Use this code to find duplicate files in a directory (GPLv3+)

dedupe.py

#!/usr/bin/env python

import os
import hashlib
import collections
import argparse

class File(object):
    def __init__(self, filepath):
        self.filepath = filepath
        self._filesize = None
        self._md5 = None
        
    @property
    def filesize(self):
        if self._filesize is None:
            self._filesize = os.path.getsize(self.filepath)
        return self._filesize
        
    @property
    def content(self):
        return open(self.filepath, 'rb').read()
        
    @property
    def md5(self):
        if self._md5 is None:
            self._md5 = hashlib.md5(self.content).hexdigest()
        return self._md5
        
    def __cmp__(self, other):
        if other.filesize == self.filesize:
            if other.md5 == self.md5:
                return 0
        return 1
        
    def __str__(self):
        return self.filepath

class DeDupe(object):
    def __init__(self, path):
        self.path = path
        
    def walk(self):
        file_list = []
        for root, dirs, files in os.walk(self.path):
            for name in files:
                file = File(os.path.join(root, name))
                file_list.append(file)
        return file_list

    @staticmethod
    def find_duplicates(file_list):
        seen = []
        duplicates = {}
        for file in file_list:
            for seen_file in seen:
                if seen_file == file:
                    if file.md5 in duplicates:
                        duplicates[file.md5].append(file)
                    else:
                        duplicates[file.md5] = [
                            file,
                            seen_file
                        ]
            seen.append(file)
        return duplicates
                
def print_list(l):
    
    print "---"
    for values in l.values():
        for file in values:
            print file.filepath
        print "---"
                
def get_args():
    parser = argparse.ArgumentParser(description='File duplicate files.')
    parser.add_argument('dir', nargs='?', default=os.getcwd())

    return parser.parse_args()
                
if __name__    == "__main__":
    args = get_args()
    source_path = os.path.abspath(args.dir)
    dedupe = DeDupe(source_path)
    files = dedupe.walk()
    print("Found {n} files.".format(n=len(files)))
    duplicates = dedupe.find_duplicates(files)
    print("Found {n} duplicates.".format(n=len(duplicates)))
    print_list(duplicates)