我有一个 google drive 文件夹,里面有很多文件夹,然后这些文件夹里面还有其他文件夹/文件等等......我正在使用这个代码列出父文件夹中的所有文件夹/文件,我我将文件/文件夹放在这样的数据框中:
import pickle
import os.path
import io
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
from numpy import cumproduct
import pandas as pd
import gdown
from pyasn1.type.constraint import ContainedSubtypeConstraint
import requests
from googleapiclient.http import MediaIoBaseDownload
import httplib2
SCOPES = ['https://www.googleapis.com/auth/drive']
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(
'test.json', SCOPES)
creds = flow.run_local_server(port=0)
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('drive', 'v3', credentials=creds)
folder_id='valid folder id'
query=f"parents = '{folder_id}'"
response=service.files().list(pageSize=1000, q=query).execute()
files=response.get('files')
nextPageToken=response.get('nextPageToken')
while nextPageToken:
response=service.files().list(pageSize=1000, pageToken=nextPageToken, q=query).execute()
files.extend(response.get('files'))
nextPageToken=response.get('nextPageToken')
df = pd.DataFrame(files)
print(df)
这是我得到的输出:
kind id name mimeType
0 drive#file valid id Testfolder application/vnd.google-apps.folder
. . . . .
. . . . .
. . . . .
2000 drive#file valid id Testfolder2000 application/vnd.google-apps.folder
如何修改此代码以同时列出子文件夹中的所有文件?
假设父文件夹名称是 root 并且我在此路径中有文件:root/folder1/folder2/folder.../test.png
。所以,我想要的输出是在一个数据框中包含所有文件/文件夹。