python如何遍历文件夹然后生成md5

wangcx_cxdn 2010-02-05 03:54:15

用python遍历一个文件夹下的所有文件，然后再生成每个文件的md5保存成xml，急呀，求求各位了?必要的地方给点注释

...全文

537 9 打赏收藏转发到动态举报

写回复

用AI写文章

9 条回复

切换为时间正序

请发表友善的回复…

发表回复

zfzaizheli 2010-02-09

打赏
举报

学习了~~~~~~~~~~~

wangcx_cxdn 2010-02-08

打赏
举报

1,2,3楼的正确，我先前没有仔细看代码,仔细一看是对的，谢谢啦

thy38 2010-02-06

打赏
举报

[Quote=引用 3 楼 angelipin 的回复:]
我无聊死了。。。。。。。
[/Quote]比较可爱的说~

notax 2010-02-06

打赏
举报

在简单点（在linux上）

find /your/path -name '*' -exec md5sum {} \; > all_md5.txt

angelipin 2010-02-05

打赏
举报

没有。。。。。
无聊。。。。

wangcx_cxdn 2010-02-05

打赏
举报

有这么麻烦吗?

angelipin 2010-02-05

打赏
举报

我无聊死了。。。。。。。

import os

import hashlib

from xml.dom import minidom,Node

import codecs



xml = ''

def Indent(dom, node, indent = 0):

    # Copy child list because it will change soon

    children = node.childNodes[:]

    # Main node doesn't need to be indented

    if indent:

	text = dom.createTextNode('\n' + '\t' * indent)

	node.parentNode.insertBefore(text, node)

    if children:

	# Append newline after last child, except for text nodes

	if children[-1].nodeType == node.ELEMENT_NODE:

	    text = dom.createTextNode('\n' + '\t' * indent)

	    node.appendChild(text)

	# Indent children which are elements

	for n in children:

	    if n.nodeType == node.ELEMENT_NODE:

		Indent(dom, n, indent + 1)



def insertnewmsg(filename,md5):

    if not os.path.exists("FileInfo.xml"):

	dom = minidom.parseString("<root></root>")

	domcopy = dom.cloneNode(True)

	f = file("FileInfo.xml",'wb')

	writer = codecs.lookup('utf-8')[3](f)

	domcopy.writexml(writer, encoding='utf-8')

	domcopy.unlink()

	writer.close()

	return

    dom = minidom.parse('FileInfo.xml')

    root = dom.getElementsByTagName('root')

    ve = dom.createElement('info')

    ve.setAttribute('name',filename)

    ve.setAttribute('md5',md5)

    root[0].appendChild(ve)

    domcopy = dom.cloneNode(True)

    f = file("FileInfo.xml",'wb')

    writer = codecs.lookup('utf-8')[3](f)

    domcopy.writexml(writer, encoding='utf-8')

    domcopy.unlink()

    writer.close()



    return 



def walk(path):

    global xml

    fl = os.listdir(path) # get what we have in the dir.

    for f in fl:

        if os.path.isdir(os.path.join(path,f)): # if is a dir.

            walk(os.path.join(path,f))

        else: # if is a file

            fp = open(os.path.join(path,f)) #open file. There is a big problem here. That is when you get a large file.

            c = fp.read() # get file content.

            m = hashlib.md5() # create a md5 object

            m.update(c) #encrypt the file

            xml += "<md5 name=\"%s\" md5=\"%s\" />\n" % (os.path.join(path,f),str(m.hexdigest())) # output to the md5 value to a string in xml format.

            fp.close() #close file

	    insertnewmsg(os.path.join(path,f),str(m.hexdigest())) #choice 2 write to xml.

if __name__ == "__main__": 

    xml = ''

    insertnewmsg('','')

    walk(os.getcwd())

    print xml

    '''

    make the xml file look nice

    '''

    dom = minidom.parse('FileInfo.xml')

    domcopy = dom.cloneNode(True)

    Indent(domcopy,domcopy.documentElement)

    f = file("FileInfo.xml",'wb')

    writer = codecs.lookup('utf-8')[3](f)

    domcopy.writexml(writer, encoding='utf-8')

    domcopy.unlink()

    writer.close()

angelipin 2010-02-05

打赏
举报

import os

import hashlib

xml = ''

def walk(path):

    global xml

    fl = os.listdir(path) # get what we have in the dir.

    for f in fl:

        if os.path.isdir(os.path.join(path,f)): # if is a dir.

            walk(os.path.join(path,f))

        else: # if is a file

            fp = open(os.path.join(path,f)) #open file. There is a big problem here. That is when you get a large file.

            c = fp.read() # get file content.

            m = hashlib.md5() # create a md5 object

            m.update(c) #encrypt the file

            xml += "<md5 name=\"%s\" md5=\"%s\" />\n" % (os.path.join(path,f),str(m.hexdigest())) # output to the md5 value to a string in xml format.

            fp.close() #close file

if __name__ == "__main__": 

    xml = ''

    walk(os.getcwd())

    print xml

angelipin 2010-02-05

打赏
举报

import os

import hashlib

xml = ''

def walk(path):

    global xml

    fl = os.listdir(path)

    for f in fl:

        if os.path.isdir(os.path.join(path,f)):

            walk(os.path.join(path,f))

        else:

            c = open(os.path.join(path,f)).read()

            m = hashlib.md5()

            m.update(c)

            xml += "<md5 name=\"%s\" md5=\"%s\" />\n" % (os.path.join(path,f),str(m.hexdigest()))

if __name__ == "__main__": 

    xml = ''

    walk(os.getcwd())

    print xml