重命名文件及html

import os
import nltk
from bs4 import BeautifulSoup as bs

def get_txt_name_from_bak_name(bak_name):
    if -1 == bak_name.find('.txt'):
        return ''
    file_names = bak_name.split('.')
    return file_names[-2]+ '.' +file_names[0]+'.txt'

def get_txt_name_no_time(file_name):
    if -1 == file_name.find('.txt'):
        return ''

    file_names = file_name.split('.')
    return file_names[1]+'.'+file_names[2]

def track_files_under_folder(folder_name):
    if os.path.exists(folder_name):
        #track every file
        for (root,dirs,files) in os.walk(folder_name):
            #process

            for filename in files:
                full_file_name = root+ '\\' +filename

                #rename files
                if '' == get_txt_name_no_time(filename):
                    continue

                new_file_name = root+'\\'+get_txt_name_no_time(filename)
                #print(full_file_name + '--> ' + new_file_name)
                os.rename(full_file_name,new_file_name)


                
def html_to_txt(file_name):
    with open(file_name,'r') as h,open(file_name+'.txt','w') as t:
        s = bs(h,'lxml')
        t.write(s.get_text())

        

if __name__ == '__main__':


    track_files_under_folder('\\Files\\tmp')

 

转载于:https://www.cnblogs.com/shaivas/p/8658375.html