这里有一个使用pathlib.Path而不是os.walk的实现。它在迭代之前对目录内容进行排序,因此应该可以在多个平台上重复运行。它还使用文件/目录名称更新哈希值,因此添加空文件和目录将更改哈希值。
版本带有类型注释(适用于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())
没有类型注释:
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()
如果您只需要哈希目录的压缩版本:
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")