Ubuntu下使用python读取doc和docx文档的内容方法

sudo pip install python-docx 

#encoding:utf8 
import docx 
doc = docx.Document('test.docx') 
docText = '\n'.join([paragraph.text for paragraph in doc.paragraphs]) 
#print(docText) 

#encoding:utf8 
import subprocess 
word = 'test.doc' 
output = subprocess.check_output(['antiword',word]) 
print(output)