如何使用Python计算文件系统目录的哈希值



我使用下面的代码来计算一个文件的哈希值:

m = hashlib.md5()
with open("calculator.pdf", 'rb') as fh:
    while True:
        data = fh.read(8192)
        if not data:
            break
        m.update(data)
    hash_value = m.hexdigest()
    print  hash_value

当我在文件夹"folder"上尝试时,我得到

IOError: [Errno 13] Permission denied: folder

如何计算一个文件夹的哈希值

使用checksumdir python包计算目录的校验和/哈希值。可以在https://pypi.python.org/pypi/checksumdir

找到。

用法:

import checksumdir
hash = checksumdir.dirhash("c:\temp")
print hash

这是一个使用pathlib的实现。路径而不是依靠os。walk。它在迭代之前对目录内容进行排序,因此在多个平台上应该是可重复的。它还使用文件/目录的名称更新哈希值,因此添加空文件和目录将改变哈希值。

带有类型注解的版本(Python 3.6或更高版本):
import hashlib
from _hashlib import HASH as Hash
from pathlib import Path
from typing import Union

def md5_update_from_file(filename: Union[str, Path], hash: Hash) -> Hash:
    assert Path(filename).is_file()
    with open(str(filename), "rb") as f:
        for chunk in iter(lambda: f.read(4096), b""):
            hash.update(chunk)
    return hash

def md5_file(filename: Union[str, Path]) -> str:
    return str(md5_update_from_file(filename, hashlib.md5()).hexdigest())

def md5_update_from_dir(directory: Union[str, Path], hash: Hash) -> Hash:
    assert Path(directory).is_dir()
    for path in sorted(Path(directory).iterdir(), key=lambda p: str(p).lower()):
        hash.update(path.name.encode())
        if path.is_file():
            hash = md5_update_from_file(path, hash)
        elif path.is_dir():
            hash = md5_update_from_dir(path, hash)
    return hash

def md5_dir(directory: Union[str, Path]) -> str:
    return str(md5_update_from_dir(directory, hashlib.md5()).hexdigest())

不带类型注释:

import hashlib
from pathlib import Path

def md5_update_from_file(filename, hash):
    assert Path(filename).is_file()
    with open(str(filename), "rb") as f:
        for chunk in iter(lambda: f.read(4096), b""):
            hash.update(chunk)
    return hash

def md5_file(filename):
    return md5_update_from_file(filename, hashlib.md5()).hexdigest()

def md5_update_from_dir(directory, hash):
    assert Path(directory).is_dir()
    for path in sorted(Path(directory).iterdir()):
        hash.update(path.name.encode())
        if path.is_file():
            hash = md5_update_from_file(path, hash)
        elif path.is_dir():
            hash = md5_update_from_dir(path, hash)
    return hash

def md5_dir(directory):
    return md5_update_from_dir(directory, hashlib.md5()).hexdigest()

精简版,如果你只需要散列目录:

def md5_update_from_dir(directory, hash):
    assert Path(directory).is_dir()
    for path in sorted(Path(directory).iterdir(), key=lambda p: str(p).lower()):
        hash.update(path.name.encode())
        if path.is_file():
            with open(path, "rb") as f:
                for chunk in iter(lambda: f.read(4096), b""):
                    hash.update(chunk)
        elif path.is_dir():
            hash = md5_update_from_dir(path, hash)
    return hash

def md5_dir(directory):
    return md5_update_from_dir(directory, hashlib.md5()).hexdigest()

用法:md5_hash = md5_dir("/some/directory")

这个Recipe提供了一个很好的函数来完成您的请求。我已经将其修改为使用MD5哈希,而不是SHA1,正如您最初的问题所问的那样

def GetHashofDirs(directory, verbose=0):
  import hashlib, os
  SHAhash = hashlib.md5()
  if not os.path.exists (directory):
    return -1
  try:
    for root, dirs, files in os.walk(directory):
      for names in files:
        if verbose == 1:
          print 'Hashing', names
        filepath = os.path.join(root,names)
        try:
          f1 = open(filepath, 'rb')
        except:
          # You can't open the file for some reason
          f1.close()
          continue
        while 1:
          # Read file in as little chunks
          buf = f1.read(4096)
          if not buf : break
          SHAhash.update(hashlib.md5(buf).hexdigest())
        f1.close()
  except:
    import traceback
    # Print the stack traceback
    traceback.print_exc()
    return -2
  return SHAhash.hexdigest()

你可以这样使用:

print GetHashofDirs('folder_to_hash', 1)

输出看起来像这样,因为它散列了每个文件:

...
Hashing file1.cache
Hashing text.txt
Hashing library.dll
Hashing vsfile.pdb
Hashing prog.cs
5be45c5a67810b53146eaddcae08a809

这个函数调用的返回值作为散列返回。在本例中,5be45c5a67810b53146eaddcae08a809

我不喜欢答案中引用的食谱是如何编写的。我有一个更简单的版本,我正在使用:

import hashlib
import os

def hash_directory(path):
    digest = hashlib.sha1()
    for root, dirs, files in os.walk(path):
        for names in files:
            file_path = os.path.join(root, names)
            # Hash the path and add to the digest to account for empty files/directories
            digest.update(hashlib.sha1(file_path[len(path):].encode()).digest())
            # Per @pt12lol - if the goal is uniqueness over repeatability, this is an alternative method using 'hash'
            # digest.update(str(hash(file_path[len(path):])).encode())
            if os.path.isfile(file_path):
                with open(file_path, 'rb') as f_obj:
                    while True:
                        buf = f_obj.read(1024 * 1024)
                        if not buf:
                            break
                        digest.update(buf)
    return digest.hexdigest()

我发现每当遇到alias之类的东西时,通常会抛出异常(出现在os.walk()中,但您不能直接打开它)。os.path.isfile()检查会处理这些问题。

如果在我尝试散列的目录中有一个实际的文件,并且它无法打开,跳过该文件并继续不是一个好的解决方案。这会影响哈希的结果。最好完全取消散列尝试。这里,try语句将被封装在对hash_directory()函数的调用中。

>>> try:
...   print(hash_directory('/tmp'))
... except:
...   print('Failed!')
... 
e2a075b113239c8a25c7e1e43f21e8f2f6762094
>>> 

我一直看到这段代码在各种论坛上传播。

ActiveState配方答案是有效的,但是,正如Antonio指出的,它不能保证跨文件系统的可重复,因为不能以相同的顺序呈现文件(尝试一下)。一种修复方法是修改

for root, dirs, files in os.walk(directory):
  for names in files:

for root, dirs, files in os.walk(directory):
  for names in sorted(files): 
(是的,我是在偷懒。这只对文件名进行排序,而不对目录进行排序。

使用checksumdir https://pypi.org/project/checksumdir/


directory  = '/path/to/directory/'
md5hash    = dirhash(directory, 'md5')

我对Andy的回复做了进一步优化。

下面是python3而不是python2的实现。它使用SHA1,处理一些需要编码的情况,被限制,并包含一些教义。

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""dir_hash: Return SHA1 hash of a directory.
- Copyright (c) 2009 Stephen Akiki, 2018 Joe Flack
- MIT License (http://www.opensource.org/licenses/mit-license.php)
- http://akiscode.com/articles/sha-1directoryhash.shtml
"""
import hashlib
import os

def update_hash(running_hash, filepath, encoding=''):
    """Update running SHA1 hash, factoring in hash of given file.
    Side Effects:
        running_hash.update()
    """
    if encoding:
        file = open(filepath, 'r', encoding=encoding)
        for line in file:
            hashed_line = hashlib.sha1(line.encode(encoding))
            hex_digest = hashed_line.hexdigest().encode(encoding)
            running_hash.update(hex_digest)
        file.close()
    else:
        file = open(filepath, 'rb')
        while True:
            # Read file in as little chunks.
            buffer = file.read(4096)
            if not buffer:
                break
            running_hash.update(hashlib.sha1(buffer).hexdigest())
        file.close()

def dir_hash(directory, verbose=False):
    """Return SHA1 hash of a directory.
    Args:
        directory (string): Path to a directory.
        verbose (bool): If True, prints progress updates.
    Raises:
        FileNotFoundError: If directory provided does not exist.
    Returns:
        string: SHA1 hash hexdigest of a directory.
    """
    sha_hash = hashlib.sha1()
    if not os.path.exists(directory):
        raise FileNotFoundError
    for root, dirs, files in os.walk(directory):
        for names in files:
            if verbose:
                print('Hashing', names)
            filepath = os.path.join(root, names)
            try:
                update_hash(running_hash=sha_hash,
                            filepath=filepath)
            except TypeError:
                update_hash(running_hash=sha_hash,
                            filepath=filepath,
                            encoding='utf-8')
    return sha_hash.hexdigest()

相关内容

  • 没有找到相关文章