Download all photos and videos from your Class Dojo account

download_class_dojo_archive.py

"""
Download all ClassDojo photos and videos in your timeline.
by kecebongsoft

How it works:

1. Fetch list of items in the timeline, if there are multiple pages, it will fetch for all pages.
2. Collect list of URLs for the attachment for each item
3. Download the files into local temporary directory, and also save the timeline activity as a json file.

How to use:

1. Modify the session cookie in this script, check your session cookie by opening classdojo in browser and copy
the following cookies: dojo_log_session_id, dojo_login.sid, and dojo_home_login.sid
2. Run this script and wait for it to finish.

If error happens:

1. I ran this script in windows, make sure your path is correct if you are on linux
2. Make sure "classdojo_output" directory exists in the same folder as this script
3. Make sure you have a correct session cookies set in this script.
4. Make sure you can open the FEED_URL listed in this script from within your browser (assuming you can open ClassDojo website)
"""

import requests, json, tempfile

print('Starting')

FEED_URL = 'https://home.classdojo.com/api/storyFeed?includePrivate=true'
DESTINATION = tempfile.mkdtemp(dir='classdojo_output') #make sure this directory exists in the same place as this script.
SESSION_COOKIES = {
    'dojo_log_session_id': '<insert here>',
    'dojo_login.sid': '<insert here>',
    'dojo_home_login.sid': '<insert here>',
}


def save_json(json_content):
    with open('%s\\data.json' % DESTINATION, 'w') as f: #you might want something like '/' if you're on linux.
        f.write(json.dumps(json_content, indent=4))


def get_items(feed_url):
    print('Fetching items: %s..' % feed_url)
    resp = requests.get(feed_url, cookies=SESSION_COOKIES)
    data = resp.json()
    prev = data.get('_links', {}).get('prev', {}).get('href')

    return data['_items'], prev


def get_urls(feed_url):
    items, prev = get_items(feed_url)

    while prev and feed_url != prev:
        prev_urls, prev = get_items(prev)
        items.extend(prev_urls)

    save_json(items)

    urls = []
    for item in items:
        attachments = item['contents'].get('attachments', {})
        if not attachments: continue

        for attachment in attachments:
            urls.append(attachment['path'])

    return urls


def get_name_from_url(url):
    parts = url.split('/')
    return '_'.join(parts[3:]).replace('-', '_')


def download_urls(urls):
    total = len(urls)
    for index, url in enumerate(urls):
        name = get_name_from_url(url)
        print('Downloading %s/%s %s -> %s' % (index, total, url, name))
        with open('%s\\%s' % (DESTINATION, name), 'wb') as f:
            resp = requests.get(url, cookies=SESSION_COOKIES)
            f.write(resp.content)


download_urls(get_urls(FEED_URL))
print('Done!')