MultipartPostHandler.py

#!/usr/bin/python

####
# 02/2006 Will Holcomb <wholcomb@gmail.com>
# 
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
# 
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Lesser General Public License for more details.
#
# 7/2/10 refactored by Jason Grout--made two functions instead of a class
# 7/26/07 Slightly modified by Brian Schneider  
# in order to support unicode files ( multipart_encode function )
# from http://peerit.blogspot.com/2007/07/multipartposthandler-doesnt-work-for.html

"""
Usage:
  Enables the use of multipart/form-data for posting forms

Inspirations:
  Upload files in python:
    http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/146306
  urllib2_file:
    Fabien Seisen: <fabien@seisen.org>

Example:
  import MultipartPostHandler, urllib2, cookielib

  cookies = cookielib.CookieJar()
  opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookies),
                                MultipartPostHandler.MultipartPostHandler)
  params = { "username" : "bob", "password" : "riviera",
             "file" : open("filename", "rb") }
  opener.open("http://wwww.bobsite.com/upload/", params)

Further Example:
  The main function of this file is a sample which downloads a page and
  then uploads it to the W3C validator.
"""

import urllib
import urllib2
import mimetools, mimetypes
import os, stat
from cStringIO import StringIO

# Controls how sequences are uncoded. If true, elements may be given multiple values by
#  assigning a sequence.
doseq = 1


def encode_request(request):
    data = request.get_data()
    if data is not None and type(data) != str:
        v_files = []
        v_vars = []
        if isinstance(data, dict):
            data=data.items()
        try:
             for(key, value) in data:
                 if type(value) == file:
                     v_files.append((key, value))
                 else:
                     v_vars.append((key, value))
        except TypeError:
            systype, value, traceback = sys.exc_info()
            raise TypeError, "not a valid non-string sequence or mapping object", traceback

        if len(v_files) == 0:
            data = urllib.urlencode(v_vars, doseq)
        else:
            boundary, data = multipart_encode(v_vars, v_files)

            contenttype = 'multipart/form-data; boundary=%s' % boundary
            if(request.has_header('Content-Type')
               and request.get_header('Content-Type').find('multipart/form-data') != 0):
                print "Replacing %s with %s" % (request.get_header('content-type'), 'multipart/form-data')
            request.add_unredirected_header('Content-Type', contenttype)

        request.add_data(data)

    return request

def multipart_encode(vars, files, boundary = None, buf = None):
    if boundary is None:
        boundary = mimetools.choose_boundary()
    if buf is None:
        buf = StringIO()
    for(key, value) in vars:
        buf.write('--%s\r\n' % boundary)
        buf.write('Content-Disposition: form-data; name="%s"' % key)
        buf.write('\r\n\r\n%s\r\n'%value)
    for(key, fd) in files:
        file_size = os.fstat(fd.fileno())[stat.ST_SIZE]
        filename = fd.name.split('/')[-1]
        contenttype = mimetypes.guess_type(filename)[0] or 'application/octet-stream'
        buf.write('--%s\r\n' % boundary)
        buf.write('Content-Disposition: form-data; name="%s"; filename="%s"\r\n' % (key, filename))
        buf.write('Content-Type: %s\r\n' % contenttype)
        # buffer += 'Content-Length: %s\r\n' % file_size
        fd.seek(0)
        buf.write('\r\n' + fd.read() + '\r\n')
    buf.write('--' + boundary + '--\r\n\r\n')
    buf = buf.getvalue()
    return boundary, buf