Question

我遵循this教程，我可以访问我的bitbucket并获取所有数据，但是当我将它用于另一个也需要登录的网站时。它没有用。

当我在登录页面打印内容时，我仍然堆栈。凭证是正确的，网站中的令牌也是我成功获得的价值。 Bdw该网站由laravel制成。

教程中的代码

import requests
from lxml import html

USERNAME = "<USERNAME>"
PASSWORD = "<PASSWORD>"

LOGIN_URL = "https://bitbucket.org/account/signin/?next=/"
URL = "https://bitbucket.org/dashboard/repositories"

def main():
    session_requests = requests.session()

    # Get login csrf token
    result = session_requests.get(LOGIN_URL)
    tree = html.fromstring(result.text)
    authenticity_token = list(set(tree.xpath("//input[@name='csrfmiddlewaretoken']/@value")))[0]

    # Create payload
    payload = {
        "username": USERNAME, 
        "password": PASSWORD, 
        "csrfmiddlewaretoken": authenticity_token
    }

    # Perform login
    result = session_requests.post(LOGIN_URL, data = payload, headers = dict(referer = LOGIN_URL))

    # Scrape url
    result = session_requests.get(URL, headers = dict(referer = URL))
    tree = html.fromstring(result.content)
    bucket_names = tree.xpath("//div[@class='repo-list--repo']/a/text()")

    print(bucket_names)

if __name__ == '__main__':
    main()

使用lxml进行Python web报废

0 个答案: