爬虫进阶-反爬破解7（逆向破解被加密数据：全方位了解字体渲染的全过程+字体文件的检查和数据查看+字体文件转换并实现网页内容还原+完美还原上百页的数据内容）

# &#x9ea3;&#x9f92;&#x9fa4;&#x9f92;&#x9f92
# 10400

import requests
from fontTools.ttLib import TTFont # pip install fontTools
from lxml import etree

fonturl = 'http://shanzhi.spbeen.com/static/fonts/szec.ttf'
fontresponse = requests.get(fonturl)
print(fontresponse)
with open('font.ttf','wb') as file:
    file.write(fontresponse.content)

font = TTFont("font.ttf")
# font.saveXML("font.xml")
result_dict = {}
for k,v in font['cmap'].getBestCmap().items():
    # hex()函数是将十进制转成16进制
    k = hex(k).replace('0x','&#x')+';'
    v = int(v[8:10])-1
    result_dict[k]=str(v)
print(result_dict)

url = 'http://shanzhi.spbeen.com/search/?word='
response = requests.get(url)
html = response.text
for k,v in result_dict.items():
    html = html.replace(k,v)
# print(html)

htmlobj = etree.HTML(html)
divcard = htmlobj.xpath('.//div[@class="content"]/div')
for dc in divcard:
    td = {}
    td['标题'] = dc.xpath('./div/h5/a/text()')
    td['薪资'] = dc.xpath('./div/h5/small/text()')
    print(td)

四、完美还原上百页的数据内容

1.字体文件的转换

2.替换网页内容

3.实践操作：爬虫实战，还原数据内容

python 复制代码

import requests
from fontTools.ttLib import TTFont
from lxml import etree
from time import sleep

import logging

logging.basicConfig(level=logging.DEBUG,filename='debug.log',filename='a',format='%(asctime)s-%(levelname)s-[%(filename)s:%(lineno)d]-%(message)s')

font = TTFont("font.ttf")
result_dict = {}
for k,v in font['cmap'].getBestCmap().items():
    # hex()函数是将十进制转成16进制
    k = hex(k).replace('0x','&#x')+';'
    v = int(v[8:10])-1
    result_dict[k]=str(v)

def replace_html(html:str):
    for k,v in result_dict.items():
        html = html.replace(k,v)
    return html

url = 'http://shanzhi.spbeen.com/search/?word=%E5%B5%8C%E5%85%A5%E5%BC%8F&page={}&_=1631261605624'

for i in range(1,10000):
    turl = url.format(i)
    response = requests.get(turl)
    html = replace_html(reponse.text)
    htmlobj = etree.HTML(html)
    divcard = htmlobj.xpath('.//div[contains(@class, "animate__animated")]')
    total_num += len(divcard)
    print("当前页面是第{}页，总计有{}条数据,当前页数据如下：".format(i,len(divcard),total_num))
    for dc in divcard:
        td = {}
        td['标题'] = dc.xpath('./div/h5/a/text()')
        td['薪资'] = dc.xpath('./div/h5/small/text()')
        print('               ',td)
    if len(divcard) < 10:
        break
    else:
        pass
    sleep(0.1)

4.总结：

（1）提取出具体的原数据和对应数字，进行网页内容的替换

（2）注意原数据的完整格式，确保替换后的数据没有多余符号

（3）找数据接口和具体参数，循环请求接口拿数据