Python爬虫实例之2021猫眼票房字体加密反爬策略(粗略版)

import requests
import urllib.request as down
import json
from fontTools.ttLib import TTFont
import re
#分析用
import matplotlib.pyplot as plt #绘图
import numpy as np # 科学计算库

baseFont=TTFont('maoyan.woff')
# 获取相应数字的namecode和形状坐标的关系，可用来获取坐标
glyf=baseFont['glyf']
#通过对一份字体样本分析得出的字体映射
baseNumberMaps={
 0:glyf['uniF632'],
 1:glyf['uniF2F1'],
 2:glyf['uniF0A4'],
 3:glyf['uniF7B7'],
 4:glyf['uniE82D'],
 5:glyf['uniF653'],
 6:glyf['uniE756'],
 7:glyf['uniF41A'],
 8:glyf['uniE79B'],
 9:glyf['uniE81E']
}
for num,name in baseNumberMaps.items():
 print(name.coordinates)

import requests
import urllib.request as down
import json
from fontTools.ttLib import TTFont
import re
import MyPyClass

# 得到字体斜率列表（部分）
def font_Kdict(mapstype,maps=None):
 '''
 得到字体斜率字典（部分）
 参数：
 mapstype：str->maps类型，判断是是base/new
 maps：映射字典

 return kdict
 kdict字典关系：
 num:Klist 数字对应每条线段的斜率列表
 '''
 kdict={}
 # 遍历maps字典，找到对应的num和namecode
 for num, namecode in maps.items():
 # 跳过无用数据
 if namecode == 'x': continue
 # 判断类型，并从.coordinates得到对应num的所有坐标
 if mapstype=='base':coordinates = namecode.coordinates
 elif mapstype=='new':coordinates=glyf[namecode].coordinates
 # 得到坐标 X列表和坐标 Y列表
 x = [i[0] for i in coordinates]
 y = [i[1] for i in coordinates]
 Klist = []
 # 遍历X列表并切片为前10个数据进行斜率计算，即代表绘图的前10条线段的斜率
 for index, absx in enumerate(x[:10]):
  # 当斜率为0/1时，认为斜率为1计算
  if x[index + 1] == x[index] or y[index + 1] == y[index]:
  absxy = 1
  else:
  absxy = (y[index + 1] - y[index]) / (x[index + 1] - x[index])
  # 将斜率加入到列表
  Klist.append(-absxy if absxy < 0 else absxy)
 kdict[num]=Klist
 #print('base:', code, Klist, name)
 return kdict
# 对比斜率字典
def contrast_K(kbase,knew):
 '''
 对比斜率映射差距
 参数：
 kbase:基础字体映射表的斜率字典
 knew:当前链接的字体映射表的斜率字典

 return:dict
 fontMaps:根据对比得出正确的字体映射关系字典

 '''
 fontMaps = {}
 # 遍历kbase字典
 for base in kbase.items():
 n = 0 # 成功匹配的斜率个数
 # 遍历knew字典
 for new in knew.items():
  # 遍历kbase>knew>下的两组斜率，进行大小匹配，
  # 如果斜率k的差值小于0.5，并且样本数>=9时，认为两个坐标图形相识只是大小比例不同
  # 即k<=0.5 n>=9
  for (k1,k2) in zip(base[1],new[1]):
  # k取正数
  k=k1-k2 if k1>k2 else k2-k1
  if k<=0.5:
   n+=1
   continue
  else:
   break
  if n>=9:
  # 匹配正确则添加进字典中 此时的字典关系是：code:num 代码对应数字的关系
  fontMaps[str(hex(new[0]).replace('0x','&#x'))]=str(base[0])
  break
  n=0
 #print(fontMaps)
 return fontMaps

# 建立基础字体对象
baseFont=TTFont('maoyan.woff')
# 获取相应数字的namecode和形状坐标的关系，可用来获取坐标
glyf=baseFont['glyf']
#通过对一份字体样本分析得出的字体映射
baseNumberMaps={
 0:glyf['uniF632'],
 1:glyf['uniF2F1'],
 2:glyf['uniF0A4'],
 3:glyf['uniF7B7'],
 4:glyf['uniE82D'],
 5:glyf['uniF653'],
 6:glyf['uniE756'],
 7:glyf['uniF41A'],
 8:glyf['uniE79B'],
 9:glyf['uniE81E']
}
url='https://piaofang.maoyan.com/dashboard-ajax"([\s\S]*"',fontStyle[::-1])
 fonturl='http:'+fontStyle[0][::-1]# 字体url链接
 # 将加载的字体下载保存到本地，并对其进行分析
 down.urlretrieve(fonturl,'newfont.woff')
 # 爬取的电影数据内容
 content = json.loads(response.content)['movieList']['data']['list']
# 信息字典
movieNum={}#综合票房数字典
movieDayOne= {}#上映首日数量
movieRate={}#票房占比
movieshowCount={}#排片场次
movieViewerAvg={}#场均人数
movieInfos={}
# 页面内容
for i in content:
 moviename=i['movieInfo']['movieName']
 movieNum[moviename]=i['boxSplitUnit']['num']
 movieDayOne[moviename]=i['sumBoxDesc']
 movieRate[moviename]=i['splitBoxRate']
 movieshowCount[moviename]=i['showCount']
 movieViewerAvg[moviename]=i['avgShowView']

# 新字体对象
fontnew=TTFont('newfont.woff')
# 得到当前字体的映射关系表
newNumberMaps=fontnew.getBestCmap()
# 获取字形
glyf=fontnew['glyf']
# 基础字体斜率字典
k_base_dict=font_Kdict(maps=baseNumberMaps,mapstype='base')
# 新字体斜率字典
k_new_dict=font_Kdict(maps=fontnew.getBestCmap(),mapstype='new')
# 得到字体映射字典
fontcodes=contrast_K(k_base_dict,k_new_dict)
# 对加密的字体遍历分组，并去除无用字符
for name,numbercode in movieNum.items():
 movieNum[name]=re.findall('([\S]*"text-align: center">