import hashlib
with open("your_filename.txt", "rb") as f:
file_hash = hashlib.md5()
while chunk := f.read(8192):
file_hash.update(chunk)
print(file_hash.digest())
print(file_hash.hexdigest()) # to get a printable str instead of bytes
def md5_for_file(f, block_size=2**20):
md5 = hashlib.md5()
while True:
data = f.read(block_size)
if not data:
break
md5.update(data)
return md5.digest()
注意:确保你用'rb'打开你的文件-否则你会得到错误的结果。
所以要在一种方法中完成所有的事情-使用如下的方法:
def generate_file_md5(rootdir, filename, blocksize=2**20):
m = hashlib.md5()
with open( os.path.join(rootdir, filename) , "rb" ) as f:
while True:
buf = f.read(blocksize)
if not buf:
break
m.update( buf )
return m.hexdigest()
import hashlib
def checksum(filename, hash_factory=hashlib.md5, chunk_num_blocks=128):
h = hash_factory()
with open(filename,'rb') as f:
for chunk in iter(lambda: f.read(chunk_num_blocks*h.block_size), b''):
h.update(chunk)
return h.digest()
Python 3.8及以上版本
import hashlib
def checksum(filename, hash_factory=hashlib.md5, chunk_num_blocks=128):
h = hash_factory()
with open(filename,'rb') as f:
while chunk := f.read(chunk_num_blocks*h.block_size):
h.update(chunk)
return h.digest()
最初的发布
如果你想要一种更Pythonic(非while True)的方式读取文件,请检查以下代码:
import hashlib
def checksum_md5(filename):
md5 = hashlib.md5()
with open(filename,'rb') as f:
for chunk in iter(lambda: f.read(8192), b''):
md5.update(chunk)
return md5.digest()
import hashlib
def md5_for_file(path, block_size=256*128, hr=False):
'''
Block size directly depends on the block size of your filesystem
to avoid performances issues
Here I have blocks of 4096 octets (Default NTFS)
'''
md5 = hashlib.md5()
with open(path,'rb') as f:
for chunk in iter(lambda: f.read(block_size), b''):
md5.update(chunk)
if hr:
return md5.hexdigest()
return md5.digest()
def hash_for_file(path, algorithm=hashlib.algorithms[0], block_size=256*128, human_readable=True):
"""
Block size directly depends on the block size of your filesystem
to avoid performances issues
Here I have blocks of 4096 octets (Default NTFS)
Linux Ext4 block size
sudo tune2fs -l /dev/sda5 | grep -i 'block size'
> Block size: 4096
Input:
path: a path
algorithm: an algorithm in hashlib.algorithms
ATM: ('md5', 'sha1', 'sha224', 'sha256', 'sha384', 'sha512')
block_size: a multiple of 128 corresponding to the block size of your filesystem
human_readable: switch between digest() or hexdigest() output, default hexdigest()
Output:
hash
"""
if algorithm not in hashlib.algorithms:
raise NameError('The algorithm "{algorithm}" you specified is '
'not a member of "hashlib.algorithms"'.format(algorithm=algorithm))
hash_algo = hashlib.new(algorithm) # According to hashlib documentation using new()
# will be slower then calling using named
# constructors, ex.: hashlib.md5()
with open(path, 'rb') as f:
for chunk in iter(lambda: f.read(block_size), b''):
hash_algo.update(chunk)
if human_readable:
file_hash = hash_algo.hexdigest()
else:
file_hash = hash_algo.digest()
return file_hash
import hashlib,re
opened = open('/home/parrot/pass.txt','r')
opened = open.readlines()
for i in opened:
strip1 = i.strip('\n')
hash_object = hashlib.md5(strip1.encode())
hash2 = hash_object.hexdigest()
print hash2
import hashlib
from django.db import models
class MyModel(models.Model):
file = models.FileField() # Any field based on django.core.files.File
def get_hash(self):
hash = hashlib.md5()
for chunk in self.file.chunks(chunk_size=8192):
hash.update(chunk)
return hash.hexdigest()
import hashlib
import io
def md5sum(src):
md5 = hashlib.md5()
with io.open(src, mode="rb") as fd:
content = fd.read()
md5.update(content)
return md5
如果你的文件很大,你可能更喜欢按块读取文件,以避免将整个文件内容存储在内存中:
def md5sum(src, length=io.DEFAULT_BUFFER_SIZE):
md5 = hashlib.md5()
with io.open(src, mode="rb") as fd:
for chunk in iter(lambda: fd.read(length), b''):
md5.update(chunk)
return md5