如何訪問 AWS Lambda 的 /tmp 目錄中的文件

Question

我已經從 URL 下載了一個文件到 AWS Lambda 的 /tmp 目錄中（因為這是 Lambda 中唯一的可寫路徑）。

我的動機是創建一個 Alexa Skill，它將從 URL 下載文件。 因此我創建了一個 lambda function。

如何從 lambda 的 /tmp 文件夾訪問下載的文件？

我的代碼是： -

#!/usr/bin/python
# -*- coding: utf-8 -*-
from __future__ import print_function
import xml.etree.ElementTree as etree
from datetime import datetime as dt
import os
import urllib
import requests

from urllib.parse import urlparse


def lambda_handler(event, context):
    """ Route the incoming request based on type (LaunchRequest, IntentRequest,
    etc.) The JSON body of the request is provided in the event parameter.
    """

    print('event.session.application.applicationId=' + event['session'
          ]['application']['applicationId'])

    # if (event['session']['application']['applicationId'] !=
    #         "amzn1.echo-sdk-ams.app.[unique-value-here]"):
    #     raise ValueError("Invalid Application ID")

    if event['session']['new']:
        on_session_started({'requestId': event['request']['requestId'
                           ]}, event['session'])

    if event['request']['type'] == 'LaunchRequest':
        return on_launch(event['request'], event['session'])
    elif event['request']['type'] == 'IntentRequest':
        return on_intent(event['request'], event['session'])
    elif event['request']['type'] == 'SessionEndedRequest':
        return on_session_ended(event['request'], event['session'])


def on_session_started(session_started_request, session):
    """ Called when the session starts """

    print('on_session_started requestId='
          + session_started_request['requestId'] + ', sessionId='
          + session['sessionId'])


def on_launch(launch_request, session):
    """ Called when the user launches the skill without specifying what they
    want
    """

    print('on_launch requestId=' + launch_request['requestId']
          + ', sessionId=' + session['sessionId'])

    # Dispatch to your skill's launch

    return get_welcome_response()


def on_intent(intent_request, session):
    """ Called when the user specifies an intent for this skill """

    print('on_intent requestId=' + intent_request['requestId']
          + ', sessionId=' + session['sessionId'])

    intent = intent_request['intent']
    intent_name = intent_request['intent']['name']

    # Dispatch to your skill's intent handlers

    if intent_name == 'DownloadFiles':
        return get_file(intent, session)
    elif intent_name == 'AMAZON.HelpIntent':
        return get_welcome_response()
    else:
        raise ValueError('Invalid intent')


def on_session_ended(session_ended_request, session):
    """ Called when the user ends the session.Is not called when the skill returns should_end_session=true """

    print('on_session_ended requestId='
          + session_ended_request['requestId'] + ', sessionId='
          + session['sessionId'])


    # add cleanup logic here

# --------------- Functions that control the skill's behavior ------------------

def get_welcome_response():
    """ If we wanted to initialize the session to have some attributes we could add those here """

    session_attributes = {}
    card_title = 'Welcome'
    speech_output = \
        "Welcome to file download Application. Please ask me to download files by saying, Ask auto downloader for download"

    # If the user either does not reply to the welcome message or says something
    # that is not understood, they will be prompted again with this text.

    reprompt_text = \
        "Please ask me to download files by saying, Ask auto downloader for download"
    should_end_session = False
    return build_response(session_attributes,
                          build_speechlet_response(card_title,
                          speech_output, reprompt_text,
                          should_end_session))


def get_file(intent, session):
    """ Grabs the files from the path that have to be downloaded """

    card_title = intent['name']
    session_attributes = {}
    should_end_session = True
    username = '*******'
    password = '*******'

    url = 'https://drive.google.com/drive/my-drive/abc.pdf'
    filename = os.path.basename(urlparse(url).path)

    # urllib.urlretrieve(url, "code.zip")

    r = requests.get(url, auth=(username, password))

    if r.status_code == 200:
        with open("/tmp/" + filename, 'wb') as out:
            for bits in r.iter_content():
                out.write(bits)

    speech_output = 'The file filename has been downloaded'
    return build_response(session_attributes,
                          build_speechlet_response(card_title,
                          speech_output, reprompt_text,
                          should_end_session))


# --------------- Helpers that build all of the responses ----------------------

def build_speechlet_response(
    title,
    output,
    reprompt_text,
    should_end_session,
    ):
    return {
        'outputSpeech': {'type': 'PlainText', 'text': output},
        'card': {'type': 'Simple', 'title': 'SessionSpeechlet - ' \
                 + title, 'content': 'SessionSpeechlet - ' + output},
        'reprompt': {'outputSpeech': {'type': 'PlainText',
                     'text': reprompt_text}},
        'shouldEndSession': should_end_session,
        }


def build_response(session_attributes, speechlet_response):
    return {'version': '1.0', 'sessionAttributes': session_attributes,
            'response': speechlet_response}

Answer 1

只需像往常一樣打開文件：

with open('/tmp/'+ filename, 'rb') as file:
    ...

這對我來說一直有效。 您是否嘗試過並遇到任何問題？

請注意，Lambda 在容器中運行。 下載一次后，該文件將位於/tmp文件夾中，直到此容器存在為止。 在啟動容器以提供您的功能后，它通常會存活 10-30 分鍾（可能更少或更多，這不是官方的固定時間）。 因此，與其總是下載文件，不如檢查該文件是否不在/tmp目錄中。 如果是，您顯然不必再次下載！ ;)

要進行此檢查，請使用：

if not os.path.isfile('/tmp/' + filename):
    download...

Answer 2

For anyone who ends up here and is using a Docker image as the Lambda function: AWS cleans out /tmp either when the Docker image is uploaded to ECS or when the Lambda function is executed.

這意味着，如果您依賴 /tmp 中的任何內容（例如，您正在將文件復制到 Dockerfile 中的 /tmp），您將觀察到 Docker 映像在本地運行良好，並且按預期包含 /tmp 中的文件，但是您當您嘗試在 AWS 中將相同的 Docker 圖像作為 Lambda function 運行時出現錯誤，因為該文件不在 /tmp 中。

我建議將文件放在只讀的 LAMBDA_TASK_ROOT（現在是 /var/task 目錄）中。 如果你需要修改這個文件，那么我會從 LAMBDA_TASK_ROOT 目錄中讀取它，並將它寫入 /tmp。