# -*- encoding: utf-8 -*-

from zipfile import ZipFile
from urllib import urlopen
from io import BytesIO
from bs4 import BeautifulSoup

# url="http://www.pythonscraping.com/pages/AwordDocument.doxc"
# word_file = urlopen(url).read()
# word_file = BytesIO(worl_file)

word_file = open("AWordDocument.docx", "rb")
document = ZipFile(word_file)
xml_content = document.read("word/document.xml")
text = xml_content.decode("utf-8")
print text

pip install python-docx

import docx

doc = docx.Document("AWordDocument.docx")
print doc

# 打印所有段落内容
for p in  doc.paragraphs:
    print p.text