pythonttf字体反爬虫_python-字体反爬(一)

import base64

from fontTools.ttLib import TTFont

import requests

import re

def spider(i):

url = f"http://glidedsky.com/level/web/crawler-font-puzzle-1?page={i}"

headers = {

'Cookie': '_ga=GA1.2.1509539893.1587014930; Hm_lvt_020fbaad6104bcddd1db12d6b78812f6=1587014930,1587108479; _gid=GA1.2.1660844838.1587200384; footprints=eyJpdiI6InhiY0dWRVQ0dFM2XC9QYjZsTDZNOG5RPT0iLCJ2YWx1ZSI6IlBLNjUyZmFwU2pnaFBXekJySllONkx4alhrV2xJSDNiajV3N29oR0xwdXlmeDlzK1R4S1wvdHZ5UGliRGk4RjZwIiwibWFjIjoiZmFmMmQ3NTU1MzhmYmJkODkyZmM2NTRlNjRkMmViM2VhZGMxYWUzYjYwNjJlZWQzYjViMTA3MjVlNDYxYjJiMiJ9; remember_web_59ba36addc2b2f9401580f014c7f58ea4e30989d=eyJpdiI6IlI1TUZsQ0NSVkpxYWZTeWhZSXVYeUE9PSIsInZhbHVlIjoiMWs5S0p3NUhic0UxdjU3OHdXVkR5NVwvMXFDZ3NUTmdrQ0E5TzE5N2MzamR0a1pLVzBJVXU0cmVUVHRLbFJFOFwvV1NuYnpEQVBQVnVLS2ZtOHo5RlwvdmlFWmd2UXF5TFE0MVMzV0FkckVRbmUxVlNDek1NK3cwRjkyWjRUejlPRlk3S0VoNHJycG5yRWNjRTBiTHRQZjk3RUFkZkxvSWFSZTFLQjBpVmRjU2RZPSIsIm1hYyI6ImNlZDUxYWJhNmVhODY1MzllYWNiYjQyOWUxOWE1OTk2NGY3NjdkMjFkOTc4NjBlZWZlNmFmMDAwZDg2MTJmNTgifQ%3D%3D; XSRF-TOKEN=eyJpdiI6InpuMFFUZmY1RHhrYlwva24rTUdYQmR3PT0iLCJ2YWx1ZSI6InpaSDRWUTk1MFVQeG1Mc1FydllzRkVaQ0tURTBaWktIcWVDcmZMWGZXRUt1NVBtRlFrUmhvS2w1Y1NPSlRwUUQiLCJtYWMiOiI4NzNkMjA0MDBlMGUzNTljZWViYWQ4MWIxOTc1ZTc0MTVhZjFjMzdiNjhkZjA1NGQ5NmRjN2NmYWI3YzVmMjYyIn0%3D; glidedsky_session=eyJpdiI6ImVESlVHR3ZkMktkZ0NncTcyVzZraUE9PSIsInZhbHVlIjoiRXZqV0lcL3pBdjAwOGJnYkt3d3hUbXJBcnVZMFZqTWh2S0ExQ1NzZ1RjREtsd3cxd0cwSTgzZG95VGw1MzRtMjgiLCJtYWMiOiIyYzE1MTAxOWE3MjMxMDdkNDdlNzg0NzEyNWQyNDY3ZWI0MzdhMjYyN2RlZTNjODcyZTFkNjRjYjM0ZmVjMWFhIn0%3D; _gat_gtag_UA_75859356_3=1; Hm_lpvt_020fbaad6104bcddd1db12d6b78812f6=1587291491'

}

resp = requests.get(url,headers=headers).text

# 得到加密的字符串

encrypted = re.search(r'\(data:font;charset=utf-8;base64,(.*?)\) format',resp,re.S).group(1)

# 进行解码

data = base64.b64decode(encrypted)

with open('gs-1.ttf','wb') as f:

f.write(data)

# 解析字体库

fonts = TTFont('gs-1.ttf')

# fonts.saveXML('gs-1.xml')

# 得到编码

enNum_list = fonts.getGlyphOrder()[1:] # print(enNum_list) # ['five', 'three', 'nine', 'zero', 'eight', 'seven', 'one', 'four', 'six', 'two'] base_dict = { 'zero':0, 'one':1, 'two':2, 'three':3, 'four':4, 'five':5,'six':6, 'seven':7, 'eight':8, 'nine':9}

num = [base_dict[i] for i in enNum_list] # print(num) # [5, 3, 9, 0, 8, 7, 1, 4, 6, 2] online_dict = {str(j):str(i) for i,j in enumerate(num)}

# print(online_dict) # {'5': '0', '3': '1', '9': '2', '0': '3', '8': '4', '7': '5', '1': '6', '4': '7', '6': '8', '2': '9'}

base_num = re.findall(r'.*?(\d+).*?

',resp,re.S)

sum1 = 0

for num in base_num:

rel_num = ''

for i in num:

rel_num += online_dict[i] sum1 += int(rel_num)

return sum1

if __name__ == '__main__':

sums = 0

for i in range(1,1001):

sum1 = spider(i)

sums += sum1

print(i,sums)