Downloads student submissions in Google Classroom programatically and group them into folders based on name of students.

gcr.py

"""
This script helps you (as a teacher in Google Classroom) download all the files submitted by students.
I'm not sure where I partially copy pasted this from, but some parts have been modified by me to suit my needs.


Have fun!
- Nathan Adhitya

---

How to operate:

Preparing the script (conda example):
```bash
conda create -n gcr
conda activate gcr
pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib --user
```

Operating the script:
1. Create a Google Cloud Platform project (if you haven't)
2. Enable the Google Classroom API
3. Enable the Google Drive API
4. In the OAuth2 consent screen, add the scopes present in the SCOPES list
5. Create a desktop client for the OAuth 2.0 Client ID
6. Download the credentials, rename it as credentials.json and place it in the same directory as gcr.py
7. Run the script `python ./gcr.py`
"""

from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
import google.auth
from googleapiclient.discovery import build
from googleapiclient.http import MediaIoBaseDownload
import os
import time

# If modifying these scopes, delete the file token.json.
SCOPES = [
    "https://www.googleapis.com/auth/classroom.courses.readonly",
    "https://www.googleapis.com/auth/classroom.coursework.students",
    "https://www.googleapis.com/auth/classroom.student-submissions.students.readonly",
    "https://www.googleapis.com/auth/classroom.profile.emails",
    "https://www.googleapis.com/auth/drive.readonly",
    "https://www.googleapis.com/auth/classroom.rosters.readonly",
]

creds = None
# The file token.json 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.json"):
    creds = Credentials.from_authorized_user_file("token.json", SCOPES)
# 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.json", "w") as token:
        token.write(creds.to_json())

service = build("classroom", "v1", credentials=creds)
drive_service = build("drive", "v3", credentials=creds)


# List classes and prompt to pick one
def list_classes():
    results = service.courses().list(pageSize=10).execute()
    courses = results.get("courses", [])
    if not courses:
        print("No courses found.")
        return None
    for i, course in enumerate(courses):
        print(f"{i + 1}. {course['name']}")

    print("\r")
    time.sleep(0.5)
    choice = int(input("Pick a class by number: ")) - 1
    return courses[choice]["id"], courses[choice]["name"]


# List assignments and prompt to pick one
def list_assignments(course_id):
    results = service.courses().courseWork().list(courseId=course_id).execute()
    assignments = results.get("courseWork", [])
    if not assignments:
        print("No assignments found.")
        return None
    # assignments.sort(key=lambda x: x["dueDate"], reverse=True)
    for i, assignment in enumerate(assignments):
        print(f"{i + 1}. {assignment['title']} (Due: {assignment['dueDate']})")

    print("\r")
    time.sleep(0.5)
    choice = int(input("Pick an assignment by number: ")) - 1
    return assignments[choice]["id"], assignments[choice]["title"]


# Download files submitted by students
def download_files(course_id, assignment_id, assignment_name):
    results = (
        service.courses()
        .courseWork()
        .studentSubmissions()
        .list(courseId=course_id, courseWorkId=assignment_id)
        .execute()
    )
    submissions = results.get("studentSubmissions", [])
    if not submissions:
        print("No submissions found.")
        return

    print(f"Found {len(submissions)} submissions.")
    print("\r")
    time.sleep(0.1)

    for submission in submissions:
        student_id = submission["userId"]
        student_name = (
            service.userProfiles().get(userId=student_id).execute()["name"]["fullName"]
        )

        print(f"Processing submission from {student_name}...")
        if "assignmentSubmission" in submission:
            assignment_submission = submission["assignmentSubmission"]
            if "attachments" in assignment_submission:
                print(f"Found {len(assignment_submission['attachments'])} attachments.")

                for attachment in assignment_submission["attachments"]:
                    if "driveFile" in attachment:
                        file_id = attachment["driveFile"]["id"]
                        file_name = attachment["driveFile"]["title"]
                        file_path = (
                            f"files/{assignment_name}/{student_name}/{file_name}"
                        )
                        os.makedirs(os.path.dirname(file_path), exist_ok=True)

                        request = drive_service.files().get_media(fileId=file_id)
                        with open(file_path, "wb") as f:
                            downloader = MediaIoBaseDownload(f, request)
                            done = False
                            while done is False:
                                status, done = downloader.next_chunk()
                                print(f"Download {int(status.progress() * 100)}%.")


course_id, course_name = list_classes()
if course_id:
    assignment_id, assignment_name = list_assignments(course_id)
    if assignment_id:
        download_files(course_id, assignment_id, assignment_name)