python反编译chm文件并生成pdf文件

1 # -*- coding: utf-8 -*-
2
3 import os
4 import os.path
5 import logging
6 import pdfkit
7
8 original_chm = r'C:\Users\hushaojun\Documents\canoe\Help01\CAPLfunctions.chm'
9 root_dir = r'C:\Users\hushaojun\Documents\canoe\Help01\canoe\Topics'
10 seperator = os.sep
11
12 #    HH.EXE -decompile <输出路径> <目标chm文件>
13
14 logging.basicConfig(level=logging.WARNING,
15                     format='%(asctime)s %(pathname)s %(filename)s %(funcName)s [line:%(lineno)d] %(levelname)s %(message)s',
16                     datefmt='%Y-%m-%d %H:%M:%S',
17                     filename='all_file_name.log',
18                     filemode='w+')
19
20 #深度优先算法
21 def recursionFunction(level, path):
22     for file_content in os.listdir(path):    #列举显示所有文件夹下的内容
23         #“-”用于显示目录层次结构
24         full_path_name = os.path.join(path, file_content)
25         print('-'*(level+1) + full_path_name)
26
27         if os.path.isdir(full_path_name):    #如果是文件夹就递归显示
28             recursionFunction(level+1, full_path_name)
29         else:    #如果是文件那就要直接显示
30             (shotname, extension) = os.path.splitext(file_content)
31
32             logging.error('文件全名为：' + full_path_name)
33             print('文件名为：' + shotname)
34             print('文件后缀名为：' + extension)
35
36             pdf_file_name = os.path.join(path, shotname + '.pdf')
37
38             if (not os.path.exists(pdf_file_name)) and ((extension == '.htm') or (extension == '.html')):
39                 try:
40                     pdfkit.from_file(full_path_name, pdf_file_name)
41                 except OSError:
42                     print('just skip!')
43                 except Exception as e:
44                     print(type(e))
45
46 if __name__ == '__main__':
47     decomplile_cmd = 'HH.EXE -decompile %s %s' % (root_dir, original_chm)
48     os.system(decomplile_cmd)
49     recursionFunction(0, root_dir)