Google AppEngine with Service Account but invalid Credentials - python

I have tried to get a group settings with group settings API using Google App Engine 1.7.5 with python 2.5 following a simple example here.
this is my app.yaml:
application: {{APP_ID}}
version: 1
runtime: python
api_version: 1
handlers:
- url: /.*
script: main.py
and my main.py is like following:
def main():
application = webapp.WSGIApplication([('/', TestHandler)])
run_wsgi_app(application)
class TestHandler(webapp.RequestHandler):
"""Handles a request for the query page."""
def get(self):
self.response.out.write(Test())
def Test():
credentials = AppAssertionCredentials(scope='https://www.googleapis.com/auth/apps.groups.settings')
http = credentials.authorize(httplib2.Http(memcache))
service = build('groupssettings', 'v1', http=http)
group = service.groups().get(groupUniqueId='{{GROUP_ID}}').execute()
logging.error(group)
if __name__=="__main__":
main()
and this is the stacktrace telling me invalid credentials!
Traceback (most recent call last):
File "C:\Program Files (x86)\Google\google_appengine\google\appengine\ext\webapp\_webapp25.py", line 714, in __call__
handler.get(*groups)
File "D:\Projets\GS\main.py", line 26, in get
self.response.out.write(Test())
File "D:\Projets\GS\main.py", line 41, in Test
group = service.groups().get(groupUniqueId='{{GROUP_ID}}').execute()
File "D:\Projets\GS\oauth2client\util.py", line 132, in positional_wrapper
return wrapped(*args, **kwargs)
File "D:\Projets\GS\apiclient\http.py", line 723, in execute
raise HttpError(resp, content, uri=self.uri)
HttpError: <HttpError 401 when requesting https://www.googleapis.com/groups/v1/groups/{{GROUP_ID}}?alt=json returned "Invalid Credentials">
INFO 2014-11-21 15:51:45,423 dev_appserver.py:3104] "GET / HTTP/1.1" 500 -
INFO 2014-11-21 15:51:45,611 dev_appserver.py:3104] "GET /favicon.ico HTTP/1.1" 404 -
Have anyone got this error before or have an idea of the root cause?

Have you turned on access to the groups API through the developer console for the project? This is a simple step that is often missed by people trying to get APIs going.
Also, I'd recommend using the decorator patterns for OAuth as described here to simplify the reasoning around authorization flows.
In addition, your app.yaml should specify python27 rather than just python. App Engine runs python27.

Related

Sending emails from Google Appengine fails because of missing api proxy

I am trying to send e-mails from a GAE application using this code:
from google.appengine.api.mail import send_mail
send_mail(
"sender#nowhere.com",
["user#example.com"],
"Subject",
"Body",
)
I have configured usage of the apis in app.yaml with:
app_engine_apis: true
And deploy to App Engine is done with gcloud beta app deploy.
However, I get this error:
Traceback (most recent call last):
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/flask/app.py", line 2073, in wsgi_app response = self.full_dispatch_request()
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/flask/app.py", line 1518, in full_dispatch_request rv = self.handle_user_exception(e)
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/flask/app.py", line 1516, in full_dispatch_request rv = self.dispatch_request()
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/flask/app.py", line 1502, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**req.view_args)
File "/srv/infrastructure/view_modifiers.py", line 12, in view_method response_val = f(*args, **kwargs)
File "/srv/views/orders.py", line 25, in create_order vm.create_order()
File "/srv/viewmodels/orders/order_viewmodel.py", line 74, in create_order self._send_order_email()
File "/srv/viewmodels/orders/order_viewmodel.py", line 54, in _send_order_email send_mail(
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/google/appengine/api/mail.py", line 401, in send_mail message.send(make_sync_call=make_sync_call)
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/google/appengine/api/mail.py", line 1209, in send make_sync_call('mail', self._API_CALL, message, response)
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/google/appengine/api/apiproxy_stub_map.py", line 96, in MakeSyncCall return stubmap.MakeSyncCall(service, call, request, response)
File "/layers/google.python.pip/pip/lib/python3.9/site-packages/google/appengine/api/apiproxy_stub_map.py", line 348, in MakeSyncCall assert stub, 'No api proxy found for service "%s"' % service AssertionError: No api proxy found for service "mail"
This seems to suggest that even for the default behavior of the mail service, some kind of proxy needs to be configured. However, I cannot find any information about the setup of this proxy.
And, my initial understanding was that setting up a proxy is only needed for unit-testing or local development.
Here is an example that works with fastapi. (answer to anton's comment)
from google.appengine.api import mail
from fastapi.middleware.wsgi import WSGIMiddleware
from google.appengine.api import wrap_wsgi_app
from flask import Flask
app = create_app() # this is just app = FastAPI() and somes middleware but but no relevance here
app_flask = Flask(__name__)
app_flask.wsgi_app = wrap_wsgi_app(app_flask.wsgi_app, use_deferred=True)
def send_approved_mail(sender_address):
# [START send_message]
message = mail.EmailMessage(
sender=sender_address,
subject="Your account has been approved")
message.to = "test#gmail.com"
message.body = """Dear Albert:
Your example.com account has been approved. You can now visit
http://www.example.com/ and sign in using your Google Account to
access new features.
Please let us know if you have any questions.
The example.com Team
"""
message.send()
#app_flask.route("/send_email", methods=['GET'])
def send_email():
send_approved_mail("registred_email#domain.com")
return "message sent"
app.mount("/v1", WSGIMiddleware(app_flask))
here app.yaml
runtime: python39
entrypoint: gunicorn -k uvicorn.workers.UvicornWorker app.main:app
instance_class: F1
app_engine_apis: true
inbound_services:
- mail
- mail_bounce
You will not see flask route on swagger.
and for some reason, i could not sent email with app engine's default service account. I had to register my email ( with same domain) here : https://console.cloud.google.com/appengine/settings/emailsenders?project=your_project
I just tested this and it worked for me (i.e. I received the email I supplied for recipient_email_address in the code below). Note that sender must be a value specified under Email Senders in App Engine settings page
requirements.txt file
Flask
appengine-python-standard>=1.0.0
app.yaml file
runtime: python39
app_engine_apis: true
handlers:
- url: /static
static_dir: static/
- url: /.*
script: auto
main.py
from flask import Flask
from google.appengine.api import wrap_wsgi_app
from google.appengine.api.mail import send_mail
app = Flask(__name__)
app.wsgi_app = wrap_wsgi_app(app.wsgi_app)
#app.route("/")
def sendMail():
send_mail(sender= <authorized_email_sender>,
to= <recipient_email_address>,
subject="Testing Python3 sending mails",
body="""Dear Albert:
Your example.com account has been approved. You can now visit
http://www.example.com/ and sign in using your Google Account to
access new features.
Please let us know if you have any questions.
The example.com Team
""")
return "Mail was sent"

Unable to deploy Python Flask application in Google App Engine Flex Environment

I have searched in multiple places and have tried multiple ways to find a solution to this. But nothing was helpful, can you please help me provide the solution. It is getting extremely difficult to host a python flask application in google app engine flexible environment. Python code: "getresource.py"
Here is the link from google to deploy Python Flask application
Here is the simple code:
from flask import Flask, jsonify
from pymysql import connections, ProgrammingError, DatabaseError, MySQLError, DataError
from os import environ
DB_HOST = environ.get("DB_HOST")
USER = environ.get("USER")
PWD = environ.get("PASSWORD")
DATABASE = environ.get("DATABASE")
app = Flask(__name__)
dbconn = connections.Connection(
host=DB_HOST,
port=3306,
user=USER,
password=PWD,
db=DATABASE
)
#app.route("/getResource/<id>", methods=['GET'])
def getresource(id):
result = ()
select_sql = "SELECT `id`, `firstName`, `middleName`, `lastName`, `listOfTechWorkedOn`, `certifications`, `projects`, `applicationWorkLoadTypes` FROM `resource` WHERE `id`=%s"
cursor = dbconn.cursor()
try:
cursor.execute(select_sql, (id))
result = cursor.fetchone()
response = {}
response['id'] = result[0]
response['firstName'] = result[1]
response['middleName'] = result[2]
response['lastName'] = result[3]
response['listOfTechWorkedOn'] = result[4]
response['certifications'] = result[5]
response['projects'] = result[6]
response['applicationWorkLoadTypes'] = result[7]
return jsonify(response)
except ProgrammingError as p:
return
except DatabaseError as d:
return d
except MySQLError as m:
return m
except DataError as de:
return de
dbconn.close()
if __name__ == '__main__':
app.run(host='127.0.0.1',port=8080, debug=True)
Here is the app.yaml file
runtime: python
env: flex
entrypoint: gunicorn -b :$PORT getresource:app
service: getresource
runtime_config:
python_version: 3
manual_scaling:
instances: 1
env_variables:
DB_HOST: "1.2.3.4"
USER: "root"
PASSWORD: "abcdefg"
DATABASE: "abcd"
requirements.txt file
Flask==1.0.2
gunicorn==19.9.0
PyMySQL==0.9.2
I am getting the following error: "gcloud app deploy"
ERROR: (gcloud.app.deploy) Error Response: [13] An internal error occurred during deployment.
I have tried multiple ways, like changing the python code, putting google cloud libraries in the requirements.txt, chaning port, service name etc. But nothing seems to be working.
And surprisingly, I am not getting the error trace in stackdriver logs as well. And Google does not have proper answer it seems (at least from all the googling that i have done)
gcloud version
Google Cloud SDK 222.0.0
bq 2.0.36
core 2018.10.19
gsutil 4.34
**
EDIT:
** Thanks for all the response. I tried all the options, but getting the same error with following debug message. I cannot make anything out of it
Thanks for the response. I tried with all the suggested options, but getting the same error. Following is the debug log, and I cannot make anything out of it.
Updating service [getresource] (this may take several minutes)...failed.
DEBUG: (gcloud.app.deploy) Error Response: [13] An internal error occurred during deployment.
Traceback (most recent call last):
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\calliope\cli.py", line 841, in Execute
resources = calliope_command.Run(cli=self, args=args)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\calliope\backend.py", line 770, in Run
resources = command_instance.Run(args)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\surface\app\deploy.py", line 90, in Run
parallel_build=False)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\command_lib\app\deploy_util.py", line 620, in RunDeploy
flex_image_build_option=flex_image_build_option)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\command_lib\app\deploy_util.py", line 422, in Deploy
extra_config_settings)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\api_lib\app\appengine_api_client.py", line 207, in DeployService
poller=done_poller)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\api_lib\app\operations_util.py", line 315, in WaitForOperation
sleep_ms=retry_interval)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\api_lib\util\waiter.py", line 254, in WaitFor
sleep_ms, _StatusUpdate)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\api_lib\util\waiter.py", line 316, in PollUntilDone
sleep_ms=sleep_ms)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\core\util\retry.py", line 229, in RetryOnResult
if not should_retry(result, state):
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\api_lib\util\waiter.py", line 310, in _IsNotDone
return not poller.IsDone(operation)
File "C:\Users\M1044921\AppData\Local\Google\Cloud SDK\google-cloud-sdk\lib\googlecloudsdk\api_lib\app\operations_util.py", line 184, in IsDone
encoding.MessageToPyValue(operation.error)))
OperationError: Error Response: [13] An internal error occurred during deployment.
ERROR: (gcloud.app.deploy) Error Response: [13] An internal error occurred during deployment.

Forbidden: 403 User not authorized even though the user is logged in

I am getting 403 error on Mac trying to hit a URL that uses the Python client:
Traceback (most recent call last):
File "/Users/cchilders/.virtualenvs/myproject/lib/python2.7/site-packages/flask/app.py", line 1639, in full_dispatch_request
rv = self.dispatch_request()
File "/Users/cchilders/.virtualenvs/myproject/lib/python2.7/site-packages/flask/app.py", line 1625, in dispatch_request
return self.view_functions[rule.endpoint](**req.view_args)
File "/Users/cchilders/work_projects/myproject/myproject/blueprints/admin.py", line 25, in health
return admin.Health.read()
File "/Users/cchilders/work_projects/myproject/myproject/views/admin.py", line 52, in read
if not topic.exists():
File "/Users/cchilders/.virtualenvs/myproject/lib/python2.7/site-packages/gcloud-0.18.3-py2.7.egg/gcloud/pubsub/topic.py", line 179, in exists
api.topic_get(topic_path=self.full_name)
File "/Users/cchilders/.virtualenvs/myproject/lib/python2.7/site-packages/gcloud-0.18.3-py2.7.egg/gcloud/pubsub/connection.py", line 171, in topic_get
return conn.api_request(method='GET', path='/%s' % (topic_path,))
File "/Users/cchilders/.virtualenvs/ourapi/lib/python2.7/site-packages/gcloud-0.18.3-py2.7.egg/gcloud/connection.py", line 347, in api_request
error_info=method + ' ' + url)
Forbidden: 403 User not authorized to perform this action. (GET https://pubsub.googleapis.com/v1/projects/myproject/topics/mytopic)
127.0.0.1 - - [10/Nov/2016 16:40:58] "GET /admin/health/ HTTP/1.1" 500 -
views/admin.py
ps = pubsub.Client()
topic = ps.topic(application.config['PUBSUB_TOPIC'])
# topic.project = application.config['PUBSUB_PROJECT']
t_component = Component()
t_component.name = 'topic'
t_component.status = 'UP'
t_component.desc = ('{} exists and is healthy.'
.format(topic.full_name))
if not topic.exists():
t_component.status = 'DOWN'
t_component.desc = (
'Configured PUBSUB topic ({}) does not exist.'
.format(topic.full_name)
)
I created the topic/subscription so I have permissions. My config and gcloud user is correct, I did gcloud auth ... and double-checked. I'm the only one getting this error and I did have my personal account used on this laptop to practice the gcloud tutorial. My coworker thought using that other account in the past may cause an issue. I checked my config and the project I'm pointing to, it's the right project.
There is a difference between gcloud auth login and gcloud auth application-default login
Re-logging in under gcloud auth application-default login fixed

Google App Engine configuring Endpoints API

I have a problem configuring Endpoints API. Any code i use, from my own, to google's examples on site fail with the same traceback
WARNING 2016-11-01 06:16:48,279 client.py:229] no scheduler thread, scheduler.run() will be invoked by report(...)
Traceback (most recent call last):
File "/home/vladimir/projects/sb_fork/sb/lib/vendor/google/api/control/client.py", line 225, in start
self._thread.start()
File "/home/vladimir/sdk/google-cloud-sdk/platform/google_appengine/google/appengine/api/background_thread/background_thread.py", line 108, in start
start_new_background_thread(self.__bootstrap, ())
File "/home/vladimir/sdk/google-cloud-sdk/platform/google_appengine/google/appengine/api/background_thread/background_thread.py", line 87, in start_new_background_thread
raise ERROR_MAP[error.application_error](error.error_detail)
FrontendsNotSupported
INFO 2016-11-01 06:16:48,280 client.py:327] created a scheduler to control flushing
INFO 2016-11-01 06:16:48,280 client.py:330] scheduling initial check and flush
INFO 2016-11-01 06:16:48,288 client.py:804] Refreshing access_token
/home/vladimir/projects/sb_fork/sb/lib/vendor/urllib3/contrib/appengine.py:113: AppEnginePlatformWarning: urllib3 is using URLFetch on Google App Engine sandbox instead of sockets. To use sockets directly instead of URLFetch see https://urllib3.readthedocs.io/en/latest/contrib.html.
AppEnginePlatformWarning)
ERROR 2016-11-01 06:16:49,895 service_config.py:125] Fetching service config failed (status code 403)
ERROR 2016-11-01 06:16:49,896 wsgi.py:263]
Traceback (most recent call last):
File "/home/vladimir/sdk/google-cloud-sdk/platform/google_appengine/google/appengine/runtime/wsgi.py", line 240, in Handle
handler = _config_handle.add_wsgi_middleware(self._LoadHandler())
File "/home/vladimir/sdk/google-cloud-sdk/platform/google_appengine/google/appengine/runtime/wsgi.py", line 299, in _LoadHandler
handler, path, err = LoadObject(self._handler)
File "/home/vladimir/sdk/google-cloud-sdk/platform/google_appengine/google/appengine/runtime/wsgi.py", line 85, in LoadObject
obj = __import__(path[0])
File "/home/vladimir/projects/sb_fork/sb/main.py", line 27, in <module>
api_app = endpoints.api_server([SolarisAPI,], restricted=False)
File "/home/vladimir/projects/sb_fork/sb/lib/vendor/endpoints/apiserving.py", line 497, in api_server
controller)
File "/home/vladimir/projects/sb_fork/sb/lib/vendor/google/api/control/wsgi.py", line 77, in add_all
a_service = loader.load()
File "/home/vladimir/projects/sb_fork/sb/lib/vendor/google/api/control/service.py", line 110, in load
return self._load_func(**kw)
File "/home/vladimir/projects/sb_fork/sb/lib/vendor/google/api/config/service_config.py", line 78, in fetch_service_config
_log_and_raise(Exception, message_template.format(status_code))
File "/home/vladimir/projects/sb_fork/sb/lib/vendor/google/api/config/service_config.py", line 126, in _log_and_raise
raise exception_class(message)
Exception: Fetching service config failed (status code 403)
INFO 2016-11-01 06:16:49,913 module.py:788] default: "GET / HTTP/1.1" 500 -
My app.yaml is configured like the new Endpoints Migrating to 2.0 document states:
- url: /_ah/api/.*
script: api.solaris.api_app
And main.py imports the API into the app:
api_app = endpoints.api_server([SolarisAPI,], restricted=False)
I use Google Cloud SDK with these versions:
Google Cloud SDK 132.0.0
app-engine-python 1.9.40
bq 2.0.24
bq-nix 2.0.24
core 2016.10.24
core-nix 2016.10.24
gcloud
gsutil 4.22
gsutil-nix 4.22
Have you tried generating and uploading the OpenAPI configuration for the service? See the sections named "Generating the OpenAPI configuration file" and "Deploying the OpenAPI configuration file" in the python library documentation.
Note that in step 2 of the generation process, you may need to prepend python to the command (e.g python lib/endpoints/endpointscfg.py get_swagger_spec ...), since the PyPi package doesn't preserve executable file permissions right now.
To get rid of the "FrontendsNotSupported" you need to use a "B*" instance class.
The error "Exception: Fetching service config failed" should be gone if you follow the steps in https://cloud.google.com/endpoints/docs/frameworks/python/quickstart-frameworks-python. As already pointed out by Brad, the section "OpenAPI configuration" and the resulting environment variables are required to make the service configuration work.

GAE Simple Request Handler only run once

Good day!
https://developers.google.com/appengine/docs/python/gettingstarted/helloworld
this is the hello world that I'm trying to run.
I can seeing the
Hello, world!
Status: 500
message. however it will be turned to a "HTTP Error 500" after I hit the refresh.
and... it seems that the appengine only shows me the good result once after I re-save either app.yaml or helloworld.py
This is the trace for the good result
Traceback (most recent call last):
File "C:\Program Files\Google\google_appengine\google\appengine\runtime\wsgi.py", line 187, in Handle
handler = _config_handle.add_wsgi_middleware(self._LoadHandler())
File "C:\Program Files\Google\google_appengine\google\appengine\runtime\wsgi.py", line 239, in _LoadHandler
raise ImportError('%s has no attribute %s' % (handler, name))
ImportError: <module 'helloworld' from 'D:\work\[GAE] tests\helloworld\helloworld.pyc'> has no attribute app
INFO 2012-06-23 01:47:28,522 dev_appserver.py:2891] "GET /hello HTTP/1.1" 200 -
ERROR 2012-06-23 01:47:30,040 wsgi.py:189]
and this is the trace for the Error 500
Traceback (most recent call last):
File "C:\Program Files\Google\google_appengine\google\appengine\runtime\wsgi.py", line 187, in Handle
handler = _config_handle.add_wsgi_middleware(self._LoadHandler())
File "C:\Program Files\Google\google_appengine\google\appengine\runtime\wsgi.py", line 239, in _LoadHandler
raise ImportError('%s has no attribute %s' % (handler, name))
ImportError: <module 'helloworld' from 'D:\work\[GAE] tests\helloworld\helloworld.pyc'> has no attribute app
INFO 2012-06-23 01:47:30,127 dev_appserver.py:2891] "GET /hello HTTP/1.1" 500 -
here's my helloworld.py
print 'Content-Type: text/plain'
print ''
print 'Hello, world!'
my main.py. (app is used instead of application)
import webapp2
class hello(webapp2.RequestHandler):
def get(self):
self.response.out.write('normal hello')
app = webapp2.WSGIApplication([
('/', hello),
], debug = True)
and the app.yaml
application: helloworld
version: 1
runtime: python27
api_version: 1
threadsafe: true
handlers:
- url: /favicon\.ico
static_files: favicon.ico
upload: favicon\.ico
- url: /hello
script: helloworld.app
- url: /.*
script: main.app
libraries:
- name: webapp2
version: "2.5.1"
any clue what's causing this?
Regards,
You aren't creating a helloworld.app object in your helloworld.py module.
See the lines
app = webapp2.WSGIApplications([...
in your main.py file? That creates the main.app object that's referenced by the script: main.app handler in your app.yaml.
You're referencing a helloworld.app object a couple of lines above; that object doesn't exist. Python 2.7 in App Engine doesn't support the simple module model -- no WSGI handler, just a simple script -- that's used in the 2.5 "Hello World" demo.
As presveva said, use the 2.7 Getting Started guide for less confusion.

Categories