为什么应该放弃或减少使用MD5

VerifyRepeatedMd5.py

# MD5 在现实中已经被发现有相当多的数据都可能导致冲突。举例而言，如下两段数据的MD5哈希值就是完全一样的
# ref:  blog.jianguoyun.com/?p=481
# date: 2012-09-20


import os
from hashlib import md5

def save_strs2bin(text, file_name):
    if not isinstance(text, str):
        return False
    text_list = text.strip().split()
    with open(file_name, 'wb') as fp:
        for i in text_list:
            pure_num = int(i, 16)
            fp.write((pure_num).to_bytes(1, 'little', signed=False))
    return True


def md5_file(file_path):
	if not os.path.exists(file_path):
		print("{} not exists".format(file_path))
		return False
	m = md5()
	m.update(open(file_path, 'rb').read())
	return m.hexdigest()



def test():						 
	data = [ (
		 '''4d c9 68 ff 0e e3 5c 20 95 72 d4 77 7b 72 15 87
		    d3 6f a7 b2 1b dc 56 b7 4a 3d c0 78 3e 7b 95 18
		    af bf a2 00 a8 28 4b f3 6e 8e 4b 55 b3 5f 42 75
		    93 d8 49 67 6d a0 d1 55 5d 83 60 fb 5f 07 fe a2''', 'test1'),
					 #^ data differ  
			(
		''' 4d c9 68 ff 0e e3 5c 20 95 72 d4 77 7b 72 15 87
		    d3 6f a7 b2 1b dc 56 b7 4a 3d c0 78 3e 7b 95 18
		    af bf a2 02 a8 28 4b f3 6e 8e 4b 55 b3 5f 42 75
		    93 d8 49 67 6d a0 d1 d5 5d 83 60 fb 5f 07 fe a2''', 'test2')]
					 #^ data differ  

	for text, file_name in data:
		save_strs2bin(text, file_name)
		print("writing to {} ==> {}".format(file_name, md5_file(file_name)))

# output 
# writing to test1 ==> 008ee33a9d58b51cfeb425b0959121c9
# writing to test2 ==> 008ee33a9d58b51cfeb425b0959121c9
if __name__ == '__main__':
    test()