python 读取doc文件_python读取doc

import os, time, fnmatch

from docx import Document

class search:

def __init__(self, path, search_string, file_filter):

self.search_path = path

self.search_string = search_string

self.file_filter = file_filter

print ("Search %s in %s..." % (

self.search_string, self.search_path

) )

print ("_" * 80)

time_begin = time.time()

file_count = self.walk()

print ("_" * 80)

print ("%s files searched in %0.2fsec." % (

file_count, (time.time() - time_begin)

))

#遍历所有的文件，记录文件数量

def walk(self):

file_count = 0

for root, dirlist, filelist in os.walk(self.search_path, followlinks=True):

for filename in filelist:

for file_filter in self.file_filter:

if fnmatch.fnmatch(filename, file_filter):

s