An almost-pure python script to download all files off of Canvas

canvas_daemon.py

from typing import Any, Dict, Literal, Optional
import urllib.parse
import urllib.request
import requests
import urllib
import re
import os
import platform
import subprocess
import sys

def sanitize_for_dirname(s:str):
    s = re.sub(pattern=r'[^\w\d]', repl='_', string=s.lower())
    s = re.sub(pattern=r'([\_]{2,})', repl='_', string=s)
    return s

class CanvasAPI:
    COURSES_ENDPOINT = 'api/v1/courses'
    COURSE_FILES_ENDPOINT = 'api/v1/courses/{course_id}/files'

    def __init__(self, scheme:Literal['http', 'https']='https', netloc:str='canvas.instructure.com', access_token:Optional[str]=None, max_notify:int=3):
        self.scheme = scheme
        self.netloc = netloc
        self.access_token = access_token
        self.max_notify = max_notify
        self.current_notify = 0

    def _create_url(self, path:str, query:Dict[str, Any]):
        return urllib.parse.urlunsplit((
            self.scheme,
            self.netloc,
            path,
            urllib.parse.urlencode(query),
            None
        ))
    
    def courses_raw(self):
        url = self._create_url(path=self.COURSES_ENDPOINT, query={'access_token':self.access_token,'page':1,'per_page':100})
        return requests.get(url=url)
    
    def courses(self,):
        return [{k:v for k,v in c.items() if k in ['id', 'name', 'course_code']} for c in self.courses_raw().json() if c['workflow_state']=='available']
    
    def file_list_raw(self, course_id:int, page:int=1):
        url = self._create_url(path=self.COURSE_FILES_ENDPOINT.format(course_id=course_id), query={'access_token':self.access_token,'page':page,'per_page':20})
        return requests.get(url=url)
    
    def notify(self, message:str):
        if platform.system() == 'Linux':
            if self.current_notify <= self.max_notify:
                subprocess.run(["notify-send", message])
                self.current_notify += 1
        
    
    def download_files(self, root_dir:str):
            newly_downloaded = []

            for course in api.courses():

                course_name = sanitize_for_dirname(course['name'])
                course_dir = os.path.join(root_dir, course_name)

                if not os.path.isdir(course_dir):
                    os.mkdir(course_dir)
                
                has_results = True
                page=1

                while has_results:
                    file_list_results = api.file_list_raw(course_id=course['id'], page=page).json()
                    has_results = bool(file_list_results)

                    for file in file_list_results:
                        proposed_fpath = os.path.join(course_dir, file['display_name'])

                        if not os.path.isfile(proposed_fpath):
                            try:
                                urllib.request.urlretrieve(url=file['url'], filename=proposed_fpath)
                                self.notify(f"CanvasDaemon: Downloaded '{file['display_name']}' in {course_name}.")
                                newly_downloaded.append(proposed_fpath)
                            except Exception as e:
                                pass


                    page += 1


if __name__ == '__main__':
    CANVAS_SYNC_DIR = '/home/elias/Documents/CanvasSync'
    api = CanvasAPI(
        netloc='canvas.its.virginia.edu',
        access_token='YOUR ACCESS TOKEN HERE',
    )
    api.download_files(CANVAS_SYNC_DIR)

Create a virtual environment with dependencies

python3 -m venv /path/to/venv
source /path/to/venv/bin/activate
/path/to/venv/bin/python -m pip install requests

Edit linux crontab file

crontab -e

Add this to make the daemon run every two minutes

*/2 * * * * /path/to/venv/bin/python /path/to/canvas_daemon.py