import sys
import os
import hashlib

def chunk_reader(fobj, chunk_size=1024):
    """Generator that reads a file in chunks of bytes"""
    while True:
        chunk = fobj.read(chunk_size)
        if not chunk:
            return
        yield chunk

def check_for_duplicates(paths, hash=hashlib.sha1):
    hashes = {}
    for path in paths:
        for dirpath, dirnames, filenames in os.walk(path):
            for filename in filenames:
                full_path = os.path.join(dirpath, filename)
                hashobj = hash()
                for chunk in chunk_reader(open(full_path, 'rb')):
                    hashobj.update(chunk)
                file_id = (hashobj.digest(), os.path.getsize(full_path))
                duplicate = hashes.get(file_id, None)
                if duplicate:
                    print "Duplicate found: %s and %s" % (full_path, duplicate)
                else:
                    hashes[file_id] = full_path

if sys.argv[1:]:
    check_for_duplicates(sys.argv[1:])
else:
    print "Please pass the paths to check as parameters to the script"

import sys
import os
import hashlib

check_path = (lambda filepath, hashes, p = sys.stdout.write:
        (lambda hash = hashlib.sha1 (file (filepath).read ()).hexdigest ():
                ((hash in hashes) and (p ('DUPLICATE FILEn'
                                          '   %sn'
                                          'of %sn' % (filepath, hashes[hash])))
                 or hashes.setdefault (hash, filepath)))())

scan = (lambda dirpath, hashes = {}:
                map (lambda (root, dirs, files):
                        map (lambda filename: check_path (os.path.join (root, filename), hashes), files), os.walk (dirpath)))

((len (sys.argv) > 1) and scan (sys.argv[1]))

def remove_duplicates(dir):
   unique = []
   for filename in os.listdir(dir)
      if os.path.isfile(filename):
        filehash = md5.md5(file(filename).read()).hexdigest()
        if filehash not in unique: unique.append(filehash)
        else: os.remove(filename)