我正在尝试比较本地和远程文件MD5哈希（我复制/粘贴在wamp“ www”目录中的同一文件），但是我不明白为什么“校验和”不对应... >
下面的校验代码：
#-*- coding: utf-8 -*-
import hashlib
import requests
def md5Checksum(filePath,url):
if url==None:
with open(filePath, 'rb') as fh:
m = hashlib.md5()
while True:
data = fh.read(8192)
if not data:
break
m.update(data)
return m.hexdigest()
else:
r = requests.get(url, stream=True)
m = hashlib.md5()
for line in r.iter_lines():
m.update(line)
return m.hexdigest()
print "checksum_local :",md5Checksum("projectg715gb.pak",None)
print "checksum_remote :",md5Checksum(None,"http://testpangya.ddns.net/projectg715gb.pak")
和我惊讶得到这个输出：
checksum_local : 9d33806fdebcb91c3d7bfee7cfbe4ad7
checksum_remote : a13aaeb99eb020a0bc8247685c274e7d
的 “projectg715gb.pak” 的大小为14.7MB
但是，如果我尝试使用文本文件（大小为1Kb）：
print "checksum_local :",md5Checksum("toto.txt",None)
print "checksum_remote :",md5Checksum(None,"http://testpangya.ddns.net/toto.txt")
然后它起作用，我得到以下输出：
checksum_local : f71dbe52628a3f83a77ab494817525c6
checksum_remote : f71dbe52628a3f83a77ab494817525c6
我是比较MD5哈希的新手，所以请好^^'我可能犯了一些大错误，我不明白为什么它不适用于大文件，如果有人可以给我一个提示，它将超级好！
但是感谢阅读并帮助！
答案 0 :(得分：2)
好吧，看来我找到了解决方案，所以我会在这里发布:)
首先，您需要将 .htaccess 文件编辑到您的文件在服务器上的目录中。
.htaccess 文件的内容：
ContentDigest On
既然您已经设置了这个，服务器应该在 HTTP 标头中发送 Content-MD5 数据。
它会导致类似：
'Content-MD5': '7dVTxeHRktvI0Wh/7/4ZOQ=='
好的，现在让我们看看 Python 部分，所以我修改了我的代码，以便能够比较这个 HTTP 标头数据和本地 md5 校验和。
#-*- coding: utf-8 -*-
import hashlib
import requests
import base64
def md5Checksum(filePath,url):
m = hashlib.md5()
if url==None:
with open(filePath, u'rb') as fh:
m = hashlib.md5()
while True:
data = fh.read(8192)
if not data:
break
m.update(data)
#Get BASE 64 Local File md5
return base64.b64encode(m.digest()).decode('ascii')#Encode MD5 digest to BASE 64
else:
#Get BASE 64 Remote File md5
r = requests.head(url) #You read HTTP Header here
return r.headers['Content-MD5'] #Take only Content-MD5 string
def compare():
local = md5Checksum("projectg502th.pak.zip",None)
remote = md5Checksum(None,"http://127.0.0.1/md5/projectg502th.pak.zip")
if local == remote :
print("The soft don't download the file")
else:
print("The soft download the file")
print ("checksum_local :",md5Checksum("projectg_ziinf.pak.zip",None))
print ("checksum_remote : ",md5Checksum(None,"http://127.0.0.1/md5/projectg_ziinf.pak.zip"))
compare()
输出：
checksum_local : 7dVTxeHRktvI0Wh/7/4ZOQ==
checksum_remote : 7dVTxeHRktvI0Wh/7/4ZOQ==
The soft don't download the file
我希望这会有所帮助;)
答案 1 :(得分：1)
因此，感谢助手的帮助，这是最后的代码：
#-*- coding: utf-8 -*-
import hashlib
import requests
def md5Checksum(filePath,url):
m = hashlib.md5()
if url==None:
with open(filePath, 'rb') as fh:
m = hashlib.md5()
while True:
data = fh.read(8192)
if not data:
break
m.update(data)
return m.hexdigest()
else:
r = requests.get(url)
for data in r.iter_content(8192):
m.update(data)
return m.hexdigest()
print "checksum_local :",md5Checksum("projectg715gb.pak",None)
print "checksum_remote :",md5Checksum(None,"http://testpangya.ddns.net/projectg715gb.pak")
答案 2 :(得分：0)
感谢您发布解决方案https://stackoverflow.com/users/7495742/framb-axa
对我的问题超级有帮助。
我稍微修改了md5部分和python3的print语句，并将它们交换为使用sha256供我使用，并且对于我为我构建的应用程序下载/检查本地和远程sqlite数据库的需求而言，它的效果非常棒。在这里留下代码，并作为参考，供其他可能偶然发现本文的人参考。
import hashlib
import requests
# current release version url
current_release_url = 'https://somedomain.here/current_release.txt'
current_release_notes_url = 'https://somedomain.here/current_release_notes.txt'
# current database release version url
current_db_release_url = 'https://somedomain.here/current_db_release.txt'
current_db_release_notes_url = 'https://somedomain.here/current_db_release_notes.txt'
current_db_release_notes_hash_url = 'https://somedomain.here/current_db_release_hash.txt'
current_db_release = ''
wizard_db_version = ''
# Default commands DB url
wizard_cmd_db_url = 'https://somedomain.here/sqlite.db'
wizard_cmd_db = 'some/path'
checksum_local = ''
checksum_remote = ''
checksum_remote_hash = ''
checksum_status = ''
def download_cmd_db():
try:
print('Downloading database update version: ' + str(current_db_release))
url = wizard_cmd_db_url
r = requests.get(url)
with open(wizard_cmd_db, 'wb') as f:
f.write(r.content)
# Retrieve HTTP meta-data
print(r.status_code)
# print(r.headers['content-type'])
# print(r.encoding)
settings.setValue('wizard_db_version', current_db_release)
print('Database downloaded to:' + str(wizard_cmd_db))
except:
print('Commands Database download failed.... ;( ')
def sha256_checksum(filepath, url):
m = hashlib.sha256()
if url is None:
with open(filepath, 'rb') as fh:
m = hashlib.sha256()
while True:
data = fh.read(8192)
if not data:
break
m.update(data)
return m.hexdigest()
else:
r = requests.get(url)
for data in r.iter_content(8192):
m.update(data)
return m.hexdigest()
def wizard_db_hash_check():
global checksum_local, checksum_remote, checksum_status
try:
checksum_local = sha256_checksum(wizard_cmd_db, None)
checksum_remote = sha256_checksum(None, wizard_cmd_db_url)
print("checksum_local : " + checksum_local)
print("checksum_remote: " + checksum_remote)
print("checksum_remote_hash: " + checksum_remote_hash)
if checksum_local == checksum_remote_hash:
print('Hash Check passed')
checksum_status = True
else:
print('Hash Check Failed')
checksum_status = False
except:
print('Could not perform wizard_db_hash_check')
# Sanity check for missing database file
file = pathlib.Path(wizard_cmd_db)
if file.exists():
print("DB File exists: " + wizard_cmd_db)
wizard_db_hash_check()
else:
print("DB File does NOT exist: " + wizard_cmd_db)
download_cmd_db()
wizard_db_hash_check()
# Check hash
# # Logic to decide when to download DB here
try:
if int(current_db_release) > int(wizard_db_version):
print('Database update available: ' + str(current_db_release))
download_cmd_db()
wizard_db_hash_check()
except:
print('Unable to check wizard_db_release')
if checksum_local != checksum_remote:
download_cmd_db()
wizard_db_hash_check()
# Logic to fallback to default packaged DB if no internet to download and compare hash
if checksum_status is True:
target_db = str(wizard_cmd_db)
else:
print('All hash checks and attempts to update commands DB have failed. Switching to bundled DB')
target_db = os.path.join(os.path.abspath(os.path.dirname(sys.argv[0])), "sqlite.db")
print('Sanity Checks completed')