-
Notifications
You must be signed in to change notification settings - Fork 1.9k
/
Copy pathsearch_files.py
67 lines (57 loc) · 2.29 KB
/
search_files.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
import pickle
import os
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
from tabulate import tabulate
# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/drive.metadata']
def get_gdrive_service():
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)
return build('drive', 'v3', credentials=creds)
def search(service, query):
# search for the file
result = []
page_token = None
while True:
response = service.files().list(q=query,
spaces="drive",
fields="nextPageToken, files(id, name, mimeType)",
pageToken=page_token).execute()
# iterate over filtered files
for file in response.get("files", []):
result.append((file["id"], file["name"], file["mimeType"]))
page_token = response.get('nextPageToken', None)
if not page_token:
# no more files
break
return result
def main():
# filter to text files
filetype = "text/plain"
# authenticate Google Drive API
service = get_gdrive_service()
# search for files that has type of text/plain
search_result = search(service, query=f"mimeType='{filetype}'")
# convert to table to print well
table = tabulate(search_result, headers=["ID", "Name", "Type"])
print(table)
if __name__ == '__main__':
main()