2022年 11月 3日

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):

self.search_file(os.path.join(root, filename))

file_count += 1

return file_count

#遍历文件中的字符串,并且剪切显示出来

def search_file(self, filepath):

d = Document(filepath)

for para in d.paragraphs:

if self.search_string in d.paragraphs:

print(filepath)

self.cutout_content(content)

#剪切字符串并且显示

def cutout_content(self, content):

current_pos = 0

search_string_len = len(self.search_string)

for i in xrange(max_cutouts):

try:

#从current_pos位置往后寻找self.search_string个字符串

pos = content.index(self.search_string, current_pos)

except ValueError:

break

#将显示窗口定义为寻找到的关键字向前向后各content_extract个字符

content_window = content[ pos – content_extract : pos + content_extract ]

print (“>>>”, content_window.encode(“String_Escape”))

current_pos += pos + search_string_len

print

#主程序入口

if __name__ == “__main__”:

search_path = r”c:\Users\Administrator\Desktop”

file_filter = (“*.docx”,”.doc”) # fnmatch-Filter

search_string = “history”

content_extract = 35 #获取摘要35

max_cutouts = 20 #显示窗口20

search(search_path, search_string, file_filter)