acwing查看做题总数-凯发app官方网站

import re

import requests

from lxml import etree

class spider(object):

    def __init__(self):

        self.base_url = '{}/'

        self.headers = {

            'cookie': 'csrftoken=mixu7wxav35yyycdhqbxciow3z3ms0nh31jbbqh; sessionid='

                      '344bo4nowvp9misa9suynjiwz2i5jcof; file_2922585_readed=""; file_2302034_readed=""',

            'referer': '',

            'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36'

                          ' (khtml, like gecko) chrome/93.0.4577.63 safari/537.36'

        }

        self.count = 0

    def get_html(self, url):

        html = requests.get(

            url=url,

            headers=self.headers

        ).text

        return html

    def xpath_func(self, html):

        name_bds = '//tbody/tr[./td/span[@title="已通过这道题目"]]/td/a/text()'

        base_obj = etree.html(html)

        name_lists = base_obj.xpath(name_bds)

        l = []

        for i in name_lists:

            l.append(i.strip())

        return l

    def re_func(self, html, re_bds):

        pattern = re.compile(re_bds, re.s)

        re_list = pattern.findall(html)

        return re_list

    def parse_html(self, url):

        html = self.get_html(url)

        l = self.xpath_func(html)

        return l

    def run(self):

        warning = input('您马上就要爬取acwing了，看一下你的做题数，您的劳动成果将会在下面展示出来，外汇跟单gendan5.com确定要看吗？(y/n)')

        if warning == 'y':

            print('爬虫系统已经启动...正在努力抓取，请稍等....')

            print(' --------------------------------- ')

            print('|            name                 |')

            print(' --------------------------------- ')

            for i in range(1, 80):

                url = self.base_url.format(i)

                l = self.parse_html(url)

                for _ in l:

                    self.count = 1

                    print('|   ' _)

            print(' --------------------------------- ')

            print('经过您的不懈努力，您一共做了' str(self.count) '道题，继续努力！！')

        else:

            print('已经退出，你这个弱者')

if __name__ == '__main__':

    spider = spider()

    spider.run()