工作笔记

使用Python搭建文件服务器进行简单文件上传

2019-01-31
阅读次数:

“在操作Docker容器时,有时想将一些文件回传到宿主机,容器中通常只支持简单的命令,无法通过浏览器等GUI的方式进行。在编译的Ubuntu基础镜像中是安装了curl软件包的,通过curl可以进行文件上传,那就需要在宿主机上搭建个简单的HTTP上传服务器即可。如果你急需一个简单的Web Server,但你又不想去下载并安装那些复杂的HTTP服务程序,那么Python是一个不错的选择。”

Python搭建简单HTTP上传服务器

在Python中内置了HTTPServer模块,在终端输入如下命令:

$ python3 -m http.server [8000]

就可以在目录下快速建立一个HTTP服务器,只需要在浏览器中输入http://127.0.0.1:8000就可以访问并下载文件了,不过python内置的模块并没有提供上传功能,上传功能需要自己实现,以下是实现上传功能的Python脚本:

#!/usr/bin/env python3

"""Simple HTTP Server With Upload.

This module builds on BaseHTTPServer by implementing the standard GET
and HEAD requests in a fairly straightforward manner.

see: https://gist.github.com/UniIsland/3346170
"""


__version__ = "0.1"
__all__ = ["SimpleHTTPRequestHandler"]
__author__ = "bones7456"
__home_page__ = "http://li2z.cn/"

import os
import posixpath
import http.server
import urllib.request, urllib.parse, urllib.error
import cgi
import shutil
import mimetypes
import re
from io import BytesIO


class SimpleHTTPRequestHandler(http.server.BaseHTTPRequestHandler):

    """Simple HTTP request handler with GET/HEAD/POST commands.

    This serves files from the current directory and any of its
    subdirectories.  The MIME type for files is determined by
    calling the .guess_type() method. And can reveive file uploaded
    by client.

    The GET/HEAD/POST requests are identical except that the HEAD
    request omits the actual contents of the file.

    """

    server_version = "SimpleHTTPWithUpload/" + __version__

    def do_GET(self):
        """Serve a GET request."""
        f = self.send_head()
        if f:
            self.copyfile(f, self.wfile)
            f.close()

    def do_HEAD(self):
        """Serve a HEAD request."""
        f = self.send_head()
        if f:
            f.close()

    def do_POST(self):
        """Serve a POST request."""
        r, info = self.deal_post_data()
        print((r, info, "by: ", self.client_address))
        f = BytesIO()
        f.write(b'<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">')
        f.write(b"<html>\n<title>Upload Result Page</title>\n")
        f.write(b"<body>\n<h2>Upload Result Page</h2>\n")
        f.write(b"<hr>\n")
        if r:
            f.write(b"<strong>Success:</strong>")
        else:
            f.write(b"<strong>Failed:</strong>")
        f.write(info.encode())
        f.write(("<br><a href=\"%s\">back</a>" % self.headers['referer']).encode())
        f.write(b"<hr><small>Powerd By: bones7456, check new version at ")
        f.write(b"<a href=\"http://li2z.cn/?s=SimpleHTTPServerWithUpload\">")
        f.write(b"here</a>.</small></body>\n</html>\n")
        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)
        content_type = self.headers['content-type']
        if not content_type:
            return (False, "Content-Type header doesn't contain boundary")
        boundary = content_type.split("=")[1].encode()
        remainbytes = int(self.headers['content-length'])
        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.decode())
        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(b'\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 send_head(self):
        """Common code for GET and HEAD commands.

        This sends the response code and MIME headers.

        Return value is either a file object (which has to be copied
        to the outputfile by the caller unless the command was HEAD,
        and must be closed by the caller under all circumstances), or
        None, in which case the caller has nothing further to do.

        """
        path = self.translate_path(self.path)
        f = None
        if os.path.isdir(path):
            if not self.path.endswith('/'):
                # redirect browser - doing basically what apache does
                self.send_response(301)
                self.send_header("Location", self.path + "/")
                self.end_headers()
                return None
            for index in "index.html", "index.htm":
                index = os.path.join(path, index)
                if os.path.exists(index):
                    path = index
                    break
            else:
                return self.list_directory(path)
        ctype = self.guess_ty‵‵‵pe(path)
        try:
            # Always read in binary mode. Opening files in text mode may cause
            # newline translations, making the actual size of the content
            # transmitted *less* than the content-length!
            f = open(path, 'rb')
        except IOError:
            self.send_error(404, "File not found")
            return None
        self.send_response(200)
        self.send_header("Content-type", ctype)
        fs = os.fstat(f.fileno())
        self.send_header("Content-Length", str(fs[6]))
        self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
        self.end_headers()
        return f

    def list_directory(self, path):
        """Helper to produce a directory listing (absent index.html).

        Return value is either a file object, or None (indicating an
        error).  In either case, the headers are sent, making the
        interface the same as for send_head().

        """
        try:
            list = os.listdir(path)
        except os.error:
            self.send_error(404, "No permission to list directory")
            return None
        list.sort(key=lambda a: a.lower())
        f = BytesIO()
        displaypath = cgi.escape(urllib.parse.unquote(self.path))
        f.write(b'<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">')
        f.write(("<html>\n<title>Directory listing for %s</title>\n" % displaypath).encode())
        f.write(("<body>\n<h2>Directory listing for %s</h2>\n" % displaypath).encode())
        f.write(b"<hr>\n")
        f.write(b"<form ENCTYPE=\"multipart/form-data\" method=\"post\">")
        f.write(b"<input name=\"file\" type=\"file\"/>")
        f.write(b"<input type=\"submit\" value=\"upload\"/></form>\n")
        f.write(b"<hr>\n<ul>\n")
        for name in list:
            fullname = os.path.join(path, name)
            displayname = linkname = name
            # Append / for directories or @ for symbolic links
            if os.path.isdir(fullname):
                displayname = name + "/"
                linkname = name + "/"
            if os.path.islink(fullname):
                displayname = name + "@"
                # Note: a link to a directory displays with @ and links with /
            f.write(('<li><a href="%s">%s</a>\n'
                     % (urllib.parse.quote(linkname), cgi.escape(displayname))).encode())
        f.write(b"</ul>\n<hr>\n</body>\n</html>\n")
        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()
        return f

    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.parse.unquote(path))
        words = path.split('/')
        words = [_f for _f in words if _f]
        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 guess_type(self, path‵‵‵):
        """Guess the type of a file.

        Argument is a PATH (a filename).

        Return value is a string of the form type/subtype,
        usable for a MIME Content-type header.

        The default implementation looks the file's extension
        up in the table self.extensions_map, using application/octet-stream
        as a default; however it would be permissible (if
        slow) to look inside the data to make a better guess.

        """

        base, ext = posixpath.splitext(path)
        if ext in self.extensions_map:
            return self.extensions_map[ext]
        ext = ext.lower()
        if ext in self.extensions_map:
            return self.extensions_map[ext]
        else:
            return self.extensions_map['']

    if not mimetypes.inited:
        mimetypes.init() # try to read system mime.types
    extensions_map = mimetypes.types_map.copy()
    extensions_map.update({
        '': 'application/octet-stream', # Default
        '.py': 'text/plain',
        '.c': 'text/plain',
        '.h': 'text/plain',
    })


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

if __name__ == '__main__':
    test()

将以上文件命名为httpserver.py, 执行命令即可启动服务器:

$ python3 httpserver.py

使用curl命令行上传文件

curl使用-F参数即可实现文件上传

$ curl -F "file=@ambari-server_2.7.3.0-0-dist.deb" -H 'Expect:' http://192.168.2.42:8000

<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"><html>
<title>Upload Result Page</title>
<body>
<h2>Upload Result Page</h2>
<hr>
<strong>Success:</strong>File '/home/lizhiyong/Programs/emr/emr-agent/emr-agent/src/test/python/emr_agent_test/agent/ambari-server_2.7.3.0-0-dist.deb' upload success!<br><a href="None">back</a><hr><small>Powerd By: bones7456, check new version at <a href="http://li2z.cn/?s=SimpleHTTPServerWithUpload">here</a>.</small></body>
</html>

参考链接


评论

目录