python Delete the same files and pictures that cannot be opened under the folder

  • 2021-07-22 10:01:06
  • OfStack

The day before yesterday I accidentally formatted the hard disk and lost a lot of photos. Later I used Recuva this software to restore the files successfully, but there are many duplicate files and pictures that can't be opened in the recovered files, so I wrote two small programs of python to solve this problem

Delete the same file:


#coding=utf-8
 
import os
import os.path
import Image
import hashlib
 
def get_md5(filename):
 m = hashlib.md5()
 mfile = open(filename, "rb")
 m.update(mfile.read())
 mfile.close()
 md5_value = m.hexdigest()
 return md5_value
 
if __name__ == '__main__':
 ipath = "E:\\20161019_photo"
 uipath = unicode(ipath, "utf8")
 
 for parent, dirnames, filenames in os.walk(uipath):
  md5_list = []
  #for dirname in dirnames: #  Output folder information 
   #print "parent is:" + parent
   #print "dirname is: " + dirname
  for filename in filenames:
   #print "parent is :" + parent
   #print "filename is:" + filename
   #print "md5_list is : "
 
   if(get_md5(os.path.join(parent, filename)) in md5_list):
    os.remove(os.path.join(parent, filename))
   else:
    md5_list.append(get_md5(os.path.join(parent, filename)))
   #print md5_list
   #md5 = []

Delete Unable to Open File:


#coding=utf-8
 
import os
import os.path
import Image
import hashlib
 
def get_md5(filename):
 m = hashlib.md5()
 mfile = open(filename, "rb")
 m.update(mfile.read())
 mfile.close()
 md5_value = m.hexdigest()
 return md5_value
 
if __name__ == '__main__':
 ipath = "E:\\20161019_photo"
 uipath = unicode(ipath, "utf8")
 for parent, dirnames, filenames in os.walk(uipath):
  for filename in filenames:
   name ,ext = os.path.splitext(filename)
   if((ext == ".png") or (ext == ".tif") or (ext == ".gif")):
    os.remove(os.path.join(parent, filename))
   else:
    if(ext == ".jpg"):
     try:
      fp = open(os.path.join(parent, filename), 'rb')
      img = Image.open(fp)
     except:
      fp.close()
      os.remove(os.path.join(parent, filename))
     else:
      continue

Related articles: