使用python的指纹打印块
我正在尝试将一个文件分块,并为这些分块创建SHA1指纹。下面是代码。我的文件只有一行“测试”,当我从python命令提示符生成指纹时,我得到了不同的答案使用python的指纹打印块,python,sha1,chunking,Python,Sha1,Chunking,我正在尝试将一个文件分块,并为这些分块创建SHA1指纹。下面是代码。我的文件只有一行“测试”,当我从python命令提示符生成指纹时,我得到了不同的答案 >>> m = hashlib.sha1() >>> m.update("tests") >>> m.digest() '\x04\xd1?\xd0\xaao\x01\x97\xcf,\x99\x90\x19\xa6\x07\xc3l\x81\xeb\x9f' >>> &
>>> m = hashlib.sha1()
>>> m.update("tests")
>>> m.digest()
'\x04\xd1?\xd0\xaao\x01\x97\xcf,\x99\x90\x19\xa6\x07\xc3l\x81\xeb\x9f'
>>>
>>> m.hexdigest()
'04d13fd0aa6f0197cf2c999019a607c36c81eb9f'
-------------------------------------------------------------
import sys, os,hashlib
kilobytes = 1024
megabytes = kilobytes * 1000
chunksize = int(1.4 * megabytes) # default: roughly a floppy
hash = hashlib.sha1()
def split(fromfile, todir, chunksize=chunksize):
if not os.path.exists(todir): # caller handles errors
os.mkdir(todir) # make dir, read/write parts
else:
print " path exists"
##for fname in os.listdir(todir): # delete any existing files
## os.remove(os.path.join(todir, fname))
partnum = 0
input = open(fromfile, 'rb') # use binary mode on Windows
while 1: # eof=empty string from read
chunk = input.read(chunksize) # get next part <= chunksize
print "chunk=",chunk,"\n"
if not chunk: break
partnum = partnum+1
filename = os.path.join(todir, ('hashpart%04d' % partnum))
fileobj = open(filename, 'wb')
print "chunk before hashin is =",chunk, "of type ",type(chunk)
hash.update(chunk)
print "finger print is ",hash.hexdigest()
fileobj.write(hash.digest())
fileobj.close()
input.close( )
assert partnum <= 9999 # join sort fails if 5 digits
return partnum
-----------------------------------------------------------
but with the code written above it gives me
chunk before hashin is = tests
of type <type 'str'>
finger print is 64853233b4bd86fc53565e1383f2b19b6ede2995
Can someone help me?
>m=hashlib.sha1()
>>>m.更新(“测试”)
>>>m.文摘()
“\x04\xd1?\xd0\xaao\x01\x97\xcf\x99\x90\x19\xa6\x07\xc3l\x81\xeb\x9f”
>>>
>>>m.hexdigest()
‘04D13FD0AA6F0197CF2C99901A607C36C81EB9F’
-------------------------------------------------------------
导入sys、os、hashlib
千字节=1024
兆字节=千字节*1000
chunksize=int(1.4兆字节)#默认值:大约是一张软盘
hash=hashlib.sha1()
def拆分(fromfile,todir,chunksize=chunksize):
如果不存在os.path.exists(todir):#调用方处理错误
os.mkdir(todir)#生成dir,读/写部分
其他:
打印“路径存在”
##对于os.listdir(todir)中的fname:#删除任何现有文件
##os.remove(os.path.join(todir,fname))
partnum=0
输入=打开(来自文件“rb”)#在Windows上使用二进制模式
而1:#eof=读取的空字符串
chunk=input.read(chunksize)#获取下一部分您的文件是“tests\n”。这就是为什么你的打印声明跨越多行。添加新行,得到正确的哈希值
>>> m.update("tests\n")
>>> m.hexdigest()
'64853233b4bd86fc53565e1383f2b19b6ede2995'