如何从python文件中提取信息？3分钟搞懂Python文本分析和提取

#coding:utf-8
 
import os
import win32com
from win32com.client import Dispatch, constants
from docx import Document
 
def parse_doc(f):
  """读取doc，返回姓名和行业
  """
  doc = w.Documents.Open( FileName = f )
  t = doc.Tables[0] # 根据文件中的图表选择信息
  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):
  """读取docx，返回姓名和行业
  """
  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')
   
  # 遍历文件
  PATH = "H:\work\\aaa" # windows文件路径
  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