如何使用Google Sheets API V4导入CSV文件-（不覆盖现有数据和跳过重复项）

Question

我正在尝试通过python将.csv文件上传到Google电子表格。我让这项工作进行了一些自己的研究，并通过下面的链接阅读了自己的方式。但我正在寻找一种更高级的方法来进行此操作。

问题：

[API.spreadsheets().batchUpdate覆盖所有现有数据。

目标：

将.csv数据上传到Google表格中，并跳过现有数据以避免重复。

Link to post for uploading a csv file to Google Sheets

注意：我使用@Ufos解决方案

到目前为止，我的代码：

"""
Getting an connection to Google Sheets API and imports a csv file into a sheet and inserts all new data. If
data already exists in file it will ignore it and ony insert data that is not already in the sheet.
"""

# import pickle
from googleapiclient.discovery import build
from google.oauth2.service_account import Credentials

try:
    # for Python2
    from Tkinter import *   ## notice capitalized T in Tkinter
    import tkFileDialog as filedialog
except ImportError:
    # for Python3
    from tkinter import *   ## notice lowercase 't' in tkinter here
    from tkinter import messagebox
    from tkinter import filedialog

import sys

SPREADSHEET_ID = ''  # TODO: Get this one from the link in browser
worksheet_name = ''  # TODO: Insert sheet name
# path_to_csv = ''

# path_to_credentials = 'Credentials/token.pickle'
#path_to_credentials = 'creds.json'

scopes = ["https://spreadsheets.google.com/feeds",
          'https://www.googleapis.com/auth/spreadsheets',
          "https://www.googleapis.com/auth/drive.file",
          "https://www.googleapis.com/auth/drive"]


# convenience routines
def find_sheet_id_by_name(sheet_name):
    # ugly, but works
    sheets_with_properties = API \
        .spreadsheets() \
        .get(spreadsheetId=SPREADSHEET_ID, fields='sheets.properties') \
        .execute() \
        .get('sheets')

    for sheet in sheets_with_properties:
        if 'title' in sheet['properties'].keys():
            if sheet['properties']['title'] == sheet_name:
                return sheet['properties']['sheetId']


def push_csv_to_gsheet(csv_path, sheet_id):
    with open(csv_path, 'r') as csv_file:
        csvContents = csv_file.read()
    body = {
        'requests': [{
            'pasteData': {
                "coordinate": {
                    "sheetId": sheet_id,
                    "rowIndex": "0",  # adapt this if you need different positioning
                    "columnIndex": "0", # adapt this if you need different positioning
                },
                "data": csvContents,
                "type": 'PASTE_NORMAL',
                "delimiter": ';',
            }
        }]
    }
    request = API.spreadsheets().batchUpdate(spreadsheetId=SPREADSHEET_ID, body=body)
    response = request.execute()
    return response


def get_csv_file():
    root_tk = Tk()
    root_tk.withdraw()
    user_prompt_file_path = filedialog.askopenfilename(title='Choose .csv file')  # // initialdir = "C:/<whatever>"
    if len(user_prompt_file_path) == 0:
        sys.exit("Stopped because no csv file was given")

    print(f'File path to csv is: {user_prompt_file_path}')
    return user_prompt_file_path


csv_file_path = get_csv_file()

# upload
# with open(path_to_credentials, 'rb') as token:
#     # credentials = pickle.load(token)
#     credentials = token.read()

credentials = Credentials.from_service_account_file("creds.json", scopes=scopes)

API = build('sheets', 'v4', credentials=credentials)

push_csv_to_gsheet(
    csv_path=csv_file_path,
    sheet_id=find_sheet_id_by_name(worksheet_name)
)

Answer 1

您可以使用list q使用search parameter在云端硬盘中的文件，以检查是否已经存在具有该名称的文件，并避免执行代码。我使用Quickstart中的示例进行了一些修改：

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/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.
    """
    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(port=0)
        # Save the credentials for the next run
        with open('token.pickle', 'wb') as token:
            pickle.dump(creds, token)

    service = build('drive', 'v3', credentials=creds)

    # Call the Drive v3 API
    results = service.files().list(q="name = 'yourFile.csv'",fields="nextPageToken, files(id, name)").execute()
    items = results.get('files', [])

    if not items:
    #------------------------------------  
    # Your uploading code here
    #------------------------------------

    else:
        print('Files:')
        for item in items:
            print(u'{0} ({1})'.format(item['name'], item['id']))

if __name__ == '__main__':
    main()

[有趣的部分始于# Call the Drive v3 API，其余部分可以应用于任何Drive API python代码（当然，将范围更改为所需的范围）。关于快速入门，我只更改了service.files()调用。添加用于将文件上传到if not条件的代码。