python逐个读取文件并处理_python 读取文件夹下的所有文件并处理重新分类写入...

import os

import sys

import io

import time

# sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030') #改变标准输出的默认编码

def read():

path = r"C:\Users\mzj\Desktop\高精准"# 文件夹目录

for i in os.listdir(path):

try:

for q in os.listdir(os.path.join(path,i)):

paths=os.path.join(path,i,q)

f = open(paths, "r", encoding="UTF-8")

lines = f.readlines()

f.close()

url = os.path.basename(paths)

li = url.split('_')

temp_lines_list = [x.strip() for x in lines]

# print(temp_lines_list)

if len(temp_lines_list) < 2:

# 行数不够，不进行处理

print('行数太短了。。。。。。')

# #去掉空行

for t in temp_lines_list:

download_file_path = r'C:\Users\mzj\Desktop'

now_title = t.split("|")

while now_title:

if now_title[8] == 'ztb':

download_path = os.path.join(download_file_path, now_title[8])

if not os.path.exists(download_path):

os.mkdir(download_path)

time_path = os.path.join(download_path, str(li[0][:4] + '-' + li[0][4:6] + '-' + li[0][6:8]))

if not os.path.exists(time_path):

os.mkdir(time_path)

urls = time_path + '/' + str(

li[0] + '_' + li[1] + '_' + str(now_title[8]) + '_' + li[3] + '_' + li[4])

with open(urls, 'a', encoding='utf-8')as f:

f.write(t + '\n')

break

else:

break

except Exception as e:

# 文件读取失败

print(e)

#去掉\n

if __name__=='__main__':

read()