第十二章：互联网-urllib.request:网络资源访问--上传文件

12.2.6 上传文件
要对文件编码以完成上传，与使用简单表单相比，这需要多做一些工作。要在请求体中构造已给完整的MIME消息，使得服务器可以把收到的表单域与上传的文件区分开。

开启POST服务器。

import io
import mimetypes
from urllib import request
import uuid

class MultiPartForm:
    """Accumulate the data to be used  when posting a form."""

    def __init__(self):
        self.form_fields = []
        self.files = []
        # Use a large random byte string to separate
        # parts of the MIME data.
        self.boundary = uuid.uuid4().hex.encode('utf-8')

    def get_content_type(self):
        return 'multipart/form-data;boundary={}'.format(
            self.boundary.decode('utf-8'))

    def add_field(self,name,value):
        """Add a simple field to the form data."""
        self.form_fields.append((name,value))

    def add_file(self,fieldname,filename,fileHandle,mimetype=None):
        """Add a file to be uploaded."""
        body = fileHandle.read()
        if mimetype is None:
            mimetype = (
            mimetypes.guess_type(filename)[0] or
            'application/octet-stream'
            )
        self.files.append((fieldname,filename,mimetype,body))
        return

    @staticmethod
    def _form_data(name):
        return ('Content-Disposition: form-data; '
                'name="{}"\r\n').format(name).encode('utf-8')

    @staticmethod
    def _attached_file(name,filename):
        return ('Content-Disposition:file; '
                'name="{}";filename="{}"\r\n').format(
                    name,filename).encode('utf-8')

    @staticmethod
    def _content_type(ct):
        return 'Content-Type: {}\r\n'.format(ct).encode('utf-8')

    def __bytes__(self):
        """Return a byte-string representing the form data,
        including attached files.
        """
        buffer = io.BytesIO()
        boundary = b'--' + self.boundary + b'\r\n'

        # Add the form fields.
        for name,value in self.form_fields:
            buffer.write(boundary)
            buffer.write(self._form_data(name))
            buffer.write(b'\r\n')
            buffer.write(value.encode('utf-8'))
            buffer.write(b'\r\n')

        # Add the files to upload.
        for f_name,filename,f_content_type,body in self.files:
            buffer.write(boundary)
            buffer.write(self._attached_file(f_name,filename))
            buffer.write(self._content_type(f_content_type))
            buffer.write(b'\r\n')
            buffer.write(body)
            buffer.write(b'\r\n')

        buffer.write(b'--' + self.boundary + b'--\r\n')
        return buffer.getvalue()

if __name__ == '__main__':
    # Create the form with simple fields.
    form = MultiPartForm()
    form.add_field('firstname','Dong')
    form.add_field('lastname','iglesias')

    # Add a fake file.
    form.add_file(
        'biography','bio.txt',
        fileHandle=io.BytesIO(b'Python developer and blogger.'))

    # Build the request,including the byte-string
    # for the data to be posted.
    data = bytes(form)
    r = request.Request('http://localhost:8080/',data=data)
    r.add_header(
        'User-agent',
        'PyMOTW(https://pymotw.com/)',
        )
    r.add_header('Content-type',form.get_content_type())
    r.add_header('Content-length',len(data))

    print()
    print('OUTGOING DATA:')
    for name,value in r.header_items():
        print('{}:{}'.format(name,value))
    print()
    print(r.data.decode('utf-8'))

    print()
    print('SERVER RESPONSE:')
    print(request.urlopen(r).read().decode('utf-8'))

MultiPartForm类可以把一个任意的表单表示为一个带附加文件的多部分MIME消息。
运行结果：