charcount_thesis.py

from apiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
from time import time
from datetime import datetime


def main():
    service = setup_api()
    file_ids = get_files_in_folder(service, folder_id="folder_id")
    service = setup_api(version='v3')
    wc = get_wordcount(service, file_ids)
    now = datetime.fromtimestamp(time()).strftime('%Y-%m-%d %H:%M:%S')
    print(f"{now}\t{wc}")


def setup_api(version='v2'):
    """
    Load api, or open browser for authorization
    If you adapt the scopes you have to delete the credentials.json file
    to enable reauthorization
    """
    SCOPES = (
        'https://www.googleapis.com/auth/drive.metadata.readonly',
        'https://www.googleapis.com/auth/drive.file',
        'https://www.googleapis.com/auth/drive',
        'https://www.googleapis.com/auth/spreadsheets.readonly',
    )
    store = file.Storage('credentials.json')
    client_secret = 'client_secret.json'
    creds = store.get()
    if not creds or creds.invalid:
        flow = client.flow_from_clientsecrets(client_secret, SCOPES)
        creds = tools.run_flow(flow, store)
    return build('drive', version, http=creds.authorize(Http()))


def get_files_in_folder(service, folder_id):
    """Return files belonging to a folder."""
    page_token = None
    ids = []
    while True:
        param = {}
        if page_token:
            param['pageToken'] = page_token
        files = service.children().list(folderId=folder_id, **param).execute()
        ids.extend([f['id'] for f in files['items']])
        page_token = files.get('nextPageToken')
        if not page_token:
            break
    return ids


def get_wordcount(service, file_ids):
    """Return the total wordcount of the list of files.
    Ignore line breaks and underscores (titles)
    """
    character_count = 0
    for f in file_ids:
        data = service.files().export(fileId=f, mimeType='text/plain').execute()
        if data:
            decoded = data.decode('utf-8')
            character_count += len([i for i in decoded if i not in ['\n', '\r', '_']])
    return character_count


if __name__ == '__main__':
    main()