p+在python中表示什么
作者:siseniao
从该文章改进:https://post.smzdm.com/p/an370emp/?zdm_ss=Android_1106136211_&send_by=1106136211&from=other&invite_code=zdmwffzv7winv
原文每次扫描都需要重新计算MD5,对于大文件来说,磁盘消耗较大,增加了缓存文件存储md5,每次扫描只计算新文件,提高效率。
不废话,直接贴代码:
import os
import hashlib
# 只删除以下列表中的重复文件类型.如果想删除其他类型的文件,自己添加一下就行了
file_type = ['.jpg', '.jpeg', '.png', '.gif', '.psd', '.bmp', '.webp', '.mp4', '.mkv', '.avi', '.mov', 'mpeg', 'mpg',
'.rar', '.zip']
check_files = []
#自行修改目录列表
work_dir_list = [r'/volume2/111', r'/volume1/222']
def save_md5_file(files_dict:dict):
if files_dict is None:
return
try:
with open("md5.txt", "w") as f:
for path_md5, file_md5, in files_dict.items():
f.write(str(path_md5) + "=" + str(path_md5) + 'n')
except Exception as e:
pass
def open_md5_file():
files_md5 = {}
try:
with open("md5.txt", "r") as f:
for md5_line in iter(lambda: f.readline(), ""):
list_keys = md5_line.split('=')
if len(list_keys) == 2:
files_md5[list_keys[0].strip()] = list_keys[1].strip()
except Exception as e:
pass
return files_md5
def remove_repeat_files():
for work_dir in work_dir_list:
for root, dirs, files in os.walk(work_dir):
for name in files:
p_type = os.path.splitext(os.path.join(root, name))[1]
if p_type in file_type:
check_files.append(os.path.join(root, name))
for name in dirs:
p_type = os.path.splitext(os.path.join(root, name))[1]
if p_type in file_type:
check_files.append(os.path.join(root, name))
files_dict = {}
files_md5 = open_md5_file()
r_index = 0
print('Files Num:%s' % len(check_files))
for file_path in check_files:
try:
md5_path = hashlib.md5()
md5_path.update(file_path.encode('utf-8'))
path_md5 = md5_path.hexdigest()
file_md5 = files_md5.get(path_md5)
if file_md5 is None:
md5_hash = hashlib.md5()
with open(file_path, "rb+") as f:
for byte_block in iter(lambda: f.read(4096), b""):
md5_hash.update(byte_block)
file_md5 = md5_hash.hexdigest()
print('Check file MD5:%s' % file_path)
files_md5[path_md5] = file_md5
if files_dict.get(file_md5) is None:
files_dict[file_md5] = file_path
else:
d_path = files_dict[file_md5]
d_path_stats = os.stat(d_path)
file_stats = os.stat(file_path)
d_time = d_path_stats.st_ctime
f_time = file_stats.st_ctime
if d_time > f_time:
os.remove(d_path)
files_dict[file_md5] = file_path
print('Delete File:', d_path)
r_index += 1
else:
os.remove(file_path)
print('Delete File:', file_path)
r_index += 1
except Exception as e:
pass
print('File Count:%s, Repeat Files Num:%s. All deleted!' %( len(check_files),str(r_index)))
save_md5_file(files_md5)
if __name__ == '__main__':
remove_repeat_files()
可以在ssh或者任务计划里执行
","gnid":"9a931522e9730c14b","img_data":[{"flag":2,"img":[{"desc":"","height":"385","title":"","url":"https://p0.ssl.img.360kuai.com/t01a2508b2adc68479c.jpg","width":"600"}]}],"original":0,"pat":"art_src_1,fts0,sts0","powerby":"cache","pub_time":1679316661000,"pure":"","rawurl":"http://zm.news.so.com/1715a84bea2900132874605fea6f9a81","redirect":0,"rptid":"71260418b6e0ce01","rss_ext":[],"s":"t","src":"什么值得买","tag":[],"title":"利用python删除群晖重复文件(缓存文件MD5方式)
姬艺鸿932python +=表示什么?
房中桦13589047887 ______ 如下: year += 1 等同于 year = year + 1
姬艺鸿932""" """在python中是什么意思 -
房中桦13589047887 ______ 一般在格式化的时候会用到%.这里你用的 %Y表示年,%m表示月,%d表示日 %H表示时,%M表示分,%S表示秒 单独用%号的时候,实际上没什么意义.