如何使用 Python / pyodbc 将数据推送到 Google 表格？
How can I use Python / pyodbc to push data to Google Sheets?
前期：我对 Python 非常陌生。 :)
我已经学习了 Google 的 Python Quickstart information, and can successfully connect to my Google Sheet with read/write privilege and clear the sheet for any previous information. Also, I was able to follow the pyodbc docs，并且可以成功连接到我们使用的 MSSQL 服务器并写出 MSSQL table 的 Excel 副本.
但是，我似乎无法弄清楚如何获取附加到 Google Sheet 的 table MSSQL 查询结果。在 VSCode 内，它确实在回溯中提供了最近的调用，而且它似乎工作正常，没有错误。但是，sheet 不会更新。
注意：如果我将 dfListFormat 的值更改为文本字符串，它会在目标范围的 A1 中附加该单个值。
value_range_body = {
"majorDimension": "ROWS",
"values": [
[dfListFormat]
]
}
下面是我目前拥有的完整代码。任何help/advice你们都可以提供将不胜感激。
from __future__ import print_function
import httplib2
import oauth2client
import os
import googleapiclient
import openpyxl
import pandas
import pyodbc
from apiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage
from googleapiclient.discovery import build
from openpyxl import Workbook
from pandas import DataFrame, ExcelWriter
""" This is the code to get raw data from a specific Google Sheet"""
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/sheets.googleapis.com-python-quickstart.json
SCOPES = 'https://www.googleapis.com/auth/spreadsheets'
CLIENT_SECRET_FILE = 'client_secret_noemail.json'
APPLICATION_NAME = 'Google Sheets API Python'
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,
'sheets.googleapis.com-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(flow, store)
print('Storing credentials to ' + credential_path)
return credentials
def main():
"""Shows basic usage of the Sheets API.
Creates a Sheets API service object and prints the names and majors of
students in a sample spreadsheet:
https://docs.google.com/spreadsheets/d/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms/edit
"""
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
discoveryUrl = ('https://sheets.googleapis.com/$discovery/rest?version=v4')
service = discovery.build(
'sheets', 'v4', http=http, discoveryServiceUrl=discoveryUrl)
# Google Sheet Url Link and Range name. Can use tab names to get full page.
spreadsheetId = '[spreadsheetid]'
rangeName = 'tblActiveEmployees'
# TODO: Add desired entries to the request body if needed
clear_values_request_body = {}
# Building Service to Clear Google Sheet
request = service.spreadsheets().values().clear(spreadsheetId=spreadsheetId,
range=rangeName, body=clear_values_request_body)
response = request.execute()
# Prints response that Google Sheet has been cleared
responseText = '\n'.join(
[str(response), 'The Google Sheet has been cleared!'])
print(responseText)
# SQL Server Connection
server = '[SQLServerIP]'
database = '[SQLServerDB]'
username = '[SQLServerUserID]'
password = '[SQLServerPW]'
cnxn = pyodbc.connect('Driver={ODBC Driver 13 for SQL Server};SERVER=' +
server+';DATABASE='+database+';UID='+username+';PWD='+password)
# Sample SQL Query to get Data
sql = 'select * from tblActiveEmployees'
cursor = cnxn.cursor()
cursor.execute(sql)
list(cursor.fetchall())
# Pandas reading values from SQL query, and building table
sqlData = pandas.read_sql_query(sql, cnxn)
# Pandas building dataframe, and exporting .xlsx copy of table
df = DataFrame(data=sqlData)
df.to_excel('tblActiveEmployees.xlsx',
header=True, index=False)
dfListFormat = df.values.tolist()
# How the input data should be interpreted.
value_input_option = 'USER_ENTERED' # TODO: Update placeholder value.
# How the input data should be inserted.
insert_data_option = 'OVERWRITE' # TODO: Update placeholder value.
value_range_body = {
"majorDimension": "ROWS",
"values": [
[dfListFormat]
]
}
request = service.spreadsheets().values().append(spreadsheetId=spreadsheetId, range=rangeName,
valueInputOption=value_input_option, insertDataOption=insert_data_option, body=value_range_body)
response = request.execute()
if __name__ == '__main__':
main()
感谢@tehhowch 的输入，以下内容能够解决我的问题。问题是我的数据已经在列表中，并且将其用作 "values": [[dfListFormat]] 使 "values" 成为数组数组的数组，而不仅仅是数组数组。简单地分配给 "values" 没有括号就可以完美地工作。
下面是更新后的代码，非常感谢 tehhowch！
from __future__ import print_function
import httplib2
import oauth2client
import os
import googleapiclient
import openpyxl
import pandas
import pyodbc
from googleapiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage
from openpyxl import Workbook
from pandas import DataFrame, ExcelWriter
""" This is the code to get raw data from a specific Google Sheet"""
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/sheets.googleapis.com-python-quickstart.json
SCOPES = 'https://www.googleapis.com/auth/spreadsheets'
CLIENT_SECRET_FILE = 'client_secret_noemail.json'
APPLICATION_NAME = 'Google Sheets API Python'
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,
'sheets.googleapis.com-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(flow, store)
print('Storing credentials to ' + credential_path)
return credentials
def main():
"""Shows basic usage of the Sheets API.
Creates a Sheets API service object and prints the names and majors of
students in a sample spreadsheet:
https://docs.google.com/spreadsheets/d/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms/edit
"""
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
discoveryUrl = ('https://sheets.googleapis.com/$discovery/rest?version=v4')
service = googleapiclient.discovery.build(
'sheets', 'v4', http=http, discoveryServiceUrl=discoveryUrl)
# Google Sheet Url Link and Range name. Can use tab names to get full page.
spreadsheetId = '[spreadsheetID'
rangeName = 'tblActiveEmployees'
# TODO: Add desired entries to the request body if needed
clear_values_request_body = {}
# Building Service to Clear Google Sheet
request = service.spreadsheets().values().clear(spreadsheetId=spreadsheetId,
range=rangeName, body=clear_values_request_body)
response = request.execute()
# Prints response that Google Sheet has been cleared
responseText = '\n'.join(
[str(response), 'The Google Sheet has been cleared!'])
print(responseText)
# SQL Server Connection
server = '[SQLServerIP]'
database = '[SQLServerDB]'
username = '[SQLServerUserID]'
password = '[SQLServerPW]'
cnxn = pyodbc.connect('Driver={ODBC Driver 13 for SQL Server};SERVER=' +
server+';DATABASE='+database+';UID='+username+';PWD='+password)
# Sample SQL Query to get Data
sql = 'select * from tblActiveEmployees'
cursor = cnxn.cursor()
cursor.execute(sql)
list(cursor.fetchall())
# Pandas reading values from SQL query, and building table
sqlData = pandas.read_sql_query(sql, cnxn)
# Pandas building dataframe, and exporting .xlsx copy of table
df = DataFrame(data=sqlData)
df.to_excel('tblActiveEmployees.xlsx',
header=True, index=False)
dfHeaders = df.columns.values.tolist()
dfHeadersArray = [dfHeaders]
dfData = df.values.tolist()
print(dfHeaders)
print(dfData)
# How the input data should be interpreted.
value_input_option = 'USER_ENTERED' # TODO: Update placeholder value.
# How the input data should be inserted.
insert_data_option = 'OVERWRITE' # TODO: Update placeholder value.
value_range_body = {
"majorDimension": "ROWS",
"values": dfHeadersArray + dfData
}
request = service.spreadsheets().values().append(spreadsheetId=spreadsheetId, range=rangeName,
valueInputOption=value_input_option, insertDataOption=insert_data_option, body=value_range_body)
response = request.execute()
if __name__ == '__main__':
main()
前期：我对 Python 非常陌生。 :)
我已经学习了 Google 的 Python Quickstart information, and can successfully connect to my Google Sheet with read/write privilege and clear the sheet for any previous information. Also, I was able to follow the pyodbc docs，并且可以成功连接到我们使用的 MSSQL 服务器并写出 MSSQL table 的 Excel 副本.
但是，我似乎无法弄清楚如何获取附加到 Google Sheet 的 table MSSQL 查询结果。在 VSCode 内，它确实在回溯中提供了最近的调用，而且它似乎工作正常，没有错误。但是，sheet 不会更新。
注意：如果我将 dfListFormat 的值更改为文本字符串，它会在目标范围的 A1 中附加该单个值。
value_range_body = {
"majorDimension": "ROWS",
"values": [
[dfListFormat]
]
}
下面是我目前拥有的完整代码。任何help/advice你们都可以提供将不胜感激。
from __future__ import print_function
import httplib2
import oauth2client
import os
import googleapiclient
import openpyxl
import pandas
import pyodbc
from apiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage
from googleapiclient.discovery import build
from openpyxl import Workbook
from pandas import DataFrame, ExcelWriter
""" This is the code to get raw data from a specific Google Sheet"""
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/sheets.googleapis.com-python-quickstart.json
SCOPES = 'https://www.googleapis.com/auth/spreadsheets'
CLIENT_SECRET_FILE = 'client_secret_noemail.json'
APPLICATION_NAME = 'Google Sheets API Python'
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,
'sheets.googleapis.com-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(flow, store)
print('Storing credentials to ' + credential_path)
return credentials
def main():
"""Shows basic usage of the Sheets API.
Creates a Sheets API service object and prints the names and majors of
students in a sample spreadsheet:
https://docs.google.com/spreadsheets/d/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms/edit
"""
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
discoveryUrl = ('https://sheets.googleapis.com/$discovery/rest?version=v4')
service = discovery.build(
'sheets', 'v4', http=http, discoveryServiceUrl=discoveryUrl)
# Google Sheet Url Link and Range name. Can use tab names to get full page.
spreadsheetId = '[spreadsheetid]'
rangeName = 'tblActiveEmployees'
# TODO: Add desired entries to the request body if needed
clear_values_request_body = {}
# Building Service to Clear Google Sheet
request = service.spreadsheets().values().clear(spreadsheetId=spreadsheetId,
range=rangeName, body=clear_values_request_body)
response = request.execute()
# Prints response that Google Sheet has been cleared
responseText = '\n'.join(
[str(response), 'The Google Sheet has been cleared!'])
print(responseText)
# SQL Server Connection
server = '[SQLServerIP]'
database = '[SQLServerDB]'
username = '[SQLServerUserID]'
password = '[SQLServerPW]'
cnxn = pyodbc.connect('Driver={ODBC Driver 13 for SQL Server};SERVER=' +
server+';DATABASE='+database+';UID='+username+';PWD='+password)
# Sample SQL Query to get Data
sql = 'select * from tblActiveEmployees'
cursor = cnxn.cursor()
cursor.execute(sql)
list(cursor.fetchall())
# Pandas reading values from SQL query, and building table
sqlData = pandas.read_sql_query(sql, cnxn)
# Pandas building dataframe, and exporting .xlsx copy of table
df = DataFrame(data=sqlData)
df.to_excel('tblActiveEmployees.xlsx',
header=True, index=False)
dfListFormat = df.values.tolist()
# How the input data should be interpreted.
value_input_option = 'USER_ENTERED' # TODO: Update placeholder value.
# How the input data should be inserted.
insert_data_option = 'OVERWRITE' # TODO: Update placeholder value.
value_range_body = {
"majorDimension": "ROWS",
"values": [
[dfListFormat]
]
}
request = service.spreadsheets().values().append(spreadsheetId=spreadsheetId, range=rangeName,
valueInputOption=value_input_option, insertDataOption=insert_data_option, body=value_range_body)
response = request.execute()
if __name__ == '__main__':
main()
感谢@tehhowch 的输入，以下内容能够解决我的问题。问题是我的数据已经在列表中，并且将其用作 "values": [[dfListFormat]] 使 "values" 成为数组数组的数组，而不仅仅是数组数组。简单地分配给 "values" 没有括号就可以完美地工作。
下面是更新后的代码，非常感谢 tehhowch！
from __future__ import print_function
import httplib2
import oauth2client
import os
import googleapiclient
import openpyxl
import pandas
import pyodbc
from googleapiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage
from openpyxl import Workbook
from pandas import DataFrame, ExcelWriter
""" This is the code to get raw data from a specific Google Sheet"""
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/sheets.googleapis.com-python-quickstart.json
SCOPES = 'https://www.googleapis.com/auth/spreadsheets'
CLIENT_SECRET_FILE = 'client_secret_noemail.json'
APPLICATION_NAME = 'Google Sheets API Python'
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,
'sheets.googleapis.com-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(flow, store)
print('Storing credentials to ' + credential_path)
return credentials
def main():
"""Shows basic usage of the Sheets API.
Creates a Sheets API service object and prints the names and majors of
students in a sample spreadsheet:
https://docs.google.com/spreadsheets/d/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms/edit
"""
credentials = get_credentials()
http = credentials.authorize(httplib2.Http())
discoveryUrl = ('https://sheets.googleapis.com/$discovery/rest?version=v4')
service = googleapiclient.discovery.build(
'sheets', 'v4', http=http, discoveryServiceUrl=discoveryUrl)
# Google Sheet Url Link and Range name. Can use tab names to get full page.
spreadsheetId = '[spreadsheetID'
rangeName = 'tblActiveEmployees'
# TODO: Add desired entries to the request body if needed
clear_values_request_body = {}
# Building Service to Clear Google Sheet
request = service.spreadsheets().values().clear(spreadsheetId=spreadsheetId,
range=rangeName, body=clear_values_request_body)
response = request.execute()
# Prints response that Google Sheet has been cleared
responseText = '\n'.join(
[str(response), 'The Google Sheet has been cleared!'])
print(responseText)
# SQL Server Connection
server = '[SQLServerIP]'
database = '[SQLServerDB]'
username = '[SQLServerUserID]'
password = '[SQLServerPW]'
cnxn = pyodbc.connect('Driver={ODBC Driver 13 for SQL Server};SERVER=' +
server+';DATABASE='+database+';UID='+username+';PWD='+password)
# Sample SQL Query to get Data
sql = 'select * from tblActiveEmployees'
cursor = cnxn.cursor()
cursor.execute(sql)
list(cursor.fetchall())
# Pandas reading values from SQL query, and building table
sqlData = pandas.read_sql_query(sql, cnxn)
# Pandas building dataframe, and exporting .xlsx copy of table
df = DataFrame(data=sqlData)
df.to_excel('tblActiveEmployees.xlsx',
header=True, index=False)
dfHeaders = df.columns.values.tolist()
dfHeadersArray = [dfHeaders]
dfData = df.values.tolist()
print(dfHeaders)
print(dfData)
# How the input data should be interpreted.
value_input_option = 'USER_ENTERED' # TODO: Update placeholder value.
# How the input data should be inserted.
insert_data_option = 'OVERWRITE' # TODO: Update placeholder value.
value_range_body = {
"majorDimension": "ROWS",
"values": dfHeadersArray + dfData
}
request = service.spreadsheets().values().append(spreadsheetId=spreadsheetId, range=rangeName,
valueInputOption=value_input_option, insertDataOption=insert_data_option, body=value_range_body)
response = request.execute()
if __name__ == '__main__':
main()