使用Python自动化破解自定义字体混淆信息的方法实例

# -*- coding: utf-8 -*-
本例采用 tesseract ocr 引擎，根据字体文件自动生成密文与明文的字符映射表，实现解密功能。
@author: 李毅
from tesserocr import pytessbaseapi, psm
from pil import image, imagedraw, imagefont
from fonttools.ttlib import ttfont
import string
class ocr(object):
 default_config = {
 # ocr engine
 'data_path': none,
 'lang': 'chi_sim',
 'white_list': none,
 'black_list': none,
 # image
 'font': none,
 'image_size': (60, 60),
 'font_size': 30,
 'text_offset': (15, 15),
 }
 def __init__(self, config={}):
 c = dict(self.default_config)
 c.update(config)
 self.api = pytessbaseapi(path=c['data_path'], lang=c['lang'], psm=psm.single_char)
 self.img = image.new('rgb', c['image_size'], color='white')
 self.draw = imagedraw.draw(self.img)
 self.font = imagefont.truetype(c['font'], size=c['font_size'])
 self.text_offset = c['text_offset']
 if c['white_list']:
  self.api.setvariable('tessedit_char_whitelist', c['white_list'])
 if c['black_list']:
  self.api.setvariable('tessedit_char_blacklist', c['black_list'])
 self.font_tool = ttfont(c['font'])
 self.empty_char = self._predict_empty_char()
 def _predict_empty_char(self):
 self.api.setimage(self.img)
 return self.api.getutf8text().strip()
 def is_char_in_font(self, char):
 for t in self.font_tool['cmap'].tables:
  if t.isunicode():
  if ord(char) in t.cmap:
   return true
 return false
 def predict(self, char):
 ''' 返回转换后的字符，或空串'' '''
 if not self.is_char_in_font(char):
  return char # 若字体无法渲染该字符，则原样返回。此处可酌情移除。
 self.img.paste('white', (0, 0, self.img.size[0], self.img.size[1]))
 self.draw.text(self.text_offset, char, fill='black', font=self.font)
 self.api.setimage(self.img)
 c2 = self.api.getutf8text().strip()
 if c2 == self.empty_char:
  return '' # 某些字符可能渲染成空白，此时返回空串。
 return c2
class decoder(object):
 def __init__(self, data_path, font):
 self.cache = {} # 缓存已知的映射关系。
 ocr.default_config.update(dict(data_path=data_path, font=font))
 self.ocr_digit = ocr(dict(
  lang='eng',
  white_list=string.digits,
  black_list=string.ascii_letters,
 ))
 self.ocr_letter = ocr(dict(
  lang='eng',
  black_list=string.digits,
  white_list=string.ascii_letters,
 ))
 self.ocr_other = ocr()
 def decode(self, char):
 if char not in self.cache:
  c2 = self._decode_when_cache_miss(char)
  self.cache[char] = c2 or char
 return self.cache[char]
 def _decode_when_cache_miss(self, char):
 ocr = self.ocr_other
 if char in string.digits:
  ocr = self.ocr_digit
 elif char in string.ascii_letters:
  ocr = self.ocr_letter
 return ocr.predict(char)
if __name__ == '__main__':
 s = '''你好，青划长务, 8175-13-79'''
 d = decoder('tessdata/', 'a.ttf')
 print(''.join(map(d.decode, s)))