tds = tr.find_all('td')
            for td in tds:
                issueClass[td.attrs['class'][0]] = td.text
            issueList.append(issueClass)
        print(issueList)

else:
    print('无法访问目标页面')