Python上传文件MultipartPostHandler.py

hitl

#!/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.
#
"""
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
class Callable:
def __init__(self, anycallable):
self.__call__ = anycallable
# Controls how sequences are uncoded. If true, elements may be given multiple values by
#  assigning a sequence.
doseq = 1
class MultipartPostHandler(urllib2.BaseHandler):
handler_order = urllib2.HTTPHandler.handler_order - 10 # needs to run first
def http_request(self, request):
data = request.get_data()
if data is not None and type(data) != str:
v_files = []
v_vars = []
try:
for(key, value) in data.items():
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 = self.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, buffer = None):
if boundary is None:
boundary = mimetools.choose_boundary()
if buffer is None:
buffer = ''
for(key, value) in vars:
buffer += '--%s\r\n' % boundary
buffer += 'Content-Disposition: form-data; name="%s"' % key
buffer += '\r\n\r\n' + value + '\r\n'
for(key, fd) in files:
file_size = os.fstat(fd.fileno())[stat.ST_SIZE]
filename = os.path.basename(fd.name)
contenttype = mimetypes.guess_type(filename)[0] or 'application/octet-stream'
buffer += '--%s\r\n' % boundary
buffer += 'Content-Disposition: form-data; name="%s"; filename="%s"\r\n' % (key, filename)
buffer += 'Content-Type: %s\r\n' % contenttype
# buffer += 'Content-Length: %s\r\n' % file_size
fd.seek(0)
buffer += '\r\n' + fd.read() + '\r\n'
buffer += '--%s--\r\n\r\n' % boundary
return boundary, buffer
multipart_encode = Callable(multipart_encode)
https_request = http_request
def main():
import tempfile, sys
validatorURL = "http://validator.w3.org/check"
opener = urllib2.build_opener(MultipartPostHandler)
def validateFile(url):
temp = tempfile.mkstemp(suffix=".html")
os.write(temp[0], opener.open(url).read())
params = { "ss" : "0",            # show source
"doctype" : "Inline",
"uploaded_file" : open(temp[1], "rb") }
print opener.open(validatorURL, params).read()
os.remove(temp[1])
if len(sys.argv[1:]) > 0:
for arg in sys.argv[1:]:
validateFile(arg)
else:
validateFile("http://www.google.com")
if __name__=="__main__":
main()

　　上传文件的Demo： 
　　import MultipartPostHandler
　　res = urllib2.urlopen('http://group.xiaonei.com/GetThread.do?id=328762314&tribeId=251102045')
  self.data = {
    'body':'闪电刀好用',\
    'theFile':open('aa.gif','rb'),\
    'ac':'c75271d1c4681d2be369ee3d390fec4f10d0e51b262586850c73c8c0bd6133052120b6c280cefe86',\
    'tribeId':'251102045',\
   }
  
  req = urllib2.Request(
             url     = 'http://upload.xiaonei.com/ReplyPost.do?thread=328762314',\
      data    = self.data)
  req.add_header('Referer', 'http://group.xiaonei.com/GetThread.do?id=328762314&tribeId=251102045')
  req.add_header('Host', 'group.xiaonei.com') 
  response = self.opener.open(req)