可导入文档类型为doc或docx
思路:导入文档,解析
# 找到文件,解析文件
from win32com import client as wc
root_file = MEDIA_ROOT + "/" + file.name
pythoncom.CoInitialize()
word = wc.Dispatch('Word.Application')
if u'.doc' in file.name and u'~$' not in file.name:
word.Visible = 0
doc = word.Documents.Open(root_file)
file_path_list = root_file.split('/')
title = file_path_list[-1].split('.')[0]
del file_path_list[-1]
a = '/'.join(file_path_list)
f = os.path.join(a, title+'.html')
doc.SaveAs(f ,8)
word.Quit()