#coding:utf-8 import osimport win32comfrom win32com.client import Dispatch, constantsfrom docx import Document def parse_doc(f):  """讀取doc，返回姓名和行業  """  doc = w.Documents.Open( FileName = f )  t = doc.Tables[0] # 根據文件中的圖表選擇信息  name = t.Rows[0].Cells[1].Range.Text    situation = t.Rows[0].Cells[5].Range.Text  people = t.Rows[1].Cells[1].Range.Text  title = t.Rows[1].Cells[3].Range.Text    print name, situation, people,title  doc.Close() def parse_docx(f):  """讀取docx，返回姓名和行業  """  d = Document(f)  t = d.tables[0]  name = t.cell(0,1).text  situation = t.cell(0,8).text  people = t.cell(1,2).text  title = t.cell(1,8).text  print name, situation, people,title  if __name__ == "__main__":     w = win32com.client.Dispatch('Word.Application')     # 遍歷文件  PATH = "H:/work//aaa" # windows文件路徑  doc_files = os.listdir(PATH)  for doc in doc_files:    if os.path.splitext(doc)[1] == '.docx':      try:        parse_docx(PATH+'//'+doc)      except Exception as e:        print e    elif os.path.splitext(doc)[1] == '.doc':      try:        parse_doc(PATH+'//'+doc)      except Exception as e:        print e

from win32com import client as wc word = wc.Dispatch('Word.Application') doc = word.Documents.Open('c:/test') doc.SaveAs('c:/test.text', 2) doc.Close() word.Quit()

 open(r'c:/text','r')wdFormatDocument = 0 wdFormatDocument97 = 0 wdFormatDocumentDefault = 16 wdFormatDOSText = 4 wdFormatDOSTextLineBreaks = 5 wdFormatEncodedText = 7 wdFormatFilteredHTML = 10 wdFormatFlatXML = 19 wdFormatFlatXMLMacroEnabled = 20 wdFormatFlatXMLTemplate = 21 wdFormatFlatXMLTemplateMacroEnabled = 22 wdFormatHTML = 8 wdFormatPDF = 17 wdFormatRTF = 6 wdFormatTemplate = 1 wdFormatTemplate97 = 1 wdFormatText = 2 wdFormatTextLineBreaks = 3 wdFormatUnicodeText = 7 wdFormatWebArchive = 9 wdFormatXML = 11 wdFormatXMLDocument = 12 wdFormatXMLDocumentMacroEnabled = 13 wdFormatXMLTemplate = 14 wdFormatXMLTemplateMacroEnabled = 15 wdFormatXPS = 18 

from win32com import client as wc  word = wc.Dispatch('Word.Application')  doc = word.Documents.Open(r'c:/test1.doc')  doc.SaveAs('c:/test1.text', 4)  doc.Close() import re strings=open(r'c:/test1.text','r').read() result=re.findall('/(/s*[A-D]/s*/)|/(/xa1*[A-D]/xa1*/)|/（/s*[A-D]/s*/）|/（/xa1*[A-D]/xa1*/）',strings) chan=re.sub('/(/s*[A-D]/s*/)|/(/xa1*[A-D]/xa1*/)|/（/s*[A-D]/s*/）|/（/xa1*[A-D]/xa1*/）','()',strings) question=open(r'c:/question','a+') question.write(chan) question.close() answer=open(r'c:/answeronly','a+') for i,a in enumerate(result):  m=re.search('[A-D]',a)  answer.write(str(i+1)+' '+m.group()+'/n') answer.close()chan=re.sub(r'/xa3/xa8/s*[A-D]/s*/xa3/xa9','()',strings) #不要()，容易引起歧義。