《封号码罗》python爬虫之某同城字体反爬（十二）

最新推荐文章于 2023-04-23 11:12:42 发布

原创

最新推荐文章于 2023-04-23 11:12:42 发布 · 1.1k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #xpath #xml #url #字体反爬

本文介绍了解析58同城网站中使用的字体加密技术的方法，包括如何抓取并解析特殊字体文件，以及如何替换页面上的加密字符为真实文本。

from xml import etree

import requests
import re
import base64
from fontTools.ttLib import TTFont, BytesIO

headers = {
   
   
    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
    "accept-encoding": "gzip, deflate, br",
    "accept-language": "zh-CN,zh;q=0.9",
    "cache-control": "max-age=0",
    # 拿cookie是因为现在需要登陆状态才行
    "cookie": 'f=n; commontopbar_new_city_info=5%7C%E8%8B%8F%E5%B7%9E%7Csu; id58=UvTEUl/zCqajUJaybRC9bw==; 58tj_uuid=7009bbe1-76f8-4b73-8376-1f7a69d5f496; als=0; wmda_new_uuid=1; wmda_uuid=c67559bfe142299dbd374d9dab028df8; xxzl_deviceid=KaV0c6cV6yrVONO9yTVEfuxpPimKScDGVOLYxOl3UXSNS5GD%2BMfPxb30M3qNp5Fi; xxzl_smartid=e80e9b7ddd64b4b4d1a2cd8041cebe27; gr_user_id=b371d8ff-2cf7-43ca-9097-e7dd72fc6224; xxzl_cid=e61ae401e08e40388d40a8e34b29956a; xzuid=7f33cba3-b8fd-43f1-839e-fa2c1cc9cafa; Hm_lvt_3bb04d7a4ca3846dcc66a99c3e861511=1610121167,1610166089,1610166404,1610369641; Hm_lvt_e15962162366a86a6229038443847be7=1610121167,1610166090,1610166405,1610369641; Hm_lvt_e2d6b2d0ec536275bb1e37b421085803=1610120643,1610166104,1610369657; ppStore_fingerprint=43A259D40092AFB43E772FCC9350C463700EAEBE5D26276C%EF%BC%BF1610369657573; 58home=su; f=n; commo