Canvas LMS script to export course assignment/quiz grades into Excel sheets.

canvas-export.py

"""MIT License

Copyright (c) 2024 Mate Cserep, https://mcserep.web.elte.hu/

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
"""

### SETTINGS ###
# Base URL of your Canvas instance
base_url = 'https://canvas.elte.hu'
# Create a new token at the '<base_url>/profile/settings' page.
access_token = 'INSERT YOUR ACCESS TOKEN'
# Define the course name part to look for
course_name_match = 'Programming'

### PROGRAM ###
import requests
import pandas as pd
import numpy as np
import time

class CourseExporter():
    def __init__(self, course):
        self.course = course
        self.__assignments = 0
        self.__submissions = 0

    def collect(self):
        course_name = self.course['course_code']        
        print(f'Exporting {course_name} ... ')            
        self.get_users()
        self.get_assignments()

    def write(self):
        if self.__submissions == 0:
            print('Not writing output, would be empty.')
            return
        
        course_name = self.course['course_code']
        filename = course_name.replace('/', '_') + '.xlsx'        
        self.df.to_excel(filename)            
        print(f'Output written: {filename}')    

    def get_users(self):
        course_id = self.course['id']
        
        page = 1
        has_more_pages = True
        ids = []
        names = []
        
        while has_more_pages:
            response = requests.get(f'{base_url}/api/v1/courses/{course_id}/enrollments', {
                'access_token': access_token,
                'type[]': 'StudentEnrollment',
                'per_page': 50,
                'page': page
            })
            response.raise_for_status()
            handle_throttling(response)
            enrollments = response.json()
            
            page += 1
            has_more_pages = len(enrollments) > 0
            
            for enrollment in enrollments:
                if enrollment['user_id'] not in ids:
                    ids.append(enrollment['user_id'])
                    names.append(enrollment['user']['name'])
        
        print(f'Found {len(names)} students');
        self.df = pd.DataFrame({'UserId': ids, 'Name': names})
        self.df.set_index('UserId', inplace = True)

    def get_assignments(self):
        course_id = self.course['id']
        
        page = 1
        has_more_pages = True
        
        while has_more_pages:
            response = requests.get(f'{base_url}/api/v1/courses/{course_id}/assignments', {
                'access_token': access_token,
                'per_page': 50,
                'page': page
            })
            response.raise_for_status()
            handle_throttling(response)
            assignments = response.json()
            
            page += 1
            has_more_pages = len(assignments) > 0
            
            for assignment in assignments:    
                assignment_id = assignment['id']
                assignment_name = assignment['name']
                self.df[assignment_name] = [None] * len(self.df.index)
                self.get_submissions(assignment_id, assignment_name)
        
        self.__assignments = self.df.shape[1] - 1
        print(f'Found {self.__assignments} assignments')
        self.__submissions = np.sum(self.df.count()) - len(self.df.index)
        print(f'Found {self.__submissions} graded submissions')

    def get_submissions(self, assignment_id: int, assignment_name: str):
        course_id = self.course['id']
        
        page = 1
        has_more_pages = True
        
        while has_more_pages:
            response = requests.get(f'{base_url}/api/v1/courses/{course_id}/assignments/{assignment_id}/submissions', {
                'access_token': access_token,
                'per_page': 50,
                'page': page
            })
            response.raise_for_status()
            handle_throttling(response)
            submissions = response.json()
            
            page += 1
            has_more_pages = len(submissions) > 0
            
            for submission in submissions:
                if submission['grader_id'] is not None:
                    student_id = submission['user_id']
                    self.df.loc[student_id, assignment_name] = submission['score']

# see: https://canvas.instructure.com/doc/api/file.throttling.html
def handle_throttling(response: requests.Response):
    rate_limit = float(response.headers['X-Rate-Limit-Remaining'])
    sleep_time = 0
    if rate_limit < 100:
        sleep_time = 30
    elif rate_limit < 200:
        sleep_time = 15
    
    if sleep_time > 0:
        print(f'Canvas API throttling, waiting {sleep_time} seconds ...', end = ' ', flush = True)
        time.sleep(sleep_time)
        print(' done')

# main
try:
    page = 1
    has_more_pages = True
    while has_more_pages:
        response = requests.get(f'{base_url}/api/v1/courses', {
            'access_token': access_token,
            'per_page': 50,
            'page': page
        })
        response.raise_for_status()
        handle_throttling(response)
        courses = response.json()
        
        page += 1
        has_more_pages = len(courses) > 0
        
        for course in courses:
            if course_name_match.lower() not in course['course_code'].lower():
                continue
            
            exporter = CourseExporter(course)
            exporter.collect()
            exporter.write()
            print()

except requests.exceptions.RequestException as err:
    print('Canvas communication error occurred, HTTP response code: {0}'.format(err.response.status_code))
    print('Response: {0}'.format(err.response.text))

requirements.txt

certifi==2024.8.30
charset-normalizer==3.4.0
et_xmlfile==2.0.0
idna==3.10
numpy==2.1.3
openpyxl==3.1.5
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
requests==2.32.3
six==1.16.0
tzdata==2024.2
urllib3==2.2.3