将Google表格放入Pandas Dataframe

Question

I am looking for a code which would help me get an excel printed automatically of a google sheet using Python

I have tried a few codes, but to no success

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



# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/Dummy Dataset.readonly']

# The ID and range of a sample spreadsheet.
SAMPLE_SPREADSHEET_ID = '1NXenqaum6PHsDBXyv-_tGKIL-z4tSaCsZpUT9Q5wpkY'
SAMPLE_RANGE_NAME = 'Sheet1!A1:L'

def main():
    """Shows basic usage of the Sheets API.
    Prints values from a sample spreadsheet.
    """
    creds = None
    # The file token.pickle 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.pickle'):
        with open('token.pickle', 'rb') as token:
            creds = pickle.load(token)
    # 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()
        # Save the credentials for the next run
        with open('token.pickle', 'wb') as token:
            pickle.dump(creds, token)

    service = build('sheets', 'v4', credentials=creds)

    # Call the Sheets API
    sheet = service.spreadsheets()
    result = sheet.values().get(spreadsheetId=SAMPLE_SPREADSHEET_ID,
                                range=SAMPLE_RANGE_NAME).execute()
    values = result.get('values', [])

    if not values:
        print('No data found.')
    else:

        for row in values:
            # Print columns A and E, which correspond to indices 0 and 4.
            print('%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s' % (row[0], row[1], row[2], row[3], row[4], row[5], row[6], row[7], row[8], row[9], row[10], row[11]))

if __name__ == '__main__':
main()  

While I am able to print the google sheet, I am not able to store into a dataframe, such that I can later print it into an excel workbook

Answer 1

This is how I got a working Google Sheets to Pandas dataframe, with help from Google's Python Quickstart page & an article that I found on Medium , and tailored to meet my needs.

# This works in Python 3.6+
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
import os.path
import pickle
import pandas as pd


SCOPES = ["https://www.googleapis.com/auth/spreadsheets.readonly"]
SPREADSHEET_ID = YOUR_ID_GOES_HERE
RANGE_NAME = YOUR_RANGE_GOES_HERE


def get_google_sheet(spreadsheet_id, range_name):
    """ Retrieve sheet data using OAuth credentials and Google Python API. """
    creds = None
    # The file token.pickle 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.pickle"):
        with open("token.pickle", "rb") as token:
            creds = pickle.load(token)
    # 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()
        # Save the credentials for the next run
        with open("token.pickle", "wb") as token:
            pickle.dump(creds, token)
    service = build("sheets", "v4", credentials=creds)

    return (
        service.spreadsheets()
        .values()
        .get(spreadsheetId=spreadsheet_id, range=range_name)
        .execute()
    )


def to_dataframe(gsheet):
    """ Converts Google sheet data to a Pandas DataFrame.
    Note: This script assumes that your data contains a header file on the first row!
    Also note that the Google API returns 'none' from empty cells - in order for the code
    below to work, you'll need to make sure your sheet doesn't contain empty cells,
    or update the code to account for such instances.
    """
    return pd.DataFrame(gsheet.get("values")[1:], columns=gsheet.get("values")[0])