Exports Canvas LMS discussion forums and comments/replies/entries

canvas-discussion-forum-exporter.py

# I'm surprised this doesn't already exist

# Just add Institute, Course ID and your bearer token
# check settings, default only selects threads which are 'closed for comments' 

import requests
import json
import urllib.request

# Define the Canvas Discussion Variable
INSTITUTE = ""
COURSE_ID = ""

# OAUTH token https://canvas.instructure.com/doc/api/file.oauth_endpoints.html#post-login-oauth2-token
headers = {
    "Authorization": ""
}

# Settings
# closed for comments
# https://github.com/instructure/canvas-lms/blob/master/app/controllers/discussion_topics_controller.rb#L149
data = {"scope": "locked"} #"per_page": 100

CANVAS_URL = "https://%s.instructure.com/api/v1/courses/%s/discussion_topics/"
END_OF_URL = "/view?include_new_entries=1"

itemsdone = 0
all_discussions = []

response = requests.get(CANVAS_URL % (INSTITUTE, COURSE_ID), data=data, headers=headers)
while True:
    raw = response.json()
    for discussion in raw:
        # comments
        discussion['ENTRIES'] = requests.get(CANVAS_URL % (INSTITUTE, COURSE_ID) + str(discussion['id']) + END_OF_URL, headers=headers).json()
        all_discussions.append(discussion) 
        print("Processed", itemsdone += 1, "discussions")
    
    if (response.links["current"]["url"] == response.links["last"]["url"]):
        break    
    response = requests.get(response.links["next"]["url"], data=data, headers=headers)

print("Done processing... writing to file")
with open("%s_discussion_scraper-course_%s.json" % (INSTITUTE, COURSE_ID), "w", encoding="utf-8") as f:
    json.dump(all_discussions, f, ensure_ascii=False, indent=4)
    print("Complete! %s" % f.name)