python2 post 上传压缩文件编码报错

Question

python版本是2.7，使用urllib2将文件推送至微信，在上传文件时，碰到这样一个问题：上传未经压缩的文本文件，可以成功；上传经过压缩的二进制文件，则提示编码错误
代码如下

def upload_tmpfile_old(self,filepath):
        try:
            #文件存在、文件可读、文件大小小于19M
            if not (os.path.isfile(filepath) and os.access(filepath,os.R_OK)
                and os.path.getsize(filepath)<19922944):
                return -1

            boundary = '----------%s' % hex(int(time.time() * 1000))
            data = []
            data.append('--%s' % boundary)
            fr = open(filepath, 'rb')
            data.append('Content-Disposition: form-data; name="media"; filename="pickdump"')
            data.append('Content-Type: application/octet-stream\r\n\r\n')
            data.append(fr.read())
            fr.close()
            data.append('--%s--\r\n' % boundary)
            http_body = '\r\n'.join(data)

            print http_body
            sendurl = "https://qyapi.weixin.qq.com/cgi-bin/media/upload?access_token=" + Token.gettoken() + "&type=file"
            req = urllib2.Request(sendurl, data=http_body)
            req.add_header('Content-Type', 'multipart/form-data; boundary=%s' % boundary)
            req.add_header('Content-Length',len(http_body))
            print req.headers
            self.resp = urllib2.urlopen(req, timeout=5)
            print self.resp.__dict__
            print self.resp.read()
        except:
            logger.exception("上传文件出现异常")
            raise

if __name__ == '__main__':
    uploadfile = wxRequest("WZ", '', '', "file", 1000002)
    uploadfile.upload_tmpfile_old("/home/wz/12306.txt.zip")    

报错信息如下：

Traceback (most recent call last):
  File "/home/wzk/wx2x/wxpush.py", line 264, in <module>
    uploadfile.upload_tmpfile_old("/home/wzk/12306.txt.zip")
  File "/home/wzk/wx2x/wxpush.py", line 227, in upload_tmpfile_old
    self.resp = urllib2.urlopen(req, timeout=5)
  File "/usr/lib64/python2.7/urllib2.py", line 154, in urlopen
    return opener.open(url, data, timeout)
  File "/usr/lib64/python2.7/urllib2.py", line 431, in open
    response = self._open(req, data)
  File "/usr/lib64/python2.7/urllib2.py", line 449, in _open
    '_open', req)
  File "/usr/lib64/python2.7/urllib2.py", line 409, in _call_chain
    result = func(*args)
  File "/usr/lib64/python2.7/urllib2.py", line 1242, in https_open
    context=self._context)
  File "/usr/lib64/python2.7/urllib2.py", line 1196, in do_open
    h.request(req.get_method(), req.get_selector(), req.data, headers)
  File "/usr/lib64/python2.7/httplib.py", line 1057, in request
    self._send_request(method, url, body, headers)
  File "/usr/lib64/python2.7/httplib.py", line 1097, in _send_request
    self.endheaders(body)
  File "/usr/lib64/python2.7/httplib.py", line 1053, in endheaders
    self._send_output(message_body)
  File "/usr/lib64/python2.7/httplib.py", line 895, in _send_output
    msg += message_body
UnicodeDecodeError: 'utf8' codec can't decode byte 0xb6 in position 149: invalid start byte

以前用python3，byte和str有明确的区分。这个功能由于版本问题，只能用python2，结果发现编码各种坑啊。
压缩文件本来就是一个二进制文件，不能被utf-8解码也是正常的，不知道对于这个问题有没有方法解决？
PS 以前用requests的时候,是把文件读成bytes后，直接拼回body里面的，不知道这样做在python2中应该如何写？

Answer 1

这个是urllib2库本身的逻辑导致的。他会将含有bytestring的字符串解码为unicode字符串后，与msg相加，再进行发送。如果要发送流文件，需要直接使用httplib。