python 黑板课爬虫闯关-第三关

 

import re
import requests
import time


def main():
    # 访问第三关，需要登录，登录的url
    url_login = 'http://www.heibanke.com/accounts/login/?next=/lesson/crawler_ex02/'
    # 登录成功后，访问第三关url
    url = 'http://www.heibanke.com/lesson/crawler_ex02/'
    session = requests.Session()
    # 获取cookie
    session.get(url_login)
    # 获取csrftoken
    token = session.cookies['csrftoken']

    # 将用户名密码和csrftoken一起提交给登录页面
    session.post(url_login, data={'csrfmiddlewaretoken': token, 'username': 'tianlegg', 'password': '123456'})
    # 登录成功后，携带了token再来访问页面会看到第三关内容，和第二关一样，只不过每次提交时同样需要带着csrftoken，否则还是会报错
    for psd in range(30):
        print(f'test password {psd}')
        session.get(url)
        token = session.cookies['csrftoken']
        r = session.post(url, data={'csrfmiddlewaretoken': token, 'username': 'aa', 'password': psd})
        html = r.text
        if '密码错误' not in html:
            m = re.search('(?<=\<h3\>).*?(?=\</h3\>)', html)
            print(m.group())
            m = re.search('(\<).*?href="([^"]*?)".*?(\>下一关\</a\>)', html)
            print(f'下一关 http://www.heibanke.com{m.group(2)}')
            return
        else:
            time.sleep(1)


if __name__ == '__main__':
    main()