前言

就是这个地址了http://2050.acmclub.cn/
用的是杭电的OJ，杭电的OJ查看不了本校排名，简单分析了下，发现爬起来挺方便的

思路

首先要模拟登陆，不然看不到

登陆之后直接访问排名的网址
"http://2050.acmclub.cn/contests/contest_ranklist.php?cid=3&page=1" 逻辑很简单，page=1,2,3,4…

一般有成绩的就在前100页了，所以循环访问一百次就行

代码

from pyquery import PyQuery as pq
import requests

s = requests.session()


def login(username, pwd, college):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/70.0.3538.77 Safari/537.36"
    }
    data = {
        "username": username,
        "userpass": pwd,
        "login": "Sign In"
    }
    s.post('http://2050.acmclub.cn/userloginex.php?action=login&cid=3&notice=0', data=data, headers=headers)

    for i in range(1, 100):
        url = "http://2050.acmclub.cn/contests/contest_ranklist.php?cid=3&page=" + str(i)
        res = s.get(url)
        res.encoding = 'gb2312'
        doc = pq(res.text)

        trs = doc('tr').items()
        for tr in trs:
            tds = pq(tr('td'))
            rank = tds[0].text
            temp_list = pq(tds[1]).html().replace("\n", "").split("<br/>")
            if temp_list[0] == 'Team':
                continue
            name = temp_list[0]
            school = temp_list[1]
            if school == college:
                ac = tds[2].text
                print(f'{rank} {name} {school}  {ac}')


def main():
    # 输入账号，密码，学校三个参数
    login("xxx", "xxx", "xxxx")


if __name__ == '__main__':
    main()