This script downloads all the mp4 files for a tele-task course

download.py

#!/usr/bin/python3

##  The MIT License (MIT)
##
##  Copyright (c) 2014 Nicco Kunzmann
##
##    https://gist.github.com/niccokunzmann/9c60cb40d3d3975ef830
##
##  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.

"""

This Python Script downloads whole tele-task classes into a folder.

use python 3

source and updates
    https://gist.github.com/niccokunzmann/9c60cb40d3d3975ef830

"""
import webbrowser
import urllib.request
import re
import os
import concurrent.futures
import traceback

def _download(url, name, to_directory, number):
    try:
        print('downloading number {}: {}'.format(number, name))
        urllib.request.urlretrieve(url, os.path.join(to_directory, name))
        print('downloaded number {}: {}'.format(number, name))
    except:
        traceback.print_exc()


def download_course(number_or_url, downloads_at_a_time = 2, to_directory = 'tele-task'):
    """ download all chapters of the course
    number_or_url
        is the number or url of the tele-task course
    downloads_at_a_time
        how many files should be downloaded at a time
    to_directory
        where the download will be stored"""
    if isinstance(number_or_url, int):
        url = 'http://www.tele-task.de/archive/series/overview/{}/'.format(number_or_url)
    else:
        url = number_or_url
    if not os.path.exists(to_directory):
        print('creating download directory', to_directory)
        os.makedirs(to_directory)
    print('opening course overview')
    website = urllib.request.urlopen(url)

    # <a href="/archive/video/ipod/23411/">
    paths = re.findall(b'<a[^>]+?href="(/archive/video/ipod/[^"]*)"', website.read(), re.IGNORECASE)

    
    tpe = concurrent.futures.ThreadPoolExecutor(downloads_at_a_time)
    downloads = 0
    for path in paths:
        path = path.decode('ASCII')
        print('opening', path)
        site = urllib.request.urlopen('http://www.tele-task.de' + path)

        # <a href="http://stream.hpi.uni-potsdam.de:8080/download/podcast/SS_2014/DPS_SS14/DPS_2014_04_14/DPS_2014_04_14_part_1_podcast.mp4">
        downstreams = re.findall(b'<a[^>]+?href="(http://stream.hpi.uni-potsdam.de:8080/download/podcast/[^"]*)"', site.read(), re.IGNORECASE)
        for downstream in downstreams:
            url = downstream.decode('ASCII')
            name = os.path.basename(url)
            if name in os.listdir(to_directory):
                print('skipping', name)
            else:
                print('marking for download', name)
                downloads += 1
                tpe.submit(_download, url, name, to_directory, downloads)
            break
    print('{} file {} will be downloaded.'.format(downloads, 's' * (downloads > 1)))
    tpe.shutdown()
    print('done')

# Dependable Systems (SS 2014) is 1005 for example
# https://www.tele-task.de/archive/series/overview/1005/
# You will need to input "1005/", then. Do not forget the "/" at the end.
download_course(int(input('https://www.tele-task.de/archive/series/overview/')))