I have a python script to match files on google drive in specific folder. It worked fine with my GSuite account in the company. But If i want to use it at home with my simple Google Drive account it's not working. No files found:
Here is my code:
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
from apiclient.http import MediaFileUpload
from apiclient import errors
import io
from apiclient.http import MediaIoBaseDownload
from apiclient import errors
import os
import csv
try :
import argparse
flags = argparse.ArgumentParser(parents=[tools.argparser]).parse_args()
except ImportError:
flags = None
folder_id = 'XYZ00000'
SCOPES = 'https://www.googleapis.com/auth/drive.file'
store = file.Storage('storage.json')
creds = store.get()
if not creds or creds.invalid:
print("Create new data storage file ...")
flow = client.flow_from_clientsecrets('client_secrets.json', SCOPES)
flow.redirect_uri = client.OOB_CALLBACK_URN
authorize_url = flow.step1_get_authorize_url()
creds = tools.run_flow(flow, store, flags) \
if flags else tools.run(flow, store)
print ("Storage")
DRIVE = build('drive', 'v2', http=creds.authorize(Http()))
def getKeywordsID():
page_token = None
while True:
response = DRIVE.files().list(q="'XYZ00000' in parents and trashed = false",
spaces='drive',
fields='nextPageToken, items(id, title)',
pageToken=page_token).execute()
for file in response.get('items', []):
if ('test.txt' == file.get('title')):
print ('test.txt on Google Drive found')
page_token = response.get('nextPageToken', None)
if page_token is None:
break;
return file_id
# Download file
file_id = getKeywordsID()
if file_id != None:
request = DRIVE.files().get_media(fileId=file_id)
fh = io.FileIO('test.txt', 'wb')
downloader = MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print ("Download test.txt %d%%." % int(status.progress() * 100) )
else:
print ("File not found.")
I have no idea why it's not working. I enabled Google Drive API, created a project, added an OAuth2.0 client ID (select “Other” as option) and downloaded the json file for storage.
From the traceback posted, I can see that in the getKeywordsID function you are returning the file_id variable, which you have not initialized in the getKeywordsID function scope. Hence the UnboundLocalError: local variable 'file_id' referenced before assignment is thrown.
Related
I installed Google Drive on my computer (Windows 11 x64) to drive G:\
I want to be able to get a shared link for a specific file/folder that I have a path to.
Google Drive will have duplicate file/folder.
How can i do this whith python?
Thanks in advance
Edited:
I managed to get a link for specific file name, but now I have a problem if there are 2+ files with the same file name in Google Drive.
For example I want link of this file G:\RootFolder\Subfolder1\Subfolder2\myfile.txt but there is another file with same name G:\RootFolder\Subfolder3\Subfolder4\Subfolder5\myfile.txt. How can I give link only for G:\RootFolder\Subfolder1\Subfolder2\myfile.txt ?
from Google import Create_Service
CLIENT_SECRET_FILE = 'client-secret.json'
API_NAME = 'drive'
API_VERSION = 'v3'
SCOPES = ['https://www.googleapis.com/auth/drive']
service = Create_Service(CLIENT_SECRET_FILE, API_NAME, API_VERSION, SCOPES)
# Update Sharing Setting
file_id = '<file id>'
request_body = {
'role': 'reader',
'type': 'anyone'
}
response_permission = service.permissions().create(
fileId=file_id,
body=request_body
).execute()
print(response_permission)
# Print Sharing URL
response_share_link = service.files().get(
fileId=file_id,
fields='webViewLink'
).execute()
print(response_share_link)
# Remove Sharing Permission
service.permissions().delete(
fileId=file_id,
permissionId='anyoneWithLink'
).execute()
I managed to create script that works for me.
Packages: pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib
from __future__ import print_function
import argparse
import os.path
from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
# According the guide https://developers.google.com/drive/api/quickstart/python
# TODO: First time - Create "credentials.json" file https://developers.google.com/workspace/guides/create-credentials#oauth-client-id
# TODO: First time - Enable the Google Drive API https://developers.google.com/drive/api/guides/enable-drive-api
def is_folder_name_in_parents(service, parents, folder_name):
for parent_id in parents:
response = service.files().get(fileId=parent_id, fields='name').execute()
if folder_name == response.get("name"):
return parent_id
return None
def is_correct_file_path(service, folder_path, parents, root_folder_name, root_folder_id):
folder_name = os.path.basename(folder_path)
if folder_name == root_folder_name and root_folder_id in parents:
return True
parent_id = is_folder_name_in_parents(service=service, parents=parents, folder_name=folder_name)
if not parent_id:
return False
response = service.files().get(fileId=parent_id, fields='parents').execute()
new_parents = response.get("parents")
return is_correct_file_path(service=service,
folder_path=os.path.dirname(folder_path),
parents=new_parents,
root_folder_name=root_folder_name,
root_folder_id=root_folder_id)
def get_sharing_link_by_path(root_folder_name, root_folder_id, filepath):
# If modifying these scopes, delete the file token.json.
SCOPES = ['https://www.googleapis.com/auth/drive.metadata.readonly']
"""Shows basic usage of the Drive v3 API.
Prints the names and ids of the first 10 files the user has access to.
"""
creds = None
# 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.
if os.path.exists('token.json'):
creds = Credentials.from_authorized_user_file('token.json', SCOPES)
# If there are no (valid) credentials available, let the user log in.
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file('credentials.json', SCOPES)
creds = flow.run_local_server(port=0)
# Save the credentials for the next run
with open('token.json', 'w') as token:
token.write(creds.to_json())
try:
service = build('drive', 'v3', credentials=creds)
filename = os.path.basename(filepath)
folder_path = os.path.dirname(filepath)
page_token = None
while True:
response = service.files().list(
q=f"name='{filename}'",
spaces='drive',
fields='nextPageToken, files(name, webViewLink, parents)',
pageToken=page_token
).execute()
print(f"There are {len(response.get('files', []))} results in Google Drive for: {filename}")
for file in response.get('files', []):
if "parents" in file.keys():
if is_correct_file_path(service=service,
folder_path=folder_path,
parents=file["parents"],
root_folder_name=root_folder_name,
root_folder_id=root_folder_id):
if 'webViewLink' in file.keys():
print(f"File path: {filename}\nWeb View Link: {file['webViewLink']}")
return file['webViewLink']
print(f"Web view link for this file not found: {filepath}")
return None
page_token = response.get('nextPageToken', None)
if page_token is None:
print(f"File not found: {filepath}")
return None
except HttpError as error:
# TODO(developer) - Handle errors from drive API.
print(f'An error occurred: {error}')
from __future__ import print_function
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
# If modifying these scopes, delete the file token.json.
SCOPES = 'https://www.googleapis.com/auth/drive.metadata.readonly'
def main():
"""Shows basic usage of the Drive v3 API.
Prints the names and ids of the first 10 files the user has access to.
"""
store = file.Storage('token.json')
creds = store.get()
if not creds or creds.invalid:
flow = client.flow_from_clientsecrets('credentials.json', SCOPES)
creds = tools.run_flow(flow, store)
service = build('drive', 'v3', http=creds.authorize(Http()))
# Call the Drive v3 API
results = service.files().list(
pageSize=10, fields="nextPageToken, files(id, name)").execute()
items = results.get('files', [])
if not items:
print('No files found.')
else:
print('Files:')
for item in items:
print('{0} ({1})'.format(item['name'], item['id']))
if __name__ == '__main__':
main()
save as quickstart.py and run this file , The authentication flow has completed.
then token.json was generated in the directory.
now to download doc file
file_id = '1wzCjl51u131v1KBgpbiKLJs8DPPakhXCFosfYjp7BY0'
request = service.files().get_media(fileId=file_id)
fh = io.BytesIO()
downloader = MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print ("Download %d%%." % int(status.progress() * 100))
id was copied from
https://docs.google.com/document/d/1wzCjl51u131v1KBgpbiKLJs8DPPakhXCFosfYjp7BY0/edit?usp=sharing
and request = drive_service.files().get_media(fileId=file_id)
change to
request = service.files().get_media(fileId=file_id)
in the example as saved as p.py
when executed
line 2, in <module>
request = service.files().get_media(fileId=file_id)
NameError: name 'service' is not defined
I am going to have to assume you have not merged these two files. THe second script needs the service (variable) within your first script to run they should be merged.
from __future__ import print_function
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
# If modifying these scopes, delete the file token.json.
SCOPES = 'https://www.googleapis.com/auth/drive.metadata.readonly'
def main():
"""Shows basic usage of the Drive v3 API.
Prints the names and ids of the first 10 files the user has access to.
"""
store = file.Storage('token.json')
creds = store.get()
if not creds or creds.invalid:
flow = client.flow_from_clientsecrets('credentials.json', SCOPES)
creds = tools.run_flow(flow, store)
service = build('drive', 'v3', http=creds.authorize(Http()))
# Call the Drive v3 API
rfile_id = '1wzCjl51u131v1KBgpbiKLJs8DPPakhXCFosfYjp7BY0'
request = service.files().get_media(fileId=file_id)
fh = io.BytesIO()
downloader = MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print ("Download %d%%." % int(status.progress() * 100))
if __name__ == '__main__':
main()
Here is how I do it
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file
SCOPES = ['https://www.googleapis.com/auth/drive.readonly']
def login_gdrive(SCOPES):
store = file.Storage('../personal_token.json')
creds = store.get()
return build('drive', 'v3', http=creds.authorize(Http()))
def gdrive_download(file_id):
request = drive_service.files().get(fileId=file_id)
result = request.execute()
#will return metadata of file but I will only get file name
file_name = result['name']
print(f"File name is {file_name}")
#will get actual file
request = drive_service.files().get_media(fileId=file_id)
result = request.execute()
print("Downloading " + file_name)
#will write file using the file_name
with open(file_name, mode="wb") as f:
f.write(result)
print("Finished writing " + file_name)
drive_service = login_gdrive(SCOPES)
gdrive_download('1oiD6h-ixAUTIWebEdN-jV8MO0sssoQTI')
out... File name is sample_data_2018-10-21.csv
out... Downloading sample_data_2018-10-21.csv
out... Finished writing sample_data2018-10-21.csv
This script works for small files, but not when I try to upload a large file (250MB). When I manually upload the same large file to GD it takes less than 10 seconds, so I assume my connection is not the problem.
upload.py
from __future__ import print_function
import os
import sys
from apiclient.http import MediaFileUpload
from apiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
try:
import argparse
flags = argparse.ArgumentParser(parents=[tools.argparser]).parse_args()
except ImportError:
flags = None
SCOPES = 'https://www.googleapis.com/auth/drive.file'
store = file.Storage(r'C:\Users\lucas.rezende\.credentials\storage.json')
creds = store.get()
if not creds or creds.invalid:
flow = client.flow_from_clientsecrets(r'C:\Users\lucas.rezende\.credentials\client_secret.json', scope=SCOPES)
creds = tools.run_flow(flow, store, flags) if flags else tools.run(flow, store)
DRIVE = build('drive', 'v3', http=creds.authorize(Http()))
FILES = (
('OfertasMensais_20170418_n.xlsx', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'),
)
for filename, mimeType in FILES:
media_body = MediaFileUpload(filename, chunksize=1024*256, resumable = True)
folder_id = '0000'
metadata = {'name': filename, 'parents': [folder_id]}
if mimeType:
metadata['mimeType'] = mimeType
res = DRIVE.files().create(body=metadata, media_body=filename).execute()
if res:
print('Uploaded "%s" (%s)' % (filename, res['mimeType']))
When I run python uploadfile.py cmd screen stays like that eternally:
Can someone help to discover how to make this work? I am not a professional programmer and I am stuck into this for almost two hours trying to make this work.
Following the chunked paradigm, you need to specifically call the next_chunk() to continue with an upload. see here: https://developers.google.com/api-client-library/python/guide/media_upload#resumable-media-chunked-upload
for filename, mimeType in FILES:
media_body = MediaFileUpload(filename, chunksize=1024*256, resumable = True)
if mimeType:
metadata['mimeType'] = mimeType
req = DRIVE.files().insert(body=metadata, media_body=filename)
res = None
while res is None:
status, res = req.next_chunk()
if status :
print('Uploading %d%% "%s" (%s)' % (status.progress(), filename, res['mimeType']))
print("Upload Complete!")
The solution for this with v3 is to use the chunked approach, but with the create() function rather than insert()
res = None
media_body = MediaFileUpload(filename, chunksize=1024*256, resumable = True)
drive_request = self.drive.files().create(body=metadata,media_body=media_body)
while res is None:
status, res = drive_request.next_chunk()
My goal is to have a list of all of the items & folders in everyone's Google Drive. I'm starting with trying to make sure the script works on my own. I have read cover-to-cover the Drive REST API documentation, and eventually found this code, which can also be found here.
from __future__ import print_function
import httplib2
import os
import sys
from apiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage
reload(sys)
sys.setdefaultencoding('utf-8')
try:
import argparse
flags = argparse.ArgumentParser(parents=[tools.argparser]).parse_args()
except ImportError:
flags = None
# If modifying these scopes, delete your previously saved credentials
# at ~/.credentials/drive-python-quickstart.json
SCOPES = 'https://www.googleapis.com/auth/drive.metadata.readonly'
CLIENT_SECRET_FILE = 'client_secret.json'
APPLICATION_NAME = 'Drive 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,
'drive-python-quickstart.json')
store = 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 main():
"""Shows basic usage of the Google Drive API.
Creates a Google Drive API service object and outputs the names and IDs
for up to 10 files.
"""
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
service = discovery.build('drive', 'v3', http=http)
results = service.files().list(
pageSize=1000,fields="nextPageToken, files(mimeType, name)").execute()
items = results.get('files', [])
if not items:
print('No files found.')
else:
print('Files:')
for item in items:
print('{0} ({1})'.format(item['name'], item['mimeType']))
if __name__ == '__main__':
main()
My problem is with the nextPageToken, and how to properly use it. The max PageSize is 1000, so I must loop over the nextPageToken, fetch it from the resulting JSON, put it back into the original loop (line 66?), to get another 1000 results. How do I do this?
Let's look the google drive api documentation for the File:list Method
In the fields of your request you are asking the nextPageToken, the result will contain the token for the nextPage (if the nextPage exists).
The result will be something like this :
{
...,
"nextPageToken": "V1*3|0|XXXXXX",
"files": [
{
...
},...
]
}
you can extract nextPageToken value like :
token = results.get('nextPageToken', None)
The List method can take the string parameter pageToken :
The token for continuing a previous list request on the next page.
This should be set to the value of 'nextPageToken' from the previous
response.
Just set the parameter pageToken in the next request to get the next page of results :
results = service.files().list(
pageSize=1000,
pageToken=token,
fields="nextPageToken, files(mimeType, name)").execute()
items = results.get('files', [])
Now you can easily make a loop to get all result.
I will try to demonstrate the concept for you but you'll do the implementation in Python. The short answer is, nextPageToken. nextPageTokens enable you to retrieve the results from the next page.
When you perform a GET request, a nextPageToken will always be included in the response so if you had 1000 results but you only wanted to display 20 per page, you can fetch the remaining 980 files using nextPageToken.
Run this URL and you'll see something like:
"kind": "drive#fileList",
"nextPageToken": "V1*3|0|CjkxOHY2aDdROE9JYkJGWUJEaU5Ybm1OVURSemJTcWFMa2lRQlVJSnVxYmI2YkYzMmhnVHozeWkwRnASBxCqqcG4kis",
"incompleteSearch": false,
The value of the nextPageToken here is what you use to get to the next page. When you get to the next page and you have more results, a new nextPageToken will be generated for you until you view/get all the results (980-1000).
You must looping while token (for the nextpage) is not null, like this code at the end:
(do not forget to install -->
pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib
Copy and paste this code (Do not forget to change your paths and your googleDrive folder ID, at the end)
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
from googleapiclient.http import MediaFileUpload, MediaIoBaseDownload
# If modifying these scopes, delete the file token.pickle.
SCOPES = [
'https://www.googleapis.com/auth/spreadsheets',
"https://www.googleapis.com/auth/drive.file",
"https://www.googleapis.com/auth/drive"
]
# FOR AUTHENTICATION
def authenticate():
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'YOUR PATH FOR THE CREDENTIALS JSON/credentials.json', SCOPES)
creds = flow.run_local_server(port=0)
with open('YOUR PATH /token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('drive', 'v3', credentials=creds)
return service
# LISTS TO TAKE ALL FILES AND IDs FROM SPECIFIC FOLDER
listFilesDrive=[]
line = []
# TO TAKE ALL FILES FROM SPECIFIC FOLDER
def listFilesFromGoogleFolder(IDFolder):
service = authenticate()
# Call the Drive v3 API
results = service.files().list( q="'{}' in parents".format(FolderIDFromGDrive),
fields="nextPageToken, files(id, name)").execute()
items = results.get('files', [])
# TAKE TOKEN FROM THE NEXT PAGE (IF THERE IS NO ONE, THIS VALUE WILL BE NULL)
token = results.get('nextPageToken', None)
#print('token->>',nextPageToken)
if not items:
print('No files found.')
else:
print('Files:')
line = []
for item in items:
# TAKE FIRST PAGE IN A LIST ->> "listFilesDrive"
arquivo = item['name']
IDarquivo = item['id']
line.append(arquivo)
line.append(IDarquivo)
listFilesDrive.append(line)
line=[]
print(u'{0} ({1})'.format(item['name'], item['id']))
# LOOPING WHILE TOKEN FOR OTHER PAGES IS NOT NULL TOKEN
while token!=None:
service = authenticate()
results = service.files().list( q="'{}' in parents".format(IDFolder),
pageToken=token,
fields="nextPageToken, files(id, name)").execute()
items = results.get('files', [])
# TAKE A NEW TOKEN FOR THE NEXT PAGE, IF THERE IS NO, THIS TOKEN WILL BE NULL ("None")
token = results.get('nextPageToken', None)
if not items:
print('No files found.')
else:
print('Files:')
linha = []
for item in items:
arquivo = item['name']
IDarquivo = item['id']
line.append(arquivo)
line.append(IDarquivo)
listFilesDrive.append(line)
line=[]
print(u'{0} ({1})'.format(item['name'], item['id']))
print(len(listFilesDrive))
print(listFilesDrive)
# put your specific information
if __name__ == '__main__':
FolderIDFromGDrive='YOUR FOLDER ID'
listFilesFromGoogleFolder(FolderIDFromGDrive)
I had quite a bit of trouble with this. I didn't read the example closely enough to notice that nextPageToken & newStartPageToken were not the same thing.
I split up the functions a little and added a loop. Basically, return the startPageToken and loop over the same function / call the function as required.
from __future__ import print_function
import httplib2
import os
#julian
import time
from apiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage
try:
import argparse
flags = argparse.ArgumentParser(parents=[tools.argparser]).parse_args()
except ImportError:
flags = None
# If modifying these scopes, delete your previously saved credentials
# at ~/.credentials/drive-python-quickstart.json
SCOPES = 'https://www.googleapis.com/auth/drive.metadata.readonly'
CLIENT_SECRET_FILE = 'client_secret.json'
APPLICATION_NAME = 'Drive 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,'drive-python-quickstart.json')
store = 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 main():
"""Shows basic usage of the Google Drive API.
Creates a Google Drive API service object and outputs the names and IDs
for up to 10 files.
"""
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
service = discovery.build('drive', 'v3', http=http)
saved_start_page_token = StartPage_v3(service)
saved_start_page_token = DetectChanges_v3(service, saved_start_page_token)
starttime=time.time()
while True:
saved_start_page_token = DetectChanges_v3(service, saved_start_page_token)
time.sleep(10.0 - ((time.time() - starttime) % 10.0))
def StartPage_v3(service):
response = service.changes().getStartPageToken().execute()
print('Start token: %s' % response.get('startPageToken'))
return response.get('startPageToken')
def DetectChanges_v3(service, saved_start_page_token):
# Begin with our last saved start token for this user or the
# current token from getStartPageToken()
page_token = saved_start_page_token;
while page_token is not None:
response = service.changes().list(pageToken=page_token, spaces='drive').execute()
for change in response.get('changes'):
# Process change
mimeType = change.get('file').get('mimeType')
print( 'Change found for: %s' % change)
if 'newStartPageToken' in response:
# Last page, save this token for the next polling interval
saved_start_page_token = response.get('newStartPageToken')
page_token = response.get('nextPageToken')
return saved_start_page_token
if __name__ == '__main__':
main()
I am trying to download a spreadsheet file from my drive to my computer.
I am able to authenticate, get list of files and even get meta-data successfully.
But when I try to download the file, I get the following error :
downloading file starts
An error occurred: <HttpError 400 when requesting https://www.googleapis.com/dri
ve/v2/files/1vJetI_p8YEYiKvPVl0LtXGS5uIAx1eRGUupsXoh7UbI?alt=media returned "The
specified file does not support the requested alternate representation.">
downloading file ends
I couldn't get any such problem or question on SO and the other methods or solutions provided on SO for downloading the spreadsheet are outdated.Those have been deprecated by Google .
Here is the code, I am using to download the file :
import httplib2
import os
from apiclient import discovery
import oauth2client
from oauth2client import client
from oauth2client import tools
from apiclient import errors
from apiclient import http
try:
import argparse
flags = argparse.ArgumentParser(parents=[tools.argparser]).parse_args()
except ImportError:
flags = None
#SCOPES = 'https://www.googleapis.com/auth/drive.metadata.readonly'
SCOPES = 'https://www.googleapis.com/auth/drive'
CLIENT_SECRET_FILE = 'client_secrets.json'
APPLICATION_NAME = 'Drive API Quickstart'
def get_credentials():
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,
'drive-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 compatability with Python 2.6
credentials = tools.run(flow, store)
print 'Storing credentials to ' + credential_path
return credentials
def main():
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
service = discovery.build('drive', 'v2', http=http)
file_id = '1vJetI_p8YEYiKvPVl0LtXGS5uIAx1eRGUupsXoh7UbI'
print "downloading file starts"
download_file(service, file_id)
print "downloading file ends "
def download_file(service, file_id):
local_fd = open("foo.csv", "w+")
request = service.files().get_media(fileId=file_id)
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError, error:
print 'An error occurred: %s' % error
return
if download_progress:
print 'Download Progress: %d%%' % int(download_progress.progress() * 100)
if done:
print 'Download Complete'
return
if __name__ == '__main__':
main()
Google spreadsheets don't have media. Instead they have exportLinks. Get the file metadata, then look in the exportlinks and pick an appropriate URL.
This code worked for me. I only had to download client_secret.json from google developers dashboard and keep in the same directory as python script.
And in the list_of_lists variable I got a list with each row as list.
import gspread
import json
from oauth2client.client import SignedJwtAssertionCredentials
json_key = json.load(open('client_secret.json'))
scope = ['https://spreadsheets.google.com/feeds']
credentials = SignedJwtAssertionCredentials(json_key['client_email'], json_key['private_key'], scope)
gc = gspread.authorize(credentials)
sht1 = gc.open_by_key('<id_of_sheet>')
worksheet_list = sht1.worksheets()
worksheet = sht1.sheet1
list_of_lists = worksheet.get_all_values()
for row in list_of_lists :
print row