Walks a directory and generates checksums

gistfile1.py

import os
# Supports md5, sha1, sha256, and sha512
import hashlib

start_dir = '/home/mark/Pictures'

def generate_checksum_for_file(source_file_path, algorithm='md5'):
    """Generate and return a checksum for the file at source_file_path
       using the specified algorithm. 
    """
    source_file = open(source_file_path, 'rb')
    checksum = hashlib.new(algorithm)
    while True:
        # Read the file in 10 mb chunks to keep memory usage low.
        buf = source_file.read(10 * 1024 * 1024)
        if not buf:
            break
        checksum.update(buf)
    source_file.close()
    return checksum.hexdigest()

def generate_source_checksums(source_dir_path, algorithm='md5'):
    """Walk the directory at source_dir_path and generate a checksum for
       each file found. Return a dict containing checksum: path_to_file entries.
    """
    source_dir_checksums = {}
    for root, dirnames, filenames in os.walk(start_dir):
        for filename in filenames:
            path_to_file = os.path.join(root, filename)
            checksum_value = generate_checksum_for_file(path_to_file, 'md5')
            source_dir_checksums[checksum_value] = path_to_file

    return source_dir_checksums 

file_list = generate_source_checksums(start_dir, 'md5')
print file_list