找出两个文件夹中不同文件，并另存

# -*- coding:utf-8 -*-
import os
from shutil import copy

def main():
	pdf_path = r'D:\\pdf_file'
	html_path = r'D:\\html_file'
	# 遍历两个路径下的文件 其中.htm的文件进行筛选，和PDF文件内容进行文件名（不含.pdf和.HTML）的对比找出不在对方文件中.pdf文件，保存到另外一个文件中
	pdf_list = set([_.split('.')[0] for _ in os.listdir(pdf_path) ])
	html_list = set([_.split('.')[0] for _ in os.listdir(html_path) if '.htm' in _])
	diff_list = list(pdf_list^html_list)
	if not os.path.exists(os.path.join('D:\\', 'diff_file')):
		os.mkdir(os.path.join('D:\\', 'diff_file'))
	for d_file in diff_list:
		from_path = os.path.join(pdf_path,d_file+'.pdf')
		to_path = os.path.join('D:\\', 'diff_file')
		copy(from_path, to_path)
		print(d_file+'.pdf 复制成功',)

if __name__ == '__main__':
	main()