1234567891011121314151617181920212223242526272829303132333435363738 |
- #!/usr/bin/env python
- # -*- encoding: utf-8 -*-
- '''
- @Contact : liuyuqi.gov@msn.cn
- @Time : 2023/12/09 14:57:36
- @License : Copyright © 2017-2022 liuyuqi. All Rights Reserved.
- @Desc : enter point
- recycle read all files in a directory, and find *.pdf files, then convert x.pdf to x.html
- '''
- import os,sys,re,shutil
- def convert():
- ''''''
- current_dir = os.getcwd()
- if not os.path.exists(os.path.join(current_dir,'htmls')):
- os.mkdir(os.path.join(current_dir,'htmls'))
- for root, dirs, files in os.walk(current_dir):
- for file in files:
- if file.endswith('.pdf'):
- try:
- os.system('pdf2htmlEX --zoom 1.3 --process-outline 0 --page-filename %s.html %s'%(file,file))
- print('convert %s to %s.html'%(file,file))
- except Exception as e:
- print(f'convert failed: {e}')
-
- # move all .html to htmls diretory
- for root, dirs, files in os.walk(current_dir):
- for file in files:
- if file.endswith('.html'):
- try:
- shutil.move(os.path.join(root,file),os.path.join(current_dir,'htmls'))
- except Exception as e:
- print(f'move failed: {e}')
- if __name__=='__main__':
- convert()
|