【2020-11-16】Python反爬虫之字体反爬

---

前言

目标网址——起点小说：https://book.qidian.com/info/1010734492

---

一、什么是字体反爬？

字体反爬虫：在网页中的关键部分中采用自定义的字体来显示，防止爬虫爬取到关键信息。

二、如何解决？

1.获取字体文件

从页面源码入手，可以看到字体已经被转义成了𘡒𘡓𘡓𘡏𘡒𘡓
字体的源文件地址是：https://qidian.gtimg.com/qd_anti_spider/PCiagJxf.woff

2.获取字体的映射关系

1. Python导入fontTools模块：pip install fontTools

   from fontTools.ttLib import TTFont
   

2. 下载字体文件

       # 获取字体链接
       font_class = re.findall("format\('eot'\); src: url\('(.*?)'\) format\('woff'\), url", page_info)[0]
       font_name = font_class.split('/')[-1].split('.')[0]
       print(font_class,font_name)
   
       # 下载woff字体
       with open('my.woff','wb') as f:
           f.write(requests.get(url=font_class).content)
   

3. 获取映射关系

   font = TTFont('my.woff')
   font.saveXML('font.xml')
   
   with open('font.xml','rb') as f:
       txt = f.read().decode('utf8')
       # 映射关系
       y_dict = {
         
         'zero': '0', 'one': '1', 'two': '2', 'three': '3', 'four': '4', 'five': '5', 'six': '6','seven': '7','eight': '8', 'nine': '9', 'period': '.'}
       # 获取字体映射内容
       data2 = re.compile('code="(.*?)".*name="(.*?)"').findall(txt)
       x_dict = dict()
       for x in data2:
           base_code = str(int(x[0], 16))
           x_dict[base_code] = y_dict[x[1]]
       return x_dict
   

   

4. 匹配需转义的十六进制、并进行转义

       # 正则匹配需转义的十六进制
       confuse_data = re.findall('</style><span class="'+font_name+'">(.*?);</span></em><cite>',page_info)
       print(confuse_data)
       de_cnnfuse = []
       # 遍历字体转义、进行字体匹配处理
       for data in confuse_data:
           deal_data = data.replace('&#','').split(';')
           x = []
           for info in deal_data:
               x.append(font_dict[info])
           de_cnnfuse.append(''.join(x))
   

   

   

---

三、源码

'''

起点中文网 https://book.qidian.com/info/1010734492

'''

import re
from fontTools.ttLib import TTFont
import requests


def get_info(): # 获取字体映射关系
    font = TTFont('my.woff')
    font.saveXML('font.xml')

    with open('font.xml','rb') as f:
        txt = f.read().decode('utf8')
        # 映射关系
        y_dict = {
    
    'zero': '0', 'one': '1', 'two': '2', 'three': '3', 'four': '4', 'five': '5', 'six': '6','seven': '7','eight': '8', 'nine': '9', 'period': '.'}
        # 获取字体映射内容
        data2 = re.compile('code="(.*?)".*name="(.*?)"').findall(txt)
        x_dict = dict()
        for x in data2:
            base_code = str(int(x[0], 16))
            x_dict[base_code] = y_dict[x[1]]
        return x_dict


if __name__ == '__main__':
    headers = {
    
    
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36',
        '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-language': 'zh-CN,zh;q=0.9',
    }

    response = requests.get('https://book.qidian.com/info/1010734492', headers=headers)
    page_info = response.text

    # 获取字体链接
    font_class = re.findall("format\('eot'\); src: url\('(.*?)'\) format\('woff'\), url", page_info)[0]
    font_name = font_class.split('/')[-1].split('.')[0]
    print(font_class,font_name)

    # 下载woff字体
    with open('my.woff','wb') as f:
        f.write(requests.get(url=font_class).content)

    # 获取字体映射关系
    font_dict = get_info()
    print(font_dict)

    # 正则匹配需转义的十六进制
    confuse_data = re.findall('</style><span class="'+font_name+'">(.*?);</span></em><cite>',page_info)
    print(confuse_data)
    de_cnnfuse = []
    # 遍历字体转义、进行字体匹配处理
    for data in confuse_data:
        deal_data = data.replace('&#','').split(';')
        x = []
        for info in deal_data:
            x.append(font_dict[info])
        de_cnnfuse.append(''.join(x))

    title_list = ['总字数（万）','会员周点击数','总推荐数（万）','周推荐数']
    print(dict(zip(title_list, de_cnnfuse)))