镀金的天空字体反爬

最近公司看到小伙子在做这个类似于闯关的爬虫训练，闲来无事做一下。
因为这个还算是比较简单些的，就不讲解了。代码中很清晰，因为简单写的，所以在计算速率上比较慢一些。不过答案是正确的的哈哈

#!/usr/bin/python3
# -*- coding:utf-8 -*-
"""
@author: Cjp
@file: 3.py
@time: 2020/9/4 10:23
"""

import time
import requests
import re
import base64
import pandas as pd
from lxml import etree
from fontTools.ttLib import TTFont


class GlidedSky(object):
    def __init__(self):
        self.url = 'http://glidedsky.com/level/web/crawler-font-puzzle-1?page={}'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36',
            'Cookie' :'_ga=GA1.2.2076166588.1599182485; Hm_lvt_020fbaad6104bcddd1db12d6b78812f6=1599182485,1599184017; __gads=ID=c94e2e5e9c6d1406:T=1599184036:S=ALNI_Ma_JRzKSRhVrnobJU2CRfVfW3AS7A; footprints=eyJpdiI6IkQrYzM4dGtnMmFFOHlUZ3NoT3B4Rmc9PSIsInZhbHVlIjoiTnliMGNWaytFeG5uZkxacVFRRzF4Z3ZOVWVpb09pN2RHa0xDMFNUV0g3MVo5a0dkc1ZZMUhYVkFueTFIbFBSeSIsIm1hYyI6IjUzMDVkMTk4MjkyYzBlMmUzYmMxMjgwMDVjNzM3MGQ2YzU0YjBiZmMzMGEzNGQ5OGNjZTc4ZWNjZDRjMmRiOGYifQ%3D%3D; _gid=GA1.2.1046180803.1599808017; XSRF-TOKEN=eyJpdiI6IjEySDZcL3JteVYzaGUrU3AzXC9DaDNzZz09IiwidmFsdWUiOiIrWXBBbjZlbktmckthNVZPcVZodGNCNEhCWVZFd1dXbzEzVFRVY3RubnpOcVdHYmJkWDFsYzN6SkcrQ3Exb3RBIiwibWFjIjoiZjVhYzAyMzQxMTgxMjZhMGY5YTY4ZTZiOGNkY2NiYjI1NjgwYjZiZDljMzIyOGYwZDkzNWMxNWY5MjVlYWJhYyJ9; glidedsky_session=eyJpdiI6ImpGWnlHbTVYV1AxbEYrSnRkcHBZWmc9PSIsInZhbHVlIjoiallUZDNzUlk1RWowSklycjVTZjkrbEh1eDlYaGtYUHZpRE94akFCVVVTcUFqbUllUEV4RWthSkhVTFNmMW1RaiIsIm1hYyI6IjlhMmEwM2E1YTc1Mjk1NTk0MWQ1MWQwY2JiYmEyMTJiMDUzODRmNjkwMThiNjVlMWVlZGI4ZTA1YjBiOGM5MDQifQ%3D%3D; Hm_lpvt_020fbaad6104bcddd1db12d6b78812f6=1599809958',
            'Host': 'glidedsky.com',
        }

    def get_results(self,url):

        response = requests.get(url=url, headers=self.headers)
        ttf = re.findall('src: url\(data:font;charset=utf-8;base64,(.*?)\)', response.text)
        if len(ttf) > 0:
            newttf = base64.b64decode(ttf[0])
            with open('Glisky.ttf', 'wb') as f:
                f.write(newttf)


        data = self.get_xml_ttf()

        tree = etree.HTML(response.text)
        results = tree.xpath('//div[@class="row"]/div')
        bbtt = 0

        for b in results:
            a = b.xpath('./text()')[0].replace('\n','').strip()
            t = []
            for i in a:
                for key,value in data.items():
                    if i==value:
                        t.append(key)
            zhengti = ''.join(t)
            bbtt = bbtt + int(zhengti)
        # print(bbtt)
        return  bbtt


    def get_xml_ttf(self):
        font = TTFont('Glisky.ttf')
        font.saveXML('GGlisky.xml')
        get_Glyph = font.getGlyphOrder()

        #获取映射关系
        get_info= {
            '0':self.get_number(get_Glyph[1]),#这个是原页面数据
            '1':self.get_number(get_Glyph[2]),
            '2':self.get_number(get_Glyph[3]),
            '3':self.get_number(get_Glyph[4]),
            '4':self.get_number(get_Glyph[5]),
            '5':self.get_number(get_Glyph[6]),
            '6':self.get_number(get_Glyph[7]),
            '7':self.get_number(get_Glyph[8]),
            '8':self.get_number(get_Glyph[9]),
            '9':self.get_number(get_Glyph[10])
        }
        return get_info


    #转数字
    def get_number(self,en_number):

        if en_number == 'zero':
            return '0'
        elif en_number == 'one':
            return '1'
        elif en_number == 'two':
            return '2'
        elif en_number == 'three':
            return '3'
        elif en_number == 'four':
            return '4'
        elif en_number == 'five':
            return '5'
        elif en_number == 'six':
            return '6'
        elif en_number == 'seven':
            return '7'
        elif en_number == 'eight':
            return '8'
        elif en_number == 'nine':
            return '9'






if __name__ == '__main__':
    gs = GlidedSky()
    con = 0
    conn = 0

    for page in range(1,1001):
        new_url = gs.url.format(page)

        c = gs.get_results(new_url)
        conn = con+conn+c
        print(conn)
    print(conn)