$ python bonanza.py https://www.dr.dk/bonanza/serie/121/casper--mandrilafta/25670/casper--mandrilaftalen-0948

bonanza.py

import argparse
import os
import re
import string
import subprocess
import sys
from shutil import which, copyfileobj
from urllib import request
from html.parser import HTMLParser


class BonanzaParser(HTMLParser):
    playlist_url = None
    meta = {}

    def handle_starttag(self, tag, attrs):
        attr = dict(attrs)
        if tag == "source":
            self.playlist_url = attr["src"]
        elif tag == "meta":
            for k in ("name", "property"):
                if k in attr and "content" in attr:
                    self.meta[attr[k]] = attr["content"]


def progress_bar(iteration, total, prefix="", suffix="", decimals=1, length=100):
    percent = ("{0:." + str(decimals) + "f}").format(100 * (iteration / float(total)))
    filledLength = int(length * iteration // total)
    bar = "█" * filledLength + "-" * (length - filledLength)
    print("\r%s |%s| %s%% %s" % (prefix, bar, percent, suffix), end="\r")
    if iteration == total:
        print()


def format_filename(s):
    valid_chars = "-_() %s%s" % (string.ascii_letters, string.digits)
    filename = "".join(c for c in s if c in valid_chars)
    filename = filename.replace(" ", "_")
    return filename


def req(url):
    with request.urlopen(url) as response:
        return response.read().decode("utf-8")


def parse_url(url):
    parser = BonanzaParser()
    parser.feed(req(url))

    playlist_url = parser.playlist_url
    title = parser.meta["og:title"]

    return (playlist_url, title)


def get_chunks(playlist_url):
    playlist = req(playlist_url)
    chunklist_url = re.search(".*m3u8", playlist).group()

    base_url = chunklist_url[: chunklist_url.rfind("/")]

    chunks_data = req(chunklist_url)
    chunks = re.findall(".*\.ts", chunks_data)

    chunks = ["%s/%s" % (base_url, chunk) for chunk in chunks]

    return chunks


def write_file(chunks, filename):
    with open(filename, "wb") as output_file:
        chunks_total = len(chunks)
        zfill = len(str(chunks_total))

        progress_bar(0, chunks_total, prefix="Progress:", length=50)

        for i, chunk in enumerate(chunks, start=1):
            suffix = "[{i:0{len}d}/{total}]".format(i=i, total=chunks_total, len=zfill)
            progress_bar(i, chunks_total, prefix="Progress:", suffix=suffix, length=50)

            with request.urlopen("%s" % chunk) as chunk_data:
                copyfileobj(chunk_data, output_file)


def has_ffmpeg():
    return which("ffmpeg") is not None


def convert(file_input, file_output):
    cmd = [
        "ffmpeg",
        "-y",
        "-i",
        file_input,
        "-acodec",
        "copy",
        "-vcodec",
        "copy",
        file_output,
    ]

    try:
        proc = subprocess.run(cmd, check=True, capture_output=True)
    except subprocess.CalledProcessError:
        return False
    return True


def get_args(args):
    description = "Bonanza - Downloads episodes off https://dr.dk/bonanza"
    arg = argparse.ArgumentParser(description=description)
    arg.add_argument(
        "-c",
        "--convert",
        metavar="bool",
        type=bool,
        default=False,
        help="Convert ts to mp4. Requires ffmpeg",
    )
    arg.add_argument("url", type=str, help="The url to from https://dr.dk/bonanza")

    return arg.parse_args(args)


def main():
    args = get_args(sys.argv[1:])
    (playlist_url, title) = parse_url(args.url)

    print("Downloading: %s" % title)

    chunks = get_chunks(playlist_url)
    filename = "%s.ts" % format_filename(title)
    write_file(chunks, filename)

    if args.convert:
        if has_ffmpeg() == False:
            print("FFMpeg is not installed :(")
            return False

        print("Converting: %s" % filename)

        filename_out = os.path.splitext(filename)[0] + ".mp4"
        convert(filename, filename_out)


if __name__ == "__main__":
    main()