Python to achieve full backup and differential backup details

Python implements full backup and differential backup of files

Before, there was an md5 way to do differential backup, but this md5 way has the following problems:

There is a problem with md5sum getting MD5 values for some soft connections Backing up empty directories is not supported because md5sum cannot get the md5 value of an empty directory Permission modification md5sum cannot be determined

Solutions:

Use the mtime ctime file

mtime (Modified time) is changed when writing to a file as the contents of the file change

ctime (Create time) is changed as the content of Inode changes when writing to a file, changing owner, permission, or link Settings

No more nonsense said directly on the code:

#!/usr/bin/env python
import time,os,sys,cPickle
fileInfo = {}
def logger(time,fileName,status,fileNum):
  f = open('backup.log','a')
  f.write("%s\t%s\t%s\t\t%s\n" % (time,fileName,status,fileNum))
def tar(sDir,dDir,fileNum):
  command = "tar zcf %s %s >/dev/null 2>&1" % (dDir + ".tar.gz",sDir)
  if os.system(command) == 0:
    logger(time.strftime('%F %X'),dDir + ".tar.gz",'success',fileNum)
  else:
    logger(time.strftime('%F %X'),dDir + ".tar.gz",'failed',fileNum)
def fullBak(path):
  fileNum = 0
  for root,dirs,files in os.walk(path):
    for name in files:
      file = os.path.join(root, name)
      mtime = os.path.getmtime(file)
      ctime = os.path.getctime(file)
      fileInfo[file] = (mtime,ctime)
      fileNum += 1
  f = open(P,'w')
  cPickle.dump(fileInfo,f)
  f.close()
  tar(S,D,fileNum)
def diffBak(path):
  for root,dirs,files in os.walk(path):
    for name in files:
      file = os.path.join(root,name)
      mtime = os.path.getmtime(file)
      ctime = os.path.getctime(file)
      fileInfo[file] = (mtime,ctime)
  if os.path.isfile(P) == 0:
    f = open(P,'w')
    f.close()
  if os.stat(P).st_size == 0:
    f = open(P,'w')
    cPickle.dump(fileInfo,f)
    fileNum = len(fileInfo.keys())
    f.close()
    print fileNum
    tar(S,D,fileNum)
  else:
    f = open(P)
    old_fileInfo = cPickle.load(f)
    f.close()
    difference = dict(set(fileInfo.items())^set(old_fileInfo.items()))
    fileNum = len(difference)
    print fileNum
    difference_file = ' '.join(difference.keys())
    print difference_file
    tar(difference_file,D,fileNum)
    f = open(P,'w')
    cPickle.dump(fileInfo,f)
    f.close()
def Usage():
  print '''
    Syntax: python file_bakcup.py pickle_file model source_dir filename_bk
      model: 1:Full backup 2:Differential backup
    example: python file_backup.py fileinfo.pk 2 /etc etc_$(date +%F)
      explain: Automatically add '.tar.gz' suffix
  '''
  sys.exit()
if len(sys.argv) != 5:
  Usage()
P = sys.argv[1]
M = int(sys.argv[2])
S = sys.argv[3]
D = sys.argv[4]
if M == 1:
  fullBak(S)
elif M == 2:
  diffBak(S)
else:
  print "\033[;31mDoes not support this mode\033[0m"
  Usage()

Testing:

$ python file_backup.py data.pk 1 data data_$(date +%F) # Full backup 
$ > data/www.linuxeye.com # Test create file, modify file permissions 
$ chmod 777 data/py/eshop_bk/data.db
$ python file_backup.py data.pk 2 data data_$(date +%F)_1 # Backup the changed files 
2
data/py/eshop_bk/data.db data/www.linuxeye.com

Thank you for reading, I hope to help you, thank you for your support of this site!