Google Client API v3 - update a file on drive using Python - python

I'm trying to update the content of a file from a python script using the google client api. The problem is that I keep receiving error 403:
An error occurred: <HttpError 403 when requesting https://www.googleapis.com /upload/drive/v3/files/...?alt=json&uploadType=resumable returned "The resource body includes fields which are not directly writable.
I have tried to remove metadata fields, but didn't help.
The function to update the file is the following:
# File: utilities.py
from googleapiclient import errors
from googleapiclient.http import MediaFileUpload
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
def update_file(service, file_id, new_name, new_description, new_mime_type,
new_filename):
"""Update an existing file's metadata and content.
Args:
service: Drive API service instance.
file_id: ID of the file to update.
new_name: New name for the file.
new_description: New description for the file.
new_mime_type: New MIME type for the file.
new_filename: Filename of the new content to upload.
new_revision: Whether or not to create a new revision for this file.
Returns:
Updated file metadata if successful, None otherwise.
"""
try:
# First retrieve the file from the API.
file = service.files().get(fileId=file_id).execute()
# File's new metadata.
file['name'] = new_name
file['description'] = new_description
file['mimeType'] = new_mime_type
file['trashed'] = True
# File's new content.
media_body = MediaFileUpload(
new_filename, mimetype=new_mime_type, resumable=True)
# Send the request to the API.
updated_file = service.files().update(
fileId=file_id,
body=file,
media_body=media_body).execute()
return updated_file
except errors.HttpError as error:
print('An error occurred: %s' % error)
return None
And here there is the whole script to reproduce the problem.
The goal is to substitute a file, retrieving its id by name.
If the file does not exist yet, the script will create it by calling insert_file (this function works as expected).
The problem is update_file, posted above.
from __future__ import print_function
from utilities import *
from googleapiclient import errors
from googleapiclient.http import MediaFileUpload
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
def get_authenticated(SCOPES, credential_file='credentials.json',
token_file='token.json', service_name='drive',
api_version='v3'):
# The file token.json stores the user's access and refresh tokens, and is
# created automatically when the authorization flow completes for the first
# time.
store = file.Storage(token_file)
creds = store.get()
if not creds or creds.invalid:
flow = client.flow_from_clientsecrets(credential_file, SCOPES)
creds = tools.run_flow(flow, store)
service = build(service_name, api_version, http=creds.authorize(Http()))
return service
def retrieve_all_files(service):
"""Retrieve a list of File resources.
Args:
service: Drive API service instance.
Returns:
List of File resources.
"""
result = []
page_token = None
while True:
try:
param = {}
if page_token:
param['pageToken'] = page_token
files = service.files().list(**param).execute()
result.extend(files['files'])
page_token = files.get('nextPageToken')
if not page_token:
break
except errors.HttpError as error:
print('An error occurred: %s' % error)
break
return result
def insert_file(service, name, description, parent_id, mime_type, filename):
"""Insert new file.
Args:
service: Drive API service instance.
name: Name of the file to insert, including the extension.
description: Description of the file to insert.
parent_id: Parent folder's ID.
mime_type: MIME type of the file to insert.
filename: Filename of the file to insert.
Returns:
Inserted file metadata if successful, None otherwise.
"""
media_body = MediaFileUpload(filename, mimetype=mime_type, resumable=True)
body = {
'name': name,
'description': description,
'mimeType': mime_type
}
# Set the parent folder.
if parent_id:
body['parents'] = [{'id': parent_id}]
try:
file = service.files().create(
body=body,
media_body=media_body).execute()
# Uncomment the following line to print the File ID
# print 'File ID: %s' % file['id']
return file
except errors.HttpError as error:
print('An error occurred: %s' % error)
return None
# If modifying these scopes, delete the file token.json.
SCOPES = 'https://www.googleapis.com/auth/drive'
def main():
service = get_authenticated(SCOPES)
# Call the Drive v3 API
results = retrieve_all_files(service)
target_file_descr = 'Description of deploy.py'
target_file = 'deploy.py'
target_file_name = target_file
target_file_id = [file['id'] for file in results if file['name'] == target_file_name]
if len(target_file_id) == 0:
print('No file called %s found in root. Create it:' % target_file_name)
file_uploaded = insert_file(service, target_file_name, target_file_descr, None,
'text/x-script.phyton', target_file_name)
else:
print('File called %s found. Update it:' % target_file_name)
file_uploaded = update_file(service, target_file_id[0], target_file_name, target_file_descr,
'text/x-script.phyton', target_file_name)
print(str(file_uploaded))
if __name__ == '__main__':
main()
In order to try the example, is necessary to create a Google Drive API from https://console.developers.google.com/apis/dashboard,
then save the file credentials.js and pass its path to get_authenticated(). The file token.json will be created after the first
authentication and API authorization.

The problem is that the metadata 'id' can not be changed when updating a file, so it should not be in the body. Just delete it from the dict:
# File's new metadata.
del file['id'] # 'id' has to be deleted
file['name'] = new_name
file['description'] = new_description
file['mimeType'] = new_mime_type
file['trashed'] = True
I tried your code with this modification and it works

I also struggled a little bit with the function and found if you don't have to update the metadata then just remove them in the update function like :updated_file = service.files().update(fileId=file_id, media_body=media_body).execute()
At Least that worked for me

The problem is The resource body includes fields which are not directly writable. So try removing all of the metadata properties and then add them back one by one. The one I would be suspicious about is trashed. Even though the API docs say this is writable, it shouldn't be. Trashing a file has side effects beyond setting a boolean. Updating a file and setting it to trashed at the same time is somewhat unusual. Are you sure that's what you intend?

Related

python google api v3 Error on update file

I try to use google drive api v3 in python to update file on google drive using code from official google instruction.
But i receive an Error:
The resource body includes fields which are not directly writable.
How it can be solved?
Here my code i try to use:
try:
# First retrieve the file from the API.
file = service.files().get(fileId='id_file_in_google_drive').execute()
# File's new metadata.
file['title'] = 'new_title'
file['description'] = 'new_description'
file['mimeType'] = 'application/pdf'
# File's new content.
media_body = MediaFileUpload(
'/home/my_file.pdf',
mimetype='application/pdf',
resumable=True)
# Send the request to the API.
updated_file = service.files().update(
fileId='id_file_in_google_drive',
body=file,
media_body=media_body).execute()
return updated_file
except errors:
print('An error occurred: %s')
return None
The issue is that you are using the same object as you got back from the files.get method. The File.update method uses HTTP PATCH methodology, this means that all parameters that you send are going to be updated. This object returned by file.get contains all of the fields for the file object. When you send it to the file.update method you are trying to update a lot of fields which are not updatable.
file = service.files().get(fileId='id_file_in_google_drive').execute()
# File's new metadata.
file['title'] = 'new_title'
file['description'] = 'new_description'
file['mimeType'] = 'application/pdf'
What you should do is create a new object, then update the file using this new object only updating the fields you want to update. Remember in Google Drive v3 its name not title.
file_metadata = {'name': 'new_title' , 'description': 'new description'}
updated_file = service.files().update(
fileId='id_file_in_google_drive',
body=file_metadata ,
media_body=media_body).execute()

mediaItems.search_next() returns 400

Unable to get all results of mediaItems.search:
photos = google.get_service(credentials, 'photoslibrary', 'v1')
request = photos.albums().list(pageSize=50)
while request is not None:
result = request.execute()
for album in result['albums']:
request2 = photos.mediaItems().search(body={'albumId': album['id']})
while request2 is not None:
result2 = request2.execute()
request2 = photos.mediaItems().search_next(request2, result2)
print('nextpageToken' in result2, request2)
request = photos.albums().list_next(request, result)
Running this fails on the first search_next() call with
[...]
File "/usr/local/lib/python3.7/dist-packages/googleapiclient/_helpers.py", line 130, in positional_wrapper
return wrapped(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/googleapiclient/http.py", line 851, in execute
raise HttpError(resp, content, uri=self.uri)
googleapiclient.errors.HttpError: <HttpError 400 when requesting https://photoslibrary.googleapis.com/v1/mediaItems:search?alt=json returned "Invalid JSON payload received. Unexpected end of string. Expected an object key or }.
That library isn't really supported it seems, so that might be the problem, or am I missing something here?
The google-api-python-client is generic client for all the Google's discovery based APIs and as such it supports all the API based on this protocol including the Photos one.
The correct way to use the services is to invoke the build method and after that use the available methods of the services.
Beside this you always want to use list_next as search_next does not exists.
Here is an example of the photos API working on my laptop (python 3.6)
import os
import pickle
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
SCOPES = ['https://www.googleapis.com/auth/photoslibrary.readonly', ]
# we check if we save the credentials in the past and we reuse them
if not os.path.exists('credentials.dat'):
# no credentials found, we run the standard auth flow
flow = InstalledAppFlow.from_client_secrets_file('client_id.json', SCOPES)
credentials = flow.run_local_server()
with open('credentials.dat', 'wb') as credentials_dat:
pickle.dump(credentials, credentials_dat)
else:
with open('credentials.dat', 'rb') as credentials_dat:
credentials = pickle.load(credentials_dat)
if credentials.expired:
credentials.refresh(Request())
photos_sdk = build('photoslibrary', 'v1', credentials=credentials)
# photos API
photos_albums_api = photos_sdk.albums()
photos_mediaitems_api = photos_sdk.mediaItems()
albums_list_params = {
'pageSize': 50,
}
# first request
albums_list_req = photos_albums_api.list(**albums_list_params)
while albums_list_req is not None:
photos_albums_list = albums_list_req.execute()
# print(photos_albums_list)
for album in photos_albums_list['albums']:
print(album['title'])
mediaitems_search_req = photos_mediaitems_api.search(body={'albumId': album['id']})
while mediaitems_search_req is not None:
mediaitems_search = mediaitems_search_req.execute()
print(mediaitems_search)
# mediaItems pagination management
mediaitems_search_req = photos_mediaitems_api.list_next(mediaitems_search_req, mediaitems_search)
# albums pagination handling
albums_list_req = photos_albums_api.list_next(albums_list_req, photos_albums_list)
If there are more results than the specified pageSize, the API returns a pageToken, you should use to request the next part. See the example here Access Google Photo API with Python using google-api-python-client

YouTube API Python upload_video.py run from script, not command line

I have the youtube script that YouTube supplies installed and working, but I can only figure out how to use it from the command line.
For example to upload a file, I use the command prompt and enter
python upload_video.py --file="temp/british.mp4" --title="Summer vacation in California" --description="Had fun surfing in Santa Cruz" --keywords="surfing,Santa Cruz" --category="22" --privacyStatus="private" which will upload the file using the parameters.
My question is, how would I go about having script start.py, and then run something like the above command prompt command from within start.py, calling upon the parameters and passing them though to video_upload.py? I am trying to call the command three times in a row in the start.py script for three different videos. I am using Python 2.7.
I have figured out how to do it via os.system with
import os
os.system("python video_upload.py --file=\"temp/british.mp4\" --title=\"Summer vacation in California\" --description=\"Had fun surfing in Santa Cruz\" --keywords=\"surfing,Santa Cruz\" --category=\"22\" --privacyStatus=\"private\"")
But this done externally and not done straight in Python as I would like to capture the 'id' that is printed out at the end.
#!/usr/bin/python
import httplib
import httplib2
import os
import random
import sys
import time
from apiclient.discovery import build
from apiclient.errors import HttpError
from apiclient.http import MediaFileUpload
from oauth2client.client import flow_from_clientsecrets
from oauth2client.file import Storage
from oauth2client.tools import argparser, run_flow
# Explicitly tell the underlying HTTP transport library not to retry, since
# we are handling retry logic ourselves.
httplib2.RETRIES = 1
# Maximum number of times to retry before giving up.
MAX_RETRIES = 10
# Always retry when these exceptions are raised.
RETRIABLE_EXCEPTIONS = (httplib2.HttpLib2Error, IOError, httplib.NotConnected,
httplib.IncompleteRead, httplib.ImproperConnectionState,
httplib.CannotSendRequest, httplib.CannotSendHeader,
httplib.ResponseNotReady, httplib.BadStatusLine)
# Always retry when an apiclient.errors.HttpError with one of these status
# codes is raised.
RETRIABLE_STATUS_CODES = [500, 502, 503, 504]
# The CLIENT_SECRETS_FILE variable specifies the name of a file that contains
# the OAuth 2.0 information for this application, including its client_id and
# client_secret. You can acquire an OAuth 2.0 client ID and client secret from
# the Google Developers Console at
# https://console.developers.google.com/.
# Please ensure that you have enabled the YouTube Data API for your project.
# For more information about using OAuth2 to access the YouTube Data API, see:
# https://developers.google.com/youtube/v3/guides/authentication
# For more information about the client_secrets.json file format, see:
# https://developers.google.com/api-client-library/python/guide/aaa_client_secrets
CLIENT_SECRETS_FILE = "client_secrets.json"
# This OAuth 2.0 access scope allows an application to upload files to the
# authenticated user's YouTube channel, but doesn't allow other types of access.
YOUTUBE_UPLOAD_SCOPE = "https://www.googleapis.com/auth/youtube.upload"
YOUTUBE_API_SERVICE_NAME = "youtube"
YOUTUBE_API_VERSION = "v3"
# This variable defines a message to display if the CLIENT_SECRETS_FILE is
# missing.
MISSING_CLIENT_SECRETS_MESSAGE = """
WARNING: Please configure OAuth 2.0
To make this sample run you will need to populate the client_secrets.json file
found at:
%s
with information from the Developers Console
https://console.developers.google.com/
For more information about the client_secrets.json file format, please visit:
https://developers.google.com/api-client-library/python/guide/aaa_client_secrets
""" % os.path.abspath(os.path.join(os.path.dirname(__file__),
CLIENT_SECRETS_FILE))
VALID_PRIVACY_STATUSES = ("public", "private", "unlisted")
def get_authenticated_service(args):
flow = flow_from_clientsecrets(CLIENT_SECRETS_FILE,
scope=YOUTUBE_UPLOAD_SCOPE,
message=MISSING_CLIENT_SECRETS_MESSAGE)
storage = Storage("%s-oauth2.json" % sys.argv[0])
credentials = storage.get()
if credentials is None or credentials.invalid:
credentials = run_flow(flow, storage, args)
return build(YOUTUBE_API_SERVICE_NAME, YOUTUBE_API_VERSION,
http=credentials.authorize(httplib2.Http()))
def initialize_upload(youtube, options):
tags = None
if options.keywords:
tags = options.keywords.split(",")
body=dict(
snippet=dict(
title=options.title,
description=options.description,
tags=tags,
categoryId=options.category
),
status=dict(
privacyStatus=options.privacyStatus
)
)
# Call the API's videos.insert method to create and upload the video.
insert_request = youtube.videos().insert(
part=",".join(body.keys()),
body=body,
# The chunksize parameter specifies the size of each chunk of data, in
# bytes, that will be uploaded at a time. Set a higher value for
# reliable connections as fewer chunks lead to faster uploads. Set a lower
# value for better recovery on less reliable connections.
#
# Setting "chunksize" equal to -1 in the code below means that the entire
# file will be uploaded in a single HTTP request. (If the upload fails,
# it will still be retried where it left off.) This is usually a best
# practice, but if you're using Python older than 2.6 or if you're
# running on App Engine, you should set the chunksize to something like
# 1024 * 1024 (1 megabyte).
media_body=MediaFileUpload(options.file, chunksize=-1, resumable=True)
)
resumable_upload(insert_request)
# This method implements an exponential backoff strategy to resume a
# failed upload.
def resumable_upload(insert_request):
response = None
error = None
retry = 0
while response is None:
try:
print "Uploading file..."
status, response = insert_request.next_chunk()
if 'id' in response:
print "Video id '%s' was successfully uploaded." % response['id']
else:
exit("The upload failed with an unexpected response: %s" % response)
except HttpError, e:
if e.resp.status in RETRIABLE_STATUS_CODES:
error = "A retriable HTTP error %d occurred:\n%s" % (e.resp.status,
e.content)
else:
raise
except RETRIABLE_EXCEPTIONS, e:
error = "A retriable error occurred: %s" % e
if error is not None:
print error
retry += 1
if retry > MAX_RETRIES:
exit("No longer attempting to retry.")
max_sleep = 2 ** retry
sleep_seconds = random.random() * max_sleep
print "Sleeping %f seconds and then retrying..." % sleep_seconds
time.sleep(sleep_seconds)
if __name__ == '__main__':
argparser.add_argument("--file", required=True, help="Video file to upload")
argparser.add_argument("--title", help="Video title", default="Test Title")
argparser.add_argument("--description", help="Video description",
default="Test Description")
argparser.add_argument("--category", default="22",
help="Numeric video category. " +
"See https://developers.google.com/youtube/v3/docs/videoCategories/list")
argparser.add_argument("--keywords", help="Video keywords, comma separated",
default="")
argparser.add_argument("--privacyStatus", choices=VALID_PRIVACY_STATUSES,
default=VALID_PRIVACY_STATUSES[0], help="Video privacy status.")
args = argparser.parse_args()
if not os.path.exists(args.file):
exit("Please specify a valid file using the --file= parameter.")
youtube = get_authenticated_service(args)
try:
initialize_upload(youtube, args)
except HttpError, e:
print "An HTTP error %d occurred:\n%s" % (e.resp.status, e.content)
Have you tried using
your_string = raw_input('Enter your string here: ')
Then you would be able to type your string in the console running your start.py

Getting started with Google Analytics Reporting API for Python

I am just starting with the Google Analytics Reporting API and used the Hello API tutorial to get started. (https://developers.google.com/analytics/solutions/articles/hello-analytics-api)
Unfortunately, I am stuck before I even start. I read it (twice). Created the project, updates the client_secrets.jason file... but when I run the main, it crashes.
File "C:\Python27\New Libraries Downloaded\analytics-v3-python-cmd-line\hello_analytics_api_v3.py", line 173, in <module>
main(sys.argv)
File "C:\Python27\New Libraries Downloaded\analytics-v3-python-cmd-line\hello_analytics_api_v3.py", line 56, in main
service, flags = sample_tools.init(argv, 'analytics', 'v3', __doc__, __file__, scope='https://www.googleapis.com/auth/analytics.readonly')
NameError: global name '__file__' is not defined
I'm new (really really new) to this, so any help (and a more detailed tutorial) would be much appreciated.
Thanks !
EDIT: I have't changed anything from the original code in the tutorial. I'll worry about modifications after I get this running. Thanks !
CODE: hello_analytics_api_v3.py
import argparse
import sys
from apiclient.errors import HttpError
from apiclient import sample_tools
from oauth2client.client import AccessTokenRefreshError
def main(argv):
# Authenticate and construct service.
service, flags = sample_tools.init(argv, 'analytics', 'v3', __doc__, __file__, scope='https://www.googleapis.com/auth/analytics.readonly')
# Try to make a request to the API. Print the results or handle errors.
try:
first_profile_id = get_first_profile_id(service)
if not first_profile_id:
print 'Could not find a valid profile for this user.'
else:
results = get_top_keywords(service, first_profile_id)
print_results(results)
except TypeError, error:
# Handle errors in constructing a query.
print ('There was an error in constructing your query : %s' % error)
except HttpError, error:
# Handle API errors.
print ('Arg, there was an API error : %s : %s' % (error.resp.status, error._get_reason()))
except AccessTokenRefreshError:
# Handle Auth errors.
print ('The credentials have been revoked or expired, please re-run ','the application to re-authorize')
def get_first_profile_id(service):
"""Traverses Management API to return the first profile id.
This first queries the Accounts collection to get the first account ID.
This ID is used to query the Webproperties collection to retrieve the first
webproperty ID. And both account and webproperty IDs are used to query the
Profile collection to get the first profile id.
Args:
service: The service object built by the Google API Python client library.
Returns:
A string with the first profile ID. None if a user does not have any
accounts, webproperties, or profiles.
"""
accounts = service.management().accounts().list().execute()
if accounts.get('items'):
firstAccountId = accounts.get('items')[0].get('id')
webproperties = service.management().webproperties().list(
accountId=firstAccountId).execute()
if webproperties.get('items'):
firstWebpropertyId = webproperties.get('items')[0].get('id')
profiles = service.management().profiles().list(
accountId=firstAccountId,
webPropertyId=firstWebpropertyId).execute()
if profiles.get('items'):
return profiles.get('items')[0].get('id')
return None
def get_top_keywords(service, profile_id):
"""Executes and returns data from the Core Reporting API.
This queries the API for the top 25 organic search terms by visits.
Args:
service: The service object built by the Google API Python client library.
profile_id: String The profile ID from which to retrieve analytics data.
Returns:
The response returned from the Core Reporting API.
"""
return service.data().ga().get(
ids='ga:' + profile_id,
start_date='2012-01-01',
end_date='2012-01-15',
metrics='ga:visits',
dimensions='ga:source,ga:keyword',
sort='-ga:visits',
filters='ga:medium==organic',
start_index='1',
max_results='25').execute()
def print_results(results):
"""Prints out the results.
This prints out the profile name, the column headers, and all the rows of
data.
Args:
results: The response returned from the Core Reporting API.
"""
print
print 'Profile Name: %s' % results.get('profileInfo').get('profileName')
print
# Print header.
output = []
for header in results.get('columnHeaders'):
output.append('%30s' % header.get('name'))
print ''.join(output)
# Print data table.
if results.get('rows', []):
for row in results.get('rows'):
output = []
for cell in row:
output.append('%30s' % cell)
print ''.join(output)
else:
print 'No Rows Found'
if __name__ == '__main__':
main(sys.argv)
according to the error the program doesn't recognize 'file'. In IPython this error comes up (not 100% sure why) but this error shouldn't come up when running a file. In a file the 'file' argument will return the full path and the file name.
Try creating a file and running from there or simply paste in a the full path and file name instead.
Also be sure that the client secrets are located in the same folder as your script!

S3ResponseError: 403 Forbidden using boto

I have a script that copy files from one S3 account to another S3 account, It was working befoure!!!! That's for sure. Than I tried it today and it doesn't any more it gives me error S3ResponseError: 403 Forbidden. I'm 100% sure credentials are correct and I can go and download keys from both accounts manualy using aws console.
Code
def run(self):
while True:
# Remove and return an item from the queue
key_name = self.q.get()
k = Key(self.s_bucket, key_name)
d_key = Key(self.d_bucket, k.key)
if not d_key.exists() or k.etag != d_key.etag:
print 'Moving {file_name} from {s_bucket} to {d_bucket}'.format(
file_name = k.key,
s_bucket = source_bucket,
d_bucket = dest_bucket
)
# Create a new key in the bucket by copying another existing key
acl = self.s_bucket.get_acl(k)
self.d_bucket.copy_key( d_key.key, self.s_bucket.name, k.key, storage_class=k.storage_class)
d_key.set_acl(acl)
else:
print 'File exist'
self.q.task_done()
Error:
File "s3_to_s3.py", line 88, in run
self.d_bucket.copy_key( d_key.key, self.s_bucket.name, k.key, storage_class=k.storage_class)
File "/usr/lib/python2.7/dist-packages/boto/s3/bucket.py", line 689, in copy_key
response.reason, body)
S3ResponseError: S3ResponseError: 403 Forbidden
<Error><Code>AccessDenied</Code><Message>Access Denied</Message><RequestId>0729E8ADBD7A9E60</RequestId><HostId>PSbbWCLBtLAC9cjW+52X1fUSVErnZeN79/w7rliDgNbLIdCpc9V0bPi8xO9fp1od</HostId></Error>
Try this: copy key from source bucket to destination bucket using boto's Key class
source_key_name = 'image.jpg' # for example
#return Key object
source_key = source_bucket.get_key(source_key_name)
#use Key.copy
source_key.copy(destination_bucket,source_key_name)
regarding the copy function. you can set preserve_acl to True and it will be copied from the source key.
Boto's Key.copy signature:
def copy(self, dst_bucket, dst_key, metadata=None,
reduced_redundancy=False, preserve_acl=False,
encrypt_key=False, validate_dst_bucket=True):

Categories

Resources