视频1 视频21 视频41 视频61 视频文章1 视频文章21 视频文章41 视频文章61 推荐1 推荐3 推荐5 推荐7 推荐9 推荐11 推荐13 推荐15 推荐17 推荐19 推荐21 推荐23 推荐25 推荐27 推荐29 推荐31 推荐33 推荐35 推荐37 推荐39 推荐41 推荐43 推荐45 推荐47 推荐49 关键词1 关键词101 关键词201 关键词301 关键词401 关键词501 关键词601 关键词701 关键词801 关键词901 关键词1001 关键词1101 关键词1201 关键词1301 关键词1401 关键词1501 关键词1601 关键词1701 关键词1801 关键词1901 视频扩展1 视频扩展6 视频扩展11 视频扩展16 文章1 文章201 文章401 文章601 文章801 文章1001 资讯1 资讯501 资讯1001 资讯1501 标签1 标签501 标签1001 关键词1 关键词501 关键词1001 关键词1501 专题2001
Python实现网站文件的全备份和差异备份
2020-11-27 14:31:28 责编:小采
文档


之前有写利用md5方式来做差异备份,但是这种md5方式来写存在以下问题:

•md5sum获取有些软连接的MD5值存在问题
•不支持对空目录进行备份,因为md5sum无法获取空目录的md5值
•权限的修改md5sum无法判断

解决方案:

利用文件的mtime ctime

mtime(Modified time)是在写入文件时随文件内容的更改而更改的
ctime(Create time)是在写入文件、更改所有者、权限或链接设置时随Inode的内容更改而更改的
废话不多说直接上代码:

#!/usr/bin/env python
import time,os,sys,cPickle

fileInfo = {}

def logger(time,fileName,status,fileNum):
 f = open('backup.log','a')
 f.write("%s	%s	%s	%s
" % (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 "