src/libs/google_drive.py

import json
from google.oauth2 import service_account
from googleapiclient.discovery import build
import requests
from bs4 import BeautifulSoup


def get_pdf_urls_with_root_url(root_url):
    """
    Returns an array of URLs of PDF files in the specified remote directory.

    Parameters:
    root_url (str): The root URL to the directory listing.

    Returns:
    list: A list of URLs to the PDF files in the directory.
    """
    pdf_urls = []

    # Make a request to get the content of the directory
    response = requests.get(root_url)

    if response.status_code == 200:
        # Parse the HTML content
        soup = BeautifulSoup(response.content, 'html.parser')

        # Iterate over all links in the directory listing
        for link in soup.find_all('a'):
            href = link.get('href')
            if href and href.lower().endswith('.pdf'):
                # Construct the full URL for the PDF file
                file_url = root_url.rstrip('/') + '/' + href.lstrip('/')
                pdf_urls.append(file_url)
    else:
        print(f"Failed to access {root_url}, status code: {response.status_code}")

    return pdf_urls


def get_drive_file_urls(service_account_file, folder_id):
    credentials = service_account.Credentials.from_service_account_file(
        service_account_file,
        scopes=['https://www.googleapis.com/auth/drive.readonly'],
    )

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

    query = f"'{folder_id}' in parents"
    results = service.files().list(q=query, fields="files(id, webViewLink)").execute()
    items = results.get('files', [])

    file_urls = [item['webViewLink'] for item in items]

    return file_urls