如何使用Python将大文件附加到电子邮件-Gmail API

Question

我正在尝试发送带有附件（最好是多个附件）的电子邮件，这些附件大于10 MB并且小于25 MB的总限制。我提到10 MB的原因是，这似乎是正常的附加文件方式停止起作用时得到的下限Error 10053。

我在文档中已经读到，做到这一点的最佳方法是使用可恢复的上载方法，但我无法使其正常工作，也无法在Python中找到任何好的示例。关于此的大多数SO问题都只是链接回到没有Python示例的文档，否则它们的代码会导致其他错误。

我正在寻找Python中的解释，因为我想确保自己理解正确。

我浏览过的问题：

• 使用具有Gmail API的断点续传附加文件
• Gmail Api断点续传（附件大于5MB）
• 在Google API客户端中使用/ upload网址
• 如何将大邮件上传到Gmail
• 使用Gmail API发送大型附件时出现错误10053
• 通过gmail和python发送电子邮件
• MIMEMultipart，MIMEText，MIMEBase和有效载荷，用于在Python中发送带有文件附件的电子邮件

码：

import base64
import json
import os
from email import utils, encoders
from email.message import EmailMessage
from email.mime import application, multipart, text, base, image, audio
import mimetypes

from apiclient import errors
from googleapiclient import discovery, http
from google.oauth2 import service_account

def send_email(email_subject, email_body, email_sender='my_service_account@gmail.com', email_to='', email_cc='', email_bcc='', files=None):

    # Getting credentials
    with open(os.environ.get('SERVICE_KEY_PASSWORD')) as f:
        service_account_info = json.loads(f.read())

    # Define which scopes we're trying to access
    SCOPES = ['https://www.googleapis.com/auth/gmail.send']

    # Setting up credentials using the gmail api
    credentials = service_account.Credentials.from_service_account_info(service_account_info, scopes=SCOPES)

    # This allows us to assign an alias account to the message so that the messages aren't coming from 'ServiceDriod-8328balh blah blah'
    delegated_credentials = credentials.with_subject(email_sender)

    # 'Building' the service instance using the credentials we've passed
    service = discovery.build(serviceName='gmail', version='v1', credentials=delegated_credentials)

    # Building out the email 
    message = multipart.MIMEMultipart()
    message['to'] = email_to
    message['from'] = email_sender
    message['date'] = utils.formatdate(localtime=True)
    message['subject'] = email_subject
    message['cc'] = email_cc
    message['bcc'] = email_bcc
    message.attach(text.MIMEText(email_body, 'html'))


    for f in files or []:
        mimetype, encoding = mimetypes.guess_type(f)

        # If the extension is not recognized it will return: (None, None)
        # If it's an .mp3, it will return: (audio/mp3, None) (None is for the encoding)
        # For an unrecognized extension we set mimetype to 'application/octet-stream' so it won't return None again. 
        if mimetype is None or encoding is not None:
            mimetype = 'application/octet-stream'
        main_type, sub_type = mimetype.split('/', 1)

        # Creating the attachement:
        # This part is used to tell how the file should be read and stored (r, or rb, etc.)
        if main_type == 'text':
            print('text')
            with open(f, 'rb') as outfile:
                attachement = text.MIMEText(outfile.read(), _subtype=sub_type)
        elif main_type == 'image':
            print('image')
            with open(f, 'rb') as outfile:
                attachement = image.MIMEImage(outfile.read(), _subtype=sub_type)
        elif main_type == 'audio':
            print('audio')
            with open(f, 'rb') as outfile:
                attachement = audio.MIMEAudio(outfile.read(), _subtype=sub_type)          
        elif main_type == 'application' and sub_type == 'pdf':   
            with open(f, 'rb') as outfile:
                attachement = application.MIMEApplication(outfile.read(), _subtype=sub_type)
        else:                              
            attachement = base.MIMEBase(main_type, sub_type)
            with open(f, 'rb') as outfile:
                attachement.set_payload(outfile.read())

        encoders.encode_base64(attachement)
        attachement.add_header('Content-Disposition', 'attachment', filename=os.path.basename(f))
        message.attach(attachement)



    media_body = http.MediaFileUpload(files[0], chunksize=500, resumable=True)
    print('Uploading large file...')
    body = {'raw': base64.urlsafe_b64encode(message.as_bytes()).decode()}


    message = (service.users().messages().send(userId='me', body=body, media_body=media_body).execute())

注意：现在，在我正在使用的MediaFileUpload中，files[0]因为我仅使用一个文件进行测试，并且我只想暂时附加一个文件，直到它起作用为止。

错误：

Exception has occurred: ResumableUploadError
<HttpError 400 "Bad Request">
  File "C:\Users\CON01599\AppData\Local\Continuum\anaconda3\Lib\site-packages\googleapiclient\http.py", line 927, in next_chunk
    raise ResumableUploadError(resp, content)
  File "C:\Users\CON01599\AppData\Local\Continuum\anaconda3\Lib\site-packages\googleapiclient\_helpers.py", line 130, in positional_wrapper
    return wrapped(*args, **kwargs)
  File "C:\Users\CON01599\AppData\Local\Continuum\anaconda3\Lib\site-packages\googleapiclient\http.py", line 822, in execute
    _, body = self.next_chunk(http=http, num_retries=num_retries)
  File "C:\Users\CON01599\AppData\Local\Continuum\anaconda3\Lib\site-packages\googleapiclient\_helpers.py", line 130, in positional_wrapper
    return wrapped(*args, **kwargs)
  File "C:\Users\CON01599\Documents\GitHub\pipelines\components\email\send_email.py", line 105, in send_email
    message = (service.users().messages().send(userId='me', body=body, media_body=media_body).execute())

回答：

import base64
import io
import json
import os
from email import utils, encoders
from email.message import EmailMessage
from email.mime import application, multipart, text, base, image, audio
import mimetypes

from apiclient import errors
from googleapiclient import discovery, http
from google.oauth2 import service_account


def get_environment_variables():
    """ Retrieves the environment variables and returns them in
        a dictionary object.
    """
    env_var_dict = {
        'to': os.environ.get('TO'),
        'subject': os.environ.get('SUBJECT'),
        'body': os.environ.get('BODY'),
        'file': os.environ.get('FILE')
    }

    return env_var_dict


def send_email(email_subject, email_body, email_sender='my_service_account@gmail.com', email_to='', email_cc='', email_bcc='', files=None):

    # Pulling in the string value of the service key from the parameter
    with open(os.environ.get('SERVICE_KEY_PASSWORD')) as f:
        service_account_info = json.loads(f.read())

    # Define which scopes we're trying to access
    SCOPES = ['https://www.googleapis.com/auth/gmail.send']

    # Setting up credentials using the gmail api
    credentials = service_account.Credentials.from_service_account_info(service_account_info, scopes=SCOPES)
    # This allows us to assign an alias account to the message so that the messages aren't coming from 'ServiceDriod-8328balh blah blah'
    delegated_credentials = credentials.with_subject(email_sender)
    # 'Building' the service instance using the credentials we've passed
    service = discovery.build(serviceName='gmail', version='v1', credentials=delegated_credentials)

    # Building out the email 
    message = multipart.MIMEMultipart()
    message['to'] = email_to
    message['from'] = email_sender
    message['date'] = utils.formatdate(localtime=True)
    message['subject'] = email_subject
    message['cc'] = email_cc
    message['bcc'] = email_bcc
    message.attach(text.MIMEText(email_body, 'html'))


    for f in files or []:
        f = f.strip(' ')
        mimetype, encoding = mimetypes.guess_type(f)

        # If the extension is not recognized it will return: (None, None)
        # If it's an .mp3, it will return: (audio/mp3, None) (None is for the encoding)
        # For an unrecognized extension we set mimetype to 'application/octet-stream' so it won't return None again. 
        if mimetype is None or encoding is not None:
            mimetype = 'application/octet-stream'
        main_type, sub_type = mimetype.split('/', 1)

        # Creating the attachement:
        # This part is used to tell how the file should be read and stored (r, or rb, etc.)
        if main_type == 'text':
            print('text')
            with open(f, 'rb') as outfile:
                attachement = text.MIMEText(outfile.read(), _subtype=sub_type)
        elif main_type == 'image':
            print('image')
            with open(f, 'rb') as outfile:
                attachement = image.MIMEImage(outfile.read(), _subtype=sub_type)
        elif main_type == 'audio':
            print('audio')
            with open(f, 'rb') as outfile:
                attachement = audio.MIMEAudio(outfile.read(), _subtype=sub_type)          
        elif main_type == 'application' and sub_type == 'pdf':   
            with open(f, 'rb') as outfile:
                attachement = application.MIMEApplication(outfile.read(), _subtype=sub_type)
        else:                              
            attachement = base.MIMEBase(main_type, sub_type)
            with open(f, 'rb') as outfile:
                attachement.set_payload(outfile.read())

        encoders.encode_base64(attachement)
        attachement.add_header('Content-Disposition', 'attachment', filename=os.path.basename(f))
        message.attach(attachement)

    media_body = http.MediaIoBaseUpload(io.BytesIO(message.as_bytes()), mimetype='message/rfc822', resumable=True)
    body_metadata = {} # no thread, no labels in this example

    try:
        print('Uploading file...')
        response = service.users().messages().send(userId='me', body=body_metadata, media_body=media_body).execute()
        print(response)
    except errors.HttpError as error:
        print('An error occurred when sending the email:\n{}'.format(error))


if __name__ == '__main__':

    env_var_dict = get_environment_variables()
    print("Sending email...")
    send_email(email_subject=env_var_dict['subject'], 
            email_body=env_var_dict['body'], 
            email_to=env_var_dict['to'],
            files=env_var_dict['file'].split(','))

    print("Email sent!")

Answer 1

您在这里遇到的问题是您的MediaUpload附件是单个附件。

MediaUpload您需要将整个 RFC822 消息作为可续传上载，而不是上传单个附件作为可续传MediaUpload。

换句话说：

import ...
...
from io import BytesIO
from googleapiclient.http import MediaIoBaseUpload

SCOPES = [ 'scopes' ]

creds = get_credentials_somehow()
gmail = get_authed_service_somehow()

msg = create_rfc822_message(headers, email_body)
to_attach = get_attachment_paths_from_dir('../reports/tps/memos/2019/04')
add_attachments(msg, to_attach)

media = MediaIoBaseUpload(BytesIO(msg.as_bytes()), mimetype='message/rfc822', resumable=True)
body_metadata = {} # no thread, no labels in this example
resp = gmail.users().messages().send(userId='me', body=body_metadata, media_body=media).execute()
print(resp)
# { "id": "some new id", "threadId": "some new thread id", "labelIds": ["SENT"]}

我根据您提供的代码将其拼凑在一起，审查了此 GitHub 问题和 Google 的 Inbox-to-Gmail 电子邮件导入器，特别是这一点。

在发送对现有邮件的回复时，您几乎肯定会提供某种元数据，以帮助 Gmail 跟踪您的新回复和原始对话。也就是说，body您将传递信息性元数据，例如

body_metadata = { 'labelIds': [
                    "your label id here",
                    "another label id" ],
                  'threadId': "some thread id you took from the message you're replying to"
                }

其他好的参考：

• API 客户端的 Gmail PyDoc
• 实际使用的代码