import re
import requests
 
def Crawler(url):
  #url2 = 'https://www.diyifanwen.com/yanjianggao/yingyuyanjianggao/'
  response = requests.get(url).content.decode('gbk','ignore')
  html = response
  #正則表達(dá)式
  #example_for_2 = re.compile(r'<li><a.*?target="_blank".*?href="(.*?)title=(.*?)>.*?</a></li>')
  example_for_1 = re.compile(r'<i class="iTit">\s*<a href="(.*?)" rel="external nofollow" target="_blank">.*?</a>')
 
  resultHref =re.findall(example_for_1,html)
  resultHref = list(resultHref)
  Fil = []
  for each_url in resultHref:
    each_url = 'https:' + str(each_url)
 
    #構(gòu)建正則
    exam = re.compile(r'<div class="mainText">\s*(.*?)\s*<!--精彩推薦-->')
    response2 = requests.get(each_url).content.decode('gbk','ignore')
 
    html2 = response2
    result_eassy = re.findall(exam,html2)
    Fil.append(result_eassy)
 
  return str(Fil)
def WriteIntoFile(Fil,path):
  #寫(xiě)入文件
  with open(path,'a') as file:
    for i in range(len(Fil)//200):
      file.write(Fil[200*i:200*(i+1)])
      file.write('\r\n')
    if file is not None:
      print("success")
def Deleter_Chiness(str):
  #刪掉漢字、符號(hào)等
  result1 = re.sub('[<p> </p> u3000]','',str)
  result = ''.join(re.findall(r'[A-Za-z]', result1))
  return result

import Crawler
 
#產(chǎn)生一個(gè)密文加密表
def Creat_cipher_dict(num=5):
  cipher_dict = {}
  chri = [chr(i) for i in range(97,123)]
 
  for i in range(26-num):
    cipher_dict[chri[i]] = chr(ord(chri[i])+num)
  for i in range(num):
    cipher_dict[chri[26-num+i]] = chr(ord(chri[i]))
  return cipher_dict
def Get_Frequency(Str):
  Frequency = [0] * 26
  cnt = 0
  chri = [chr(i) for i in range(97, 123)]
  Frequency_dict = {}
  for i in range(len(Str)):
    Ascii = ord(Str[i]) - 97
    # 排除一些還存在的異常字符
    if Ascii >= 0 and Ascii <= 25:
      Frequency[Ascii] += 1
      cnt += 1
      Frequency_dict[chr(Ascii+97)] = Frequency[Ascii]
  for key in Frequency_dict.keys():
    #Frequency[i] = Frequency[i] / cnt
    Frequency_dict[key] = Frequency_dict[key]/cnt
  Frequency_dict = sorted(Frequency_dict.items(),key = lambda x:x[1],reverse=True)
  return dict(Frequency_dict)
def Decode(cipher,org):
  Frequency_for_cipher = Get_Frequency(cipher)
  Frequency_for_org = Get_Frequency(org)
  #print(Frequency_for_org)
  #print(Frequency_for_cipher)
  Decode_dict = {}
  Frequency = list(Frequency_for_org.keys())
  i = 0
  for key in list(Frequency_for_cipher.keys()):
    Decode_dict[key] = Frequency[i]
    i +=1
  return Decode_dict
def main():
  #爬取文章作為提取明文概率的計(jì)算文本
  for i in range(1,15):
    url = 'https://edu.pcbaby.com.cn/resource/yjg/yy/'+'index_'+str(i)+'.html'
    try:
      Fil = Crawler.Crawler(url)
      eassy = Crawler.Deleter_Chiness(Fil)
      path = 'eassy_org'
      Crawler.WriteIntoFile(path,eassy)
    except :
      print("爬蟲(chóng)發(fā)生意外！")
  
  path = 'eassy_org'
  with open(path) as file:
    org = str(file.read().splitlines())
    org = org.lower()
   #創(chuàng)建一個(gè)密文
  cipher_dict = Creat_cipher_dict(5)
  print(cipher_dict)
  #這里密文我已經(jīng)爬取好了，存在本地了，爬取過(guò)程同上面大同小異
  with open('eassy_cipher','r') as file:
    Fil2 = str(file.read().splitlines())
    Fil2 = Fil2.lower()
  cipher = []
  for i in range(len(Fil2)):
    if ord(Fil2[i])>=97 and ord(Fil2[i])<=123:
      cipher.append(cipher_dict[Fil2[i]])
  #至此 ，密文產(chǎn)生好了，每一個(gè)字母的概率也計(jì)算好了，可以說(shuō)，工作完成了一大半了
  Decode_dict = Decode(cipher,org)
  print(Decode_dict)
if __name__ == '__main__':
  main()