使用python读取txt文本

#基本环境：32位，python版本3.6,update at 2017/8/9
# -*- coding: utf-8 -*-
# -*- coding: cp936 -*-
import array
import docx   
import datetime
import re
from docx import Document
#读取docx文件格式
document = Document(u'C:/Users/Administrator/Desktop/尹学峰-区域总经理-广州（智联）2017.7.26.doc');


li = [ paragraph.text for paragraph in document.paragraphs]
print (li)
for i in li:
    print (i)


#表格读取值
tables = [table for table in document.tables];
for table in tables:
    for row in table.rows:
        for cell in row.cells:
            print (cell.text,'\t',)
        print
    print ('\n')
'''
with open('C:/Users/Administrator/Desktop/尹学峰-区域总经理-广州（智联）2017.7.26.doc','r', encoding='utf-8') as f:
   ls = f.readlines()
print(ls)
'''
#读取doc,把doc文件保存为txt
import re
from win32com import client as wc                
word = wc.Dispatch('Word.Application')
doc_jianli= word.Documents.Open(u'C:\\Users\\Administrator\\Desktop\\尹学峰-区域总经理-广州（智联）2017.7.26.doc')
doc_jianli.SaveAs('c:\\jianli_zhongzhuan.text', 4)
doc_jianli.Close()#关闭doc流
f=open(r'c:\\jianli_zhongzhuan.text','r')  
jianli_txt= f.read()
f.close()#关闭文件流
work_exper=jianli_txt.split('工作经历')[1].split('教育经历')[0]
print(work_exper)
keywords=re.compile(u"群体形态|软件|方案分享")
for i in keywords.finditer(work_exper):

    print (i.start(),i.group()) 

print('--------------------------------------------------------------------------------------')


#从PDF到txt
from urllib.request import urlopen
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
from io import open


def readPDF(pdfFile):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, laparams=laparams)


    process_pdf(rsrcmgr, device, pdfFile)
    device.close()


    content = retstr.getvalue()
    retstr.close()
    return content


pdfFile = open(r"C:\Users\Administrator\Desktop\简历种类\WALRE沃锐人才推荐报告007-北京中纳联-区域总经理-李先生.pdf",'rb')
outputString = readPDF(pdfFile)
print(outputString)
pdfFile.close()
print('--------------------------------------------------------------------------------------')
'''按行读取后，按行打印
for line in f.readlines():
    print (line)   并
f.close()
'''  
for i,j in enumerate(a):
    if(j in u'你我他'):
        print (i,j)