我使用python脚本来转换文件.doc放到一个文件里。文本。我的代码是:from subprocess import Popen, PIPE
from docx import opendocx, getdocumenttext
#http://stackoverflow.com/questions/5725278/python-help-using-pdfminer-as-a-library
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
import os
def document_to_text(filename, file_path):
if filename[-4:] == ".doc":
cmd = ['antiword', file_path]
p = Popen(cmd, stdout=PIPE)
stdout, stderr = p.communicate()
return stdout.decode('ascii', 'ignore')
elif filename[-5:] == ".docx":
document = opendocx(file_path)
paratextlist = getdocumenttext(document)
newparatextlist = []
for paratext in paratextlist:
newparatextlist.append(paratext.encode("utf-8"))
return '\n\n'.join(newparatextlist)
有人能帮帮我吗?在