新的 Python Gmail API - 仅检索昨天的邮件

Question

我一直在将一些脚本更新到新的 Python Gmail API。但是，我对如何更新以下内容感到困惑，以便我只检索昨天的消息。谁能告诉我如何做到这一点？

我目前能看到的唯一方法是遍历所有消息，并仅解析具有正确时间范围内的纪元的消息。但是，如果我有 1000 条消息，这似乎非常低效。必须有更有效的方法来做到这一点。

from apiclient import discovery
import oauth2client
from oauth2client import client
from oauth2client import tools
import os
import httplib2
import email
from apiclient.http import BatchHttpRequest
import base64
from bs4 import BeautifulSoup
import re
import datetime

try:
    import argparse
    flags = argparse.ArgumentParser(parents=[tools.argparser]).parse_args()
except ImportError:
    flags = None

SCOPES = 'https://www.googleapis.com/auth/gmail.readonly'
CLIENT_SECRET_FILE = '/Users/sokser/Downloads/client_secret.json'
APPLICATION_NAME = 'Gmail API Python Quickstart'


def get_credentials():
    """Gets valid user credentials from storage.

    If nothing has been stored, or if the stored credentials are invalid,
    the OAuth2 flow is completed to obtain the new credentials.

    Returns:
        Credentials, the obtained credential.
    """
    home_dir = os.path.expanduser('~')
    credential_dir = os.path.join(home_dir, '.credentials')
    if not os.path.exists(credential_dir):
        os.makedirs(credential_dir)
    credential_path = os.path.join(credential_dir,
                                   'gmail-python-quickstart.json')

    store = oauth2client.file.Storage(credential_path)
    credentials = store.get()
    if not credentials or credentials.invalid:
        flow = client.flow_from_clientsecrets(CLIENT_SECRET_FILE, SCOPES)
        flow.user_agent = APPLICATION_NAME
        if flags:
            credentials = tools.run_flow(flow, store, flags)
        else: # Needed only for compatibility with Python 2.6
            credentials = tools.run(flow, store)
        print('Storing credentials to ' + credential_path)
    return credentials

def visible(element):
    if element.parent.name in ['style', 'script', '[document]', 'head', 'title']:
        return False
    elif re.match('<!--.*-->', str(element)):
        return False
    return True

def main():
    """Shows basic usage of the Gmail API.

    Creates a Gmail API service object and outputs a list of label names
    of the user's Gmail account.
    """
    credentials = get_credentials()
    http = credentials.authorize(httplib2.Http())
    service = discovery.build('gmail', 'v1', http=http)
    #Get yesterdays date and the epoch time
    yesterday = datetime.date.today() - datetime.timedelta(1)
    unix_time= int(yesterday.strftime("%s"))

    messages = []

    message = service.users().messages().list(userId='me').execute()
    for m in message['messages']:
        #service.users().messages().get(userId='me',id=m['id'],format='full')
        message = service.users().messages().get(userId='me',id=m['id'],format='raw').execute()
        epoch = int(message['internalDate'])/1000

        msg_str = str(base64.urlsafe_b64decode(message['raw'].encode('ASCII')),'utf-8')
        mime_msg = email.message_from_string(msg_str)
        #print(message['payload']['parts'][0]['parts'])
        #print()
        mytext = None
        for part in mime_msg.walk():
            mime_msg.get_payload()
            #print(part)
            #print()
            if part.get_content_type() == 'text/plain':
                soup = BeautifulSoup(part.get_payload(decode=True))
                texts = soup.findAll(text=True)
                visible_texts = filter(visible,texts)
                mytext = ". ".join(visible_texts)
            if part.get_content_type() == 'text/html' and not mytext:
                mytext = part.get_payload(decode=True)
        print(mytext)
        print()

if __name__ == '__main__':
    main()

Answer 1

您可以将查询传递给在日期范围内搜索消息的messages.list 方法。您实际上可以使用任何query supported by Gmail's advanced search。

你这样做，它只会返回消息。

message = service.users().messages().list(userId='me').execute()

但是可以通过传递q 关键字参数和指定before: 和after: 关键字的查询来搜索昨天发送的消息。

from datetime import date, timedelta

today = date.today()
yesterday = today - timedelta(1)

# do your setup...

user_id = 'user email address'

# Dates have to formatted in YYYY/MM/DD format for gmail
query = "before: {0} after: {1}".format(today.strftime('%Y/%m/%d'),
                                        yesterday.strftime('%Y/%m/%d'))

response = service.users().messages().list(userId=user_id,
                                           q=query).execute()
# Process the response for messages...

您也可以针对他们的GMail messages.list reference page 尝试此操作。