Skip to content

Instantly share code, notes, and snippets.

@jevy
Created July 13, 2017 15:07
Show Gist options
  • Save jevy/ff49c26fd5a8d607be087ef156c66a5b to your computer and use it in GitHub Desktop.
Save jevy/ff49c26fd5a8d607be087ef156c66a5b to your computer and use it in GitHub Desktop.
Simple script to compare MD5s between two dirs and all subdirs to be there all the same files exists (ignores filenames and dir structure)
import argparse
import os
import hashlib
# Origin_dir_files = Build an MD5 hash of files with filenames in original dir (with subdirs)
# Destination_dir_files = Do the same for all in the destination dir
# Iterate over origin_dir_files to see each hash exists in Destination_dir_files. Print any that aren't
def get_all_filenames(root):
all_file_names = []
for path, subdirs, files in os.walk(root):
for name in files:
all_file_names.append((os.path.join(path, name)))
return all_file_names
def md5(fname):
hash_md5 = hashlib.md5()
with open(fname, "rb") as f:
for chunk in iter(lambda: f.read(4096), b""):
hash_md5.update(chunk)
return hash_md5.hexdigest()
# Main
parser = argparse.ArgumentParser(description='Compare the MD5s of all files and subdirectories')
parser.add_argument('origin_dir', help='original directory with correct data',action='store')
parser.add_argument('dest_dir', help='destination directory with same desired data',action='store')
args = parser.parse_args()
origin_file_names= get_all_filenames(args.origin_dir)
dest_file_names = get_all_filenames(args.dest_dir)
origin_md5s = {}
dest_md5s = {}
for file_name in origin_file_names:
origin_md5s[md5(file_name)] = file_name
for file_name in dest_file_names:
dest_md5s[md5(file_name)] = file_name
for o_md5 in origin_md5s:
try:
dest_md5s[o_md5]
except:
print "Not in destination anywhere: " + origin_md5s[o_md5]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment