Download all files from a Gumroad purchase in your library

gumroad-library-download.py

"""
Download all files from Gumroad directory
"""

import re
import json
import requests
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC


CONTENT_URL = '' # directory to download (ex. https://gumroad.com/d/16f471d07602451bfff70ce676728ca3)


def sanitize_filename(filename):
    sanitized = ''
    invalid_chars = '<>:"/\\|?*'
    for c in filename:
        if c not in invalid_chars:
            sanitized += c
    return sanitized


def download_file(url, filename, file_size):
    response = requests.get(url, stream=True)
    response.raise_for_status()
    progress = 0
    with open(filename, 'wb') as file:
        for chunk in response.iter_content(chunk_size=8192):
            file.write(chunk)
            progress += len(chunk)
            percent_progress = (progress/file_size) * 100
            print(f'{filename} - {percent_progress:.2f}%')


def init_session():
    session = requests.Session()
    driver = webdriver.Chrome()
    driver.get(CONTENT_URL)
    WebDriverWait(driver, 9999999999999).until(EC.url_matches(CONTENT_URL))
    for cookie in driver.get_cookies():
        session.cookies.set(cookie['name'], cookie['value'])
    driver.close()
    return session


def main():
    s = init_session()
    r = s.get(CONTENT_URL)
    match = re.search(
        r"<script type=\"application/json\" class=\"js-react-on-rails-component\" data-component-name=\"DownloadPageWithContent\".*>(.*)</script>",
        r.text)
    match.group(1)
    content = json.loads(match.group(1))
    to_download = [d for d in content['content']['content_items'] if
                   'download_url' in d.keys() and d['download_url']]
    for item in to_download:
        dl_url = f'https://gumroad.com/{item['download_url']}'
        attachment_url = s.get(dl_url).url
        clean_filename = sanitize_filename(item['file_name'])
        filename = f'{clean_filename}.{item['extension']}'
        download_file(attachment_url, filename, item['file_size'])

if __name__ == '__main__':
    main()